8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

A Comparison of Simultaneous 3-channel Blind Source Separation to Selective Separation on Channel Pairs using 2-channel BSS

Erik Visser, Kwokleung Chan, Stanley Kim, Te-Won Lee

SoftMax Inc, USA

A number of real-life speech applications using BSS have been reported for two channel applications but only a few have been reported for multi-channel (more than 2 channels) applications. Moreover these mostly involve simulation studies or real-life separations in controlled settings. In this paper some practical problems of multichannel applications will be analyzed. A methodology is proposed to bypass the full fledged higher dimensional BSS problem by exploiting the relative spatial arrangement of microphones to achieve improved speech enhancement by selective 2-channel BSS. The concept is illustrated on a 3 source / 3 microphone setup in speech recognition experiments involving an acoustic scene with a human speaker and interferring noise sources.

Full Paper

Bibliographic reference.  Visser, Erik / Chan, Kwokleung / Kim, Stanley / Lee, Te-Won (2004): "A comparison of simultaneous 3-channel blind source separation to selective separation on channel pairs using 2-channel BSS", In INTERSPEECH-2004, 2869-2872.