Speech recognition algorithms using weighted finite-state transducers

Synthesis Lectures on Speech and Audio Processing

Volumn 10, Issue , 2013, Pages 1-162

  Hori, Takaaki ^a   Nakamura, Atsushi ^a  

^a Japan   (Japan)

Author keywords

automaton; decoder; optimization; speech recognition; Viterbi algorithm; weighted finite state transducer

Indexed keywords

AUTOMATON; BEST MATCH; BLACK BOXES; COMPUTATIONAL COSTS; CONVENTIONAL METHODS; DECODER; DECODING ALGORITHM; DECODING PROCESS; DECODING SPEED; IMPLEMENTATION TECHNIQUES; RECOGNITION ALGORITHM; RECOGNITION ERROR; SEARCH PROBLEM; SPEECH RECOGNITION TECHNOLOGY; SPEECH RECOGNIZER; SPEECH SIGNALS; SPOKEN LANGUAGE PROCESSING; VOCABULARY SIZE; WEIGHTED FINITE-STATE TRANSDUCERS;

AUTOMATA THEORY; DECODING; OPTIMIZATION; REVIEWS; TRANSDUCERS; VITERBI ALGORITHM;

SPEECH RECOGNITION;

EID: 84872838032     PISSN: 1932121X     EISSN: 19321678     Source Type: Book Series    
DOI: 10.2200/S00462ED1V01Y201212SAP010     Document Type: Article

References (131)

