T. Pfau, D. P. W. Ellis and A. Stolcke, “Multispeaker speech activity detection for the ICSI meeting recorder,” IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU ’01., 2001, pp. 107-110, doi: 10.1109/ASRU.2001.1034599.
As part of a project into speech recognition in meeting environments, we have collected a corpus of multi-channel meeting recordings. We expected the identification of speaker activity to be straightforward given that the participants had individual microphones, but simple approaches yielded unacceptably erroneous labelings, mainly due to crosstalk between nearby speakers and wide variations in channel characteristics. Therefore, we have developed a more sophisticated approach for multichannel speech activity detection using a simple hidden Markov model (HMM).
A baseline HMM speech activity detector has been extended to use mixtures of Gaussians to achieve robustness for different speakers under different conditions. Feature normalization and crosscorrelation processing are used to increase the channel independence and to detect crosstalk. The use of both energy normalization and crosscorrelation based post-processing results in a 35% relative reduction of the frame error rate.
Speech recognition experiments show that it is beneficial in this multi-speaker setting to use the output of the speech activity detector for pre-segmenting the recognizer input, achieving word error rates within 10% of those achieved with manual turn labeling.