EXPORT AS: TaggedXMLBibTex

2011

  • I. Jang, P. Kudumakis, M. Sandler, and K. ;. Kang, “The MPEG Interactive Music Application Format Standard,” IEEE Signal Processing Magazine, 2011.
    [Bibtex]
    @article { omras2-130,
      title = {The MPEG Interactive Music Application Format Standard},
      journal = {IEEE Signal Processing Magazine},
      year = {2011},
      month = {Jan., 2011},
      abstract = {The music industry is going through a transformation: new interactive music services emerged. It is envisaged that this new concept of digital music content will dominate the next generation of music services. A standardised file format is inevitably required to provide the interoperability between various interactive music players and interactive music albums. The new MPEG-A Interactive Music Application Format (IM AF) comes to address this issue. IM AF integrates multiple audio tracks with appropriate additional information enabling users to experience various preset mixes and to make their own mixes complying with interactivity rules imposed by the music composers with the aim of fitting their artistic creation. },
      keywords = {Music, Format, Interactivity, Interoperability, Standard, MPEG},
      author = {Jang, I. and Kudumakis, P. and Sandler, M. and Kang, K.;}
    }
  • Y. Zhu, I. Jang, P. Kudumakis, A. Zacharakis, R. Yu, and T. E. Chan, “Report for Core Experiment on Dynamic Volume Change Representation for IM AF,” , Daegu, S. Korea 2011.
    [Bibtex]
    @techreport { omras2-187,
      title = {Report for Core Experiment on Dynamic Volume Change Representation for IM AF},
      year = {2011},
      month = {01/2011},
      address = {Daegu, S. Korea},
      author = {Yongwei Zhu and Inseon Jang and Panos Kudumakis and  Asteris Zacharakis and Rongshan Yu and Ti Eu Chan}
    }
  • B. Fields, K. Jacobson, C. Rhodes, M. Sandler, M. d’Inverno, and M. Casey, “Analysis and Exploitation of Musician Social Networks for Recommendation and Discovery,” IEEE Transactions on Multimedia, 2011.
    [Bibtex]
    @article { Fields:2010b,
      title = {Analysis and Exploitation of Musician Social Networks for Recommendation and Discovery},
      journal = {IEEE Transactions on Multimedia},
      year = {2011},
      keywords = {playlists, social networks, community},
      author = {Fields, Ben and Jacobson, Kurt and Rhodes, Christophe and Sandler, Mark and d'Inverno, Mark and Casey, Micheal}
    }
  • R. Stewart, P. Kudumakis, and M. Sandler, “Interactive music applications and standards,” in CMMR 2010 Post Symposium proceedings, K. Y. J. R. S. K. M. Aramaki, Ed., Berlin / Heidelberg: Springer-Verlag, 2011.
    [Bibtex]
    @inbook { omras2-179,
      title = {Interactive music applications and standards},
      booktitle = {CMMR 2010 Post Symposium proceedings},
      editor = {R. Kronland-Martinet; S. Ystad; K. Jensen; M. Aramaki},
      year = {2011},
      publisher = {Springer-Verlag},
      address = {Berlin / Heidelberg},
      abstract = {Music is now consumed in interactive applications that allow for the user to directly influence the musical performance. These appli- cations are distributed as games for gaming consoles and applications for mobile devices that currently use proprietary file formats, but standard- ization orgranizations have been working to develop an interchangeable format. This paper surveys the applications and their requirements. It then reviews the current standards that address these requirements fo- cusing on the MPEG Interactive Music Application Format. The paper closes by looking at additional standards that address similar applica- tions and outlining the further requirements that need to be met.},
      author = {R. Stewart and P. Kudumakis and M. Sandler}
    }
  • S. Kolozali, M. Barthet, G. Fazekas, and M. Sandler, “Knowledge Representation Issues in Musical Instrument Ontology Design.” 2011.
    [Bibtex]
    @inproceedings { Kolozali:2011,
      title = {Knowledge Representation Issues in Musical Instrument Ontology Design},
      journal = {12th International Society for Music Information Retrieval Conference},
      year = {2011},
      note = {to appear},
      author = {Kolozali, S. and Barthet, M. and Fazekas, G. and Sandler, M.}
    }
  • S. Dixon, M. Mauch, and A. Anglade, “Probabilistic and Logic-Based Modelling of Harmony,” in CMMR 2010 Post Symposium Proceedings, K. Y. J. R. S. K. M. Aramaki, Ed., Berlin / Heidelberg: Springer, 2011.
    [Bibtex]
    @inbook { omras2-178,
      title = {Probabilistic and Logic-Based Modelling of Harmony},
      booktitle = {CMMR 2010 Post Symposium Proceedings},
      editor = {R. Kronland-Martinet; S. Ystad; K. Jensen; M. Aramaki},
      year = {2011},
      publisher = {Springer},
      address = {Berlin / Heidelberg},
      author = {S. Dixon and M. Mauch and A. Anglade}
    }
  • R. Stewart and M. Sandler, “Playlist generation and navigation in mobile listening,” IEEE Signal Processing Magazine, 2011.
    [Bibtex]
    @article { omras2-180,
      title = {Playlist generation and navigation in mobile listening},
      journal = {IEEE Signal Processing Magazine},
      year = {2011},
      author = {R. Stewart and M. Sandler}
    }
  • S. M. Barthet M.;Hargreaves, “Speech/Music Discrimination in Audio Podcast Using Structural Segmentation and Timbre Recognition,” in CMMR 2010 Post Symposium proceedings, R. Kronland-Martinet, S. Ystad, K. Jensen, and M. Aramaki, Eds., Berlin / Heidelberg: Springer-Verlag, 2011.
    [Bibtex]
    @inbook { omras2-176,
      title = {Speech/Music Discrimination in Audio Podcast Using Structural Segmentation and Timbre Recognition},
      booktitle = {CMMR 2010 Post Symposium proceedings},
      editor = {R. Kronland-Martinet and S. Ystad and K. Jensen and M. Aramaki},
      year = {2011},
      publisher = {Springer-Verlag},
      address = {Berlin / Heidelberg},
      abstract = {We propose two speech/music discrimination methods using timbre models and measure their performances on a 3 hour long database of radio podcasts from the BBC. In the first method, the machine estimated classifications obtained with an automatic timbre recognition (ATR) model are post-processed using median filtering. The classification system (LSF/K-means) was trained using two different taxonomic levels, a high-level one (speech, music), and a lower-level one (male and female speech, classical, jazz, rock & pop). The second method combines automatic structural segmentation and timbre recognition (ASS/ATR). The ASS evaluates the similarity between feature distributions (MFCC, RMS) using HMM and soft K-means algorithms. Both methods were evaluated at a semantic (relative correct overlap RCO), and temporal (boundary retrieval F-measure) levels. The ASS/ATR method obtained the best results (average RCO of 94.5% and boundary F-measure of 50.1%). These performances were favourably compared with that obtained by a SVM-based technique providing a good benchmark of the state of the art.},
      keywords = {Speech/Music Discrimination, Audio Podcast, Timbre Recognition, Structural Segmentation, Line Spectral Frequencies, K-means clustering, Mel-Frequency Cepstral Coefficients, Hidden Markov Models},
      author = {Barthet, M.;Hargreaves, S.;Sandler, M.}
    }
  • S. Dixon, D. Tidhar, and E. Benetos, “The Temperament Police: The Truth, The Ground Truth, and Nothing but the Truth.” 2011.
    [Bibtex]
    @inproceedings { Dixon:2011b,
      title = {The Temperament Police: The Truth, The Ground Truth, and Nothing but the Truth},
      journal = {12th International Society for Music Information Retrieval Conference},
      year = {2011},
      note = {to appear},
      author = {Dixon, S. and Tidhar, D. and Benetos, E.}
    }
  • S. Dixon, M. Mauch, and D. Tidhar, “Estimation of Harpsichord Inharmonicity and Temperament from Musical Recordings,” Journal of the Acoustical Society of America, p. to appear, 2011.
    [Bibtex]
    @article { Dixon:2011a,
      title = {Estimation of Harpsichord Inharmonicity and Temperament from Musical Recordings},
      journal = {Journal of the Acoustical Society of America},
      year = {2011},
      pages = {to appear},
      author = {Dixon, S. and Mauch, M. and Tidhar, D.}
    }
  • G. Fazekas and M. B. Sandler, “The Studio Ontology Framework.” 2011.
    [Bibtex]
    @inproceedings { Fazekas:2011,
      title = {The Studio Ontology Framework},
      journal = {12th International Society for Music Information Retrieval Conference},
      year = {2011},
      note = {to appear},
      author = {Fazekas, G. and Sandler, M.B.}
    }