1. G. Antoniol, F. Brugnara, M. Cettolo, and M. Frederico, "Language model representations for beam-search decoding," in Proc. ICASSP, 1995, pp. 588-591. DOI: 10.1109/ICASSP.1995.47966633
2. A. V. Aho, J. E. Hopcroft, and J. D. Ullman, The Design and Analysis of Computer Algorithms. Addison-Wesley Publishing Company, 1974. 4
3. C. Allauzen and M. Mohri, "General indexation of weighted automata-application to spoken utterance retrieval," in Proc. HLT-NAACL, 2004. 135
4. C. Allauzen, M. Mohri, and B. Roark, "Generalized algorithms for constructing statistical language models," in Proc. ACL, 2003, pp. 40-47. DOI: 10.3115/1075096.1075102 77, 130
5. C. Allauzen, M. Mohri, M. Riley, and B. Roark, "A generalized construction of integrated speech recognition transducers," in Proc. ICASSP, vol. I, 2004, pp. 761-764. DOI: 10.1109/CASSP.2004.132609791
6. 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, pp. 11-23. DOI: 10.1007/978-3-540-76336- 9-3136
7. C. Allauzen, M. Riley, and J. Schalkwyk, "A generalized composition algorithm for weighted finite-state transducers," in Proc. Interspeech, 2009, pp. 1203-1206. 71, 91, 95, 99, 104, 105, 107
8. C. Allauzen, M. Riley, and J. Schalkwyk, "A filter-based algorithm for efficient composition of finite-state transducers," International Journal of Foundations of Computer Science, 2011. DOI: 10.1142/S0129054111009033 105, 106
9. S. Austin, R. Schwartz, and P. Placeway, "The forward-backward search algorithm," in Proc. ICASSP, vol. 1, 1991, pp. 697-700. DOI: 10.1109/ICASSP.1991.1504354
10. X.L.Aubert, "An overview of decoding techniques for large vocabulary continuous speech recognition," Computer Speech and Language, vol. 16, pp. 89-114, 2002. DOI: 10.1006/csla.2001.01854
11. J. S. Bridle, M. D. Brown, and R. M. Chamberlain, "An algorithm for connected word recognition," in Proc. ICASSP, 1982, pp. 899-902. 3
12. J. Berstel, L. Boasson, O. Carton, and I. Fagnot, "Minimization of automata," CoRR, vol. abs/1010.5318, 2010. 61
13. F. Brugnara and M. Cettolo, "Improvements in tree-based language model representation," in Proc. EUROSPEECH, 1995, pp. 1797-1800. 33
14. R.Bellman and S.Dreyfus, AppliedDynamic Programming. New Jersey:Princeton Univ. Press, 1962. 2, 16
15. P. F. Brown, P. V. deSouza, R. L. Mercer, V. J. Della Pietra, and J. C. Lai, "Class-based n-gram models of natural language," Computational Linguistics, vol. 18(4), pp. 467-479, 1992. 130
16. L. R. Bahl, P. V. de Souza, and P. S. Gopalakrishman, "Decision trees for phonological rules in continuous speech," in Proc. ICASSP, 1991, pp. 185-188. DOI: 10.1109/ICASSP.1991.150308 18, 131
17. S. Bangalore and M. Johnston, "Robust understanding in multimodal interfaces," Computer Linguistics, vol. 35, no. 3, pp. 345-397, 2009. DOI: 10.1162/coli.08-022-R2-06-26135
18. L. R. Bahl, F. Jelinek, and R. L. Mercer, "Maximum likelihood approach to continuous speech recognition," IEEE Transactions on Patten Analysis and Machine Intelligence, vol. PAMI-5, no. 2, pp. 179-190, Mar. 1983. DOI: 10.1109/TPAMI.1983.47673709
19. K. Booth and G. Lueker, "Testing for the consecutive ones property, interval graphs, and graph planarity using pq-tree algorithms," Journal of Computer and System Sciences, vol. 13, pp. 335-379, 1976. DOI: 10.1016/S0022-0000(76)80045-1109
20. I. Bulyko and M. Ostendorf, "Joint prosody prediction and unit selection for concatenative speech synthesis," in Proc. ICASSP, vol. 2, 2001, pp. 781-784. DOI: 10.1109/ICASSP.2001.941031135
21. I. Bulyko and M.Ostendorf, "Efficient integrated response generation from multiple targets using weighted finite state transducers," Computer Speech and Language, vol. 16(3-4), pp. 533-550, 2002. DOI: 10.1016/S0885- 2308(02)00023-2135
22. F. Casacuberta, "Finite-state transducers for speech-input translation," in Proc. ASRU, 2001, pp. 375-380. DOI: 10.1109/ASRU.2001. 1034664133
23. 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. DOI: 10.1109/ICASSP.2007.36692095, 99
