Study of a voice activity detector and its influence on a noise reduction system

Noise robust voice activity detection based on periodic to aperiodic component ratio

“…VAD in the ''real world" such as in a car, or on the street, is particularly important in relation to speech enhancement techniques for estimating noise statistics from the non-speech periods (Le Bouquin-Jeannès and Faucon, 1995), speech coding techniques that allow a variable bit-rate for discontinuous transmission (Srinivasan and Gersho, 1993;ITU-T Recommendation G.729 Annex B, 1996;ETSI TS 101 707, 2000), and automatic speech recognition (ASR) techniques designed to prevent false alarms that occur when noise signals are recognized as speech signals (Junqua et al, 1994). Since these techniques depend strongly on VAD accuracy or sometimes assume ideal VAD, insufficient VAD accuracy seriously affects their practical performance.…”

A study of lip movements during spontaneous dialog and its application to voice activity detection

“…Various types of audio VAD have been studied, and they can achieve good performance even with a low signal-to-noise ratio (SNR) (Le Bouquin-Jeannès and Faucon, 1995;Sohn, et al, 1999;Tanyer and Ozer, 2000;Ramírez et al, 2005). However these techniques are based on the analysis of the acoustic signal, and consequently their performance depends strongly on the environment noise.…”

New Advances in Voice Activity Detection using HOS and Optimization Strategies

“…The speech/non-speech classification task is not as trivial as it appears, and most of the VAD algorithms fail when the level of background noise increases. During the last decade, numerous researchers have developed different strategies for detecting speech on a noisy signal (Sohn et al, 1999), (Cho & Kondoz 2001) and have evaluated the influence of the VAD effectiveness on the performance of speech processing systems (Bouquin-Jeannes & Faucon, 1995) (see also the preceding chapter about VAD). Most of them have focussed on the development of robust algorithms with special attention on the derivation and study of noise robust features and decision rules (Woo et al, 2000), (Li et al, 2002), (Marzinzik & Kollmeier, 2002), (Sohn et al, 1999).…”