Perceptually Weighted Mel-Cepstrum Analysis of Speech Based on Psychoacoustic Model

Hongwu YANG
Dezhi HUANG
Lianhong CAI

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E89-D    No.12    pp.2998-3001
Publication Date: 2006/12/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.12.2998
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
weighted mel-cepstral analysis,  auditory properties,  

Full Text: PDF(138.1KB)>>
Buy this Article



Summary: 
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 re-synthesis showed that the proposed method not only improved the speaker recognition performance, but also improved the speech quality of the re-synthesized speech.


open access publishing via