2010

  • B. Fields, C. Rhodes, and M. d’Inverno, “Using Song Social Tags and Topic Models to Describe and Compare Playlists,” , Barcelona, 2010.
    [Bibtex]
    @inproceedings { Fields:2010,
      title = {Using Song Social Tags and Topic Models to Describe and Compare Playlists},
      journal = {Workshop on Music Recommendation and Discovery},
      year = {2010},
      month = {September},
      publisher = {ACM},
      organization = {ACM},
      address = {Barcelona},
      keywords = {Playlist, Evaluation systems, distance estimation},
      author = {Fields, Ben and Rhodes, Christophe and d'Inverno, Mark}
    }
  • E. Benetos and S. Dixon, “Multiple-F0 estimation of piano sounds exploiting spectral structure and temporal evolution.” 2010, pp. 13-18.
    [Bibtex]
    @inproceedings { Ben10a,
      title = {Multiple-F0 estimation of piano sounds exploiting spectral structure and temporal evolution},
      journal = {ISCA Tutorial and Research Workshop on Statistical and Perceptual Audition},
      year = {2010},
      month = {Sept 2010},
      pages = {13-18},
      author = {E. Benetos and S. Dixon}
    }
  • K. Page, B. Fields, B. Nagel, G. O’Neill, D. D. Roure, and T. Crawford, “Semantics for music researchers: How country is my country?,” , Shanghai, China, 2010.
    [Bibtex]
    @inproceedings { Page:2010a,
      title = {Semantics for music researchers: How country is my country?},
      journal = {Demonstrated at International Sematic Web Conference (ISWC)},
      year = {2010},
      month = {November},
      address = {Shanghai, China},
      author = {Kevin Page and Benjamin Fields and Bart Nagel and Gianni O'Neill and David De Roure and Tim Crawford}
    }
  • K. Page, B. Fields, B. Nagel, G. O’Neill, D. D. Roure, and T. Crawford, “Semantics for music analysis through linked data: How country is my country?,” , Brisbane, Australia, 2010.
    [Bibtex]
    @inproceedings { Page:2010b,
      title = {Semantics for music analysis through linked data: How country is my country?},
      journal = {Proc. of the IEEE eScience Conference},
      year = {2010},
      month = {December},
      address = {Brisbane, Australia},
      author = {Kevin Page and Benjamin Fields and Bart Nagel and Gianni O'Neill and David De Roure and Tim Crawford}
    }
  • K. Page, B. Fields, T. Crawford, D. D. Roure, G. O’Neill, and B. Nagel, “Semantics for Signal and Result Collections through Linked Data: How Country is my Country?,” , Utrecht, The Netherlands, 2010.
    [Bibtex]
    @inproceedings { Page:2010,
      title = {Semantics for Signal and Result Collections through Linked Data: How Country is my Country?},
      journal = {Demonstrated at Int. Conference on Music Information Retrieval},
      year = {2010},
      month = {August},
      address = {Utrecht, The Netherlands},
      author = {Kevin Page and Benjamin Fields and Tim Crawford and David De Roure and Gianni O'Neill and Bart Nagel}
    }
  • B. Fields and P. Lamere, Finding a path through the Juke Box – The Playlist Tutorial, 2010.
    [Bibtex]
    @misc { Fields:2010a,
      title = {Finding a path through the Juke Box – The Playlist Tutorial},
      year = {2010},
      month = {Aug.},
      keywords = {Playlist, MIR},
      URL = {http://benfields.net/playlist_ismir_2010.pdf},
      author = {Fields, Ben and Lamere, Paul}
    }
  • T. Wilmering and M. Sandler, “RDFx: Audio Effects Utilising Musical Metadata.” 2010.
    [Bibtex]
    @inproceedings { omras2-111,
      title = {RDFx: Audio Effects Utilising Musical Metadata},
      journal = {IEEE International Conference on Semantic Computing (ICSC), Pittsburgh, PA, USA},
      year = {2010},
      month = {22/09/2010},
      author = {Thomas Wilmering and Mark Sandler}
    }
  • S. Hargreaves, C. Landone, M. Sandler, and P. Kudumakis, Segmentation and Discovery of Podcast ContentAudio Engineering Society, 2010.
    [Bibtex]
    @proceedings { omras2-109,
      title = {Segmentation and Discovery of Podcast Content},
      year = {2010},
      month = {22/05/2010},
      publisher = {Audio Engineering Society},
      abstract = {With ever increasing amounts of radio broadcast material being made available as podcasts, sophisticated methods of enabling the listener to quickly locate material matching their own personal tastes become essential. Given the ability to segment a podcast which may be in the order of one or two hours duration into individual song previews, the time the listener spends searching for material of interest is minimised. This paper investigates the effectiveness of applying multiple feature extraction techniques to podcast segmentation, and describes how such techniques could be exploited by a vast number of digital media delivery platforms in a commercial cloud-based radio recommendation and summarisation service.},
      keywords = {Segmentation, Audio, Podcast},
      author = {S. Hargreaves and C. Landone and M. Sandler and P. Kudumakis}
    }
  • T. Wilmering, G. Fazekas, and M. Sandler, “The effects of reverberation on onset detection tasks.” 2010.
    [Bibtex]
    @inproceedings { omras2-110,
      title = {The effects of reverberation on onset detection tasks},
      journal = {AES 128th Convention, London, UK},
      year = {2010},
      month = {22/05/2010},
      abstract = {The task of onset detection is relevant in various contexts such as music information retrieval and music production, while reverberation has always been an important part of the production process. The effect may be the product of the recording space, or it may be artificially added, and in our context destructive. In this paper, we investigate the effect of reverberation on onset detection tasks. We compare state-of-the art techniques and show that the algorithms have varying degrees of robustness in the presence of reverberation depending on the content of the analysed audio material.},
      author = {Thomas Wilmering and Gyorgy Fazekas and Mark Sandler}
    }
  • P. Kudumakis, I. Jang, and M. ;. Sandler, A New Interactive MPEG Format for the Music IndustryMálaga, Spain: , 2010.
    [Bibtex]
    @proceedings { omras2-129,
      title = {A New Interactive MPEG Format for the Music Industry},
      year = {2010},
      month = {21-24 June, 2010},
      address = {Málaga, Spain},
      abstract = {It is well known that the music industry is going through a transformation. In this direction, a new interactive music service has emerged. It is expected that this new concept of digital music content will be the next generation of music services. However, a standardised file format is inevitably required to provide the interoperability between various interactive music players and interactive music albums. The new MPEG-A Interactive Music Application Format (IM AF) comes to address this issue. It integrates multiple audio tracks with appropriate additional information enabling users to experience various preset mixes and to make their own mixes complying with interactivity rules imposed by the music producer. },
      keywords = {Music, Format, Interactivity, Interoperability, Standard, MPEG},
      author = { Kudumakis, P. and Jang, I. and Sandler, M.;}
    }
  • G. Fazekas, Y. Raimond, K. Jacobson, and M. Sandler, “An Overview of Semantic Web Activities in the OMRAS2 Project,” Journal of New Music Research, vol. 39, pp. 295-311, 2010.
    [Bibtex]
    @article { omras2-159,
      title = {An Overview of Semantic Web Activities in the OMRAS2 Project},
      journal = {Journal of New Music Research},
      volume = {39},
      year = {2010},
      month = {2010},
      pages = {295-311},
      chapter = {295},
      author = {Gyorgy Fazekas and Yves Raimond and Kurt Jacobson and Mark Sandler}
    }
  • A. Anglade, E. Benetos, M. Mauch, and S. Dixon, “Improving Music Genre Classification Using Automatically Induced Harmony Rules ,” Journal of New Music Research, vol. 39, pp. 349-361, 2010.
    [Bibtex]
    @article { omras2-116,
      title = {Improving Music Genre Classification Using Automatically Induced Harmony Rules },
      journal = {Journal of New Music Research},
      volume = {39},
      year = {2010},
      month = {2010},
      pages = {349-361},
      chapter = {349},
      abstract = {We present a new genre classification framework using both low-level signal-based features and high-level harmony features. A state of-the-art statistical genre classifier based on timbral features is extended using a first-order random forest containing for each genre rules derived from harmony or chord sequences. This random forest has been automatically induced, using the first-order logic induction algorithm TILDE, from a dataset, in which for each chord the degree and chord category are identified, and covering classical, jazz and pop genre classes. The audio descriptor-based genre classifier contains 206 features, covering spectral, temporal, energy, and pitch characteristics of the audio signal. The fusion of the harmony-based classifier with the extracted feature vectors is tested on three-genre subsets of the GTZAN and ISMIR04 datasets, which contain 300 and 448 recordings, respectively. Machine learning classifiers were tested using 5x5-fold cross-validation and feature selection. Results indicate that the proposed harmony-based rules combined with the timbral descriptor-based genre classification system lead to improved genre classification rates.},
      author = {Amélie Anglade and Emmanouil Benetos and Matthias Mauch and Simon Dixon}
    }
  • C. Rhodes, T. Crawford, M. Casey, and M. d’Inverno, “Investigating Music Collections at Different Scales with AudioDB,” Journal of New Musical Research, vol. 39, pp. 337-348, 2010.
    [Bibtex]
    @article { Rhodes:2010,
      title = {Investigating Music Collections at Different Scales with AudioDB},
      journal = {Journal of New Musical Research},
      volume = {39},
      year = {2010},
      month = {2010},
      pages = {337-348},
      chapter = {337},
      keywords = {audioDB, similarity, sequence matching},
      author = {Rhodes, Christophe and Crawford, Tim and Casey, Michael and d'Inverno, Mark}
    }
  • D. Tidhar, G. Fazekas, M. Mauch, and S. Dixon, “TempEst: Harpsichord Temperament Estimation in a Semantic-Web Environment,” Journal of New Music Research, vol. 39, pp. 327-336, 2010.
    [Bibtex]
    @article { omras2-160,
      title = {TempEst: Harpsichord Temperament Estimation in a Semantic-Web Environment},
      journal = {Journal of New Music Research},
      volume = {39},
      year = {2010},
      month = {2010},
      pages = {327-336},
      chapter = {327},
      author = {Dan Tidhar and Gyorgy Fazekas and Matthias Mauch and Simon Dixon}
    }
  • C. Cannam, M. O. Jewell, C. Rhodes, M. Sandler, and M. d’Inverno, “Linked Data And You: Bringing music research software into the Semantic Web,” Journal of New Music Research, vol. 39, pp. 313-325, 2010.
    [Bibtex]
    @article { omras2-117,
      title = {Linked Data And You: Bringing music research software into the Semantic Web},
      journal = {Journal of New Music Research},
      volume = {39},
      year = {2010},
      month = {12/2010},
      pages = {313-325},
      chapter = {313},
      abstract = {The promise of the Semantic Web is to democratise access to data, allowing anyone to make use of and contribute back to the global store of knowledge.  Within the scope of the OMRAS2 Music Information Retrieval project, we have made use of and contributed to Semantic Web technologies for purposes ranging from the publication of music recording metadata to the online dissemination of results from audio analysis algorithms.  In this paper, we assess the extent to which our tools and frameworks can assist in research and facilitate distributed work among audio and music researchers, and enumerate and motivate further steps to improve collaborative efforts in music informatics using the Semantic Web.  To this end, we review some of the tools developed by the OMRAS2 project, examine the extent to which our work reflects the Semantic Web paradigm, and discuss some of the remaining work needed to fulfil the promise of online music informatics research.
    },
      author = {Chris Cannam and Michael O. Jewell and Christophe Rhodes and Mark Sandler and Mark d'Inverno}
    }
  • M. Mauch and S. Dixon, “Approximate Note Transcription for the Improved Identification of Difficult Chords,” , Utrecht, Netherlands, 2010, pp. 135-140.
    [Bibtex]
    @inproceedings { omras2-106,
      title = {Approximate Note Transcription for the Improved Identification of Difficult Chords},
      journal = {11th International Society for Music Information Retrieval Conference (ISMIR 2010)},
      year = {2010},
      pages = {135-140},
      address = {Utrecht, Netherlands},
      abstract = {The automatic detection and transcription of musical chords from audio is an established music computing task. The choice of chord profiles and higher-level time-series modelling have received a lot of attention, resulting in methods with an overall performance of more than 70% in the MIREX Chord Detection task 2009. Research on the front end of chord transcription algorithms has often con- centrated on finding good chord templates to fit the chroma features. In this paper we reverse this approach and seek to find chroma features that are more suitable for usage in a musically-motivated model. We do so by performing a prior approximate transcription using an existing technique to solve non-negative least squares problems (NNLS). The resulting NNLS chroma features are tested by using them as an input to an existing state-of-the-art high-level model for chord transcription. We achieve very good results of 80% accuracy using the song collection and metric of the 2009 MIREX Chord Detection tasks. This is a significant increase over the top result (74%) in MIREX 2009. The na- ture of some chords makes their identification particularly susceptible to confusion between fundamental frequency and partials. We show that the recognition of these diffcult chords in particular is substantially improved by the prior approximate transcription using NNLS.},
