Large Vocabulary Continuous Speech Recognition Using Weighted Finite-State Transducers
Weighted finite-state transducers are an unifying formalism for the implementation and integration of the various knowledge sources and structures typical of a large vocabulary continuous speech recognition system.
In this work we show how those knowledge sources can be converted to this formalism, and how they can be integrated in an optimized network, using our finite-state library and tools.
Experiments performed using our system showed the importance of the optimization of the integrated network, and allowed us to obtain very significant improvements in the speed of the recognizer.
Unable to display preview. Download preview PDF.
- M. Mohri, M. Riley, D. Hindle, A. Ljolje, and F. Pereira. Full expansion of context-dependent networks in large vocabulary speech recognition. In Proc. ICASSP’ 98, Seattle, USA, May 1998.Google Scholar
- M. Mohri and M. Riley. Integrated context-dependent networks in very large vocabulary speech recognition. In Proc. Eurospeech’ 99, Budapest, Hungary, September 1999.Google Scholar
- J. Glass, T. Hazen, and I. Hetherington. Real-time telephone-based speech recognition in the jupiter domain. In Proc. ICASSP’ 2001, Utah, USA, May 2001.Google Scholar
- R. Haeb-Umbach and H. Ney. Improvements in beam search for 10000-word continuous-speech recognition. In IEEE Transactions on Speech and Audio Processing, April 1994.Google Scholar
- M. Mohri, F. Pereira, and M. Riley. Weighted automata in text and speech processing. In ECAI 96 Workshop, August 1996.Google Scholar
- D. Caseiro and I. Trancoso. On integrating the lexicon with the language model. In Proc. Eurospeech’ 2001, September 2001.Google Scholar
- D. Caseiro and I. Trancoso. Transducer composition for ”on-the-fly” lexicon and language model integration. In ASRU 2001 Workshop, December 2001.Google Scholar
- M. Mohri. Finite-state transducers in language and speech processing. Computational Linguistics, 23(2):269–311, June 1997.Google Scholar
- M. Mohri, F. Pereira, and M. Riley. A rational design for a weighted finite-state transducer library. In Automata Implementation. Second International Workshop on Implementing Automata, WIA’ 97. Springer Verlag, 1998. Lecture Notes in Computer Science 1436.Google Scholar
- J. Neto, C. Martins, H. Meinedo, and L. Almeida. The design of a large vocabulary speech corpus for portuguese. In Proc. Eurospeech’ 97, September 1997.Google Scholar
- H. Meinedo and J. Neto. Combination of acoustic models in continuous speech recognition hybrid systems. In Proc. ICSLP’ 2000, Beijing, China, October 2000.Google Scholar