標題: Noise spectrum estimation with entropy-based VAD in non-stationary environments
作者: Wu, BF
Wang, KC
交大名義發表
National Chiao Tung University
關鍵字: noise measurement;voice activity detection;spectrum entropy
公開日期: 1-Feb-2006
摘要: This study presents a fast adaptive algorithm for noise estimation in non-stationary environments. To make noise estimation adapt quickly to non-stationary noise environments, a robust entropy-based voice activity detection (VAD) is thus required. It is well-known that the entropy-based measure defined in spectral domain is very insensitive to the changing level of nose. To exploit the specific nature of straight lines existing on speech-only spectrogram, the proposed spectrum entropy measurement improved from spectrum entropy proposed by Shen et al. is further presented and is named band-splitting spectrum entropy (BSE). Consequently, the proposed recursive noise estimator including BSE-based VAD can update noise power spectrum accurately even if the noise-level quickly changes.
URI: http://dx.doi.org/10.1093/ietfec/e89-a.2.479
http://hdl.handle.net/11536/12685
ISSN: 0916-8508
DOI: 10.1093/ietfec/e89-a.2.479
期刊: IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES
Volume: E89A
Issue: 2
起始頁: 479
結束頁: 485
Appears in Collections:Articles