For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Noise-Robust Speech Analysis Using Running Spectrum Filtering
Qi ZHU Noriyuki OHTSUKI Yoshikazu MIYANAGA Norinobu YOSHIDA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2005/02/01
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Speech and Hearing
robust speech processing, noise reduction, running spectrum filtering, speech analysis, ARMA modeling,
Full Text: PDF(5.9MB)>>
This paper proposes a new robust adaptive processing algorithm that is based on the extended least squares (ELS) method with running spectrum filtering (RSF). By utilizing the different characteristics of running spectra between speech signals and noise signals, RSF can retain speech characteristics while noise is effectively reduced. Then, by using ELS, autoregressive moving average (ARMA) parameters can be estimated accurately. In experiments on real speech contaminated by white Gaussian noise and factory noise, we found that the method we propose offered spectrum estimates that were robust against additive noise.