• Home
  • Search
  • A New VAD Algorithm using Sparse Representation in Spectro-Temporal Domain
  • https://doi.org/10.7508/jist.2019.01.007Copy DOI Icon

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

  • Nov 4, 2019
  • Mohadese Eshaghi +2 more
Show More
  • Abstract
  • Literature Map
  • Similar Papers
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.

Similar Papers
  • Research Article
  • Citations2

A voice activity detection algorithm in spectro-temporal domain using sparse representation

  • Aug 01, 2018
  • International Journal of Machine Learning and Cybernetics
  • Mohadese Eshaghi +2
  • PDF
  • Research Article
  • Citations1

A Novel Voice Sensor for the Detection of Speech Signals

  • Dec 02, 2013
  • Sensors (Basel, Switzerland)
  • Kun-Ching Wang
  • Conference Article
  • Citations2

Quick and efficient definition of hangbefore and hangover criteria for voice activity detection

  • May 01, 2016
  • Damjan Vlaj +2
  • Conference Article
  • Citations18

Using Artificial Neural Network for Robust Voice Activity Detection Under Adverse Conditions

  • Jan 01, 2009
  • Tuan V Pham +2
  • Research Article
  • Citations1

CASA 시스템의 청각장면과 PAR를 이용한 음성 영역 검출에 관한 연구

  • Oct 25, 2013
  • Journal of the Institute of Electronics and Information Engineers
  • Jung-Ho Kim +2
  • Research Article
  • Citations24

Improved MO-LRT VAD based on bispectra Gaussian model

  • Jul 21, 2005
  • Electronics Letters
  • J.M GóRriz +3
  • Research Article
  • Citations2

Voice Activity Detector for Noise Spectrum Estimation Using a Dynamic Band-Splitting Entropy Estimate

  • Jan 01, 2011
  • International Journal of Computers and Applications
  • Kun-Ching Wang
  • Research Article
  • Citations6

Analysis of derivative of instantaneous frequency and its application to voice activity detection

  • May 14, 2021
  • Applied Acoustics
  • Binh Thien Nguyen +3
  • Conference Article
  • Citations3

A Robust Voice Activity Detection Method Based on Speech Enhancement

  • Jan 01, 2013
  • Xulei Bao +2
  • Book Chapter
  • Citations2

Low Computational Complexity Pitch Based VAD for Dynamic Environment in Hearing Aids

  • Jan 01, 2011
  • Yu-Jui Chen +3
  • Conference Article
  • Citations5

Research of Voice Activity Detection Algorithm

  • Oct 01, 2011
  • Zheng Hao +1
  • Research Article
  • Citations18

Deformable segmentation of 3D MR prostate images via distributed discriminative dictionary and ensemble learning.

  • Jun 30, 2014
  • Medical physics
  • Yanrong Guo +5
  • Research Article
  • Citations29

Kernel-Based Sensor Fusion With Application to Audio-Visual Voice Activity Detection

  • Dec 15, 2016
  • IEEE Transactions on Signal Processing
  • David Dov +2
  • Research Article
  • Citations3

Voice Activity Detection under Rayleigh distribution

  • Jul 01, 2009
  • Journal of Electronics (China)
  • Yu Li +2
  • Conference Article
  • Citations6

Development of an emotional speech synthesiser in Spanish

  • Sep 05, 1999
  • J M Montero +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.