      keywords = {chord transcription, NNLS, transcription, chroma},
      URL = {http://matthiasmauch.net/},
      author = {Matthias Mauch and Simon Dixon}
    }
  • M. Chudy and S. Dixon, “A Study of Timbre Descriptors for Cello Player Discrimination.” 2010.
    [Bibtex]
    @inproceedings { Chu10b,
      title = {A Study of Timbre Descriptors for Cello Player Discrimination},
      journal = {AES XIII Symposium on New Trends in Audio and Video},
      year = {2010},
      author = {M. Chudy and S. Dixon}
    }
  • M. Mauch, “Automatic Chord Transcription Using Computational Models of Musical Context,” Doctor of Philosophy (PhD) PhD Thesis, London, 2010.
    [Bibtex]
    @phdthesis { omras2-105,
      title = {Automatic Chord Transcription Using Computational Models of Musical Context},
      year = {2010},
      pages = {168},
      school = {Queen Mary, University of London},
      type = {Doctor of Philosophy (PhD)},
      address = {London},
      abstract = {This thesis is concerned with the automatic transcription of chords from audio, with an emphasis on modern popular music. Musical context such as the key and the structural segmentation aid the interpretation of chords in human beings. In this thesis we propose computational models that integrate such musical context into the automatic chord estimation process.
    We present a novel dynamic Bayesian network (DBN) which integrates models of met- ric position, key, chord, bass note and two beat-synchronous audio features (bass and treble chroma) into a single high-level musical context model. We simultaneously infer the most prob- able sequence of metric positions, keys, chords and bass notes via Viterbi inference. Several experiments with real world data show that adding context parameters results in a significant increase in chord recognition accuracy and faithfulness of chord segmentation. The proposed, most complex method transcribes chords with a state-of-the-art accuracy of 73% on the song collection used for the 2009 MIREX Chord Detection tasks. This method is used as a baseline method for two further enhancements.
    Firstly, we aim to improve chord confusion behaviour by modifying the audio front end processing. We compare the effect of learning chord profiles as Gaussian mixtures to the effect of using chromagrams generated from an approximate pitch transcription method. We show that using chromagrams from approximate transcription results in the most substantial increase in accuracy. The best method achieves 79% accuracy and significantly outperforms the state of the art.
    Secondly, we propose a method by which chromagram information is shared between repeated structural segments (such as verses) in a song. This can be done fully automatically using a novel structural segmentation algorithm tailored to this task. We show that the technique leads to a significant increase in accuracy and readability. The segmentation algorithm itself also obtains state-of-the-art results. A method that combines both of the above enhancements reaches an accuracy of 81%, a statistically significant improvement over the best result (74%) in the 2009 MIREX Chord Detection tasks.},
      keywords = {chord transcription, key, beat, meter, bass, NNLS, structural segmentation},
      URL = {http://matthiasmauch.de/},
      author = {Matthias Mauch}
    }
  • D. Tidhar, M. Mauch, and S. Dixon, “High Precision Frequency Estimation for Harpsichord Tuning Classification.” 2010, p. 61–64.
    [Bibtex]
    @inproceedings { Tid10a,
      title = {High Precision Frequency Estimation for Harpsichord Tuning Classification},
      journal = {Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing},
      year = {2010},
      pages = {61–64},
      author = {D. Tidhar and M. Mauch and S. Dixon}
    }
  • K. Jacobson, S. Dixon, and M. Sandler, LinkedBrainz: Providing the MusicBrainz Next Generation Schema as Linked Data, 2010.
    [Bibtex]
    @unpublished { Jac10a,
      title = {LinkedBrainz: Providing the MusicBrainz Next Generation Schema as Linked Data},
      year = {2010},
      author = {K. Jacobson and S. Dixon and M. Sandler}
    }
  • X. Wen and M. Sandler, “On the characterization of slowly varying sinusoids,” EURASIP Journal on Audio, Speech, and Music Processing, vol. 2010, 2010.
    [Bibtex]
    @article { omras2-120,
      title = {On the characterization of slowly varying sinusoids},
      journal = {EURASIP Journal on Audio, Speech, and Music Processing},
      volume = {2010},
      year = {2010},
      abstract = {We give a brief discussion on the amplitude and frequency variation rates of the sinusoid representation of signals. In particular, we derive three inequalities that show that these rates are upper bounded by the 2nd and 4th spectral moments, which, in a loose sense, indicates that every complex signal with narrow short-time bandwidths is a slowly varying sinusoid. Further discussions are given to show how this result helps providing extra insights into relevant signal processing techniques.},
      author = {Wen, X. and Sandler, M.}
    }
  • T. Crawford, M. Mauch, and C. Rhodes, “Recognizing Classical Works in Historic Recordings.” 2010.
    [Bibtex]
    @inproceedings { omras2-107,
      title = {Recognizing Classical Works in Historic Recordings},
      journal = {11th International Society for Music Information Retrieval Conference (ISMIR 2010)},
      year = {2010},
      author = {Tim Crawford and Matthias Mauch and Christophe Rhodes}
    }
  • X. Wen and M. Sandler, “Source-filter modeling in sinusoid domain,” Journal of the Audio Engineering Society, vol. 58, pp. 795-808, 2010.
    [Bibtex]
    @article { omras2-119,
      title = {Source-filter modeling in sinusoid domain},
      journal = {Journal of the Audio Engineering Society},
      volume = {58},
      year = {2010},
      pages = {795-808},
      chapter = {795},
      abstract = {This paper presents the theory and implementation of source-filter modelling in the sinusoid domain and its applications to timbre processing. We show that the sinusoid-domain source-filter modelling is roughly equivalent to its time- or frequency-domain counterparts. Two methods are proposed for estimating the source-filter model. Tests show the effectiveness of the algorithms for isolating frequency-driven amplitude variations. Example applications are given to demonstrate the use of the technique for timbre processing.},
      author = {Wen, X. and Sandler, M.}
    }
  • C. Cannam, C. Landone, and M. Sandler, Sonic Visualiser: An Open Source Application for Viewing, Analysing, and Annotating Music Audio Files, 2010.
    [Bibtex]
    @proceedings { omras2-118,
      title = {Sonic Visualiser: An Open Source Application for Viewing, Analysing, and Annotating Music Audio Files},
      year = {2010},
      author = {Chris Cannam and Christian Landone and Mark Sandler}
    }
  • S. Dixon, M. Sandler, M. d’Inverno, and C. Rhodes, “Towards a Distributed Research Environment for Music Informatics and Computational Musicology,” Journal of New Music Research, vol. 39, pp. 291-294, 2010.
    [Bibtex]
    @article { omras2-188,
      title = {Towards a Distributed Research Environment for Music Informatics and Computational Musicology},
      journal = {Journal of New Music Research},
      volume = {39},
      year = {2010},
      pages = {291-294},
      author = {S. Dixon and M. Sandler and M. d'Inverno and C. Rhodes}
    }
  • S. Kolozali, M. Barthet, G. Fazekas, and M. Sandler, “Towards Automatic Generation of a Semantic Web Ontology for Musical Instruments,” , Saarbrucken, Germany, 2010.
    [Bibtex]
    @inproceedings { omras2-177,
      title = {Towards Automatic Generation of a Semantic Web Ontology for Musical Instruments},
      journal = {International Conference on Semantic and Digital Media Technologies},
      year = {2010},
      address = {Saarbrucken, Germany},
      keywords = {Semantic Web Intelligence, Automatic Ontology Generation, Instrument Recognition},
      author = {Sefki Kolozali and Mathieu Barthet and George Fazekas and Mark Sandler}
    }
  • R. Macrae and S. Dixon, “A Guitar Tablature Score Follower.” 2010, p. 725–726.
    [Bibtex]
    @inproceedings { Mac10a,
      title = {A Guitar Tablature Score Follower},
      journal = {{IEEE} International Conference on Multimedia & Expo},
      year = {2010},
      pages = {725–726},
      author = {R. Macrae and S. Dixon}
    }
  • R. Macrae and S. Dixon, “Accurate Real-Time Windowed Time Warping.” 2010, p. 423–428.
    [Bibtex]
    @inproceedings { Mac10b,
      title = {Accurate Real-Time Windowed Time Warping},
      journal = {11th International Society for Music Information Retrieval Conference},
      year = {2010},
      pages = {423–428},
      author = {R. Macrae and S. Dixon}
    }
  • M. d’Inverno, C. Rhodes, M. Jewell, and M. Casey, “Content-Based Search for Time-Based Media,” (in preperation) Journal of the American Society for Information Science and Technology, 2010.
    [Bibtex]
    @article { dInverno:2010,
      title = {Content-Based Search for Time-Based Media},
      journal = {(in preperation) Journal of the American Society for Information Science and Technology},
      year = {2010},
      author = {Mark d'Inverno and Christophe Rhodes and Michael Jewell and Michael Casey}
    }
  • S. Dixon, “Computational Modelling of Harmony.” 2010.
    [Bibtex]
    @inproceedings { Dix10a,
      title = {Computational Modelling of Harmony},
      journal = {7th International Symposium on Computer Music Modeling and Retrieval},
      year = {2010},
      author = {S. Dixon}
    }
  • L. Mearns, D. Tidhar, and S. Dixon, “Characterisation of Composer Style using High-Level Musical Features.” 2010.
    [Bibtex]
    @inproceedings { Mea10b,
      title = {Characterisation of Composer Style using High-Level Musical Features},
      journal = {3rd {ACM} Workshop on Machine Learning and Music},
      year = {2010},
      author = {L. Mearns and D. Tidhar and S. Dixon}
    }
  • L. Mearns and S. Dixon, Characterisation of Composer Style Using High Level Musical Features, 2010.
    [Bibtex]
    @unpublished { Mea10a,
      title = {Characterisation of Composer Style Using High Level Musical Features},
      year = {2010},
      author = {L. Mearns and S. Dixon}
    }
  • L. Mearns and S. Dixon, “How Do You Characterise Musical Style?.” 2010.
    [Bibtex]
    @inproceedings { Mea10c,
      title = {How Do You Characterise Musical Style?},
      journal = {Third International Conference of Students of Systematic Musicology},
      year = {2010},
      author = {L. Mearns and S. Dixon}
    }
  • M. Barthet and M. Sandler, “On the effect of reverberation on musical instrument automatic recognition.” 2010.
    [Bibtex]
    @inproceedings { Barthet:10d,
      title = {On the effect of reverberation on musical instrument automatic recognition},
      journal = {Proc. AES 128th Convention (paper 8110)},
      year = {2010},
      author = {Barthet, M. and Sandler, M.}
    }
  • M. O. Jewell, C. Rhodes, and M. d’Inverno, “Querying Improvised Music: Do You Sound Like Yourself?.” 2010.
    [Bibtex]
    @inproceedings { Jewell:2010,
      title = {Querying Improvised Music: Do You Sound Like Yourself?},
      journal = {Proc. of Int. Conference on Music Information Retrieval},
      year = {2010},
      author = {Michael O. Jewell and Christophe Rhodes and Mark d'Inverno}
    }
  • M. Mauch and S. Dixon, “Simultaneous Estimation of Chords and Musical Context from Audio,” IEEE Transactions on Audio, Speech and Language Processing, vol. 18, iss. 6, p. 1280–1289, 2010.
    [Bibtex]
    @article { Mau10a,
      title = {Simultaneous Estimation of Chords and Musical Context from Audio},
      journal = {{IEEE} Transactions on Audio, Speech and Language Processing},
      volume = {18},
      number = {6},
      year = {2010},
      pages = {1280–1289},
      author = {M. Mauch and S. Dixon}
    }
  • M. Barthet and M. Sandler, “Time-dependent automatic musical instrument recognition in solo recordings,” , Malaga (Spain), 2010, pp. 183-194.
    [Bibtex]
    @inproceedings { Barthet:10e,
      title = {Time-dependent automatic musical instrument recognition in solo recordings},
      journal = {7th Int. Symposium on Computer Music Modeling and Retrieval (CMMR 2010)},
      year = {2010},
      pages = {183-194},
      address = {Malaga (Spain)},
      author = {Barthet, M. and Sandler, M.}
    }
  • M. Chudy and S. Dixon, “Towards Music Performer Recognition Using Timbre Features.” 2010.
    [Bibtex]
    @inproceedings { Chu10a,
      title = {Towards Music Performer Recognition Using Timbre Features},
      journal = {Third International Conference of Students of Systematic Musicology},
      year = {2010},
      author = {M. Chudy and S. Dixon}
    }