24. C. Cortes, P. Haffner, and M. Mohri, "Rational kernels: Theory and algorithms," The Journal of Machine Learning Research, vol. 5, pp. 1035-1062, 2004.
25. D. Caseiro and I.Trancoso, "Transducer composition for "on-The-fly" lexicon and language model integration," in Proc. ASRU, 2001, pp. 393-396. DOI: 10.1109/ASRU.2001.103466795, 99
26. D. Caseiro and I. Trancoso, "A tail-sharing WFST composition for large vocabulary speech recognition," in Proc. ICASSP, vol. I, 2003, pp. 356-359. DOI: 10.1109/ICASSP.2003.119879195
27. D. 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. DOI: 10.1109/TSA.2005.86083899
28. D. Caseiro, L. Trancoso, L. Oliveira, and C. Viana, "Grapheme-to- phone using finite-state transducers," in Proc. IEEE Workshop on Speech Synthesis, 2002, pp. 215-218. DOI: 10.1109/WSS.2002.1224412135
29. P.R. Dixon, D. Caseiro, T. Oonishi, and S. Furui, "The TITECH large vocabulary WFST speech recognition system," in Proc. ASRU, 2007, pp. 443-448. DOI: 10.1109/ASRU.2007.4430153136
30. 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. DOI: 10.1109/ASRU.2001.1034620 95, 110
31. P. R. Dixon, C. Hori, and H. Kashioka, "A comparison of dynamic WFST decoding approaches," in Proc. ICASSP, Kyoto, Japan, 2012, pp. 4209-4212. DOI: 10.1109/ICASSP.2012.6288847 93, 126
32. J. Eisner, "Parameter estimation for probabilistic finite-state transducers," in Proc. ACL, 2002, pp. 1-8. DOI: 10.3115/1073083.1073085133
33. W. M. Fisher, J. Bernstein, and D. S. Pallett, "The DARPA 1000-word resource management database for continuous speech recognition," in Proc. ICASSP, vol. 1, 1988, pp. 651-654. DOI: 10.1109/ICASSP.1988.1966691
34. S.Furui, K.Maekawa, and H. Isahara, "A Japanese national project on spontaneous speech corpus and processing technology," in Proc. of ASR, 2000, pp. 244-248. 83
35. "AT&T FSM Library," web page http://www.itl.nist.gov/iad/ mig/tests/rt/2009/index.html. 136
36. S. Furui, "Speaker-independent isolated word recognition using dynamic features of speech spectrum," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 34, no. 1, pp. 52-59, 1986. DOI: 10.1109/TASSP.1986.116478812
37. P.Garner, "Silence models in weighted finite-state transducers," in Proc.Interspeech, Brisbane, Australia, 2008, pp. 1817-1820. 75
38. P. S. Gopalakrishnan, L. R. Bahl, and R. L. Mercer, "A tree search strategy for large-vocabulary continuous speech recognition," in Proc. ICASSP, vol. 572-575, 1995. DOI: 10.1109/ICASSP.1995.4796624
39. I. J.Good, "The population frequencies of species and the estimation of population parameters," Biometrika, vol. 40, no. 3-4, pp. 237-264, 1953. DOI: 10.2307/233334422
40. X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall, 2001. 12
41. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. ICASSP, vol. 3, 2000, pp. 1635-1638. DOI: 10.1109/ICASSP.2000.86202412
42. I. L. Hetherington, "The MIT finite-state transducer toolkit for speech and language processing," in Proc. Interspeech-ICSLP, 2004. 136
43. I. L. Hetherington, "A multi-pass, dynamic-vocabulary approach to real-time, large-vocabulary speech recognition," in Proc. Interspeech-Eurospeech, 2005, pp. 545-548. 131
44. C.T.Hemphill, J.J.Godfrey, and G.R.Doddington, "The ATIS spoken language systems pilot corpus," in DARPA Speech and Natural Language Workshop, Hidden Valley, Pennsylvania, June 1990. DOI: 10.3115/116580.1166131
45. T. Hori, C. Hori, and Y. Minami, "Speech summarization using weighted finite-state transducers," in Proc. Eurospeech, 2003, pp. 2817-2820. 134
46. 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-ICSLP, vol. 1, 2004, pp. 289-292. 6, 95, 110
47. 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," IEEETransactions on Audio, Speech, and Language Processing, vol.15, no.4, pp.1352-1365, 2007.DOI: 10.1109/TASL.2006.889790 6, 95, 110
