Article


Article Code : 13980114178440(DOI : 10.7508/jist.2019.01.007)

Article Title : A New VAD Algorithm using Sparse Representation in Spectro-Temporal Domain

Journal Number : 25 Winter 2019

Visited : 70

Files : 1.05 MB


List of Authors

  Full Name Email Grade Degree Corresponding Author
1 Mohadeseh Eshaghi eshaghi463@yahoo.com Faculty Member PhD
2 Farbod Razzazi farbod_razzazi@yahoo.com Associate Professor PhD
3 Alireza Behrad behrad@shahed.ac.ir Associate Professor PhD

Abstract

This paper proposes two algorithms for Voice Activity Detection (VAD) based on sparse representation in spectro-temporal domain. The first algorithm was made using two-dimensional STRF (Spectro-Temporal Response Field) space based on sparse representation. Dictionaries with different atomic sizes and two dictionary learning methods were investigated in this approach. This algorithm revealed good results at high SNRs (signal-to-noise ratio). The second algorithm, whose approach is more complicated, suggests a speech detector using the sparse representation in four-dimensional STRF space. Due to the large volume of STRF's four-dimensional space, this space was divided into cubes, with dictionaries made for each cube separately by NMF (non-negative matrix factorization) learning algorithm. Simulation results were presented to illustrate the effectiveness of our new VAD algorithms. The results revealed that the achieved performance was 90.11% and 91.75% under -5 dB SNR in white and car noise respectively, outperforming most of the state-of-the-art VAD algorithms.