New robust speech recognition using DTW in noise

Author

Zhang Yuxin ; Miyanaga, Yoshikazu ; Siriteanu, Constantin

Author_Institution

Grad. Sch. of Inf. Sci. & Technol., Hokkaido Univ., Sapporo, Japan

fYear

2010

Firstpage

34

Lastpage

38

Abstract

This paper proposes a new robust speech recognition method. Since the hidden Markov model (HMM) algorithm need a lot of training calculation, The dynamic time warping (DTW) algorithm based on median filter is used instead in our system. According to the short-term energy method, the non-speech segment can be removed. Recognition accuracy is thus improved. The cepstral mean subtraction (CMS), running spectrum filtering (RSF) and dynamic range adjustment (DRA) methods are also applied for noise reduction. Our results show that the RSF/DRA and CMS/DRA are good. The median filter improved the accuracy of DTW and The recognition accuracy almost are same and that one using HMM in the 10 dB and 20 dB white noise.

Keywords

cepstral analysis; hidden Markov models; median filters; speech recognition; white noise; cepstral mean subtraction; dynamic range adjustment; dynamic time warping algorithm; hidden Markov model; median filter; robust speech recognition; running spectrum filtering; short-term energy method; white noise; Accuracy; Hidden Markov models; Noise; Noise reduction; Robustness; Speech; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Information Technologies (ISCIT), 2010 International Symposium on

Conference_Location

Tokyo

Print_ISBN

978-1-4244-7007-5

Electronic_ISBN

978-1-4244-7009-9

Type

conf

DOI

10.1109/ISCIT.2010.5664917

Filename

5664917