Abstract
We describe the development of a speech activity detection system using an HMM-based segmenter for automatic speech recognition on individual headset microphones in multispeaker meetings. We look at cross-channel features (energy and correlation based) to incorporate into the segmenter for the purpose of addressing errors related to cross-channel phenomena such as crosstalk. Results demonstrate that these features provide a marked improvement (18pct. relative) over a baseline system using single-channel features as well as an improvement (8pct. relative) over our previous solution of separate speech activity detection and cross-channel analysis. In addition, the simple cross-channel energy features are shown to be more robust—and consequently better performing—than the more common correlation-based features.
Share this
