The performance degradation of automatic speech recognition system due to acoustic mismatch in training and testing environment is a severe problem for practical use of speech recognizer [1]. In this paper, we explore the effects of noise on individual speech feature vector statistics, and several feature normalization methods are used to compensate environment influence on feature vectors. We try to find out what kind of normalization is most effective and which feature vectors should be normalized in order to achieve robust features under adverse noise.
Cite as: Shieh, W.-C., Chang, S.-C. (1999) The dependence of feature vectors under adverse noise. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2395-2398, doi: 10.21437/Eurospeech.1999-525
@inproceedings{shieh99_eurospeech,
author={Woei-Chyang Shieh and Sen-Chia Chang},
title={{The dependence of feature vectors under adverse noise}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2395--2398},
doi={10.21437/Eurospeech.1999-525}
}