TY - GEN
T1 - Effective speaker adaptations for speaker verification
AU - Ahn, Sungjoo
AU - Kang, Sunmee
AU - Ko, Hanseok
PY - 2000
Y1 - 2000
N2 - This paper concerns effective speaker adaptation methods to solve the over-training problem in speaker verification, which frequently occurs when modeling a speaker with sparse training data. While various speaker adaptations have already been applied to speech recognition, these methods have not yet been formally considered in speaker verification. This paper proposes speaker adaptation methods using a combination of maximum a posteriori (MAP) and maximum likelihood linear regression (MLLR) adaptations, which are successfully used in speech recognition, and applies to speaker verification. Our aim is to remedy the small training data problem by investigating effective speaker adaptations for speaker modeling. Experimental results show that the speaker verification system using a weighted MAP and MLLR adaptation outperforms that of the conventional speaker models without adaptation by a factor of up to 5 times. From these results, we show that the speaker adaptation method achieves significantly better performance even when only small training data is available for speaker verification.
AB - This paper concerns effective speaker adaptation methods to solve the over-training problem in speaker verification, which frequently occurs when modeling a speaker with sparse training data. While various speaker adaptations have already been applied to speech recognition, these methods have not yet been formally considered in speaker verification. This paper proposes speaker adaptation methods using a combination of maximum a posteriori (MAP) and maximum likelihood linear regression (MLLR) adaptations, which are successfully used in speech recognition, and applies to speaker verification. Our aim is to remedy the small training data problem by investigating effective speaker adaptations for speaker modeling. Experimental results show that the speaker verification system using a weighted MAP and MLLR adaptation outperforms that of the conventional speaker models without adaptation by a factor of up to 5 times. From these results, we show that the speaker adaptation method achieves significantly better performance even when only small training data is available for speaker verification.
UR - http://www.scopus.com/inward/record.url?scp=0033676899&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033676899&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2000.859151
DO - 10.1109/ICASSP.2000.859151
M3 - Conference contribution
AN - SCOPUS:0033676899
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1081
EP - 1084
BT - Signal Processing Theory and Methods IIAudio and ElectroacusticsSpeech Processing I
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000
Y2 - 5 June 2000 through 9 June 2000
ER -