Robust voice activity detection using the spectral peaks of vowel sounds

Chul Yoo, Dongsuk Yook

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

This letter proposes the use of vowel sound detection for voice activity detection. Vowels have distinctive spectral peaks. These are likely to remain higher than their surroundings even after severe corruption. Therefore, by developing a method of detecting the spectral peaks of vowel sounds in corrupted signals, voice activity can be detected as well even in low signal-to-noise ratio (SNR) conditions. Experimental results indicate that the proposed algorithm performs reliably under various noise and low SNR conditions. This method is suitable for mobile environments where the characteristics of noise may not be known in advance.

Original languageEnglish
Pages (from-to)451-453
Number of pages3
JournalETRI Journal
Volume31
Issue number4
DOIs
Publication statusPublished - 2009 Aug 1

Fingerprint

Signal to noise ratio
Acoustic waves

Keywords

  • Mobile environment
  • Spectral peak
  • Voice activity detection (VAD)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)
  • Electronic, Optical and Magnetic Materials

Cite this

Robust voice activity detection using the spectral peaks of vowel sounds. / Yoo, Chul; Yook, Dongsuk.

In: ETRI Journal, Vol. 31, No. 4, 01.08.2009, p. 451-453.

Research output: Contribution to journalArticle

@article{7638a9a69ae44725bd6691e6c88fb9da,
title = "Robust voice activity detection using the spectral peaks of vowel sounds",
abstract = "This letter proposes the use of vowel sound detection for voice activity detection. Vowels have distinctive spectral peaks. These are likely to remain higher than their surroundings even after severe corruption. Therefore, by developing a method of detecting the spectral peaks of vowel sounds in corrupted signals, voice activity can be detected as well even in low signal-to-noise ratio (SNR) conditions. Experimental results indicate that the proposed algorithm performs reliably under various noise and low SNR conditions. This method is suitable for mobile environments where the characteristics of noise may not be known in advance.",
keywords = "Mobile environment, Spectral peak, Voice activity detection (VAD)",
author = "Chul Yoo and Dongsuk Yook",
year = "2009",
month = "8",
day = "1",
doi = "10.4218/etrij.09.0209.0104",
language = "English",
volume = "31",
pages = "451--453",
journal = "ETRI Journal",
issn = "1225-6463",
publisher = "ETRI",
number = "4",

}

TY - JOUR

T1 - Robust voice activity detection using the spectral peaks of vowel sounds

AU - Yoo, Chul

AU - Yook, Dongsuk

PY - 2009/8/1

Y1 - 2009/8/1

N2 - This letter proposes the use of vowel sound detection for voice activity detection. Vowels have distinctive spectral peaks. These are likely to remain higher than their surroundings even after severe corruption. Therefore, by developing a method of detecting the spectral peaks of vowel sounds in corrupted signals, voice activity can be detected as well even in low signal-to-noise ratio (SNR) conditions. Experimental results indicate that the proposed algorithm performs reliably under various noise and low SNR conditions. This method is suitable for mobile environments where the characteristics of noise may not be known in advance.

AB - This letter proposes the use of vowel sound detection for voice activity detection. Vowels have distinctive spectral peaks. These are likely to remain higher than their surroundings even after severe corruption. Therefore, by developing a method of detecting the spectral peaks of vowel sounds in corrupted signals, voice activity can be detected as well even in low signal-to-noise ratio (SNR) conditions. Experimental results indicate that the proposed algorithm performs reliably under various noise and low SNR conditions. This method is suitable for mobile environments where the characteristics of noise may not be known in advance.

KW - Mobile environment

KW - Spectral peak

KW - Voice activity detection (VAD)

UR - http://www.scopus.com/inward/record.url?scp=68949114820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68949114820&partnerID=8YFLogxK

U2 - 10.4218/etrij.09.0209.0104

DO - 10.4218/etrij.09.0209.0104

M3 - Article

VL - 31

SP - 451

EP - 453

JO - ETRI Journal

JF - ETRI Journal

SN - 1225-6463

IS - 4

ER -