TY - GEN
T1 - Integrating detailed information into a language model
AU - Zhang, Ruiqiang
AU - Black, Ezra
AU - Finch, Andrew
AU - Sagisaka, Yoshinori
N1 - Publisher Copyright:
© 2000 IEEE.
PY - 2000
Y1 - 2000
N2 - Applying natural language processing technique to language modeling is a key problem in speech recognition. This paper describes a maximum entropy-based approach to language modeling in which both words together with syntactic and semantic tags in the long history are used as a basis for complex linguistic questions. These questions are integrated with a standard trigram language model or a standard trigram language model combined with long history word triggers and the resulting language model is used to rescore the N-best hypotheses output of the ATRSPREC speech recognition system. The technique removed 24% of the correctable error of the recognition system.
AB - Applying natural language processing technique to language modeling is a key problem in speech recognition. This paper describes a maximum entropy-based approach to language modeling in which both words together with syntactic and semantic tags in the long history are used as a basis for complex linguistic questions. These questions are integrated with a standard trigram language model or a standard trigram language model combined with long history word triggers and the resulting language model is used to rescore the N-best hypotheses output of the ATRSPREC speech recognition system. The technique removed 24% of the correctable error of the recognition system.
UR - http://www.scopus.com/inward/record.url?scp=0033676745&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033676745&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2000.861995
DO - 10.1109/ICASSP.2000.861995
M3 - Conference contribution
AN - SCOPUS:0033676745
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1595
EP - 1598
BT - Speech Processing II
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 -