A comparison of dynamic WFST decoding approaches

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2012, Pages 4209-4212

  Dixon, Paul R ^a   Hori, Chiori ^a   Kashioka, Hideki ^a  

^a NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY   (Japan)

Author keywords

on the fly composition; Speech recognition; WFST

Indexed keywords

DYNAMIC CONSTRUCTION; ERROR RATE; LARGE VOCABULARY SPEECH RECOGNITION; LOOK-AHEAD; MEMORY USAGE; ON-THE-FLY; REAL TIME; WFST;

SIGNAL PROCESSING;

SPEECH RECOGNITION;

EID: 84867588266     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288847     Document Type: Conference Paper

References (27)

1. M. Mohri, F. C. N. Pereira, and M. Riley, "Speech recognition with weighted finite-state transducers," Springer Handbook of Speech Processing, pp. 1-31, 2008.
2. C. Allauzen, M. Riley, and J. Schalkwyk, "A generalized composition algorithm for weighted finite-state transducers," in Proc. Interspeech, 2000, pp. 1203-1206.
3. D. Caseiro and I. Trancoso, "Transducer composition for on-the-fly lexicon and language model integration," in Proc. ASRU, 2001, pp. 393-396.
4. D. Caseiro and I. Trancoso, "Using dynamic WFST composition for recognizing broadcast news," in Proc. ICSLP, 2002, pp. 1301-1304.
5. 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 Proc. Interspeech, 2004, pp. 289-292.
6. T. Hori and A. Nakamura, "Generalized fast on-the-fly composition algorithm for WFST-based speech recognition," in Proc. Interspeech, 2005, pp. 847-850.
7. D. A. Caseiro and I. Trancoso, "A specialized on-the-fly algorithm for lexicon and language model composition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 4, pp. 1281-1291, 2006.
8. T. Hori, C. Hori, Y. Minami, and A. Nakamura, "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, vol. 15, pp. 1352-1365, 2007.
9. T. Oonishi, P. R. Dixon, K. Iwano, and S. Furui, "Implementation and evaluation of fast on-the-fly WFST composition algorithms," in Proc. Interspeech, 2008, pp. 2110-2113.
10. T. Oonishi, P. R. Dixon, K. Iwano, and S. Furui, "Generalization of specialized on-the-fly composition," in Proc. ICASSP, 2009, pp. 4317-4320.
11. H. Sak, M. Saraclar, and T. Gungor, "On-the-fly lattice rescoring for real-time automatic speech recognition," in Proc. Interspeech, 2010, pp. 2450-2453.
12. D. Rybach, R. Schluter, and H. Ney, "A comparative analysis of dynamic network decoding," in Proc. ICASPP, 2011, pp. 5184-5187.
13. S. Kanthak, H. Ney, M. Riley, and M. Mohri, "A comparison of two LVR search optimization techniques," in Proc. ICSLP, 2002, pp. 1309-1312.
14. H. Soltau and G. Saon, "Dynamic network decoding revisited," in Proc. ASRU, 2009, pp. 276-281.
15. J. R. Novak, P. R. Dixon, and S. Furui, "An empirical comparison of the t3, juicer, hdecode and sphinx3 decoders," in Proc. Interspeech, 2010, pp. 1890-1893.
16. M. Riley, F. Pereira, and M. Mohri, "Transducer composition for context-dependent network expansion," in Proc. Eurospeech, 1997, pp. 1427-1430.
17. 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, 1998, pp. 393-396.
18. M. Riley, A. Ljolje, D. Hindle, and F. Pereira, "The ATT 60,000 word speech-to-text system," in Proc. ESCA, 1995, pp. 207-210.
19. F. Pereira and M. Riley, "Speech recognition by composition of weighted finite automata," Tech. Rep., AT&T Research, 1996.
20. 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.
21. D.Willett and S. Katagiri, "Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation," in Proc. ICASSP, 2002, pp. 713-716.
22. O. Cheng, J. Dines, and M. M. Doss, "A generalized dynamic composition algorithm of weighted finite state transducers for large vocabulary speech recognition," in Proc ICASSP, 2007, pp. 348-351.
23. J. McDonough, E. Stoimenov, and D. Klakow, "An algorithm for fast composition of weighted finite-state transducers," in Proc. ASRU, 2007, pp. 1-4.
24. K. Maekawa, "Corpus of spontaneous Japanese: Its design and evaluation," in Proc. ISCA and IEEE Workshop on Spontaneous Speech Processing and Recognition, 2003, pp. 7-12.
25. H. Bo-June and J. Glass, "Iterative language model estimation: Efficient data structure & algorithms," in Proc. Interspeech, 2008, pp. 841-844.
26. P. R. Dixon, D. A. Caseiro, T. Oonishi, and S. Furui, "The Titech large vocabulary WFST speech recognition system," in Proc. ASRU, 2007, pp. 1301-1304.
27. C. Allauzen, M. Riley, J. Schalkwyk, W. Skut, and M. Mohri, "OpenFst: A general and efficient weighted finite-state transducer library," in Proc. of CIAA 2007, 2007, pp. 11-23.