11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Intra-Frame Variability as a Predictor of Frame Classifiability

Trond Skogstad, Torbjørn Svendsen

NTNU, Norway

This paper examines the association between the variability of the speech signal inside an analysis frame and the relative difficulty of classifying that frame. We introduce a novel measure of speech frame variability and show through classification experiments that this measure is a strong predictor of classifiability, even when conditioning on the distance to segment boundaries. Finally, we show how to incorporate the measure as weights in the discriminant function of a GMM-HMM recognizer, thereby increasing the relative importance of low variability frames in both decoding and training. This is shown to give a reduction in error rates.

Full Paper

Bibliographic reference.  Skogstad, Trond / Svendsen, Torbjørn (2010): "Intra-frame variability as a predictor of frame classifiability", In INTERSPEECH-2010, 1708-1711.