OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Optimal spectral transportation with application to music transcription

Flamary, Rémi and Févotte, Cédric and Courty, Nicolas and Emiya, Valentin Optimal spectral transportation with application to music transcription. (2016) In: 29th Conference on Advances in Neural Information Processing Systems (NIPS 2016), 5 December 2016 - 10 December 2016 (Barcelona, Spain).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
802kB

Official URL: https://papers.nips.cc/paper/6479-optimal-spectral-transportation-with-application-to-music-transcription

Abstract

Many spectral unmixing methods rely on the non-negative decomposition of spectral data onto a dictionary of spectral templates. In particular, state-of-the-art music transcription systems decompose the spectrogram of the input signal onto a dictionary of representative note spectra. The typical measures of fit used to quantify the adequacy of the decomposition compare the data and template entries frequency-wise. As such, small displacements of energy from a frequency bin to another as well as variations of timber can disproportionally harm the fit. We address these issues by means of optimal transportation and propose a new measure of fit that treats the frequency distributions of energy holistically as opposed to frequency-wise. Building on the harmonic nature of sound, the new measure is invariant to shifts of energy to harmonically-related frequencies, as well as to small and local displacements of energy. Equipped with this new measure of fit, the dictionary of note templates can be considerably simplified to a set of Dirac vectors located at the target fundamental frequencies (musical pitch values). This in turns gives ground to a very fast and simple decomposition algorithm that achieves state-of-the-art performance on real musical data.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Thanks to NIPS : Neural Information Processing Systems https://nips.cc/. This papers appears in Advances in Neural Information Processing Systems 29 : https://papers.nips.cc/book/advances-in-neural-information-processing-systems-29-2016 The original PDF is available at: https://papers.nips.cc/paper/6479-optimal-spectral-transportation-with-application-to-music-transcription
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Other partners > Aix-Marseille Université - AMU (FRANCE)
French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - INPT (FRANCE)
Other partners > Observatoire de la Côte d'Azur (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UPS (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Université de Bretagne Sud - UBS (FRANCE)
Laboratory name:
Funders:
European Research Council (ERC) under the European Union’s Horizon 2020 research & innovation programme (project FACTORY) - French ANR under the JCJC programme (project MAD)
Statistics:download
Deposited By: IRIT IRIT
Deposited On:13 Feb 2018 13:19

Repository Staff Only: item control page