Infoscience

Conference paper

Exploiting Contextual Information for Speech/Non-Speech Detection

Parthasarathi, Sree Hari Krishnan; Motlicek, Petr; Hermansky, Hynek
  • Presented at: Text, Speech and Dialogue, Brno, Czech Republic
  • Series: Series of Lecture Notes In Artificial Intelligence (LNAI)
  • Springer-Verlag Berlin, Heidelberg, 2008

In this paper, we investigate the effect of temporal context for speech/non-speech detection (SND). It is shown that even a simple feature such as full-band energy, when employed with a large-enough context, shows promise for further investigation. Experimental evaluations on the test data set, with a state-of-the-art multi-layer perceptron based SND system and a simple energy threshold based SND method, using the F-measure, show an absolute performance gain of 4.4% and 5.4% respectively. The optimal contextual length was found to be 1000 ms. Further numerical optimizations yield an improvement (3.37% absolute), resulting in an absolute gain of 7.77% and 8.77% over the MLP based and energy based methods respectively. ROC based performance evaluation also reveals promising performance for the proposed method, particularly in low SNR conditions.

Fulltext

Related material

Contacts

EPFL authors