Perceptually Weighted Mel-Cepstrum Analysis of Speech Based on Psychoacoustic Model(Speech and Hearing)
スポンサーリンク
概要
- 論文の詳細を見る
This letter proposes a novel approach for mel-cepstral analysis based on the psychoacoustic model of MPEG. A perceptual weighting function is developed by applying cubic spline interpolation on the signal-to-mask ratios (SMRs) which are obtained from the psychoacoustic model. Experiments on speaker identification and speech resynthesis showed that the proposed method not only improved the speaker recognition performance, but also improved the speech quality of the resynthesized speech.
- 一般社団法人電子情報通信学会の論文
- 2006-12-01
著者
-
Cai Lianhong
Department Of Computer Science And Technology Tsinghua University
-
YANG Hongwu
College of Physics and Electronics Engineer, Northwest Normal University
-
HUANG Dezhi
Department of Computer Science and Technology, Tsinghua University
-
Huang Dezhi
Department Of Computer Science And Technology Tsinghua University:(present Office) France Telecom R
-
Yang Hongwu
Northwest Normal Univ. Chn