Negentropy based voice-activity detection for noise estimation in very low SNR condition


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/7792

Title:	Negentropy based voice-activity detection for noise estimation in very low SNR condition
Authors:	Rajkishore Prasad Hiroshi Saruwatari Kiyohiro Shikano
Keywords:	Negentropy VAD Generalized Gaussian distribution noise
Issue Date:	Nov-2004
Publisher:	電子情報通信学会
Journal Title:	IEICE Electronics Express
Volume:	1
Issue:	16
Start page:	495
End page:	500
Abstract:	The spectral organization in a noisy speech is different during noise-only portions and speech portions. Such chaotic difference can be tracked by using negentropy as a measure. Accordingly, a Voice Activity Detector (VAD) based on the negentropy measure of magnitude of spectral components of the pseudo-stationary segments of speech is proposed and has been used for the estimation of noise statistics from the noisy speech signal in very low SNR conditions. The results show the effectiveness and usefulness of the proposed method under very noisy conditions.
URI:	http://hdl.handle.net/10061/7792
URL:	https://search.ieice.org/
ISSN:	1349-2543
Rights:	Copyright (C) 2004 電子情報通信学会.
Text Version:	publisher
Publisher DOI:	10.1587/elex.1.495
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Size	Format
IEICEElecEx_1_16_495.pdf	6.49 MB	Adobe PDF	View/Open