TY - GEN
T1 - Generalized optimal multi-microphone speech enhancement using sequential minimum variance distortionless response (MVDR) beamforming and postfiltering
AU - Kim, Lae Hoon
AU - Hasegawa-Johnson, Mark
AU - Sung, Koeng Mo
PY - 2006
Y1 - 2006
N2 - A theoretical basis for optimal multichannel speech enhancementis presented, sufficient, flexible to be used with any assumed statistical model and optimality criterion. Any Bayesian optimal one-channel estimator for speech enhancement can be generalized to the multi-channel case as a sequentially constructed minimum variance distortionless response (MVDR) beamformer followed by an optimal one-channel postfilter. We present experimental results using the minimum mean-square error log-spectral amplitude (MMSE-logSA) optimality criterion, applied to a statistical model with simplified channel but realistic inter-microphone noise coherence. Word error rate in the audio-visual speech in a car (AVICAR) corpus (moving car. windows open) is reduced from 18% to 9%.
AB - A theoretical basis for optimal multichannel speech enhancementis presented, sufficient, flexible to be used with any assumed statistical model and optimality criterion. Any Bayesian optimal one-channel estimator for speech enhancement can be generalized to the multi-channel case as a sequentially constructed minimum variance distortionless response (MVDR) beamformer followed by an optimal one-channel postfilter. We present experimental results using the minimum mean-square error log-spectral amplitude (MMSE-logSA) optimality criterion, applied to a statistical model with simplified channel but realistic inter-microphone noise coherence. Word error rate in the audio-visual speech in a car (AVICAR) corpus (moving car. windows open) is reduced from 18% to 9%.
UR - http://www.scopus.com/inward/record.url?scp=33947661901&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33947661901&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:33947661901
SN - 142440469X
SN - 9781424404698
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - III65-III68
BT - 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
T2 - 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006
Y2 - 14 May 2006 through 19 May 2006
ER -