| Paper: | SP-L9.5 | ||
| Session: | Robust Features for Speech Recognition | ||
| Time: | Friday, May 21, 14:20 - 14:40 | ||
| Presentation: | Lecture | ||
| Topic: | Speech Processing: Robust Speech Recognition | ||
| Title: | CEPSTRAL GAIN NORMALIZATION FOR NOISE ROBUST SPEECH RECOGNITION | ||
| Authors: | Shingo Yoshizawa; Hokkaido University | ||
| Noboru Hayasaka; Hokkaido University | |||
| Naoya Wada; Hokkaido University | |||
| Yoshikazu Miyanaga; Hokkaido University | |||
| Abstract: | This report describes a robust speech recognition technique which normalizes cepstral gains in order to remove the effects of additive noise. We assume that the effects can be expressed by an approximate model which consists of gain and DC components in log-spectrum. Accordingly, we propose cepstral gain normalization (CGN) which normalizes the gains by means of calculating maximum and minimum values of cepstral coefficients in speech frames. The proposed method can extract noise robust features without a prior knowledge and environmental adaptation because it is applied to both training and testing data. We have evaluated recognition performance under noisy environments using Noisex-92 database and a 100 Japanese city names task. The CGN provides improvements of recognition accuracy at various SNRs comparing with combinations of conventional methods. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops