Title :
Speech recognition for DARPA Communicator
Author :
Aaron, A. ; Chen, S. ; Cohen, P. ; Dharanipragada, S. ; Eide, E. ; Franz, M. ; LeRoux, J.-M. ; Luo, X. ; Maison, B. ; Mangu, L. ; Mathes, T. ; Novak, M. ; Olsen, P. ; Picheny, M. ; Printz, H. ; Ramabhadran, B. ; Sakrajda, A. ; Saon, G. ; Tydlitat, B. ; Vi
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
We report the results of investigations in acoustic modeling, language modeling and decoding techniques, for the DARPA Communicator, a speaker-independent, telephone-based dialog system. By a combination of methods, including enlarging the acoustic model, augmenting the recognizer vocabulary, conditioning the language model upon the dialog state, and applying a post-processing decoding method, we lowered the overall word error rate from 21.9% to 15.0%, a gain of 6.9% absolute and 31.5% relative
Keywords :
acoustic signal processing; decoding; interactive systems; natural languages; speech coding; speech recognition; telephony; travel industry; DARPA Communicator; acoustic modeling; language modeling; post-processing decoding; recognizer vocabulary; speaker-independent dialog system; speech recognition; telephone-based dialog system; travel agent; word error rate reduction; Acoustic testing; Decoding; Error analysis; Humans; Loudspeakers; NIST; Natural languages; Speech recognition; Training data; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on
Conference_Location :
Salt Lake City, UT
Print_ISBN :
0-7803-7041-4
DOI :
10.1109/ICASSP.2001.940874