2009

  • A. Anglade, R. Ramirez, and S. Dixon, “Genre Classification Using Harmony Rules Induced from Automatic Chord Transcriptions,” , Kobe, Japan, 2009, pp. 669-674.
    [Bibtex]
    @inproceedings { omras2-103,
      title = {Genre Classification Using Harmony Rules Induced from Automatic Chord Transcriptions},
      journal = {Proceedings of the 10th International Conference on Music Information Retrieval (ISMIR 2009)},
      year = {2009},
      month = {October, 2009},
      pages = {669-674},
      address = {Kobe, Japan},
      abstract = {We present an automatic genre classification technique making use of frequent chord sequences that can be applied on symbolic as well as audio data. We adopt a first-order logic representation of harmony and musical genres: pieces of music are represented as lists of chords and musical genres are seen as context-free definite clause grammars using subsequences of these chord lists. To induce the contextfree definite clause grammars characterising the genres we use a first-order logic decision tree induction algorithm. We report on the adaptation of this classification framework to audio data using an automatic chord transcription algorithm. We also introduce a high-level harmony representation scheme which describes the chords in term of both their degrees and chord categories. When compared to another high-level harmony representation scheme used in a previous study, it obtains better classification accuracies and shorter run times. We test this framework on 856 audio files synthesized from Band in a Box files and covering 3 main genres, and 9 subgenres. We perform 3-way and 2-way classification tasks on these audio files and obtain good classification results: between 67% and 79% accuracy for the 2-way classification tasks and between 58% and 72% accuracy for the 3-way classification tasks.},
      author = {Amelie Anglade and Rafael Ramirez and Simon Dixon}
    }
  • A. Anglade, R. Ramirez, and S. Dixon, “First-Order Logic Classi cation Models of Musical Genres Based on Harmony,” , Porto, Portugal, 2009, pp. 309-314.
    [Bibtex]
    @inproceedings { omras2-102,
      title = {First-Order Logic Classication Models of Musical Genres Based on Harmony},
      journal = {Proceedings of the 6th Sound and Music Computing Conference (SMC 2009)},
      year = {2009},
      month = {July, 2009},
      pages = {309-314},
      address = {Porto, Portugal},
      abstract = {We present an approach for the automatic extraction of transparent classification models of musical genres based on harmony. To allow for human-readable classification models we adopt a first-order logic representation of harmony and musical genres: pieces of music are represented as lists of chords and musical genres are seen as context-free definite clause grammars using subsequences of these chord lists. To induce the context-free definite clause grammars characterising the genres we use a first-order logic decision tree induction algorithm, Tilde. We test this technique on 856 Band in a Box files representing academic, jazz and popular music. We perform 2-class and 3-class classification tasks on this dataset and obtain good classification results: around 66% accuracy for the 3-class problem and between 72% and 86% accuracy for the 2-class problems. A preliminary analysis of the most common rules extracted from the decision tree models built during these experiments reveals a list of interesting and/or well-known jazz, academic and popular music harmony patterns.},
      author = {Amelie Anglade and Rafael Ramirez and Simon Dixon}
    }
  • M. Magas and P. Proutskova, “A location-tracking interface for ethnomusicological collections,” , Corfu, 2009.
    [Bibtex]
    @inproceedings { omras2-93,
      title = {A location-tracking interface for ethnomusicological collections},
      journal = {ECDL, WEMIS},
      year = {2009},
      month = {27/09/2009},
      address = {Corfu},
      author = {Magas, M. and Proutskova, P}
    }
  • D. Tidhar, G. Fazekas, S. Kolozali, and M. Sandler, “Publishing Music Similarity Features on the Semantic Web.” 2009.
    [Bibtex]
    @inproceedings { omras2-100,
      title = {Publishing Music Similarity Features on the Semantic Web},
      journal = {10th International Conference on Music Information Retrieval, Kobe, Japan},
      year = {2009},
      month = {26/10/2009},
      abstract = {We describe the process of collecting, organising and publishing a large set of music similarity features produced by the SoundBite playlist generator tool. These data can be a valuable asset in the development and evaluation of new Music Information Retrieval algorithms. They can also be used in Web-based music search and retrieval applications. For this reason, we make a database of features available on the Semantic Web via a SPARQL end-point, which can be used in Linked Data services. We provide examples of using the data in a research tool, as well as in a simple web application which responds to audio queries and finds a set of similar 
    tracks in our database.},
      author = {Tidhar, D. and Fazekas, G. and Kolozali, S. and Sandler, M.}
    }
  • C. Cannam, J. Reiss, and P. ;. Kudumakis, “Semantic music functionality for OMM,” , London, UK, 2009.
    [Bibtex]
    @inproceedings { omras2-131,
      title = {Semantic music functionality for OMM},
      journal = {Digital Media Project GA23, Contribution No 1242},
      year = {2009},
      month = {26 June 2009},
      address = {London, UK},
      URL = {http://open.dmpf.org/dmp1242.doc},
      author = { Cannam, C. and Reiss, J. and Kudumakis, P.;}
    }
  • P. ;. Kudumakis, “Semantic Audio in Advanced IPTV Terminal,” , London, UK, 2009.
    [Bibtex]
    @inproceedings { omras2-135,
      title = {Semantic Audio in Advanced IPTV Terminal},
      journal = {Digital Music Research Network Workshop (DMRN+4)},
      year = {2009},
      month = {22 Dec 2009},
      address = {London, UK},
      abstract = {This paper presents the ISO/IEC MPEG & ITU-T SG 16 joint standardisation work towards the specification of the Advanced IPTV Terminal (AIT). C4DM semantic audio technologies and their integration in AIT are further discussed.},
      keywords = {Semantic Audio; IPTV; Standard; MPEG; ISO; ITU;},
      URL = {http://www.elec.qmul.ac.uk/dmrn/events/dmrnp4/},
      author = {Kudumakis, P.;}
    }
  • M. Levy and M. Sandler, “Music Information Retrieval Using Social Tags and Audio,” IEEE Transactions on Multimedia, vol. 11, pp. 383-395, 2009.
    [Bibtex]
    @article { omras2-181,
      title = {Music Information Retrieval Using Social Tags and Audio},
      journal = {IEEE Transactions on Multimedia},
      volume = {11},
      year = {2009},
      month = {2009},
      pages = {383-395},
      chapter = {383},
      author = {M. Levy and M. Sandler}
    }
  • “Interacting With Linked Data About Music,” , Athens, Greece, 2009.
    [Bibtex]
    @inproceedings { omras2-83,
      title = {Interacting With Linked Data About Music},
      journal = {Web Science},
      volume = {1},
      year = {2009},
      month = {17/03/2009},
      publisher = {WSRI},
      organization = {WSRI},
      edition = {1},
      address = {Athens, Greece},
      abstract = {In an effort to move towards intuitive visual interfaces for faceted browsing of structured data about music, we develop a visualization technique called k-pie}.  Derived from a network visualization technique know as $k$-cores decomposition, k-pie layout accounts for the semantic labels or `colors' associated with each vertex.  Vertices of a graph are arranged in a 2 dimensional circle where `slices' in the circle correspond to a specific vertex label and the most connected vertices are found in the center of the visualization.  We describe the k-pie algorithm and demonstrate how it can be useful in the context of Semantic Web technologies.  }
  • G. Fazekas and M. Sandler, “Uncovering the Details of Music Production Using Ontologies,” , London, UK, 2009.
    [Bibtex]
    @inproceedings { omras2-90,
      title = {Uncovering the Details of Music Production Using Ontologies},
      journal = {Unlocking Audio 2 - Connecting with Listeners},
      year = {2009},
      month = {16/03/2009},
      address = {London, UK},
      author = {Fazekas, G.  and Sandler, M.}
    }
  • G. Fazekas, C. Cannam, and M. Sandler, “Reusable Metadata and Software Components for Automatic Audio Analysis,” , Austin, Texas, USA, 2009.
    [Bibtex]
    @inproceedings { omras2-92,
      title = {Reusable Metadata and Software Components for Automatic Audio Analysis},
      journal = {IEEE/ACM Joint Conference on Digital Libraries JCDL’09 Workshop on Integrating Digital Library Content with Computational Tools and Services},
      year = {2009},
      month = {15/06/2009},
      address = {Austin, Texas, USA},
      author = {Fazekas, G.  and Cannam, C.  and Sandler, M.}
    }
  • G. Fazekas and M. Sandler, “Ontology Based Information Management in Music Production,” , Munich, Germany, 2009.
    [Bibtex]
    @inproceedings { omras2-91,
      title = {Ontology Based Information Management in Music Production},
      journal = {126th Convention of the AES},
      year = {2009},
      month = {07/05/2009},
      address = {Munich, Germany},
      author = {Fazekas, G.  and Sandler, M.}
    }
  • G. Fazekas, C. Cannam, and M. Sandler, “A Simple Guide To Automated Music Analysis on the Semantic Web,” 2009.
    [Bibtex]
    @techreport { omras2-98,
      title = {A Simple Guide To Automated Music Analysis on the Semantic Web},
      year = {2009},
      month = {04/2009},
      abstract = {We describe the construction of SAWA a simple Web-based system for automated audio analysis.  This system is capable of calculating an easily extended set of musically meaningful features such as beat, tempo, and key estimates from uploaded audio files, returning the results as rich RDF data suitable for interlinking on the Semantic Web. Unlike existing systems, our application is built on open and reusable components and provides an example of quick and straightforward development.},
      author = {Fazekas, G.  and Cannam, C.  and Sandler, M.}
    }
  • G. Fazekas and M. Sandler, “Novel Methods in Information Management for Advance Audio Workflows.” 2009.
    [Bibtex]
    @inproceedings { omras2-99,
      title = {Novel Methods in Information Management for Advance Audio Workflows},
      journal = {12th International Conference on Digital Audio Effects, Como, Italy},
      year = {2009},
      month = {01/09/2009},
      abstract = {This paper discusses architectural aspects of a software library for unified metadata management in audio processing applications.
    The data incorporates editorial, production, acoustical and musicological features for a variety of use cases, ranging from adaptive audio effects to alternative metadata based visualisation. Our system is designed to capture information, prescribed by modular ontology schema. This advocates the development of intelligent user interfaces and advanced media workflows in music production environments. In an effort to reach these goals, we argue for the need of modularity and interoperable semantics in representing information. We discuss the advantages of extensible Semantic Web ontologies as opposed to using specialised but disharmonious metadata formats. Concepts and techniques permitting seamless integration with existing audio production software are described in detail. 
    },
      author = {Fazekas, G.  and Sandler, M.}
