Transducer-based speech recognition with dynamic language models

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2013, Pages 642-646

  Georges, Munir ^a,b   Kanthak, Stephan ^a   Klakow, Dietrich ^b  

^a Babor Cosmetics   (Germany)

^b SAARLAND UNIVERSITY   (Germany)

Author keywords

Embedded grammars; Embedded speech recognition; Markov language models; Transducer nesting

Indexed keywords

MARKOV PROCESSES; MOBILE DEVICES; SPEECH RECOGNITION; TRANSDUCERS;

COMPUTATIONAL ENVIRONMENTS; DYNAMIC LANGUAGES; EMBEDDED GRAMMARS; LANGUAGE MODEL; PRE-PROCESSING STEP; SPEECH DECODING; WALL STREET JOURNAL; WORD ERROR RATE REDUCTIONS;

COMPUTATIONAL LINGUISTICS;

EID: 84905285948     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (31)

1. X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall PTR, May 2001.
2. L. Galescu, E. Ringger, and J. Allen, "Rapid language model development for new task domains, " in Proc. First International Conference on Language Resources and Evaluation (LREC, 1998.
3. R. Moore, D. Appelt, J. Dowding, J. M. Gawron, and D. Moran, "Combining linguistic and statistical knowledge sources in natural language processing for atis, " in In ARPA Spoken Language Technology Workshop, 1995.
4. W. Ward and S. Young, "Flexible use of semantic constraints in speech recognition, " in Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on, vol. 2, April, pp. 49-50 vol.2.
5. J. Gillett and W. Ward, "A language model combining trigrams and stochastic context-free grammars." in ICSLP. ISCA, 1998.
6. A. Nasr, Y. Esteve, F. Bechet, T. Spriet, and R. D. Mori, "A language model combining n-grams and stochastic finite automata, " in Proceedings of Euro speech, 1999, pp. 2175-2178.
7. J. Schalkwyk, I. L. Hetherington, and E. Story, "Speech recognition with dynamic grammars using finite-state transducers, " in INTERSPEECH, 2003.
8. H. J. G. A. Dolfing, P. G. Buckley, and D. Horowitz, "Unified language modeling using finite-state transducers with first applications." in INTERSPEECH. ISCA, 2004.
9. M. Mohri, "Local grammar algorithms, " in Inquiries into Words, Constraints, and Contexts., A. Arppe, L. Carlson, K. Lind̀en, J. Piitulainen, M. Suominen, M. Vainio, H. Westerlund, and A. Yli- Jyrä, Eds. Stanford University: CSLI Publications, 2005, pp. 84-93.
10. Y.-Y. Wang, M. Mahajan, and X. Huang, "A unified contextfree grammar and n-gram model for spoken language processing, " in Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on, vol. 3, 2000, pp. 1639 -1642 vol.3.
11. P. F. Brown, P. V. Desouza, R. L. Mercer, V. J. D. Pietra, and J. C. Lai, "Class-based n-gram models of natural language, " Jun. 07 1992.
12. E. Whittaker and R. Woodland, "Efficient class-based language modelling for very large vocabularies, " in Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on, vol. 1, 2001, pp. 545 -548 vol.1.
13. F. Brugnara and M. Federico, "Dynamic language models for interactive speech applications." in EUROSPEECH, G. Kokkinakis, N. Fakotakis, and E. Dermatas, Eds. ISCA, 1997.
14. C. Samuelsson and W. Reichl, "A class-based language model for large-vocabulary speech recognition extracted from part-ofspeech statistics, " in IEEE ICASSP-99. IEEE, 1999, pp. 537- 540.
15. P. R. Dixon, C. Hori, and H. Kashioka, "A specialized wfst approach for class models and dynamic vocabulary." in INTERSPEECH. ISCA, 2012.
16. D. B. Paul and J. M. Baker, "The design for the wall street journal based csr corpus." in ICSLP. ISCA, 1992.
17. E. G. Schukat-Talamazzini, Automatische Spracherkennung - Grundlagen, statistische Modelle und effiziente Algorithmen, ser. Künstliche Intelligenz. Vieweg, 1995.
18. R. Kneser and H. Ney, "Improved backing-off for m-gram language modeling, " in Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on, vol. 1, May, pp. 181-184 vol.1.
19. L. Karttunen, "The replace operator, " 1994.
20. M. Mohri, F. Pereira, and M. Riley, "Weighted automata in text and speech processing, " in IN ECAI-96 WORKSHOP. John Wiley and Sons, 1996, pp. 46-50.
21. F. C. N. Pereira and M. D. Riley, "Speech recognition by composition of weighted finite automata, " in Finite-State Language Processing. MIT Press, 1996, pp. 431-453.
22. M. Mohri, Weighted Finite State Transducer Algorithms: An Overview. Physica-Verlag, 2004.
23. M. Mohri, F. Pereira, and M. Riley, "Weighted finite state transducers in speech recognition." Computer Speech & Language, vol. 16, no. 1, pp. 69-88, 2002.
24. T. Hori, C. Hori, and Y. Minami, "Fast on-the-fly composition for weighted finite-state transducers in 1.8 million-word vocabulary continuous speech recognition, " in INTERSPEECH. ISCA, 2004.
25. T. Hori and A. Nakamura, "Generalized fast on-the-fly composition algorithm for wfst-based speech recognition." in INTERSPEECH. ISCA, 2005, pp. 557-560.
26. J. W. McDonough, E. Stoimenov, and D. Klakow, "An algorithm for fast composition of weighted finite-state transducers." in ASRU, S. Furui and T. Kawahara, Eds. IEEE, 2007, pp. 461- 466.
27. C. Allauzen and M. Mohri, "3-way composition of weighted finite-state transducers, " in CIAA, ser. Lecture Notes in Computer Science, O. H. Ibarra and B. Ravikumar, Eds., vol. 5148. Springer, 2008, pp. 262-273.
28. C. Allauzen and M. Mohri, "N-way composition of weighted finite-state transducers, " Int. J. Found. Comput. Sci., vol. 20, no. 4, pp. 613-627, 2009.
29. H. Ney and S. Ortmanns, "Dynamic programming search for continuous speech recognition, " 1999.
30. S. J. Young, "Token passing: A simple conceptual model for connected speech recognition systems, " Tech. Rep., Sep. 10 1989.
31. A. Stolcke, "Srilm - An extensible language modeling toolkit, " Jun. 06 2002.