Skip to main content
SISY 2016 - IEEE 14th International Symposium on Intelligent Systems and Informatics, Proceedings19 October 2016, Article number 7601516, Pages 45-5014th IEEE International Symposium on Intelligent Systems and Informatics, SISY 2016; Subotica; Serbia; 29 August 2015 through 31 August 2015; Category numberCFP1684C-ART; Code 124396

Advanced voice activity detection on mobile phones by using microphone array and phoneme-specific Gaussian mixture models(Conference Paper)

  Save all to author list
  • aUniversity of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia
  • bAlfaNum Speech Technologies, Novi Sad, Serbia

Abstract

This paper presents an advanced voice activity detection (VAD) system, developed for mobile Android OS platforms with limited hardware capabilities. The system uses a dual microphone array for noise suppression and a decoder with a constrained grammar for speech detection, where Gaussian mixture models (GMMs) are used together with their acoustic weights and energy in order to increase the robustness of the proposed system. The system is presented as part of the Voice Assistant application for mobile phones, and the results are given on a database that was especially designed for that purpose. The results presented in this paper show a high accuracy even when a large amount of background noise is present. © 2016 IEEE.

Indexed keywords

Engineering controlled terms:Cellular telephonesInformation scienceIntelligent systemsMicrophonesMobile devicesMobile phonesSpeech recognitionTelephone sets
Engineering uncontrolled termsBackground noiseDual microphonesGaussian Mixture ModelGaussian mixture model (GMMs)Microphone arraysNoise suppressionSpeech detectionVoice activity detection
Engineering main heading:Cellular telephone systems
  • ISBN: 978-150902866-5
  • Source Type: Conference Proceeding
  • Original language: English
  • DOI: 10.1109/SISY.2016.7601516
  • Document Type: Conference Paper
  • Sponsors:
  • Publisher: Institute of Electrical and Electronics Engineers Inc.

  Popovic, B.; University of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia;
© Copyright 2017 Elsevier B.V., All rights reserved.

Cited by 2 documents

Pertila, P. , Fagerlund, E. , Huttunen, A.
Online Own Voice Detection for a Multi-Channel Multi-Sensor In-Ear Device
(2021) IEEE Sensors Journal
Ong, W.Q. , Tan, A.W.C. , Vengadasalam, V.V.
Real-time robust voice activity detection using the upper envelope weighted entropy measure and the dual-rate adaptive nonlinear filter
(2017) Entropy
View details of all 2 citations
Inform me when this document is cited in Scopus:
Set citation alert Set citation feed
{"topic":{"name":"Voice Activity Detection; Speech Communication; Signal-to-Noise Ratio","id":12763,"uri":"Topic/12763","prominencePercentile":69.76989,"prominencePercentileString":"69.770","overallScholarlyOutput":0},"dig":"2b0afe89116fd9ae79e688d782478517a1a17d2e9561d73d82d9c5e75d138252"}

SciVal Topic Prominence

Topic:
Prominence percentile: