Robust speech recognition with feature extraction using combined method of RSF and DRA

Author

Wada, Naoya ; Hayasaka, Noboru ; Yoshizawa, Shingo ; Miyanaga, Yoshikazu

Author_Institution

Hokkaido Univ., Sapporo, Japan

Volume

2

fYear

2004

fDate

26-29 Oct. 2004

Firstpage

1001

Abstract

The paper explores the extraction of speech features aiming at noise robustness for speech recognition and proposes advanced speech analysis techniques named RSF/DRA (running spectrum filtering/dynamic range adjustment). The proposed techniques, DRA and RSF, focus on speech feature adjustment. DRA normalizes cepstral dynamic ranges and RSF eliminates the jitter influences of speech feature parameters. Experiments on isolated word recognition were carried out using 40 male and 40 female speakers for training and 5 male and 5 female speakers for recognition. The results of the recognition rate improving from 17% to 63% versus running car noise at -10 dB SNR show the effectiveness and high noise robustness of the proposed method.

Keywords

FIR filters; acoustic noise; cepstral analysis; feature extraction; filtering theory; jitter; random noise; speech processing; speech recognition; FIR filtering; SNR; car noise; cepstral dynamic range normalization; dynamic range adjustment; isolated word recognition; jitter; noise robustness; robust speech recognition; running spectrum filtering; speech analysis; speech feature extraction; Cepstral analysis; Dynamic range; Feature extraction; Filtering; Jitter; Noise robustness; Signal to noise ratio; Speech analysis; Speech enhancement; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Information Technology, 2004. ISCIT 2004. IEEE International Symposium on

Print_ISBN

0-7803-8593-4

Type

conf

DOI

10.1109/ISCIT.2004.1413870

Filename

1413870