Efficient combination of n-gram language models and recognition grammars in real-time lvcsr decoder

International Conference on Signal Processing Proceedings, ICSP

Volumn , Issue , 2008, Pages 587-591

  PraŽák, AleŠ ^a   Ircing, Pavel ^b   Švec, Jan ^b   Psutka, Josef ^b  

^a SpeechTech sro   (Czech Republic)

^b UNIVERSITY OF WEST BOHEMIA   (Czech Republic)

Author keywords

[No Author keywords available]

Indexed keywords

COMBINED MODEL; COMPOSITE MODELS; FIXED STRUCTURE; LANGUAGE MODELING; N-GRAM LANGUAGE MODELS; PROBABILITY ESTIMATE; REGULAR GRAMMAR;

DECODING; NATURAL LANGUAGE PROCESSING SYSTEMS; SIGNAL PROCESSING;

COMPUTATIONAL LINGUISTICS;

EID: 67249085232     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICOSP.2008.4697201     Document Type: Conference Paper

References (5)

1. J. Psutka, P. Ircing, J. V. Psutka, V. Radová, W. Byrne, J. Hajič, J. MírovskÝ, and S. Gustman, "Large Vocabulary ASR for Spontaneous Czech in the MALACH Project", in Proceedings of Eurospeech, Geneva, Switzerland, 2003.
2. F. Pereira and M. Riley, "Speech recognition by composition of weighted finite automata", Finite-State Language Processing, E. Roche and Y. Schabes, Eds. MIT Press, 1997.
3. A. Stolcke and J. Segal, "Precise N-gram Probabilities from Stochastic Context-free Grammars", in Proceedings of ACL, Las Cruces, USA, 1994.
4. A. Stolcke, "SRILM - An Extensible Language Modeling Toolkit", in Proceedings of ICSLP, Denver, USA, 2002.
5. A. PraŽák, L. Müller, J. Psutka, and J. Psutka, "LIVE TV SUBTITLING - Fast 2-pass LVCSR System for Online Subtitling", in Proceedings of SIGMAP, Barcelona, Spain, 2007.