September 22-25, 1997
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  based on Shannon's entropy . 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.
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.