Consistent Wiener filtering: designing generalized time-frequency masks respecting spectrogram consistency

Jonathan Le Roux 1 Emmanuel Vincent 2 Yuu Mizuno 3 Hirokazu Kameoka 1 Nobutaka Ono 3 Shigeki Sagayama 3
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Wiener filtering has been one of the most widely used methods for source separation for several decades, in particular in audio signal processing. To exploit the short-term stationarity of audio signals, it is very often applied on time-frequency representations, especially the short-time Fourier transform (STFT). However, classical Wiener filtering does not take into account the intrinsically redundant structure of STFT spectrograms, and its output is actually in general not the optimal solution. We show here that by ensuring that the output spectrograms are “consistent”, i.e., that they correspond to actual time-domain signals, we can obtain a more efficient filtering.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/inria-00544086
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, December 7, 2010 - 11:25:40 AM
Last modification on : Thursday, March 21, 2019 - 2:20:42 PM
Long-term archiving on : Tuesday, March 8, 2011 - 3:53:07 AM

File

leroux_ASJ10.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00544086, version 1

Citation

Jonathan Le Roux, Emmanuel Vincent, Yuu Mizuno, Hirokazu Kameoka, Nobutaka Ono, et al.. Consistent Wiener filtering: designing generalized time-frequency masks respecting spectrogram consistency. ASJ Spring Meeting, Mar 2010, Tokyo, Japan. ⟨inria-00544086⟩

Share

Metrics

Record views

502

Files downloads

212