Skip to main content
×
×
Home

Chord-aware automatic music transcription based on hierarchical Bayesian integration of acoustic and language models

  • Yuta Ojima (a1), Eita Nakamura (a1), Katsutoshi Itoyama (a1) and Kazuyoshi Yoshii (a1)
Abstract

This paper describes automatic music transcription with chord estimation for music audio signals. We focus on the fact that concurrent structures of musical notes such as chords form the basis of harmony and are considered for music composition. Since chords and musical notes are deeply linked with each other, we propose joint pitch and chord estimation based on a Bayesian hierarchical model that consists of an acoustic model representing the generative process of a spectrogram and a language model representing the generative process of a piano roll. The acoustic model is formulated as a variant of non-negative matrix factorization that has binary variables indicating a piano roll. The language model is formulated as a hidden Markov model that has chord labels as the latent variables and emits a piano roll. The sequential dependency of a piano roll can be represented in the language model. Both models are integrated through a piano roll in a hierarchical Bayesian manner. All the latent variables and parameters are estimated using Gibbs sampling. The experimental results showed the great potential of the proposed method for unified music transcription and grammar induction.

  • View HTML
    • Send article to Kindle

      To send this article to your Kindle, first ensure no-reply@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about sending to your Kindle. Find out more about sending to your Kindle.

      Note you can select to send to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be sent to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

      Find out more about the Kindle Personal Document Service.

      Chord-aware automatic music transcription based on hierarchical Bayesian integration of acoustic and language models
      Available formats
      ×
      Send article to Dropbox

      To send this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Dropbox.

      Chord-aware automatic music transcription based on hierarchical Bayesian integration of acoustic and language models
      Available formats
      ×
      Send article to Google Drive

      To send this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Google Drive.

