KMID : 1022420170090020103
|
|
Phonetics and Speech Sciences 2017 Volume.9 No. 2 p.103 ~ p.110
|
|
Selective pole filtering based feature normalization for performance improvement of short utterance recognition in noisy environments
|
|
Choi Bo-Kyeong
Ban Sung-Min Kim Hyung-Soon
|
|
Abstract
|
|
|
The pole filtering concept has been successfully applied to cepstral feature normalization techniques for noise-robust speech recognition. In this paper, it is proposed to apply the pole filtering selectively only to the speech intervals, in order to further improve the recognition performance for short utterances in noisy environments. Experimental results on AURORA 2 task with clean-condition training show that the proposed selectively pole-filtered cepstral mean normalization (SPFCMN) and selectively pole-filtered cepstral mean and variance normalization (SPFCMVN) yield error rate reduction of 38.6% and 45.8%, respectively, compared to the baseline system.
|
|
KEYWORD
|
|
speech recognition, feature normalization, noisy environment, pole filtering
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|