Online Unsupervised Classification With Model Comparison in the Variational Bayes Framework for Voice Activity Detection

Abstract

A new online, unsupervised method for Voice Activity Detection (VAD) is proposed. The conventional VAD methods often rely on heuristics to adapt the decision threshold to the estimated SNR. The proposed VAD method is based on the Variational Bayes (VB) approach to the online Expectation Maximization (EM), so that it can automatically adapt the decision level and the statistical model at the same time. We consider two parallel classifiers, one for the noise-only case, and the other for speech-and-noise case. Both models are trained concurrently and online using the VB framework. The VB framework also provides an explicit approximation of the log evidence called free energy. It is used to assess the reliability of the classifier in an online fashion, and to decide which model is more appropriate at a given time frame. Experimental evaluations were conducted on the CENSREC-1-C database designed for VAD evaluations. With the effect of the model comparison, the proposed scheme outperforms the conventional VAD algorithms, especially in the remote recording condition. It is also shown to be more robust with respect to changes of the noise type.