48. B. Hoffmeister, G. Heigold, D. Rybach, R. Schluter, and H. Ney, "WFST enabled solutions to ASR problems: Beyond HMM decoding," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20(2), pp. 551-564, 2012. DOI: 10.1109/TASL.2011.2162402132
49. J. E. Hopcroft, R. Motwani, and J. D. Ullman, Introduction to Automata Theory, Languages, and Computation, 3rd ed. Addison-Wesley Publishing Company, 2006. 4, 45, 75
50. T. Hori and A. Nakamura, "Generalized fast on-The-fly composition algorithm for WFST-based speech recognition," in Proc. Interspeech- Eurospeech, 2005, pp. 557-560. 94, 95, 110, 130
51. C.Hori, K.Ohtaki, T.Misu, H.Kashioka, andS.Nakamura, "Dialog management using weighted finite-state transducers," in Proc. Interspeech, 2008, pp. 211-214. DOI: 10.1109/ASRU.2009.5373350136
52. C. Hori, K. Ohtaki, T. Misu, H. Kashioka, and S. Nakamura, "Statistical dialog management applied to WFST-based dialog systems," in Proc. ICASSP, 2009, pp. 4793-4796. DOI: 10.1109/ICASSP.2009.4960703136
53. I. L. Hetherington, H. Shu, and J. R. Glass, "Flexible multi-stream framework for speech recognition using multi-tape finite-state transducers," in Proc. ICASSP, 2006, pp. 417-420. DOI: 10.1109/ICASSP.2006. 1660046132
54. G. Heigold, R. Schluter, and H. Ney, "A multimedia retrieval system using speech input," in Proc. ICASSP, 2009, pp. 3749-3752. DOI: 10.1145/1647314.1647356132
55. T. Hori, D. Willett, and Y. Minami, "Language model adaptation using WFST-based speaking-style translation," in Proc. ICASSP, vol. I, 2003, pp. 228-231. DOI: 10.1109/ICASSP.2003.1198759131
56. T. Hori, D. Willett, and Y. Minami, "Paraphrasing spontaneous speech using weighted finite-state transducers," in Proc. SSPR, 2003. 134
57. G.Heigold, G.Zweig, andP.Nguyen, "Aflat direct model for speech recognition," in Proc. ICASSP, 2009, pp. 3861-3864. DOI: 10.1109/ICASSP.2009.4960470133
58. R. Iyer, M. Ostendorf, and J. R. Rohlicek, "Language modeling with sentence-level mixtures," in Proc.Workshop on Human Language Technology, 1994, pp. 82-87. DOI: 10.3115/1075812.1075828131
59. F. Jelinek, L. R. Bahl, and R. L. Mercer, "Design of a linguistic statistical decoder for the recognition of continuous speech," IEEE Transactions on Information Theory, vol. IT-21, no. 3, pp. 250-256, 1975. DOI: 10.1109/TIT.1975.10553849
60. F. Jelinek, Ed., Statistical Methods for Speech Recognition. The MIT Press, 1998. 1, 9
61. F. Jelinek, B. Merialdo, R. S., and M. Strauss, "A dynamic language model for speech recognition," in Proc. DARPA Workshop on Speech and Natural Language, 1991, pp. 293-295. DOI: 10.3115/112405.112464131
62. A. T. Jensson, T. Oonishi, K. Iwano, and S. Furui, "Development of a WFST based speech recognition system for a resource deficient language using machine translation," in Proc. APSIPA ASC, 2009, pp. 50-56. 131
63. J. J. Schalkwyk, I. L. Hetherington, and E. Story, "Speech recognition with dynamic grammars using finite-state transducers," in Proc. Eurospeech, 2003, pp. 1969-1972. 131
64. N. Kumar and H. G. Andreou, "Heteroscendastic discriminant analysis and reduced rank HMMs for improved speech recognition," Speech Communication, vol. 26, pp. 283-297, 1998. DOI: 10.1016/S0167-6393(98)00061-212
65. S. M. Katz, "Estimation of probabilities from sparse data for the language model component of a speech recognizer," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 35, no. 3, pp. 400-401, 1987. DOI: 10.1109/TASSP.1987.116512522
66. P. Kenny, R. Hollan, V. Gupta, M. Lennig, P.Mermelstein, and D. O'Shaughnessy, "A&z.ast;-admissible heuristics for rapid lexical access," in Proc. ICASSP, 1991, pp. 689-692. DOI: 10.1109/ICASSP.1991. 1504334
67. R. Kuhn, A. Lazarides, Y. Normandin, and J. Brousseau, "Improved decision trees for phonetic modeling," in Proc. ICASSP, vol. 1, 1995, pp. 552-555. DOI: 10.1007/11965152-26131
68. S. Kanthak and H. Ney, "FSA: An efficient and flexible C++ toolkit for finite state automata using on-demand computation," in Proc. ACL, 2004, pp. 510-517. 136
