DocumentCode :
394262
Title :
A tail-sharing WFST composition algorithm for large vocabulary speech recognition
Author :
Caseiro, Diamantino ; Trancoso, Isabel
Author_Institution :
ID/IST, INESC, Lisbon, Portugal
Volume :
1
fYear :
2003
fDate :
6-10 April 2003
Abstract :
This paper presents an algorithm for approximating minimization in the context of the weighted finite-state transducers approach to large vocabulary speech recognition. The algorithm is designed for the integration of the lexicon with the language model and performs composition, determinization and pushing in one step. Furthermore, it uses tail-sharing in order to approximate minimization. Our results show that it is a good approximation to explicit minimization, with the added advantage that it can be used "on-the-fly" in a dynamic decoder.
Keywords :
approximation theory; decoding; minimisation; natural languages; speech recognition; composition; dynamic decoder; explicit minimization; language model; large vocabulary speech recognition; lexicon; minimization approximation; pushing; tail-sharing WFST composition algorithm; weighted finite-state transducers; Algorithm design and analysis; Context modeling; Decoding; Joining processes; Natural languages; Runtime; Scalability; Speech recognition; Transducers; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-7663-3
Type :
conf
DOI :
10.1109/ICASSP.2003.1198791
Filename :
1198791
Link To Document :
بازگشت