    }
  • M. Casey, “Audio Tools for Music Discovery,” in Modern Methods for Musicology: Prospects, Proposals, and Realities, T. Crawford and L. Gibson, Eds., Ashgate, 2009, pp. 127-135.
    [Bibtex]
    @inbook { omras2-171,
      title = {Audio Tools for Music Discovery},
      booktitle = {Modern Methods for Musicology: Prospects, Proposals, and Realities},
      editor = {Tim Crawford and Lorna Gibson},
      year = {2009},
      pages = {127-135},
      publisher = {Ashgate},
      ISBN = {978 0 7546 7302 6},
      author = {Michael Casey}
    }
  • M. Barthet and M. Sandler, “A Vamp plugin for musical instrument identification: towards the indexation of digital music collections,” , London, 2009.
    [Bibtex]
    @inproceedings { Barthet:09,
      title = {A Vamp plugin for musical instrument identification: towards the indexation of digital music collections},
      journal = {Digital Music Research Network (DMRN+4) workshop},
      year = {2009},
      address = {London},
      author = {Barthet, M. and Sandler, M.}
    }
  • X. Wen and M. Sandler, “Additive and multiplicative reestimation schemes for the sinusoid modeling of audio,” , Glasgow, 2009.
    [Bibtex]
    @inproceedings { omras2-122,
      title = {Additive and multiplicative reestimation schemes for the sinusoid modeling of audio},
      journal = {EUSIPCO},
      year = {2009},
      edition = {2009},
      address = {Glasgow},
      abstract = {This paper discusses an approach to accurate sinusoid modeling of audio. We propose an iterative framework which functions as a “wrapper” that works with arbitrary sinusoid modeling systems to boost their accuracy. It involves one or more reestimation steps. In each step the parameter estimates are updated by combining a second set of parameters evalulated from the latest modeling error signal. An additive scheme and a multiplicative scheme are proposed for this reestimation step. On a limited test set the framework is shown to offer 2dB to 40.5dB (average 14.6dB) improvement in signal-to-residue ratio within 5 updates, which is 56.3% to 98.6% (average 79.5%) of the largest possible improvement,in dB, obtained by interpolating exact parameters.},
      author = {Wen, X. and Sandler, M.}
    }
  • X. Wen and M. Sandler, “Composite spectrogram using multiple Fourier transforms,” IET Signal Processing, vol. 3, p. 13, 2009.
    [Bibtex]
    @article { omras2-121,
      title = {Composite spectrogram using multiple Fourier transforms},
      journal = {IET Signal Processing},
      volume = {3},
      year = {2009},
      pages = {13},
      chapter = {51},
      abstract = {The authors propose a time–frequency (T–F) analysis method that uses a time- and frequencydependent resolution to represent a signal. The method is based on the idea of splitting the T–F plane into equal-TF-area Heisenberg boxes in some optimal way that closely matches spectral events. Compared with existing methods based on orthogonal decompositions, by lifting the orthogonality constraint, extra freedom is gained in the way the T–F plane can be partitioned, which enables time and frequency adaptation at the same time. A best tiling selection algorithm of quadratic complexity is derived using dynamic programming to find the optimal frame from a family. Experiments show the advantage of this more flexible representation.},
      author = {Wen, X. and Sandler, M.}
    }
  • A. Anglade and S. Dixon, Characterisation of Harmony with Inductive Logic Programming, 2009.
    [Bibtex]
    @misc { omras2-104,
      title = {Characterisation of Harmony with Inductive Logic Programming},
      year = {2009},
      note = {This poster won the first prize of the poster competition (open to PhD students and postdoctoral researchers).},
      abstract = {The explosion of the size of personal and commercial music collections has left both content providers and customers with a common difficulty: organising their huge musical libraries in such a way that each song can be easily retrieved, recommended and included in a playlist with similar songs. Because classifying large amounts of data is expensive and/or time-consuming, people are gaining interest in the automatic characterisation of songs. We present the first step towards a framework able to automatically induce rules characterising songs by various musical phenomena (e.g. rhythm, harmony, structure, etc.). For this study we are interested in the automatic extraction of harmony patterns. We analyse manually annotated chord data available in RDF and interlinked with web identifiers which themselves give access to a detailed description of the chords. We pre-process these data to obtain high-level information before passing them to an Inductive Logic Programming software which extracts the harmony rules underlying them. This framework is tested over the Real Book (jazz) songs and the Beatles' (pop) music. It generates a total over several experiments of 12,450 harmony rules characterising and differentiating these two datasets. An analysis of the most common rules reveals a list of well-known pop and jazz patterns.},
      author = {Amelie Anglade and Simon Dixon}
    }
  • M. Magas, R. Sewart, and B. Fields, “decibel 151: Collaborative Spatial Audio Interactive Environment.” 2009.
    [Bibtex]
    @inproceedings { omras2-87,
      title = {decibel 151: Collaborative Spatial Audio Interactive Environment},
      journal = {ACM SIGGRAPH},
      year = {2009},
      author = {Magas, M. and Sewart, R. and Fields, B.}
    }
  • T. Crawford, L. Gibson, and (eds.), Modern Methods for Musicology: Prospects, Proposals, and Realities, Ashgate, 2009.
    [Bibtex]
    @book { crawford+gibson,
      title = {Modern Methods for Musicology: Prospects, Proposals, and Realities},
      series = {Digital research in the arts and humanities},
      year = {2009},
      publisher = {Ashgate},
      ISBN = {978 0 7546 7302 6},
      author = {Tim Crawford and Lorna Gibson and (eds.)}
    }
  • X. Wen and M. Sandler, “Notes on model-based non-stationary sinusoid estimation methods using derivatives,” , Como, 2009.
    [Bibtex]
    @inproceedings { omras2-123,
      title = {Notes on model-based non-stationary sinusoid estimation methods using derivatives},
      journal = {DAFx 2009},
      year = {2009},
      address = {Como},
      abstract = {This paper reviews the derivative method and explores its capacity for estimating time-varying sinusoids of complicated parameter variations. The method is reformulated on a generalized signal model. We show that under certain arrangements the estimation task becomes solving a linear system, whose coefficients can be computed from discrete samples using an integration-by-parts technique. Previous derivative and reassignment methods are shown to be special cases of this generic method. We include a discussion on the continuity criterion of window design for the derivative method. The effectiveness of the method and the window design criterion are confirmed by test results. We also show that, thanks to the generalization, off-model sinusoids can be approximated by the derivative method with a sufficiently flexible model setting.},
      author = {Wen, X. and Sandler, M.}
    }
  • M. Mauch, C. Cannam, M. Davies, C. Harte, S. Kolozali, D. Tidhar, and M. Sandler, “OMRAS2 Metadata Project 2009,” 2009.
    [Bibtex]
    @techreport { omras2-97,
      title = {OMRAS2 Metadata Project 2009},
      year = {2009},
      author = {Matthias Mauch and Chris Cannam and Matthew Davies and Christopher Harte and Sefki Kolozali and Dan Tidhar and M. Sandler}
    }
  • X. Wen and M. Sandler, “Source-filter modeling in sinusoid domain,” , Munich, Germany, 2009.
    [Bibtex]
    @inproceedings { omras2-126,
      title = {Source-filter modeling in sinusoid domain},
      journal = {AES 126th Convention},
      year = {2009},
      address = {Munich, Germany},
      abstract = {This paper presents the theory and implementation of source-filter modelling in sinusoid domain and its applications on timbre processing. The technique decomposes the instantaneous amplitude in a sinusoid model into a source part and a filter part, each capturing a different aspect of the timbral property. We show that the sinusoid domain source-filter modelling is approximately equivalent to its time or frequency domain counterparts. Two methods are proposed for the evaluation of the source and filter, including a least-square method based on the assumption of slow variation of source and filter in time, and a filter bank method the models the global spectral envelope in the filter. Tests show the effectiveness of the algorithms for isolation frequency-driven amplitude variations. Example applications are given to demonstrate the use of the technique for timbre processing.},
      author = {Wen, X. and Sandler, M.}
    }
  • M. Mauch, K. Noland, and S. Dixon, “Using Musical Structure to Enhance Automatic Chord Transcription.” 2009.
    [Bibtex]
    @inproceedings { omras2-96,
      title = {Using Musical Structure to Enhance Automatic Chord Transcription},
      journal = {10th International Conference on Music Information Retrieval, Kobe, Japan},
      year = {2009},
      abstract = {Chord extraction from audio is a well-established music computing task, and many valid approaches have been presented in recent years that use different chord templates, smoothing techniques and musical context models. The present work shows that additional exploitation of the repetitive structure of songs can enhance chord extraction, by combining chroma information from multiple occurrences of the same segment type. To justify this claim we modify an existing chord labelling method, providing it with manual or automatic segment labels, and compare chord extraction results on a collection of 125 songs to baseline methods without segmentation information. Our method results in consistent and more readily readable chord labels and provides a statistically significant boost in label accuracy.
    },
      author = {Matthias Mauch and Katy Noland and Simon Dixon}
    }
  • B. Fields and C. Rhodes, An Audience Steerable Automatic Music Director for Online Radio Broadcast, 2009.
    [Bibtex]
    @unpublished {  Fields09a,
      title = {An Audience Steerable Automatic Music Director for Online Radio Broadcast},
      year = {2009},
      author = {Ben Fields and Christophe Rhodes}
    }
  • K. Noland and M. Sandler, “Influences of Signal Processing, Tone Profiles, and Chord Progressions on a Model for Estimating the Musical Key from Audio,” Computer Music Journal, vol. 33, iss. 1, 2009.
    [Bibtex]
    @article { Noland09CMJ,
      title = {Influences of Signal Processing, Tone Profiles, and Chord Progressions on a Model for Estimating the Musical Key from Audio},
      journal = {Computer Music Journal},
      volume = {33},
      number = {1},
      year = {2009},
      author = {Katy Noland and Mark Sandler}
    }
  • M. Barthet and M. Sandler, “Reconnaissance automatique d’instruments: une application à l’indexation automatique de base de données musicales,” , Marseille, France, 2009.
    [Bibtex]
    @inproceedings { Barthet:09b,
      title = {Reconnaissance automatique d’instruments: une application à l’indexation automatique de base de données musicales},
      journal = {5e Journées Jeunes Chercheurs en Audition, Acoustique musicale et Signal audio (JJCAAS)},
      year = {2009},
      address = {Marseille, France},
      author = {Barthet, M. and Sandler, M.}
    }

