DocumentCode :
3326528
Title :
Development of the 2003 CU-HTK conversational telephone speech transcription system
Author :
Evermann, G. ; Chan, H.Y. ; Gales, M.J.F. ; Hain, T. ; Liu, X. ; Mrva, D. ; Wang, L. ; Woodland, P.C.
Author_Institution :
Eng. Dept., Cambridge Univ., UK
Volume :
1
fYear :
2004
fDate :
17-21 May 2004
Abstract :
The paper describes the development of the 2003 CU-HTK large vocabulary speech recognition system for conversational telephone speech (CTS). The system was designed based on a multipass, multibranch structure where the output of all branches is combined using system combination. A number of advanced modelling techniques, such as speaker adaptive training, heteroscedastic linear discriminant analysis, minimum phone error estimation and specially constructed single pronunciation dictionaries, were employed. The effectiveness of each of these techniques and their potential contribution to the result of system combination was evaluated in the framework of a state-of-the-art LVCSR system with sophisticated adaptation. The final 2003 CU-HTK CTS system constructed from some of these models is described and its performance on the DARPA/NIST 2003 rich transcription (RT-03) evaluation test set is discussed.
Keywords :
learning (artificial intelligence); natural languages; parameter estimation; speech recognition; conversational telephone speech transcription system; heteroscedastic linear discriminant analysis; large vocabulary speech recognition system; minimum phone error estimation; single pronunciation dictionaries; speaker adaptive training; system combination; Automatic speech recognition; Dictionaries; Error analysis; Linear discriminant analysis; NIST; Natural languages; Speech recognition; System testing; Telephony; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8484-9
Type :
conf
DOI :
10.1109/ICASSP.2004.1325969
Filename :
1325969
Link To Document :
بازگشت