A robust voice activity detector for wireless communications using soft computing

Abstract

Discontinuous transmission based on speech/pause detection represents a valid solution to improve the spectral efficiency of new-generation wireless communication systems. In this context, robust Voice Activity Detection (VAD) algorithms are required, as traditional solutions present a high misclassification rate in the presence of the background noise typical of mobile environments. This paper presents a voice detection algorithm which is robust to noisy environments thanks to a new methodology adopted for the matching process. More specifically, the VAD proposed is based on a pattern recognition approach in which the matching phase is performed by a set of six fuzzy rules trained by means of a new hybrid learning tool. A series of objective tests performed on a large speech database, varying the signal-to-noise ratio, the types of background noise and the input signal level, showed that, as compared with the VAD recently standardized by ITU-T in Rec. G.729 Annex B, the Fuzzy VAD on average achieves an improvement in reduction both of the activity factor of about 25 % and of the clipping introduced of about 43 %. Informal listening tests also confirm an improvement in the perceived speech quality.

Real-Time Robust Voice Activity Detection Using the Upper Envelope Weighted Entropy Measure and the Dual-Rate Adaptive Nonlinear Filter

“…Freeman et al proposed a set of metrics in [36], which are widely used to evaluate the performance of the voice activity detector [1,25,37]. Specifically, the five metrics are illustrated in Figure 11 and defined thereafter.…”

How to categorize emotional speech signals with respect to the speaker's degree of emotional intensity

“…Evaluations of this table show that features represented by indices of 18,24,25,26,29,34,41,48,62,64,65,68,71,86,165, and 178 are the most repeated features changed by more than 60%. Comparison between these features and those related to the intensity of angry mood shows a good match so that features indexed as follows are changed by more than 60% in both of these feelings in accordance with different emotional intensities:…”

Performance Evaluation of Automatic Speaker Recognition Techniques for Forensic Applications

“…Those two errors are then further classified according to the position of the error with respect to the nearest word; see [17] for a discussion of those parameters.…”