      Chord-aware automatic music transcription based on hierarchical Bayesian integration of acoustic and language models
      Available formats
      ×
Copyright
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
Corresponding author
Corresponding author: Kazuyoshi Yoshii Email: yoshii@kuis.kyoto-u.ac.jp
References
Hide All
[1]Smaragdis, P.; Brown, J.C.: Non-negative matrix factorization for polyphonic music transcription, in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2003, 177180.
[2]Hoffman, M.; Blei, D.M.; Cook, P.R.: Bayesian nonparametric matrix factorization for recorded music, in Int. Conf. on Machine Learning (ICML), 2010, 439446.
[3]Virtanen, T.; Klapuri, A.: Analysis of polyphonic audio using source-filter model and non-negative matrix factorization, in NIPS Workshop on Advances in Models for Acoustic Processing, 2006.
[4]Vincent, E.; Bertin, N.; Badeau, R.: Adaptive harmonic spectral decomposition for multiple pitch estimation. IEEE Trans. Audio, Speech, Language Process., 18 (3) (2010), 528537.
[5]Rocher, T.; Robine, M.; Hanna, P.; Strandh, R.: Dynamic chord analysis for symbolic music, in Int. Computer Music Conf. (ICMC), 2009, 4148.
[6]Sheh, A.; Ellis, D.P.: Chord segmentation and recognition using EM-trained hidden Markov models, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2003, 185191.
[7]Maruo, S.; Yoshii, K.; Itoyama, K.; Mauch, M.; Goto, M.: A feedback framework for improved chord recognition based on NMF-based approximate note transcription, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2015, 196200.
[8]Ueda, Y.; Uchiyama, Y.; Nishimoto, T.; Ono, N.; Sagayama, S.: HMM-based approach for automatic chord detection using refined acoustic features, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2010, 55185521.
[9]Liang, D.; Hoffman, M.: Beta process non-negative matrix factorization with stochastic structured mean-field variational inference, in NIPS Workshop on Advances in Variational Inference, 2014.
[10]Ojima, Y.; Nakamura, E.; Itoyama, I.; Yoshii, K.: A hierarchical Bayesian model of chords, pitches, and spectrograms for multipitch analysis, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2016, 309315.
[11]Emiya, V.; Badeau, R.; David, B.: Multipitch estimation of piano sounds using a new probabilistic spectral smoothness principle. IEEE Trans. Audio, Speech, Language Process., 18 (6) (2010), 16431654.
[12]Ycart, A.; Benetos, E.: A-MAPS: Augmented MAPS dataset with rhythm and key annotations, in Int. Society for Music Information Retrieval Conf. (ISMIR), Late Breaking Demo, 2018.
[13]Cemgil, A.T.: Bayesian inference for nonnegative matrix factorisation models. Comput. Intell. Neurosci., 2009 (ID:785152) (2009, 117.
[14]Durrieu, J.L.; Richard, G.; David, B.; Févotte, C.: Source/filter model for unsupervised main melody extraction from polyphonic audio signals. IEEE Trans. Audio, Speech, Language Process., 18 (3) (2010), 564575.
[15]Cheng, T.; Mauch, M.; Benetos, E.; Dixon, S.: An attack/decay model for piano transcription, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2016, 584590.
[16]Benetos, E.; Weyde, T.: Explicit duration hidden Markov models for multiple-instrument polyphonic music transcription, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2013, 269274.
[17]Berg-Kirkpatrick, T.; Andreas, J.; Klein, D.: Unsupervised transcription of piano music, in Advances in Neural Information Processing Systems (NIPS), 2014, 15381546.
[18]Benetos, E.; Weyde, T.: An efficient temporally-constrained probabilistic model for multiple-instrument music transcription, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2015, 701707.
[19]Smaragdis, P.: Convolutive speech bases and their application to speech separation. IEEE Trans. Audio, Speech, Language Process., 15 (1) (2007), 114.
[20]O'Hanlon, K.; Plumbley, M.D.: Polyphonic piano transcription using non-negative matrix factorisation with group sparsity, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2014, 31123116.
[21]Nam, J.; Ngiam, J.; Lee, H.; Slaney, M.: A classification-based polyphonic piano transcription approach using learned feature representations, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2011, 175180.
[22]Boulanger-Lewandowski, N.; Bengio, Y.; Vincent, P.: High- dimensional sequence transduction, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2013, 31783182.
[23]Hamanaka, M.; Hirata, K.; Tojo, S.: Implementing “A Generative Theory of Tonal Music”. J. New. Music. Res., 35 (4) (2006), 249277.
[24]Jackendoff, R.; Lerdahl, F.: A Generative Theory of Tonal Music. MIT Press, Cambridge, Massachusetts, 1985.
[25]Nakamura, E.; Hamanaka, M.; Hirata, K.; Yoshii, K.: Tree-structured probabilistic model of monophonic written music based on the generative theory of tonal music, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2016, 276280.
[26]Hu, D.; Saul, L.K.: A probabilistic topic model for unsupervised learning of musical key-profiles, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2009, 441446.
[27]Raczyński, S.; Vincent, E.; Bimbot, F.; Sagayama, S.: Multiple pitch transcription using DBN-based musicological models, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2010, 363368.
[28]Raczyński, S.; Vincent, E.; Sagayama, S.: Dynamic Bayesian networks for symbolic polyphonic pitch modeling. IEEE Trans. Audio, Speech, Language Process., 21 (9) (2013), 18301840.
[29]Böck, S.; Schedl, M.: Polyphonic piano note transcription with recurrent neural networks, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2012, 121124.
[30]Sigtia, S.; Benetos, E.; Dixon, S.: An end-to-end neural network for polyphonic piano music transcription. IEEE Trans. Audio, Speech, Language Process., 24 (5) (2016), 927939.
[31]Holzapfel, A.; Benetos, E.: The Sousta corpus: Beat-informed automatic transcription of traditional dance tunes, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2016, 531537.
[32]Ycart, A.; Benetos, E.: A study on LSTM networks for polyphonic music sequence modelling, in Int. Society for Music Information Retrieval Conf. (ISMIR), 2017, 421427.
[33]Smaragdis, P.; Raj, B.; Shashanka, M.: Sparse and shift-invariant feature extraction from non-negative data, in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2008, 20692072.
[34]Cemgil, A.T.; Dikmen, O.: Conjugate gamma Markov random fields for modelling nonstationary sources, in Independent Component Analysis and Signal Separation, 2007, 697705.
[35]Benetos, E.; Dixon, S.: Multiple-instrument polyphonic music transcription using a convolutive probabilistic model, in Sound and Music Computing Conf. (SMC), 2011, 1924.
[36]Schörkhuber, C.; Klapuri, A.; Holighaus, N.; Dörfler, M.: A Matlab toolbox for efficient perfect reconstruction time-frequency transforms with log-frequency resolution, in Audio Engineering Society Conf., 2014, 18.
[37]Fitzgerald, D.: Harmonic/percussive separation using median filtering, in Int. Conf. on Digital Audio Effects (DAFx), 2010, 14.
[38]Dixon, S.: On the computer recognition of solo piano music, in Australasian Computer Music Conf., 2000, 3137.
[39]Nakamura, E.; Yoshii, K.; Sagayama, S.: Rhythm transcription of polyphonic piano music based on merged-output HMM for multiple voices. IEEE Trans. Audio, Speech, Language Process., 25 (4) (2017), 794806.
[40]Johnson, M.: Using adaptor grammars to identify synergies in the unsupervised acquisition of linguistic structure, in Annual Meeting of the Association of Computational Linguistics (ACL), 2008, 398406.
[41]Mochihashi, D.; Yamada, T.; Ueda, N.: Bayesian unsupervised word segmentation with nested Pitman-Yor language modeling, in Annual Meeting of the Association of Computational Linguistics (ACL), 2009, 100108.
[42]Taniguchi, T.; Nagasaka, S.; Nakashima, R.: Nonparametric Bayesian double articulation analyzer for direct language acquisition from continuous speech signals. IEEE Trans. Cogn. Develop. Syst., 8 (3) (2016), 171185.
Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

APSIPA Transactions on Signal and Information Processing
  • ISSN: 2048-7703
  • EISSN: 2048-7703
  • URL: /core/journals/apsipa-transactions-on-signal-and-information-processing
Please enter your name
Please enter a valid email address
Who would you like to send this to? *
×

Keywords

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed