Speech separation algorithms for multiple speaker environments

Author

Kwan, C. ; Yin, J. ; Ayhan, B. ; Chu, S. ; Liu, X. ; Puckett, K. ; Zhao, Y. ; Ho, K.C. ; Kruger, M. ; Sityar, I.

Author_Institution

Signal Process., Inc., Rockville, MD

fYear

2008

fDate

1-8 June 2008

Firstpage

1644

Lastpage

1648

Abstract

Conventional speaker identification and speech recognition algorithms do not perform well if there are multiple speakers in the background. For high performance speaker identification and speech recognition applications in multiple speaker environments, a speech separation stage is essential. Here we summarize the implementation of three speech separation techniques. Advantages and disadvantages of each method are highlighted, as no single method can work under all situations. Stand-alone software prototypes for these methods have been developed and evaluated.

Keywords

source separation; speaker recognition; high performance speaker identification; multiple speaker environments; multiple speakers; speech recognition algorithms; speech separation algorithms; Acoustic sensors; Application software; Array signal processing; Frequency domain analysis; Independent component analysis; Microphones; Microwave integrated circuits; Software prototyping; Source separation; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on

Conference_Location

Hong Kong

ISSN

1098-7576

Print_ISBN

978-1-4244-1820-6

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2008.4634018

Filename

4634018