Estimation of the number of sound sources using support vector machines and its application to sound source separation

Author

Yamamoto, K. ; Asano, F. ; van Rooijen, W.F.G. ; Ling, E.Y.L. ; Yamada, T. ; Kitawaki, N.

Author_Institution

Univ. of Tsukuba, Japan

Volume

5

fYear

2003

fDate

6-10 April 2003

Abstract

A method of estimating the number of sound sources in a reverberant sound field is proposed in this paper. It is known that the eigenvalue distribution of the spatial correlation matrix calculated from a multiple microphone input reflects information on the number of sources. However, in a reverberant sound field, the feature of the number of sources in the eigenvalue distribution is degraded by the room reverberation. In this paper, support vector machines is applied to classify the eigenvalue distributions which are not clearly separable. The proposed method is then applied to the source separation system and is evaluated via automatic speech recognition.

Keywords

array signal processing; correlation methods; eigenvalues and eigenfunctions; microphones; reverberation; signal classification; source separation; speech recognition; support vector machines; automatic speech recognition; eigenvalue distribution classification; multiple microphone input; reverberant sound field; sound source number estimation; sound source separation; spatial correlation matrix; support vector machines; Acoustic noise; Background noise; Eigenvalues and eigenfunctions; Maximum likelihood detection; Microphone arrays; Noise level; Noise shaping; Source separation; Speech enhancement; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1200012

Filename

1200012