TY - GEN
T1 - Speaker adaptation for hybrid MMI/connectionist speech-recognition systems
AU - Rottland, J.
AU - Neukirchen, C.
AU - Rigoll, G.
PY - 1998
Y1 - 1998
N2 - We present a new adaptation technique for our hybrid large vocabulary continuous speech recognition system. In most adaptation approaches the HMM parameters are reestimated. In our approach, however, we train a speaker independent continuous speech recognizer, then we keep the HMM parameters fixed and we train a second network, which transforms the features of the adaptation data to fit the HMM parameters. Thus, less parameters have to be estimated, and therefore this approach performs well even for a small number of adaptation data. With this approach we achieve relative improvements in recognition rates on the Wall Street Journal (WSJ) task of 16.5%.
AB - We present a new adaptation technique for our hybrid large vocabulary continuous speech recognition system. In most adaptation approaches the HMM parameters are reestimated. In our approach, however, we train a speaker independent continuous speech recognizer, then we keep the HMM parameters fixed and we train a second network, which transforms the features of the adaptation data to fit the HMM parameters. Thus, less parameters have to be estimated, and therefore this approach performs well even for a small number of adaptation data. With this approach we achieve relative improvements in recognition rates on the Wall Street Journal (WSJ) task of 16.5%.
UR - https://www.scopus.com/pages/publications/0031624631
U2 - 10.1109/ICASSP.1998.674468
DO - 10.1109/ICASSP.1998.674468
M3 - Conference contribution
AN - SCOPUS:0031624631
SN - 0780344286
SN - 9780780344280
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 465
EP - 468
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 -