DSP seminar, Wed Nov. 02 Time and location: 4:00-5:00 PM 2269 Beckman Institute


Title: Generalized Optimal Multi-Microphone Speech Enhancement 
Using Sequential Minimum Variance Distortionless Response(MVDR) 
Beamforming and Postfiltering


Speaker: Lae-Hoon Kim

Graduate Student
ECE Department, UIUC


Abstract:


A theoretical basis for optimal multichannel speech enhancement is

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 multichannel 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\%.