A specialized on-the-fly algorithm for lexicon and language model composition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 4, 2006, Pages 1281-1291

  Caseiro, Diamantino ^a,b,c   Trancoso, Isabel ^a,b,c  

^a IEEE   (Portugal)

^b INESC ID   (Portugal)

^c INSTITUTO SUPERIOR TÉCNICO   (Portugal)

Author keywords

Speech recognition; Weighted finite state transducers (WFSTs)

Indexed keywords

ONLINE COMPUTATION; OPTIMIZATION OPERATIONS; WEIGHTED FINITE STATE TRANSDUCERS (WFST);

ALGORITHMS; COMPUTATION THEORY; FINITE AUTOMATA; OPTIMIZATION; SPEECH RECOGNITION; TRANSDUCERS;

NATURAL LANGUAGE PROCESSING SYSTEMS;

EID: 34047273021     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.860838     Document Type: Article

References (21)

1. F. Pereira and M. Riley, "Speech recognition by composition of weighted finite automata," in Finite-State Language Processing, E. Roche and Y. Schabes, Eds. Cambridge, MA: MIT Press, 1997, pp. 431-453.
2. M. Mohri, F. Pereira, and M. Riley, "Weighted automata in text and speech processing," in Proc. ECAI Workshop, Aug. 1996, pp. 46-50.
3. _, "A rational design for a weighted finite-state transducer library," in Proc. Automata Implementation. 2nd Int. Workshop on Implementing Automata, WIA '97., vol. 1436, Lecture Notes in Computer Science, 1998, pp. 144-158.
4. C. Allauzen and M. Mohri, "Generalized optimization algorithm for speech recognition transducers," in Proc. ICASSP, vol. 1, Hong Kong, China, Apr. 2003, pp. 352-355.
5. M. Mohri, F. Pereira, and M. Riley, "Transducer composition for context-dependent netword expansion," in Proc. Eurospeech, Rhodes, Greece, Sep. 1997, pp. 1427-1430.
6. M. Mohri and M. Riley, "Integrated context-dependent networks in very large vocabulary speech recognition," in Proc. Eurospeech, vol. 2, Budapest, Hungary, Sep. 1999, pp. 811-814.
7. M. Mohri, "Finite-state transducers in language and speech processing," Comput. Linguistics, vol. 23, no. 2, pp. 269-311, Jun. 1997.
8. _, "Minimization algorithms for sequential transducers," Theor. Comput. Sci., vol. 234, pp. 177-201, 2000.
9. M. Mohri and M. Riley, "A weight pushing algorithm for large vocabulary speech recognition," in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001, pp. 1603-1606.
10. H. Dolfing and I. Hetherington, "Incremental language models for speech recognition using finite-state transducers," in Proc. ASRU Workshop, Trento, Italy, Dec. 2001, pp. 194-197.
11. D. Caseiro and I. Trancoso, "A decoder for finite-state structured search spaces," in Proc. ASR Workshop, Paris, France, Sep. 2000, pp. 35-39.
12. D. Willett and S. Katagiri, "Recent advances in efficient decoding combining on-line transducer composition and smoothed language model combination," in Proc. ICASSP, vol. 1, Orlando, FL, May 2002, pp. 713-716.
13. 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, vol. 2, Seattle, WA, May 1998, pp. 665-668.
14. D. Caseiro and I. Trancoso, "On integrating the lexicon with the language model," in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001, pp. 2131-2134.
15. S. Ortmanns, H. Ney, and A. Eiden, "Language-model look-ahead for large vocabulary speech recognition," in Proc. ICSLP, vol. 4, Philadelphia, PA, Oct. 1996, pp. 2095-2098.
16. F. Brugnara and M. Cettolo, "Improvements in tree-based language model representation," in Proc. Enrospeech, Madrid, Spain, Sep. 1995, pp. 2133-2136.
17. D. Caseiro, "Finite-State Methods in Automatic Speech Recognition," Ph.D. dissertation, Instituto Superior Técnico, Lisbon, Portugal, 2003.
18. H. Dolfing, "A comparison of prefix tree and finite-state transducer search space modelings for large-vocabulary speech recognition," in Proc. ICSLP, Denver, CO, Sep. 2002, pp. 1305-1308.
19. H. Meinedo, N. Souto, and J. Neto, "Speech recognition of broadcast news for the european Portuguese language," in Proc. ASRU Workshop, Trento. Italy, Dec. 2001, pp. 319-322.
20. H. Meinedo and J. Neto, "Combination of acoustic models in continuous speech recognition hybrid systems," in Proc. ICSLP, vol. 2, Beijing, China, Oct. 2000, pp. 931-934.
21. _, "Automatic speech annotation and transcription in a broadcast news task," in Proc. MSDR, Hong Kong, Apr. 2003, pp. 95-100.