Presentation 2012/12/13
Voice activity detection under noisy environment based on augmented execution of statistical noise suppression
YASUNARI OBUCHI, RYU TAKEDA, NAOYUKI KANDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new voice activity detection method for noisy environment, which is realized as a combination of statistical noise suppression and thresholding of the sound power. The pro-posed method achieves sufficiently high accuracy even by its simplest implementation, and could be further improved by modifying the noise suppression algorithm. More specifically, we focus on the tolerance of the VAD module to the speech distortion, and apply noise suppression in the frequency domain more aggressively, meaning that all the elements which are suspicious to be noise are strongly suppressed. The evaluation ex-periments using the CENSREC-1-C public database confirmed that the proposed method outperforms many known methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) VAD / Statistical noise suppression / OM-LSA / CENSREC-1-C
Paper # SLP-94
Date of Issue

Conference Information
Committee SP
Conference Date 2012/12/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Voice activity detection under noisy environment based on augmented execution of statistical noise suppression
Sub Title (in English)
Keyword(1) VAD
Keyword(2) Statistical noise suppression
Keyword(3) OM-LSA
Keyword(4) CENSREC-1-C
1st Author's Name YASUNARI OBUCHI
1st Author's Affiliation Central Research Laboratory Hitachi Ltd()
2nd Author's Name RYU TAKEDA
2nd Author's Affiliation Central Research Laboratory Hitachi Ltd
3rd Author's Name NAOYUKI KANDA
3rd Author's Affiliation Central Research Laboratory Hitachi Ltd
Date 2012/12/13
Paper # SLP-94
Volume (vol) vol.112
Number (no) 369
Page pp.pp.-
#Pages 6
Date of Issue