DocumentCode
2996477
Title
Decoder selection based on cross-entropies
Author
Gopalakrishnan, P.S. ; Kanevsky, Dimitri ; Nadas, A. ; Nahamoo, David ; Picheny, M.A.
Author_Institution
Dept. of Comput. Sci., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
fYear
1988
fDate
11-14 Apr 1988
Firstpage
20
Abstract
The authors generalize the maximum likelihood and related optimization criteria for training and decoding with a speech recognizer. The generalizations are constructed by considering weighted linear combinations of the logarithms of the likelihoods of words, of acoustics, and of (word, acoustic) pairs. The utility of various patterns of weights are examined
Keywords
codes; decoding; optimisation; speech recognition; acoustics; cross-entropies; decoder selection; decoding; logarithms; maximum likelihood techniques; optimisation criteria; speech recognition; weighted linear combinations; words; Acoustics; Computer science; Error analysis; Maximum likelihood decoding; Maximum likelihood estimation; Mutual information; Probability distribution; Random variables; Speech recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location
New York, NY
ISSN
1520-6149
Type
conf
DOI
10.1109/ICASSP.1988.196499
Filename
196499
Link To Document