Abstract
An automatic music transcription method is proposed. The method is based on a generative model that takes into account the translation of spectrum for an instrument and the sound path from the instrument to a microphone. The fundamental frequency (note), the spectrum of the instrument (basis pattern) and the sound path are estimated simultaneously using an extended complex nonnegative matrix factorization. The effectiveness of the proposed method is confirmed by synthetic data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Klapuri, A., Davy, M. (eds.): Signal Processing Methods for Music Transcription. Springer, Heidelberg (2006)
Lee, D.D., Seung, H.S.: Learning the Parts of Objects by Non-Negative Matrix Factorization. Nature 401, 788–791 (1999)
Lee, D.D., Seung, H.S.: Algorithms for Nonnegative Matrix Factorization. In: NIPS, pp. 556–562 (2000)
Plumbley, M., Abdallah, S., Bello, J., Davies, M., Monti, G., Sandler, M.: Automatic Music Transcription and Audio Source Separation. Cybernetics and Systems 33(6), 603–627 (2002)
Blumensath, T., Davies, M.: Sparse and Shift-Invariant Representations of Music. IEEE Trans. ASLP 14(1), 50–57 (2006)
Ihara, M., Maeda, S., Ishii, S.: Estimation of the Source-Filter Model Using Temporal Dynamics. In: Proc. International Joint Conference on Neural Networks, pp. 3098–3103 (2007)
Ihara, M., Maeda, S., Ishii, S.: Instrument Identification in Monophonic Music Using Spectral Information. In: International Symposium on Signal Processing and Information Technology, pp. 607–611 (2007)
Ihara, M.: Statistical Approach to the Single-Channel Sound Source Extraction. Ph.D. Thesis. Nara Institute of Science and Technology (2010)
Ihara, M., Maeda, S., Ikeda, K., Ishii, S.: Low-Dimensional Feature Representation for Monophonic Music Instrument Identification (to appear)
Cichocki, A., Zdunek, R., Phan, A., Amari, S.: Nonnegative Matrix and Tensor Factorizations. John Wiley & Sons Ltd. (2009)
Kameoka, H., Ono, N., Kashino, K., Sagayama, S.: Complex NMF: A New Sparse Representation for Acoustic Signals. In: International Conference on Acoustics, Speech and Signal Processing, pp. 3437–3440 (2009)
Eggert, J., Wersing, H., Koerner, E.: Transformation-Invariant Representation and NMF. In: International Joint Conference on Neural Networks (2004)
Raczynski, S.A., Ono, N., Sagayama, S.: Multipitch Analysis with Harmonic Nonnegative Matrix Approximation. In: International Symposium on Music Information Retrieval, p. 381 (2007)
Ochiai, K., Nakano, M., Ono, N., Sagayama, S.: Parallel Nonnegative Matrix Factorization of High-Time-Resolution and High-Frequency-Resolution Spectrograms for Multipitch Analysis of Music Signals. In: Acoustic Society of Japan Spring Conference, pp. 705–723 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ikeuchi, R., Ikeda, K. (2011). An Automatic Music Transcription Based on Translation of Spectrum and Sound Path Estimation. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7062. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24955-6_64
Download citation
DOI: https://doi.org/10.1007/978-3-642-24955-6_64
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24954-9
Online ISBN: 978-3-642-24955-6
eBook Packages: Computer ScienceComputer Science (R0)