Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 4, 2007, Pages 1352-1365

  Hori, Takaaki ^a,b   Hori, Chiori ^a,c   Minami, Yasuhiro ^a   Nakamura, Atsushi ^a  

^a NTT Communication Science Laboratories   (Japan)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^c CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

On the fly composition; Speech recognition; Weighted finite state transducer (WFST)

Indexed keywords

HIGH-ACCURACY; LARGE VOCABULARIES; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; ON-THE-FLY COMPOSITION; ONE PASS; SEARCH ALGORITHMS; SEARCH METHODS; SEARCH SPACES; SPEECH TRANSCRIPTIONS; VITERBI SEARCHES; WEIGHTED FINITE-STATE TRANSDUCER (WFST);

CONTINUOUS SPEECH RECOGNITION; FAULT DETECTION; IMAGE CODING; LEARNING ALGORITHMS; PIEZOELECTRIC TRANSDUCERS; SPEECH ANALYSIS; SPEECH TRANSMISSION; TRANSCRIPTION; VOCABULARY CONTROL;

DECODING;

EID: 45849093239     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.889790     Document Type: Article

References (25)

1. C. Hori, T. Hori, H. Isozaki, E. Maeda, S. Katagiri, and S. Furui, "Deriving disambiguous queries in a spoken interactive ODQA system," in Proc. ICASSP, 2003, vol. I, pp. 624-627.
2. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Comput. Speech Lang., vol. 16, pp. 69-88, 2002.
3. M. Riley, F. Pereira, and M. Mohri, "Transducer composition for contextdependent network expansion," in Proc. Eurospeech, 1997, vol. 3, pp. 1427-1430.
4. M. Mohri and M. Riley, "Weighted determinization and minimization for large vocabulary speech recognition," in Proc. Eurospeech, 1997, vol. 1, pp. 131-134.
5. S. Bangalore and G. Riccardi, "A finite-state approach to machine translation," in Proc. ASRU, 2001, pp. 381-388.
6. F. Casacuberta, "Finite-state transducers for speech-input translation," in Proc. ASRU, 2001, pp. 375-380.
7. T. Hori, C. Hori, and Y. Minami, "Speech summarization using weighted finite-state transducers," in Proc. Eurospeech, 2003, pp. 2817-2820.
8. M. Mohri, F. Pereira, and M. Riley, "A rational design for a weighted finite-state transducer library," in Proc. Int. Workshop Implementing Automata 1997, 1997, vol. 1436, Lecture Notes in Computer Science, pp. 144-158.
9. H. J. G. A. Dolfing and I. L. Hetherington, "Incremental language models for speech recognition using finite-state transducers," in Proc. ASRU, 2001, pp. 194-197.
10. D.Willett and S. Katagiri, "Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation," in Proc. ICASSP, 2002, vol. I, pp. 713-716.
11. D. Caseiro and I. Trancoso, "Transducer composition for on-the-fly lexicon and language model integration," in Proc. ASRU, 2001, pp. 393-396.
12. [12] --, "A tail-sharing WFST composition for large vocabulary speech recognition," in ICASSP, 2003, vol. I, pp. 356-359.
13. S. Ortmanns, H. Ney, and X. Aubert, "A word graph algorithm for large vocabulary continuous speech recognition," Comput. Speech Lang., vol. 11, pp. 43-72, 1996.
14. A. Ljolje, F. Pereira, and M. Riley, "Efficient general lattice generation and rescoring," in Proc. Eurospeech, 1999, pp. 1251-1254.
15. T. Shimizu, H. Yamamoto, H. Masataki, S. Matsunaga, and Y. Sagisaka, "Spontaneous dialogue speech recognition using cross-word context constrained word graphs," in Proc. ICASSP, 1996, pp. 145-148.
16. M.Woszczyna and M. Finke, "Minimizing search errors due to delayed bigrams in real-time speech recognition systems," in Proc. ICASSP, 1996, pp. 137-140.
17. L. Nguyen and R. Schwartz, "The BBN single-phonetic-tree fast-match algorithm," in Proc. ICSLP, 1998, pp. 1827-1830.
18. R. Schwartz and S. Austin, "A comparison of several approximate algorithms for finding multiple (N-BEST) sentence hypotheses," in Proc. ICASSP, 1991, pp. 701-704.
19. T. Hori, Y. Noda, and S. Matsunaga, "Improved phoneme- historydependent search method for large-vocabulary continuous-speech recognition," IEICE Trans. Info. Syst., vol. E86-D, no. 6, pp. 1059-1067, 2003.
20. T. Kawahara, H. Nanjo, T. Shinozaki, and S. Furui, "Benchmark test for speech recognition using the corpus of spontaneous Japanese," in Proc. SSPR, 2003, pp. 135-138.
21. T. Hori, "NTT speech recognizer with outLook on the next generation: SOLON," in Proc. Commun. Scene Anal., 2004.
22. H. Isozaki et al., "Efficient support vector classifiers for named entity recognition," in Proc. COLING, 2002, pp. 390-396.
23. A. Stolcke, "Entropy-based pruning of backoff language models," in Proc. DARPA Broadcast News Transcription and UnderstandingWorkshop, 1998, pp. 270-274.
24. M. Saraclar,M. Riley, E. Bocchieri, and V. Goffin, "Towards automatic closed captioning: Low latency real time broadcast news transcription," in Proc. ICSLP, 2002, pp. 1741-1744.
25. E. Bocchieri, "Vector quantization for the efficient computation of continuous density likelihoods," in Proc. ICASSP, 1993, vol. II, pp. 692-695.