The ATR multilingual speech-to-speech translation system

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 2, 2006, Pages 365-375

  Nakamura, Satoshi ^a,b   Markov, Konstantin ^a,b   Nakaiwa, Hiromi ^b   Kikui, Genichiro ^b   Kawai, Hisashi ^a,b   Jitsuhiro, Takatoshi ^a,b   Zhang, Jin Song ^b   Yamamoto, Hirofumi ^b   Sumita, Eiichiro ^b   Yamamoto, Seiichi ^a,b  

^a IEEE   (Japan)

^b ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Example based machine translation (EBMT); Minimum description length (MDL); Multiclass language model; Speech to speech translation (S2S); Statistical machine translation (SMT); Successive state splitting (SSS); Text to speech (TTS) conversion

Indexed keywords

EXAMPLE BASED MACHINE TRANSLATION (EBMT); MINIMUM DESCRIPTION LENGTH (MDL); MULTICLASS LANGUAGE MODELS; SPEECH TO SPEECH TRANSLATION (S2ST) SYSTEMS; STATISTICAL MACHINE TRANSLATION (SMT); SUCCESSIVE STATE SPLITTING (SSS); TRANSLATION QUALITY;

DATABASE SYSTEMS; LEARNING SYSTEMS; LINGUISTICS; SPEECH RECOGNITION; TRANSLATION (LANGUAGES);

SPEECH SYNTHESIS;

EID: 33751057590     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.860774     Document Type: Article

References (50)