2008

  • A. Anglade and S. Dixon, “Characterisation of Harmony with Inductive Logic Programming,” , Philadelphia, Pennsylvania, USA, 2008, pp. 63-68.
    [Bibtex]
    @inproceedings { AmelieISMIR08,
      title = {Characterisation of Harmony with Inductive Logic Programming},
      journal = {Proceedings of the 9th International Conference on Music Information Retrieval (ISMIR 2008)},
      year = {2008},
      month = {September, 2008},
      pages = {63-68},
      address = {Philadelphia, Pennsylvania, USA},
      abstract = {We present an approach for the automatic characterisation of the harmony of song sets making use of relational induction of logical rules. We analyse manually annotated chord data available in RDF and interlinked with web identifiers for chords which themselves give access to the root, bass, component intervals of the chords. We pre-process these data to obtain high-level information such as chord category, degree and intervals between chords before passing them to an Inductive Logic Programming software which extracts the harmony rules underlying them. This framework is tested over the Beatles songs and the Real Book songs. It generates a total over several experiments of 12,450 harmony rules characterising and differentiating the Real Book (jazz) songs and the Beatles’ (pop) music. Encouragingly, a preliminary analysis of the most common rules reveals a list of well-known pop and jazz patterns that could be completed by a more in depth analysis of the other rules.},
      author = {Amélie Anglade and Simon Dixon}
    }
  • K. Jacobson, M. Davies, and M. Sandler, “The Effects of Lossy Audio Encoding on Onset Detection Tasks,” , San Francisco, CA, USA, 2008.
    [Bibtex]
    @inproceedings { omras2-57,
      title = {The Effects of Lossy Audio Encoding on Onset Detection Tasks},
      journal = {125th AES Convention},
      year = {2008},
      month = {October, 2008},
      address = {San Francisco, CA, USA},
      abstract = {In large audio collections, it is common to store audio content with perceptual encoding.  However, encoding parameters may vary from collection to collection or even within a collection - using different bit rates, sample rates, codecs, etc.  We evaluate the effect of various audio encodings on the onset detection task.  We show that audio-based onset detection methods are surprisingly robust in the presence of MP3 encoded audio.  Statistically significant changes in onset detection accuracy only occur at bit-rates lower than 32kbps.},
      author = {Kurt Jacobson and Matthew Davies and Mark Sandler}
    }
  • K. Jacobson, B. Fields, M. Sandler, and M. Casey, “The Effects of Lossy Audio Encoding on Genre Classification Tasks,” , Amsterdam, Netherlands, 2008.
    [Bibtex]
    @inproceedings { omras2-56,
      title = {The Effects of Lossy Audio Encoding on  Genre Classification Tasks},
      journal = {124th AES Convention},
      year = {2008},
      month = {May, 2008},
      address = {Amsterdam, Netherlands},
      abstract = {In large audio collections, it is common to store audio content using perceptual encoding.  However, encoding parameters may vary from collection to collection or even within a collection - using different bit rates, sample rates, codecs, etc.  We evaluate the effect of various lossy audio encodings on the application of audio spectrum projection features to the automatic genre classification tasks.  We show that decreases in mean classification accuracy, while small, are statistically significant for bit-rates of 96kbps or lower.  Also, a heterogeneous collection of audio encodings has statistically significant decreases in mean classification accuracy compared to a pure PCM collection.},
      author = {Kurt Jacobson and Ben Fields and Mark Sandler and Michael Casey}
    }
  • K. Jacobson, Z. Huang, and M. Sandler, “An Analysis Of On-Line Music Artist Networks,” , Norwich, UK, 2008, pp. 79-80.
    [Bibtex]
    @inproceedings { omras2-58,
      title = {An Analysis Of On-Line Music Artist Networks},
      journal = {NetSci 2008},
      year = {2008},
      month = {June, 2008},
      pages = {79-80},
      address = {Norwich, UK},
      abstract = {We are interested in using online social networks to automatically determine relationships between musicians and artists.  We hope to leverage such information for computational musicology studies and for designing new music recommendation systems.
      Myspace has become the de-facto standard for web-based music artist promotion.  It is estimated there are around 7 million artist pages on Myspace.  These pages typically include some media (streaming audio) and a list of “friends” specifying social connections.  This combination of user-authored media and a user-specified social network provides a unique data set that is unprecedented in scope and scale.
      We sample a portion of the Myspace artist network – only including artist pages in our sample (pages that include user-authored audio files).  We also collect audio data from these pages.  We show this network conforms in many respects to the topologies expected in social networks.  A variation on the concept of assortativity is used to examine the network structure in the context of musical genre.  Community structure is also evaluated with respect to musical genre.  Finally, audio-based analysis is used to  as a means of agglomerative community detection.
    The network statistics for our sample are summarized in Table 1. 
    
