Blind suppression of nonstationary diffuse noise based on spatial covariance matrix decompositionReport as inadecuate




Blind suppression of nonstationary diffuse noise based on spatial covariance matrix decomposition - Download this document for free, or read online. Document in PDF available to download.

1 NTT Communication Science Laboratories 2 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery 3 NII - National Institute of Informatics Tokyo

Abstract : We propose methods for blind suppression of nonstationary diffuse noise based on decomposition of the observed spatial covariance matrix into signal and noise parts. In modeling noise to regularize the ill-posed decomposition problem, we exploit spatial invariance isotropy instead of temporal invariance stationarity. The isotropy assumption is that the spatial cross-spectrum of noise is dependent on the distance between microphones and independent of the direction between them. We propose methods for spatial covariance matrix decomposition based on least squares and maximum likelihood estimation. The methods are validated on real-world recordings.





Author: Nobutaka Ito - Emmanuel Vincent - Tomohiro Nakatani - Nobutaka Ono - Shoko Araki - Shigeki Sagayama -

Source: https://hal.archives-ouvertes.fr/



DOWNLOAD PDF




Related documents