TY - GEN
T1 - Discriminative learning of additive noise and channel distortions for robust speech recognition
AU - Han, Jiqing
AU - Han, Munsung
AU - Park, Gyu Bong
AU - Park, Jeongue
AU - Gao, Wen
AU - Hwang, Doosung
PY - 1998
Y1 - 1998
N2 - Learning the influence of additive noise and channel distortions from training data is an effective approach for robust speech recognition. Most of the previous methods are based on maximum likelihood estimation criterion. We propose a new method of discriminative learning environmental parameters, which is based on the minimum classification error (MCE) criterion. By using a simple classifier defined by ourselves and the generalized probabilistic descent (GPD) algorithm, we iteratively learn environmental parameters. After getting the parameters, we estimate the clean speech features from the observed speech features and then use the estimation of the clean speech features to train or test the back-end HMM classifier. The best error rate reduction of 32.1% is obtained, tested on a Korean 18 isolated confusion words task, relative to the conventional HMM system.
AB - Learning the influence of additive noise and channel distortions from training data is an effective approach for robust speech recognition. Most of the previous methods are based on maximum likelihood estimation criterion. We propose a new method of discriminative learning environmental parameters, which is based on the minimum classification error (MCE) criterion. By using a simple classifier defined by ourselves and the generalized probabilistic descent (GPD) algorithm, we iteratively learn environmental parameters. After getting the parameters, we estimate the clean speech features from the observed speech features and then use the estimation of the clean speech features to train or test the back-end HMM classifier. The best error rate reduction of 32.1% is obtained, tested on a Korean 18 isolated confusion words task, relative to the conventional HMM system.
UR - https://www.scopus.com/pages/publications/0031623656
U2 - 10.1109/ICASSP.1998.674372
DO - 10.1109/ICASSP.1998.674372
M3 - 会议稿件
AN - SCOPUS:0031623656
SN - 0780344286
SN - 9780780344280
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 81
EP - 84
BT - Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Y2 - 12 May 1998 through 15 May 1998
ER -