    #nodes
    #edges
    ave degree
    ave shrt pth
    diameter
    clstr coeff
    undirected
    15478
    91326
    11.80
    4.47
    9
    .219
    directed
    15478
    120487
    15.57
    6.42
    16
    -
    Similar values are commonly reported in social networks [Costa 2007].  However our sample size is insufficient to assume these values are indicative of the entire network.  
      The cumulative degree distributions for the network sample suggest close to a scale-free topology.  However, the power-law fit breaks down for high and low values of degree.  Similar “broad-scale” degree distributions have been reported for citation networks and movie actor networks [Amaral 2000].
    
    Assortativity
    We use the concept of genre to evaluate how the network structure relates to music.  Generally, an artist or a song is associated with one or more musical genres (i.e. rock, pop, rap, etc.).  On Myspace, the artist-user is given the option to specify a genre association.  The result is each artist page is associated with between 0 and 3 genre labels selected from a static set of 119 genre labels.  We are interested in the network assortativity with respect to genre – if there is a high degree of assortative mixing with respect to genre, this suggests the network structure could be meaningful in the context of musicology and music recommendation.  However, we are confronted with the unique problem of multiple labels – each node is associated with between 0 and 3 node types.  We propose two minor modifications to the assortativity calculation proposed by [Newman 2003].  In one method, we simply truncate the list of genre labels so each node is only associated with one label.  This results in a value of r=0.35.  In the second method, we preserve all genre labels and consider two nodes to be of the same type if they share one or more genre labels.  This results in a value of r=0.78.  Both methods suggest some level of assortative mixing, although on nearly opposite ends of the spectrum.  It is also shown that the number of shared genre labels between artist pairs decreases as geodesic distance between artists increases.  These results suggest that the structure of this musician network is meaningful in the context of music-related studies.
    
    },
      author = {Kurt Jacobson and Z. Huang and Mark Sandler}
    }
  • A. Anglade and S. Dixon, “Towards Logic-based Representations of Musical Harmony for Classification, Retrieval and Knowledge Discovery,” , Helsinki, Finland, 2008.
    [Bibtex]
    @inproceedings { AmelieMML08,
      title = {Towards Logic-based Representations of Musical Harmony for Classification, Retrieval and Knowledge Discovery},
      journal = {Proceedings of the International Workshop on Machine Learning and Music (MML2008 held in conjunction with ICML/COLT/UAI 2008)},
      year = {2008},
      month = {July, 2008},
      address = {Helsinki, Finland},
      abstract = {We present a logic-based framework using a relational description of musical data and logical inference for automatic characterisation of music. It is intended to be an alternative to the bag-of-frames approach for classification tasks but is also suitable for retrieval and musical knowledge discovery. We present the first results obtained with such a system using Inductive Logic Programming as inference method to characterise the Beatles and Real Book harmony. We conclude with a discussion of the knowledge representation problems we faced during these first tests.},
      author = {Amélie Anglade and Simon Dixon}
    }
  • B. Fields, K. Jacobson, M. Casey, and M. Sandler, “Do you sound like your friends? Exploring artist similarity via artist social network relationships and audio signal processing.” 2008.
    [Bibtex]
    @inproceedings { Fields-icmc-2008,
      title = {Do you sound like your friends? Exploring artist similarity via artist social network relationships and audio signal processing},
      journal = {Proc. of ICMC},
      year = {2008},
      month = {August},
      keywords = {music networks},
      author = {B. Fields and K. Jacobson and M. Casey and M. Sandler}
    }
  • P. Kudumakis, C. Cannam, C. Sutton, X. Wen, M. Levy, C. Harte, K. Noland, Y. Raimond, R. Zhou, I. Damnjanovic, J. Reiss, and S. and Sandler, “Semantic music technologies on DMP platform,” , London, UK, 2008.
    [Bibtex]
    @inproceedings { omras2-132,
      title = {Semantic music technologies on DMP platform},
      journal = {Digital Media Project GA17, Contribution No 1093},
      year = {2008},
      month = {25 Jan 2008},
      address = {London, UK},
      URL = {http://open.dmpf.org/dmp1093.doc},
      author = {Kudumakis, P. and Cannam, C. and Sutton, C. and Wen, X. and Levy, M. and Harte, C. and Noland, K. and Raimond, Y. and Zhou, R. and Damnjanovic, I. and Reiss, J. and Sandler, S. and }
    }
  • M. Mauch and S. Dixon, “A Discrete Mixture Model for Chord Labelling.” 2008.
    [Bibtex]
    @inproceedings { mauch:dmm:2008,
      title = {A Discrete Mixture Model for Chord Labelling},
      journal = {ISMIR 2008 Conference Proceedings, Philadelphia, USA},
      year = {2008},
      month = {2008},
      author = {Matthias Mauch and Simon Dixon}
    }
  • M. Mauch, D. Müllensiefen, Dixon S, and G. Wiggins, “Can Statistical Language Models be Used for the Analysis of Harmonic Progressions? .” 2008.
    [Bibtex]
    @inproceedings { mauch:csl:2008,
      title = {Can Statistical Language Models be Used for the Analysis of Harmonic Progressions? },
      journal = {Proceedings of the 10th International Conference on Music Perception and Cognition, Sapporo, Japan},
      year = {2008},
      month = {2008},
      author = {Mauch, M and Müllensiefen, D. and Dixon, S, and Wiggins, G.}
    }
  • G. Kreutz, M. Levy, and M. Sandler, “Emotion words for music by internet users.” 2008.
    [Bibtex]
    @inproceedings { omras2-184,
      title = {Emotion words for music by internet users},
      journal = {SEMPRE Empirical Musicology Conference},
      year = {2008},
      month = {2008},
      author = {G. Kreutz and M. Levy and M. Sandler}
    }
  • M. Levy and M. Sandler, “Latent semantic models for music,” Journal of New Music Research, vol. 37, pp. 137-150, 2008.
    [Bibtex]
    @article { omras2-182,
      title = {Latent semantic models for music},
      journal = {Journal of New Music Research},
      volume = {37},
      year = {2008},
      month = {2008},
      pages = {137-150},
      author = {M. Levy and M. Sandler}
    }
  • M. Levy and M. Sandler, “Structural segmentation of musical audio by constrained clustering,” IEEE Transactions on Audio Speech and Language Processing, vol. 16, pp. 318-326, 2008.
    [Bibtex]
    @article { omras2-183,
      title = {Structural segmentation of musical audio by constrained clustering},
      journal = {IEEE Transactions on Audio Speech and Language Processing},
      volume = {16},
      year = {2008},
      month = {2008},
      pages = {318-326},
      author = {M. Levy and M. Sandler}
    }
  • I. Damnjanovic, C. Landone, P. Kudumakis, and J. Reiss, Intelligent Infrastructure for Accessing Sound and Related Multimedia ObjectsFlorence, Italy: , 2008.
    [Bibtex]
    @proceedings { omras2-128,
      title = {Intelligent Infrastructure for Accessing Sound and Related Multimedia Objects},
      year = {2008},
      month = {17-19 Nov., 2008},
      pages = {121-126},
      address = {Florence, Italy},
      abstract = {In recent years, digital sound material becomes more and more available. However, there is still lack of qualitative solutions for access to digital sound archives. Not only that there is no consistency in formats of archived materials with related media often in separate collections, but related metadata are given in non-standard specialist format, incomplete or even erroneous. Hence, the full value of the archived material is hidden from the end user. EASAIER addresses these issues with the development of an innovative remote access system which extends beyond standard content management and retrieval systems. The EASAIER system focuses on sound archives, libraries, museums, broadcast archives, and music schools. However, the tools may be used by anyone interested in accessing archived material; amateur or professional, regardless of the material involved. Furthermore, it enriches the access experience enabling the user to experiment with the materials in exciting new ways. The system features; enhanced cross media retrieval functionality, multi-media synchronization, audio and video processing, analysis and visualization tools, all combined within in a single user configurable interface.},
      keywords = {Sound Archives, Multimedia Retrieval, Music Ontology, Time-Scaling},
      URL = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4688058},
      author = { Damnjanovic, I. and Landone, C. and Kudumakis, P. and Reiss, J.}
    }
  • I. Damnjanovic, C. Landone, P. Kudumakis, and J. ;. Reiss, “Accessing sound and related multimedia objects in EASAIER project,” , London, UK, 2008.
    [Bibtex]
    @inproceedings { omras2-134,
      title = {Accessing sound and related multimedia objects in EASAIER project},
      journal = {Digital Music Research Network Workshop (DMRN+3)},
      year = {2008},
      month = {16 Dec. 2008},
      address = {London, UK},
      abstract = {In recent years, digital sound material becomes more and more available. However, there is still lack of qualitative solutions for access to digital sound archives. Not only that there is no consistency in formats of archived materials with related media often in separate collections, but related metadata are given in non-standard specialist format, incomplete or even erroneous. Hence, the full value of the archived material is hidden from the end user. EASAIER addresses these issues with the development of an innovative remote access system which extends beyond standard content management and retrieval systems. The EASAIER system focuses on sound archives, libraries, museums, broadcast archives, and music schools. However, the tools may be used by anyone interested in accessing archived material; amateur or professional, regardless of the material involved. Furthermore, it enriches the access experience enabling the user to experiment with the materials in exciting new ways. The system features; enhanced cross media retrieval functionality, multi-media synchronization, audio and video processing, analysis and visualization tools, all combined within in a single user configurable interface.},
      keywords = {Sound Archives; Multimedia Retrieval; Music Ontology; Time-Scaling;},
      URL = {http://www.elec.qmul.ac.uk/dmrn/events/dmrnp3/},
      author = {Damnjanovic, I. and Landone, C. and Kudumakis, P. and Reiss, J.;}
    }
  • R. Stewart, M. Levy, and M. Sandler, “3D interactive environment for music collection navigation.” 2008.
    [Bibtex]
    @inproceedings { omras2-69,
      title = {3D interactive environment for music collection navigation},
      journal = {DAFX 2008},
      year = {2008},
      abstract = {Previous interfaces for large collections of music have used spatial audio to enhance the presentation of a visual interface or to add a mode of interaction. An interface using only audio information is presented here as a means to explore a large music collection in a two or three-dimensional space. By taking advantage of Ambisonics and binaural technology, the application presented here can scale to large collections, have flexible playback requirements, and can be optimized for slower computers. User evaluation reveals issues in creating an intuitive mapping between between user movements in physical space and virtual movement through the collection, but the novel presentation of the music collection has positive feedback and warrants further development.},
      author = {Stewart, Rebecca and Levy, Mark and Sandler, Mark}
    }
  • M. A. Casey, C. Rhodes, and M. Slaney, “Analysis of Minimum Distances in High-Dimensional Musical Spaces,” IEEE Transactions on Audio, Speech and Language Processing, vol. 16, iss. 5, p. 1015–1028, 2008.
    [Bibtex]
    @article { caseyetal:2008b,
      title = {Analysis of Minimum Distances in High-Dimensional Musical Spaces},
      journal = {IEEE Transactions on Audio, Speech and Language Processing},
      volume = {16},
      number = {5},
      year = {2008},
      pages = {1015–1028},
      author = {Casey, M. A. and Rhodes, C. and Slaney, M.}
    }
  • X. Wen and M. Sandler, “Analysis and synthesis of audio vibrato using harmonic sinusoids,” , Amsterdam, Netherlands, 2008.
    [Bibtex]
    @inproceedings { omras2-127,
      title = {Analysis and synthesis of audio vibrato using harmonic sinusoids},
      journal = {AES 124th Convention},
      year = {2008},
      address = {Amsterdam, Netherlands},
      abstract = {This paper introduces the analysis and synthesis of vibrato in music audio. The analyzer separates frequency modulators from their carriers using a demodulation process. It then describes the frequency variations of a vibrato using a period-synchronized parameter set, and the accompanying amplitude variations using a source-filter model, both of which can be regarded slow-varying. The synthesizer, on the other hand, reconstructs a vibrato from a given set of parameters. Using this system we are able to retrieve specific characteristics of vibratos, or modify them to implement various audio effects.},
      author = {Wen, X. and Sandler, M.}
    }
  • A. Arzt, G. Widmer, and S. Dixon, “Automatic Page Turning for Musicians via Real-Time Machine Listening.” 2008, pp. 241-245.
    [Bibtex]
    @inproceedings { Art08,
      title = {Automatic Page Turning for Musicians via Real-Time Machine Listening},
      journal = {Proceedings of the 18th European Conference on Artificial Intelligence (ECAI  2008)},
      editor = {M. Ghallab and C.D. Spyropoulos and N. Fakotakis and N. Avouris},
      year = {2008},
      pages = {241-245},
      publisher = {IOS Press, Amsterdam},
      organization = {IOS Press, Amsterdam},
      author = {A. Arzt and G. Widmer and S. Dixon}
    }
  • M. A. Casey, R. Veltkap, M. Goto, M. Leman, C. Rhodes, and M. Slaney, “Content-Based Music Information Retrieval: Current Directions and Future Challenges,” Proceedings of the IEEE, vol. 96, iss. 4, p. 668–696, 2008.
    [Bibtex]
    @article { caseyetal:2008,
      title = {Content-Based Music Information Retrieval: Current Directions and Future Challenges},
      journal = {Proceedings of the IEEE},
      volume = {96},
      number = {4},
      year = {2008},
      pages = {668–696},
      author = {Casey, M. A. and Veltkap, R. and Goto, M. and Leman, M. and Rhodes, C. and Slaney, M.}
    }
  • X. Wen and M. Sandler, “Evaluating parameters of time-varying sinusoids by demodulation,” , Espoo, 2008.
    [Bibtex]
    @inproceedings { omras2-124,
      title = {Evaluating parameters of time-varying sinusoids by demodulation},
      journal = {DAFx 2008},
      year = {2008},
      address = {Espoo},
      abstract = {In this paper we propose a method for reestimating the instanta-neous parameters of time-varying sinusoids based on demodula-tion. The method uses rough primitive parameter estimates to construct a sinusoidal multiplier. By multiplying this multiplier with the original sinusoid we get a third sinusoid with slower-varying parameters than the latter. In this way the analysis of a fast-varying sinusoid is reduced to that of a slow-varying one, whose parameters can be more reliably evaluated. We also pro-pose a front-end reestimator using variable window sizes to pro-vide the input to the demodulation-based reestimator, so that the primitive estimates is reliable even for fast-varying parts. This reestimation method is non-parametric, stable, easy to implement, and do not require the use of any specific estimator. Its effective-ness is shown by results on various test sets.},
      author = {Wen, X. and Sandler, M.}
    }
  • R. Macrae and S. Dixon, “From Toy to Tutor: Note-Scroller is a Game to Teach Music.” 2008.
    [Bibtex]
    @inproceedings { Mac08a,
      title = {From Toy to Tutor: Note-Scroller is a Game to Teach Music},
      journal = {8th International Conference on New Interfaces for Musical Expression},
      year = {2008},
      author = {R. Macrae and S. Dixon}
    }
  • M. Magas, M. Casey, and C. Rhodes, “mHashup: fast visual music discovery via locality sensitive hashing.” 2008.
    [Bibtex]
    @inproceedings { magasetal:2008,
      title = {mHashup: fast visual music discovery via locality sensitive hashing},
      journal = {ACM SIGGRAPH},
      year = {2008},
      note = {New Tech Demo},
      author = {Magas, M. and Casey, M. and Rhodes, C.}
    }
  • B. Fields, K. Jacobson, C. Rhodes, and M. Casey, “Social Playlists and Bottleneck Measurements : Exploiting Musician Social Graphs Using Content-Based Dissimilarity and Pairwise Maximum Flow Values.” 2008, p. 559–564.
    [Bibtex]
    @inproceedings { fieldsetal:2008,
      title = {Social Playlists and Bottleneck Measurements : Exploiting Musician Social Graphs Using Content-Based Dissimilarity and Pairwise Maximum Flow Values},
      journal = {International Symposium on Music Information Retrieval},
      year = {2008},
      pages = {559–564},
      author = {Fields, B. and Jacobson, K. and Rhodes, C. and Casey, M.}
    }
  • K. Jacobson, B. Fields, and M. Sandler, “Using Audio Analysis and Network Structure to Identify Communities in On-line Social Networks of Artists,” Proc. of ISMIR, 2008.
    [Bibtex]
    @article { Jacobson-ismir-2,
      title = {Using Audio Analysis and Network Structure to Identify Communities in On-line Social Networks of Artists},
      journal = {Proc. of ISMIR},
      year = {2008},
      keywords = {sampling networks},
      URL = {http://ismir2008.ismir.net/papers/ISMIR2008_118.pdf},
      author = {Kurt Jacobson and Ben Fields and Mark Sandler}
    }
  • G. Fazekas, Y. Raimond, and M. Sandler, “A framework for producing rich musical metadata in creative music production.” 2008.
    [Bibtex]
    @inproceedings { MyAES125SF,
      title = {A framework for producing rich musical metadata in creative music production},
      year = {2008},
      publisher = {125th Convention of the AES, San Francisco, USA},
      organization = {125th Convention of the AES, San Francisco, USA},
      author = {Gyorgy Fazekas and Yves Raimond and Mark Sandler}
    }
  • Y. Raimond, C. Sutton, and M. Sandler, Automatic Interlinking of Music Datasets on the Semantic Web, 2008.
    [Bibtex]
    @misc { Raimond-linking,
      title = {Automatic Interlinking of Music Datasets on the Semantic Web},
      editor = {Linked Data on the Web workshop},
      year = {2008},
      keywords = {matching music},
      author = {Yves Raimond and Christopher Sutton and Mark Sandler}
    }
  • G. Widmer, S. Dixon, P. Knees, E. Pampalk, and T. Pohle, From Sound to Sense via Feature Extraction and Machine Learning: Deriving High-Level Descriptors for Characterising Music, P. Polotti and D. Rocchesso, Eds., , 2008.
    [Bibtex]
    @book { Wid08a,
      title = {From Sound to Sense via Feature Extraction and Machine Learning: Deriving High-Level Descriptors for Characterising Music},
      series = {Sound to Sense – Sense to Sound: A State of the Art in Sound and Music Computing},
      editor = {P. Polotti and D. Rocchesso},
      year = {2008},
      pages = {161–194},
      author = {G. Widmer and S. Dixon and P. Knees and E. Pampalk and T. Pohle}
    }
  • K. Jacobson and M. Sandler, “Musically meaningful or just noise, An analysis of on-line artist networks.” 2008, pp. 306-314.
    [Bibtex]
    @inproceedings { Jacobson-cmmr-20,
      title = {Musically meaningful or just noise, An analysis of on-line artist networks},
      journal = {Proc. of CMMR},
      year = {2008},
      pages = {306-314},
      author = {K. Jacobson and M. Sandler}
    }
  • W. Goebl, S. Dixon, D. G. Poli, A. Friberg, R. Bresin, and G. Widmer, Sense in Expressive Music Performance: Data Acquisition, Computational Studies, and Models, P. Polotti and D. Rocchesso, Eds., , 2008.
    [Bibtex]
    @book { Goe08a,
      title = {Sense in Expressive Music Performance: Data Acquisition, Computational Studies, and Models},
      series = {Sound to Sense – Sense to Sound: A State of the Art in Sound and Music Computing},
      editor = {P. Polotti and D. Rocchesso},
      year = {2008},
      pages = {195–242},
      author = {W. Goebl and S. Dixon and G. De Poli and A. Friberg and R. Bresin and G. Widmer}
    }

