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.

[1]  Mehryar Mohri,et al.  A Rational Design for a Weighted Finite-State Transducer Library , 1997, Workshop on Implementing Automata.

[2]  Andrej Ljolje,et al.  Full expansion of context-dependent networks in large vocabulary speech recognition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[3]  Isabel Trancoso,et al.  Transducer composition for "on-the-fly" lexicon and language model integration , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[4]  Mehryar Mohri,et al.  Integrated context-dependent networks in very large vocabulary speech recognition , 1999, EUROSPEECH.

[5]  Hermann Ney,et al.  Improvements in beam search for 10000-word continuous-speech recognition , 1994, IEEE Trans. Speech Audio Process..

[6]  Isabel Trancoso,et al.  On integrating the lexicon with the language model , 2001, INTERSPEECH.

[7]  Mehryar Mohri,et al.  Finite-State Transducers in Language and Speech Processing , 1997, CL.

[8]  João Paulo da Silva Neto,et al.  Combination of acoustic models in continuous speech recognition hybrid systems , 2000, INTERSPEECH.

[9]  James R. Glass,et al.  Real-time telephone-based speech recognition in the Jupiter domain , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[10]  Ciro Martins,et al.  The design of a large vocabulary speech corpus for portuguese , 1997, EUROSPEECH.