69. Y. Kubo, S. Watanabe, T. Hori, and A. Nakamura, "Structural classification methods based on weighted finite-state transducers for automatic speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, 2012, in press. 133
70. K.-F. Lee, "Large-vocabulary speaker-independent continuous speech recognition: the SPHINX system," PhD thesis, Carnegie Mellon University, April 1988. 17
71. X. Liu, M. J. F. Gales, J. L. Hieronymus, and P. C. Woodland, "Language model combination and adaptation using weighted finite state transducers," in Proc. ICASSP, 2010, pp. 5390-5393. 131
72. L. Labiner and B.-H. Juang, Fundamentals of Speech Recognition. Prentice Hall, 1993. 12
73. B. Lowerre, "The HARPY speech recognition system," PhD theses, Dept. of Computer Science, Carnegie-Mellon University, Pittsburgh, PA, USA, 1976. 3, 27
74. A. Ljolje, F. Pereira, and M. Riley, "Efficient general lattice generation and rescor-ing," in Proc. Eurospeech, 1999, pp. 1251-1254. 88, 94, 126
75. M. Lehr and I. Shafran, "Discriminatively estimated joint acoustic, duration, and language model for speech recognition," in Proc. ICASSP, 2010, pp. 5542-5545. DOI: 10.1109/ICASSP.2010.5495227133
76. A. Mohamed, G. Dahl, and G. Hinton, "Deep belief networks for phone recognition," in Proc. NIPS Workshop on Deep Learning for Speech Recognition, 2009. 16
77. D. Moore, J. Dines, M. Magimai Doss, J. Vepa, O. Cheng, and T. Hain, "Juicer: a weighted finite-state transducer decoder," Machine Learning for Multimodal In teraction, Lecture Notes in Computer Science, vol. 4299, pp. 285-296, 2006. 136
78. E. McDermott, T. J. Hazen, J. Le Roux, A. Nakamura, and S. Katagiri, "Discriminative training for large vocabulary speech recognition using minimum classification error," IEEE Transactions on Audio, Speech and Language Processing, vol. 15, pp. 203-223, 2007. DOI: 10.1109/TASL.2006. 876778132
79. "The MIT FST Toolkit," web page http://people.csail.mit.edu/ ilh/fst. 136
80. M. Mohri, "Generic epsilon-removal and input epsilon-normalization algorithms for weighted transducers," International Journal of Foundations of Computer Science, vol. 13(1), pp. 129-143, 2002. DOI: 10.1142/ S012905410200099665
81. M. Mohri, "Weighted automata algorithms," in Handbook of Weighted Automata, M. Droste, W. Kuich, and H. Vogler, Eds. Springer-Verlag New York Inc., 2009. DOI: 10.1007/978-3-642-01492-5 56, 57, 61, 65
82. M. Mohri, F. Pereira, and M. Riley, "Weighted automata in text and speech processing," in Proc. ECAI-96, Workshop on Extended Finite State Models of Language, Budapest, Hungary, 1996. 4
83. M. Mohri, F. Pereira, and M. Riley, "The design principles of a weighted finite-state transducer library," Theoretical Computer Science, vol. 231(1), pp. 17-32, 2000. DOI: 10.1016/S0304-3975(99)00014-6136
84. M. Mohri, F. Pereira, and M. Riley, "Weighted finite-state transducers in speech recognition," Computer Speech and Language, vol. 16, pp. 69-88, 2002. DOI: 10.1006/csla.2001.0184 4, 41, 71, 80, 83, 94, 95
85. M. Mohri and M. Riley, "Weighted determinization and minimization for large vocabulary speech recognition," in Proc. Eurospeech, vol. 1, 1997, pp. 131-134. 95
86. M. Mohri and M.Riley, "A weight pushing algorithm for large vocabulary speech recognition," in Proc. Eurospeech, 2001, pp. 1603-1606. 91
87. J. McDonough, E. Stoimenov, and D. Klakow, "An algorithm for fast composition of weighted finite-state transducers," in Proc. ASRU, 2007, pp. 461-466. DOI: 10.1109/ASRU.2007.4430156 95, 99
88. H. Ney, "The use of a one-stage dynamic programming algorithm for connected word recognition," IEEETransactions on Acoustics, Speech, and Signal Processing, vol. ASSP-32, no. 2, pp. 263-271, Apr. 1984. DOI: 10.1109/TASSP.1984.11643203
89. H.Ney, R.Haeb-Umbach, B.Tran, and M.Oerder, "Improvementsin beam search for 10000-word continuous speech recognition," in Proc. ICASSP, vol. I, 1992, pp. 9-12. DOI: 10.1109/89.27928727