1. W. Wahlster, Ed., Vennobil: Foundations of Speech-to-Speech Translations. Berlin, Germany: Springer-Verlag, 2000.
2. E. Costantini, S. Burger, and F. Pianesi, "NESPOLEI's multi-lingual and multi-modal corpus," in Proc. LREC, 2002, pp. 165-170.
3. A. Lavie, L. Levin, T. Schultz, and A. Waibel. Domain portability in speech-to-speech translation, presented at Proc. HLT Workshop. [Online] Available: http://www.is.cs.cmu.edu/papers/speech/HLT2001/HLT_alon.pdf
4. T. Hirokawa and K. Hakoda, "Segment selection and pitch modification for high quality speech synthesis using waveform segments," in Proc. Int. Conf. Spoken Language Processing, 1990, pp. 337-340.
5. R. Donovan, "Trainable speech synthesis," Ph.D. dissertation. Eng. Dept. Cambridge Univ., Cambridge, U.K., 1996.
6. A. Breen and P. Jackson, "Nonuniform unit selection and the similarity metric within BT's laureate TTS system," in Proc. 3rd ESCA/COCOSDA Workshop on Speech Synthesis, Jenolan Caves, Blue Mountians, Australia, Nov. 1998, p. G.1.
7. Y. Sagisaka, N. Kaiki, N. Iwahashi, and K. Mimura, "ATR ν-talk speech synthesis system," in Proc. Int. Conf. Spoken Language Processing, Banff, AB, Canada, Oct. 1992, pp. 483-486.
8. A. W. Black and P. Taylor, "Chatr: a genetic speech synthesis system," in Proc. Conf. Computational Linguistics, Kyoto, Japan, Aug. 1994, pp. 983-986.
9. Y. Sagisaka, "Speech synthesis by rule using an optimal selection of nonuniform synthesis units," in Proc. IEEE Int. Conf. Speech, Acoustics, Signal Processing, New York, Apr. 1988, pp. 679-682.
10. N. Iwahashi, N. Kaiki, and Y. Sagisaka, "Speech segment selection for concatenate synthesis based on spectral distortion minimization," Trans. IEICE, vol. E76-A, no. 11, pp. 1942-1948, Nov. 1993.
11. S. Young, J. Odell, and P. Woodland, "Tree-based state tying for high accuracy acoustic modeling," in Proc. ARPA Workshop on Human Language Technology, 1994, pp. 307-312.
12. J. Takami and S. Sagayama, "A successive state splitting algorithm for efficient allophone modeling," in Proc. ICASSP, vol. I, 1992, pp. 573-576.
13. M. Ostendorf and H. Singer, "HMM topology design using maximum likelihood successive state splitting," Comput. Speech Lang., vol. 11, pp. 17-41, 1997.
14. T. Jitsuhiro, T. Matsui, and S. Nakamura, "Automatic generation of nonuniform context-dependent HMM topologies based on the MDL criterion," in Proc. Etirospeech, 2003, pp. 2721-2724.
15. P. Brown, V. Pietra, P. Souza, J. Lai, and R. Mercer, "Class-based N-gram models of natural language," Comput. Linguistics, vol. 18, no. 4, pp. 467-479, 1992.
16. H. Yamamoto, S. Isogai, and Y. Sagisaka, "Multi-class composite N-gram language model," Speech Commun., vol. 41, pp. 369-379, 2003.
17. H. Ward, Jr., "Hierarchical grouping to optimize an objective function," J. Amer. Statist. Assoc., vol. 58, pp. 236-244, 1963.
18. M. Nagao, "A framework of a mechanical translation between Japanese and English by analogy principle," in Artificial and Human Intelligence, M. Elithorn and R. Banerji, Eds. Amsterdam, The Netherlands: North-Holland, 1984, pp. 173-180.
19. H. Somers, "Review article: example-based machine translation," J. Mach. Translat., pp. 113-157, 1999.
20. P. Brown et al., "A statistical approach to machine translation," Comput. Linguistics, vol. 16, pp. 79-85, 1993.
21. K. Knight, "Automating knowledge acquisition for machine translation," AI Mag., vol. 18, no. 4, pp. 81-96, 1997.
22. H. Ney, "Stochastic modeling: from pattern classification to language translation," in Proc. ACL Workshop DDMT, 2001, pp. 33-37.
23. H. Alshawi, S. Bangalore, and S. Douglas, "Learning dependency translation models as collections of finite-state head transducers," Comput. Linguistics, vol. 26, no. 1, pp. 45-60, 2000.
24. Y. Wang and A. Waibel, "Fast decoding for statistical machine translation," in Proc. ICSLP, 1998, pp. 2775-2778.
25. F. Och, C. Tillmann, and H. Ney, "Improved alignment models for statistical machine translation," in Proc. EMNLPAWLC, 1999, pp. 20-28.
26. A. Venugopal, S. Vogel, and A. Waibel, "Effective phrase translation extraction from alignment models," in Proc. ACL, 2003, pp. 319-326.
27. E. Sumita, "Example-based machine translation using DP-matching between word sequences," in Proc. ACL Workshop DDMT, 2001, pp. 1-8.
28. K. Imamura, "Application of translation knowledge acquired by hierarchical phrase alignment," in Proc. TMI, 2002, pp. 74-84.
29. K. Imamura, E. Sumita, and Y. Matsumoto, "Feedback cleaning of machine translation rules using automatic evaluation," in Proc. 41st Annu. Meeting Assoc. Computational Linguistics, 2003, pp. 447-454.
30. T. Watanabe, K. Imamura, and E. Sumita, "Statistical machine translation based on hierarchical phrase alignment," in Proc. TMI, 2002, pp. 188-198.
31. Y. Akiba, T. Watanabe, and E. Sumita, "Using language and translation models to select the best among outputs from multiple MT systems," in Proc. COLING, 2002, pp. 8-14.
32. T. Watanabe and E. Sumita, "Example-based decoding for statistical machine translation," in Proc. 9th MT Summit, 2003, pp. 410-417.
33. C. Hogan and R. Frederking, "An evaluation of the multi-engine MT architecture," in Proc. AMTA, 1998, pp. 113-123.
34. C. Callison-Burch and S. Floumoy, "A program for automatically selecting the best output from multiple machine translation engines," in Proc. MT-SUMMIT-VIII, 2001, pp. 63-66.
35. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for hmm-based speech synthesis," in Proc. IEEE Int. Conf. Speech, Acoustics, Signal Processing, Istanbul, Turkey, Jun. 2000, pp. 1315-1318.
36. T. Toda, H. Kawai, and M. Tsuzaki, "Optimizing subcost functions for segment selection based on perceptual evaluations in concatenative speech synthesis," in Proc. IEEE Int. Conf. Speech, Acoustics, Signal Processing, vol. I, Montreal, QC, Canada, Jun. 2004, pp. 657-660.
37. T. Takezawa, E. Sumita, F. Sugaya, H. Yamamoto, and S. Yamamoto, "Toward a broad-coverage bi-lingual corpus for speech translation of travel conversations in the real world," in Proc. LREC, 2002, pp. 147-152.
38. G. Kikui, E. Sumita, T. Takezawa, and S. Yamamoto, "Creating corpora for speech-to-speech translation," in Proc. Eurospeech, 2003, pp. 381-384.
39. E. Sumita, S. Yamada, K. Yamamoto, M. Paul, H. Kashioka, K. Ishikawa, and S. Shirai, "Solutions to problems inherent in spoken language stranslation: the ATR-MATRIX approach," in Proc. 7th MT Summit, 1999, pp. 229-235.
40. N. Campbell, "CHATR: a high-definition speech resequencing system," in Proc. ASA/JASA Joint Meeting, 1996, pp. 1223-1228.
41. T. Takezawa, T. Morimoto, and Y. Sagisaka, "Speech and language databases for speech translation research in ATR," in Proc. 1st Int. Workshop on East-Asian Language Resources and Evaluation (EALREW), 1998, pp. 148-155.
42. F. Lefevre, J. L. Gauvain, and L. Lamel, "Improving genericity for task-independent speech recognition," in Proc. Eurospeech, 2001, pp. 1241-1244.
43. D. Paul and J. Baker, "The design for the wall street journal-based CSR corpus," in Proc. DARPA Speech and Natural Language Workshop, Feb. 1992, pp. 357-362.
44. Proc. Spoken Language Technology Workshop, Plainsboro, NJ, Mar. 1994.
45. P. Taylor, A. Black, and R. Caley, "The architecture of the Festival speech synthesis system," in Proc. Third Int. Workshop Speech Synthesis, Sydney, Australia, Nov. 1998, pp. 147-151.
46. J. S. Zhang, M. Mizumachi, F. Soong, and S. Nakamura, "An introduction to ATRPTH: a phonetically rich sentence set based Chinese Putonghua speech database developed by ATR," in Proc. ASJ Meeting, Fall 2003, pp. 167-168.
47. J. S. Zhang, S. W. Zhang, Y. Sagisaka, and S. Nakamura, "A hybrid approach to enhance task portability of acoustic models in Chinese speech recognition," in Proc. Eurospeech, vol. 3, 2001, pp. 1661-1663.
48. J. S. Zhang, K. Markov, T. Matsui, and S. Nakamura, "A study on acoustic modeling of pauses for recognizing noisy conversational speech," Proc. IEICE Trans. Inf. Syst., vol. 86-D, no. 3, pp. 489-196, 2003.
49. F. Sugaya, T. Takezawa, A. Yokoo, Y. Sagisaka, and S. Yamamoto, "Evaluation of the ATR-MATRIX speech translation system with a pair comparison method between the system and humans," in Proc. ICSLP, 2000, pp. 1105-1108.
50. T. Watanabe, E. Sumita, and H. Okuno, "Chunk-based statistical translation," Proc. ACL, pp. 303-310, 2003.