IEICE Electronics Express
Online ISSN : 1349-2543
LETTER
Linear-scale perceptual feature extraction for Speech Bandwidth Extensions
Kuekjae LeeSang Bae ChonMingu LeeKoeng-Mo Sung
Author information
Keywords: BWE, NMF, MFCCs
JOURNALS FREE ACCESS

2011 Volume 8 Issue 14 Pages 1143-1148

Details
Abstract

This paper presents a new method to extract linear-scale perceptual feature as a subsitute of MFCCs for highband (3.4kHz∼) in Speech Bandwidth Extensions(BWE). The feature extraction method is based on the mel-scale constrained Nonnegative Matrix Factorization(NMF), which decompose linear-scale log spectrum into a linear combination of mel-scale latent variables. While MFCCs parametrization contains non-invertible procedures, suggested feature is represented in linear-scale and proper to recover the highband time-domain speech. Experiment results report that suggested feature shows better instrumental performance with narrowband MFCCs than real cepstrum without additional computation.

Information related to the author
© 2011 by The Institute of Electronics, Information and Communication Engineers
Previous article Next article
feedback
Top