90. T. Oonishi, P. R. Dixon, K. Iwano, and S. Furui, "Generalization of specialized on-The-fly composition," in Proc. ICASSP, 2009, pp. 4317-4320. DOI: 10.1109/ICASSP.2009.4960584 95, 99, 102
91. T. Oonishi, P. R. Dixon, K. Iwano, and S. Furui, "Optimization of on-The-fly composition for WFST-based speech recognition decoders," IEICE Transactions on Information and Systems, vol. J92-D, no. 7, pp. 1026-1035, 2009, (in Japanese). 102, 103
92. T. Oba, T. Hori, A. Ito, and A. Nakamura, "Round-robin duel discriminative language models in one-pass decoding with on-The-fly error correction," in Proc. ICASSP, 2011, pp. 5588-5591. DOI: 10.1109/ICASSP.2011.5947626131
93. S.Ortmanns, H.Ney, and X.Aubert, "A word graph algorithm for large vocabulary continuous speech recognition," Computer Speech and Language, vol. 1, pp. 43-72, 1997. DOI: 10.1006/csla.1996.0022 4, 33, 38, 94
94. S. Ortmanns, H. Ney, and A. Eiden, "Language-model look-ahead for large vocabulary speech recognition," in Proc. ICSLP, 1996, pp. 2095-2098. DOI: 10.1109/ICSLP.1996.607215103
95. "OpenFst Library," web page http://www.openfst.org/twiki/bin/ view/FST/WebHome. 136
96. D. S. Pallett, "Benchmark tests for DARPA resource management database performance evaluations," in Proc. ICASSP, 1989, pp. 536-539. DOI: 10.1109/ICASSP.1989.2664821
97. D. B. Paul, "Algorithm for an optimal A&z.ast; search and linearizing the search in the stack decoder," in Proc. ICASSP, 1991, pp. 693-696. DOI: 10.1109/ICASSP.1991.1504344
98. D. Povey, L. Burget, M. Agarwal, P. Akyazi, F. Kai, A. Ghoshal, O. Glembek, N. Goel, M. Karafiat, A. Rastrow, R. C. Rosei, P. Schwarz, and S. Thomas, "The subspace Gaussian mixture model-A structured model for speech recognition," Computer Speech & Language, vol. 25, no. 2, pp. 404-439, April 2011. DOI: 10.1016/j.csl.2010.06.00316
99. D. S. Pallett, W. M. Fisher, J. G. Fiscus, and J. S. Garofolo, "DARPA ATIS test results June 1990," in Proc. Speech and Natural Language Workshop, R. Stern, Ed. Morgan Kaufmann Publishers, Inc., June 1990, pp. 114-121. 1
100. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, and K. Vesely, "The Kaldi speech recognition toolkit," in Proc. ASRU, 2011. 136
101. F. Pereira and M. Riley, "Speech recognition by composition of weighted finite automata," in Finite-State Language Processing. MIT Press, 1996, pp. 431-453. 4
102. F. Pereira, M. Riley, and R. Sproat, "Weighted rational transductions and their application to human language processing," in Proc. ARPA Workshop on Human Language technology, 1994, pp. 249-254. DOI: 10.3115/1075812.10758704
103. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, vol. I, 2002, pp. 105-108. DOI: 10.1109/ICASSP.2002.5743665 13, 132
104. D. Revuz, "Minimisation of acyclic deterministic automata in linear time," Theoretical Computer Science, vol. 92(1), pp. 181-189, 1992. DOI: 10.1016/0304-3975(92)90142-364
105. D.Rybach, S.Hahn, P.Lehnen, D.Nolden, M.Sundermeyer, Z.Tuske, S.Wiesler, R. Schluter, and N. Ney, "RASR-The RWTH Aachen university open source speech recognition toolkit," in Proc. ASRU, 2011. 136
106. S. Renals, N. Morgan, H. Boulard, M. Cohen, and H. Franco, "Connectionist probability estimators in HMM speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 2, no. 1, pp. 161-174, 1994. DOI: 10.1109/89.26035916
107. M. Riley, F. Pereira, and M. Mohri, "Transducer composition for context-dependent network expansion," in Proc. Eurospeech, 1997, pp. 1427-1430. 71
108. E. Roche and Y. Schabes, Eds., Finite-State Language Processing. A Bradford Book, 1997. 44
109. B. Roark, M. Saraclar, M. Collins, and M. Johnson, "Discriminative language modeling with conditional random fields and the perceptron algorithm," in Proc. ACL, 2004. DOI: 10.3115/1218955.1218962130
110. D. Rybach, R. Schluter, and H. Ney, "Silence is golden: modeling non-speech events in WFST-based dynamic network decoders," in Proc. ICASSP, Kyoto, Japan, 2012, pp. 4205-4208. DOI: 10.1109/ICASSP.2012.628884675
