A conditional random field system for beat tracking

Autor: Thomas Fillon, Simon Durand, Cyril Joder, Slim Essid

Publikováno v: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia
ICASSP

In the present work, we introduce a new probabilistic model for the task of estimating beat positions in a musical audio recording, instantiating the Conditional Random Field (CRF) framework. Our approach takes its strength from a sophisticated tempo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eaad6e2289d9d5535f1628a5ed973906
https://hal.telecom-paris.fr/hal-02288433

A flexible multi-resolution time-frequency analysis framework for audio signals

Autor: Thomas Fillon, Jacques Prado

Publikováno v: 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)
11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), Jul 2012, Montreal, Canada. pp.1124-1129, ⟨10.1109/ISSPA.2012.6310459⟩
ISSPA

International audience; In this article, a new Constant-Q transform implementation is proposed together with a generalization of both the Short-Term Fourier Transform and the Constant-Q transform. The purpose of this generalization is to provide a di

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c72b4799796f4d98c4c9a5906d59c71
https://hal-imt.archives-ouvertes.fr/hal-00782297/document

How sparsely can a signal be approximated while keeping its class identity?

Autor: Thomas Fillon, Manuel Moussallam, Laurent Daudet, Gael Richard

Publikováno v: 3rd international workshop
3rd international workshop, Oct 2010, Firenze, France. pp.25, ⟨10.1145/1878003.1878012⟩

This paper explores the degree of sparsity of a signal approximation that can be reached while ensuring that a sufficient amount of information is retained, so that its main characteristics remains. Here, sparse approximations are obtained by decompo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::839be04a8f7322ad47be56cb685a8a2d
https://doi.org/10.1145/1878003.1878012

Adapting a High Quality Audiovisual Database to PDA Quality

Autor: Hervé Bredin, K. McTait, Thomas Fillon, S. Colon, Gérard Chollet

Publikováno v: ISISPA 2005, International Symposium on Image and Signal Processing and Analysis
ISISPA 2005, International Symposium on Image and Signal Processing and Analysis, 2005, Zaghreb, Croatia
Scopus-Elsevier

Audiovisual sequences in the BANCA database are degraded in quality so that they resemble audiovisual sequences recorded using the in-built sensors of a handheld PDA device. The quality of the new database is therefore reduced on a number of levels,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7f97e41877fd4582ab72dcf9c8e5b96
https://hal.archives-ouvertes.fr/hal-01987836

Evaluation of an ERB frequency scale noise reduction for hearing aids: a comparative study

Autor: Jacques Prado, Thomas Fillon

Publikováno v: Speech Communication
Speech Communication, Elsevier : North-Holland, 2003, 39 (1), pp.23-32

Among speech enhancement methods, the Ephraim and Malah suppression rule (EMSR) has proven to be efficient in reducing the background noise while preventing from a common artefact: the musical noise. From psychoacoustic motivation, an implementation

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d52be6ac9ad2786adb5475ba6bc8042
https://hal-imt.archives-ouvertes.fr/hal-00743104