Voice activity detection using convolutive non-negative sparse coding

Abstract

This paper presents a voice activity detection (VAD) approach using convolutive non-negative sparse coding (CNSC) to improve the detection performance in low signal-to-noise (SNR) conditions. Our idea is to use noise-robust feature for speech signal detection while noise is reduced away. We first use magnitude spectrum as the non-negative and additive lowlevel representation of audio signals, and learn a speech dictionary from clean speech as well as a noise dictionary from noise samples. Then, the two dictionaries are concatenated to form a global dictionary, and an audio signal is decomposed into coefficient vectors using CNSC on the global dictionary. Only coefficients corresponding to the bases from the speech dictionary are taken as the features for the signal. At last, the activity labels is given by decoding a conditional random field (CRF) which is constructed to model the context of an audio signal for VAD. Experiments demonstrate that our VAD approach has an excellent performance in low SNR conditions. Index Terms-voice activity detection, convolutive nonnegative sparse coding, conditional random fields

Spectrum enhancement with sparse coding for robust speech recognition

“…The difference is that the NSC concatenates sequential many frames to be a matrix and sets the constraint that the dictionary and the representations are non-negative. Recently, NSC with a speech dictionary and a noise dictionary can be found in speech recognition [39] and voice activity detection [49].…”