111. "The RWTH FSA Toolkit," web page http://www-i6.informatik.rwth- aachen.de/kanthak/fsa.html. 136
112. R. Schwartz and Y. Austin, "A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses," in Proc. ICASSP, 1990, pp. 701-704. DOI: 10.1109/ICASSP.1991.15043639
113. H. Sakoe and S. Chiba, "A similarity evaluation of speech patterns by dynamic programming (in japanese)," in the Dig. 1970 Nat. Meeting, Inst. Electrn. Comm. Eng. Japan, July 1970, p. 136. 2
114. H. Sakoe and S. Chiba, "A dynamic programming approach to continuous speech recognition," in Proc. ICA, Budapest, Hungary, Paper 20 C 13, August 1971, pp. 65-68. 2
115. R.Schwartz andY.Chow, "The N-best algorithm:an efficient and exact procedure for finding the N most likely sentence hypotheses," in Proc. ICASSP, 1990, pp. 81-84. DOI: 10.1109/ICASSP.1990.1155424
116. M. Schuster, "Memory-efficient LVCSR search using a one-pass stack decoder," Computer Speech & Language, vol. 14(1), pp. 47-77, January 2000. DOI: 10.1006/csla.1999.01354
117. F. K. Soong and E.-F. Huang, "A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognition," in Proc. ICASSP, vol. 1, 1991, pp. 705-708. DOI: 10.1109/ICASSP.1991.1504374
118. H. Shu and I. L. Hetherington, "EM training of finite-state transducers and its application to pronunciation modeling," in Proc. ICSLP, 2002, pp. 1293-1296. 132
119. M. Schuster and T. Hori, "Efficient generation of high-order context-dependent weighted finite state transducers for speech recognition," in Proc. ICASSP, 2005, pp. 201-204. DOI: 10.1109/ICASSP.2005. 1415085132
120. F. Seide, G. Li, and D. Yu, "Conversational speech transcription using context-dependent deep neural networks," in Proc. Interspeech, 2011, pp. 437-440. 16
121. E. Stoimenov and J. McDonough, "Modeling polyphone context with weighted finite-state transducers," in Proc. ICASSP, vol. I, 2006, pp. 121-124. DOI: 10.1109/ICASSP.2006.1659972132
122. R. Sproat, "Multilingual text analysis for text-to-speech synthesis," in Proc. ICSLP, vol. 3, 1996, pp. 1365-1368. DOI: 10.1017/S1351324997001654135
123. A.Stolcke, "Entropy-based pruning of backoff language models," in Proc. DARPA Broadcast News Transcription and Understanding Workshop, 1998, pp. 270-274. 78
124. K.Shinoda andT.Watanabe, "MDL-based context-dependent subword modeling for speech recognition," Acoustic Science and Technology, vol. 21, no. 2, pp. 79-86, 2000. DOI: 10.1250/ast.21.7919
125. 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. DOI: 10.1109/ICASSP.1996.540311126
126. S.Watanabe, T. Hori, E. McDermott, and A. Nakamura, "A discriminative model for continuous speech recognition based on weighted finite state transducers," in Proc. ICASSP, 2010, pp. 4922-4925. DOI: 10.1109/ICASSP.2010.5495096133
127. D. Willett, E. McDermott, Y. Minami, and S. Katagiri, "Time and memory efficient Viterbi decoding for LVCSR using a precompiled search network," in Proc. Eurospeech, 2001, pp. 847-850. 95, 110, 111
128. S. Watanabe, Y. Minami, A. Nakamura, and N. Ueda, "Variational Bayesian estimation and clustering for speech recognition," IEEE Transactions on Speech and Audio Processing, vol.12, pp.365-381, 2004.DOI: 10.1109/TSA.2004.82864019
129. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree-based state tying for high accuracy acoustics modeling," in Proc. ARPA Human Language Technology Workshop, 1994, pp. 307-312. DOI: 10.3115/1075812.107588518
130. Y. Zhao, A. Ljolje, D. Caseiro, and B.-H. Juang, "A general discriminative training algorithm for speech recognition using weighted finite-state transducers," in Proc. ICASSP, Kyoto, Japan, 2012, pp. 4217-4220. DOI: 10.1109/ICASSP.2012.6288849132
131. G. Zweig and P. Nguyen, "A segmental CRF approach to large vocabulary continuous speech recognition," in Proc. ASRU, 2009, pp. 152-157. DOI: 10.1109/ASRU.2009.5372916133