Voice Activity Detection Based on the Adaptive Multi-Rate Speech Codec Parameters
Daniele Giacobello, M. Semmoloni, David F. Neri, L. Prati, Sergio C. Brofferio · 2008
In this paper we present a new algorithm for Voice Activity Detection that operates on the Adaptive Multi-Rate codec pa-rameters. Traditionally, discriminating between speech and noise is done using time or frequency domain techniques. In speech communication systems that operate with coded speech, the discrimination cannot be done using traditional techniques unless the signal is decoded and processed, using an obviously inherently suboptimal scheme. The proposed al-gorithm performs the discrimination exploiting the statistical behavior of the set of parameters that characterize a segment of coded signal in case of presence or absence of voice. The algorithm presented provides significantly low misclassifica-tion probabilities making it competitive in speech communi-cation systems that require low computational costs, such as mobile terminals and networks.