2007

  • A. Anglade, M. Tiemann, and F. Vignoli, “Virtual communities for creating shared music channels,” , Vienna, Austria, 2007, pp. 95-100.
    [Bibtex]
    @inproceedings { AmelieISMIR07,
      title = {Virtual communities for creating shared music channels},
      journal = {Proceedings of the 8th International Conference on Music Information Retrieval (ISMIR 2007)},
      year = {2007},
      month = {September, 2007},
      pages = {95-100},
      address = {Vienna, Austria},
      abstract = {We present an approach to automatically create virtual communities of users with similar music tastes. Our goal is to create personalized music channels for these communities in a distributed way, so that they can for example be used in peer-to-peer networks. To find suitable techniques for creating these communities we analyze graphs created from real-world recommender datasets and identify specific properties of these datasets. Based on these properties we select and evaluate different graph-based community-extraction techniques. We select a technique that exploits identified properties to create clusters of music listeners. We validate the suitability of this technique using a music dataset and a large movie dataset. On a graph of 6,040 peers, the selected technique assigns at least 85% of the peers to optimal communities, and obtains a mean classification error of less than 0.05 over the remaining peers that are not assigned to the best community.},
      author = {Amélie Anglade and Marco Tiemann and Fabio Vignoli}
    }
  • A. Anglade, M. Tiemann, and F. Vignoli, “Complex-network theoretic clustering for identifying groups of similar listeners in p2p systems,” , Minneapolis, Minnesota, USA, 2007, pp. 41-48.
    [Bibtex]
    @inproceedings { AmelieRecSys07,
      title = {Complex-network theoretic clustering for identifying groups of similar listeners in p2p systems},
      journal = {Proceedings of the 1st ACM International Conference on Recommender Systems (RecSys 2007)},
      year = {2007},
      month = {October, 2008},
      pages = {41-48},
      publisher = {ACM},
      organization = {ACM},
      address = {Minneapolis, Minnesota, USA},
      abstract = {This article presents an approach to automatically create virtual communities of users with similar music preferences in a distributed system. Our goal is to create personalized music channels for these communities using the content shared by its members in peer-to-peer networks for each community. To extract these communities a complex network theoretic approach is chosen. A fully connected graph of users is created using epidemic protocols. We show that the created graph sufficiently converges to a graph created with a centralized algorithm after a small number of protocol iterations. To find suitable techniques for creating user communities, we analyze graphs created from real-world recommender datasets and identify specific properties of these datasets. Based on these properties, different graph-based community-extraction techniques are chosen and evaluated. We select a technique that exploits identified properties to create clusters of music listeners. The suitability of this technique is validated using a music dataset and two large movie datasets. On a graph of 6,040 peers, the selected technique assigns at least 85% of the peers to optimal communities, and obtains a mean classication error of less than 0.05% over the remaining peers that are not assigned to the best community.},
      author = {Amélie Anglade and Marco Tiemann and Fabio Vignoli}
    }
  • K. Jacobson, M. Davies, and M. Sandler, “Towards Textual Annotation of Rhythmic Style in Electronic Dance Music,” , New York, USA, 2007.
    [Bibtex]
    @inproceedings { omras2-55,
      title = {Towards Textual Annotation of Rhythmic Style  in Electronic Dance Music},
      journal = {123rd AES Convention},
      year = {2007},
      month = {October, 2007},
      address = {New York, USA},
      abstract = {Music information retrieval encompasses a complex and diverse set of problems.  Some recent work has focused on automatic textual annotation of audio data, paralleling work in image retrieval.  Here we take a narrower approach to the automatic textual annotation of music signals and focus on rhythmic style.  Training data for rhythmic styles are derived from simple, precisely labeled drum loops intended for content creation.  These loops are already textually annotated with the rhythmic style they represent.  The training loops are then compared against a database of music content to apply textual annotations of rhythmic style to unheard music signals.  Three distinct methods of rhythmic analysis are explored.  These methods are tested on a small collection of electronic dance music resulting in a labeling accuracy of 73\%.},
      author = {Kurt Jacobson and Matthew Davies and Mark Sandler}
    }
  • B. Fields and M. Casey, “Using Audio Classifiers as a Mechanism for Content Based Song Similarity,” , New York, NY, USA, 2007.
    [Bibtex]
    @inproceedings { Fields:2007yf,
      title = {Using Audio Classifiers as a Mechanism for Content Based Song Similarity},
      journal = {Proc. Audio Engineering Society 123rd Int. Conv.},
      year = {2007},
      month = {October, 2007},
      address = {New York, NY, USA},
      keywords = {audio classification, music similarity},
      author = {Ben Fields and Micheal Casey}
    }
  • B. Fields, “Using mixed feature extraction with multiple statistical models to achieve song categorization by genre,” , Vienna, Austria, 2007.
    [Bibtex]
    @inproceedings { Fields:2007fk,
      title = {Using mixed feature extraction with multiple statistical models to achieve song categorization by genre},
      journal = {Proc. Audio Engineering Society 122nd Int. Conv.},
      year = {2007},
      month = {May, 2007},
      publisher = {Audio Engineering Society},
      organization = {Audio Engineering Society},
      address = {Vienna, Austria},
      keywords = {music classification},
      author = {Benjamin Fields}
    }
  • M. Levy and M. Sandler, “A semantic space for music derived from social tags.” 2007, pp. 411-416.
    [Bibtex]
    @inproceedings { omras2-185,
      title = {A semantic space for music derived from social tags},
      journal = {International Conference on Music Information Retrieval},
      year = {2007},
      month = {2007},
      pages = {411-416},
      author = {M. Levy and M. Sandler}
    }
  • M. Sandler and M. Levy, “Signal-based music searching and browsing.” 2007, pp. 1-2.
    [Bibtex]
    @inproceedings { omras2-186,
      title = {Signal-based music searching and browsing},
      journal = {International Conference on Consumer Electronics},
      year = {2007},
      month = {2007},
      pages = {1-2},
      author = {M. Sandler and M. Levy}
    }
  • P. ;. Kudumakis, “Digital Media Project: Self exploiting your creativity with Open Source Interoperable DRM,” , London, UK, 2007.
    [Bibtex]
    @inproceedings { omras2-133,
      title = {Digital Media Project: Self exploiting your creativity with Open Source Interoperable DRM},
      journal = {Digital Music Research Network Workshop (DMRN+2)},
      year = {2007},
      month = {18 Dec 2007},
      address = {London, UK},
      abstract = {This paper aims to present a way on self exploiting your creativity in the multimedia world with the
    Digital Media Project’s Open Source Interoperable Digital Rights Management Platform, called Chillout®.},
      keywords = {Digital Rights Management; Multimedia; Open Source; Interoperability; Creativity; },
      URL = {http://www.elec.qmul.ac.uk/dmrn/events/dmrnp2/},
      author = {Kudumakis, P.;}
    }
  • C. Rhodes and M. Casey, “Algorithms for determining and labelling approximate hierarchical self-similarity.” 2007, p. 41–46.
    [Bibtex]
    @inproceedings { rhodescasey:2007,
      title = {Algorithms for determining and labelling approximate hierarchical self-similarity},
      journal = {International Symposium on Music Information Retrieval},
      year = {2007},
      pages = {41–46},
      author = {Rhodes, C. and Casey, M.}
    }
  • M. Mauch, S. Dixon, C. Harte, M. Casey, and B. Fields, “Discovering Chord Idioms through Beatles and Real Book Songs ,” , Vienna, Austria, 2007, pp. 255-258.
    [Bibtex]
    @inproceedings { omras2-86,
      title = {Discovering Chord Idioms through Beatles and Real Book Songs },
      journal = {8th International Conference on Music Information Retrieval, ISMIR 2007},
      year = {2007},
      pages = {255-258},
      address = {Vienna, Austria},
      abstract = {Modern collections of symbolic and audio music content provide unprecedented possibilities for musicological  research, but traditional qualitative evaluation methods cannot realistically cope with such amounts of data. We are interested in harmonic analysis and propose key-independent chord idioms derived from a bottom-up analysis of musical data as a new subject of musicological interest. In order to motivate future research on audio chord idioms and on probabilistic models of harmony we perform a quantitative study of chord progressions in two popular music collections. In particular, we extract common subsequences of chord classes from symbolic data, independent of key and context, and order them by frequency of occurrence, thus enabling us to identify chord idioms.
    We make musicological observations on selected chord idioms
    from the collections.},
      author = {Matthias Mauch and Simon Dixon and Christopher Harte and Michael Casey and Benjamin Fields}
    }
  • S. Dixon, “Evaluation of the Audio Beat Tracking System BeatRoot,” Journal of New Music Research, vol. 36, iss. 1, p. 39–50, 2007.
    [Bibtex]
    @article { Dix07a,
      title = {Evaluation of the Audio Beat Tracking System BeatRoot},
      journal = {Journal of New Music Research},
      volume = {36},
      number = {1},
      year = {2007},
      pages = {39–50},
      author = {S. Dixon}
    }
  • S. Dixon, D. Bainbridge, and T. R. (eds), Proceedings of the 8th International Conference on Music Information Retrieval (ISMIR07), Austrian Computer Society, 2007.
    [Bibtex]
    @book { Dix07c,
      title = {Proceedings of the 8th International Conference on Music Information Retrieval (ISMIR07)},
      year = {2007},
      publisher = {Austrian Computer Society},
      author = {S. Dixon and D. Bainbridge and R. Typke (eds)}
    }
  • X. Wen and M. Sandler, “Sinusoid modeling in a harmonic context,” , Bordeaux, 2007.
    [Bibtex]
    @inproceedings { omras2-125,
      title = {Sinusoid modeling in a harmonic context},
      journal = {DAFx 2007},
      year = {2007},
      address = {Bordeaux},
      abstract = {This article discusses harmonic sinusoid modeling. Unlike standard sinusoid analyzers, the harmonic sinusoid analyzer keeps close watch on partial harmony from an early stage of modeling, therefore guarantees the harmonic relationship among the sinusoids. The key element in harmonic sinusoid modeling is the harmonic sinusoid particle, which can be found by grouping short-time sinusoids. In-stead of tracking short-time sinusoids, the harmonic tracker operates on harmonic particles directly. To express harmonic partial frequen-cies in a compact and robust form, we have developed an inequality-based representation with adjustable tolerance on frequency errors and inharmonicity, which is used in both the grouping and tracking stages. Frequency and amplitude continuity criteria are considered for tracking purpose. Numerical simulations are performed on simple synthesized signals. },
      author = {Wen, X. and Sandler, M.}
    }
  • M. Levy, K. Noland, and M. Sandler, “A Comparison of Timbral and Harmonic Music Segmentation Algorithms,” , Honolulu, Hawai’i, 2007.
    [Bibtex]
    @inproceedings { Levy07Comparison,
      title = {A Comparison of Timbral and Harmonic Music Segmentation Algorithms},
      journal = {Proceedings of the 2007 {IEEE} International Conference on Acoustics, Speech and Signal Processing ({ICASSP})},
      year = {2007},
      address = {Honolulu, Hawai'i},
      author = {M. Levy and K. Noland and M. Sandler}
    }
  • F. Gouyon, S. Dixon, and G. Widmer, “Evaluating Low-Level Features for Beat Classification and Tracking.” 2007, p. 1309–1312.
    [Bibtex]
    @inproceedings { Gou07a,
      title = {Evaluating Low-Level Features for Beat Classification and Tracking},
      journal = {Proceedings of the 2007 International Conference on Acoustics, Speech and Signal Processing},
      volume = {{IV}},
      year = {2007},
      pages = {1309–1312},
      author = {F. Gouyon and S. Dixon and G. Widmer}
    }
  • K. Noland and M. Sandler, “Signal Processing Parameters for Tonality Estimation,” , Vienna, 2007.
    [Bibtex]
    @inproceedings { Noland07DSPParam,
      title = {Signal Processing Parameters for Tonality Estimation},
      journal = {Proceedings of AES 122nd Convention},
      year = {2007},
      address = {Vienna},
      author = {Katy Noland and Mark Sandler}
    }
  • S. Dixon, “Tools for Analysis of Musical Expression.” 2007, p. PPA-01-004.
    [Bibtex]
    @inproceedings { Dix07b,
      title = {Tools for Analysis of Musical Expression},
      journal = {19th International Congress on Acoustics},
      year = {2007},
      pages = {PPA-01-004},
      author = {S. Dixon}
    }
  • Y. Raimond, S. Abdallah, M. Sandler, and F. Giasson, The Music Ontology, 2007.
    [Bibtex]
    @misc { Raimond-MO-2007,
      title = {The Music Ontology},
      year = {2007},
      keywords = {music_ontology},
      author = {Y Raimond and S Abdallah and M Sandler and F Giasson}
    }

2006

  • M. Levy, M. Sandler, and M. Casey, “Extraction of High-Level Musical Structure From Audio Data and Its Application to Thumbnail Generation.” 2006, p. V-V.
    [Bibtex]
    @inproceedings { Levy:2006,
      title = {Extraction of High-Level Musical Structure From Audio Data and Its Application to Thumbnail Generation},
      journal = {Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on},
      volume = {5},
      year = {2006},
      pages = {V-V},
      abstract = {A method for segmenting musical audio with a hierarchical timbre model is introduced. New evidence is presented to show that music segmentation can be recast as clustering of timbre features, and a new clustering algorithm is described. A prototype thumbnail-generating application is described and evaluated. Experimental results are given, including comparison of machine and human segmentations},
      keywords = {musical_structure},
      ISBN = {1-4244-0469-X},
      URL = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1661200},
      author = {M. Levy and M. Sandler and M. Casey}
    }
  • K. Jacobson, “A Multifaceted Approach to Music Similarity.” 2006.
    [Bibtex]
    @inproceedings { Jacobson:2006fk,
      title = {A Multifaceted Approach to Music Similarity},
      journal = {Proc. of ISMIR},
      year = {2006},
      keywords = {music similarity, feature extraction},
      author = {K. Jacobson}
    }
  • K. Noland and M. Sandler, “Key Estimation Using a hidden Markov Model,” , Victoria, 2006.
    [Bibtex]
    @inproceedings { Noland06KeyEstim,
      title = {Key Estimation Using a hidden {M}arkov Model},
      journal = {Proceedings of the 7th International Conference on Music Information Retrieval},
      year = {2006},
      address = {Victoria},
      author = {Katy Noland and Mark Sandler}
    }

2005

  • S. Abdallah, K. Noland, M. Sandler, M. Casey, and C. Rhodes, “Theory and evaluation of a Bayesian music structure extractor,” , London, 2005.
    [Bibtex]
    @inproceedings { Abdallah05Bayesi,
      title = {Theory and evaluation of a Bayesian music structure extractor},
      journal = {Proceedings of the 6th International Conference on Music Information Retrieval},
      year = {2005},
      address = {London},
      author = {Samer Abdallah and Katy Noland and Mark Sandler and Michael Casey and Christophe Rhodes}
    }