5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Speech Signal Detection in Noisy Environement Using a Local Entropic Criterion

Imad Abdallah, Silvio Montresor, Marc Baudry

Laboratoire d'Informatique de l'Universite du Maine

This paper describes an original method for speech/non-speech detection in adverse conditions. Firstly, we define a time-dependent function called Local Entropic Criterion [1] based on Shannon's entropy [2]. Then we present the detection algorithm and show that at Signal to Noise Ratio (SNR) above 5 dB, it offers a segmentation comparable to the one obtained in clean conditions. We finally, describe how at very low SNR ( < 0 dB) , it permits to detect speech units masked by noise.

Full Paper

Bibliographic reference.  Abdallah, Imad / Montresor, Silvio / Baudry, Marc (1997): "Speech signal detection in noisy environement using a local entropic criterion", In EUROSPEECH-1997, 2595-2598.