A tail-sharing WFST composition algorithm for large vocabulary speech recognition

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.

[1]  Fernando Pereira,et al.  Weighted finite-state transducers in speech recognition , 2002, Comput. Speech Lang..

[2]  Hermann Ney,et al.  A comparison of two LVR search optimization techniques , 2002, INTERSPEECH.

[3]  MohriMehryar,et al.  Weighted finite-state transducers in speech recognition , 2002 .

[4]  Sadaoki Furui,et al.  Finite-state transducer based hungarian LVCSR with explicit modeling of phonological changes , 2002, INTERSPEECH.

[5]  James R. Glass,et al.  Learning units for domain-independent out-of- vocabulary word modelling , 2001, INTERSPEECH.

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

[7]  Fabio Brugnara,et al.  Improvements in tree-based language model representation , 1995, EUROSPEECH.

[8]  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..

[9]  Isabel Trancoso,et al.  Using dynamic WFST composition for recognizing broadcast news , 2002, INTERSPEECH.

[10]  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).

[11]  Alex Park,et al.  FST-based recognition techniques for multi-lingual and multi-domain spontaneous speech , 2001, INTERSPEECH.

[12]  Nuno Souto,et al.  Speech recognition of broadcast news for the European Portuguese language , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

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

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

[15]  Hans J. G. A. Dolfing.  Transducer search space modelings for large-vocabulary speech recognition , 2002, INTERSPEECH.