Speech translation on a tight budget without enough data

ABSTRACT

The Tongues speech-to-speech translation system was developed for the US Army chaplains, with fairly stringent constraints on time, budget, and available data. The resulting prototype was required to undergo a quite realistic field test. We describe the development and architecture of the system, the field test, and our analysis of its results. The system performed quite well, especially given its development constraints.

REFERENCES

• 1: Jeffrey Allen and Christopher Hogan. 1998. Expanding lexical coverage of parallel corpora for the ebmt approach. In First Conference on Language Resources and Evaluation (LREC '98), pages 747--754, Granada, Spain, May.
• 2: A. Black and K. Lenzo. 2001. Optimal data selection for unit selection synthesis. In 4rd ESCA Workshop on Speech Synthesis, Scotland.
• 3: A. Black, P. Taylor, and R. Caley. 1998. The Festival Speech Synthesis System. http://festvox.org/festival.
• 4: A. Black, R. Brown, R. Frederking, K. Lenzo, J. Moody, A. Rudnicky, R. Singh, and E. Steinbrecher. 2002a. Rapid devlopement of speech-to-speech translation systems. Submitted to ICSLP2002.
• 5: A. Black, R. Brown, R. Frederking, R. Singh, J. Moody, and E. Steinbrecher. 2002b. TONGUES: Rapid Development of a Speech-to-Speech Translation System. In Proceedings of HLT-2002, San Diego, CA, USA.
• 6: R. Brown and R. Frederking. 1995. Applying Statistical English Language Modeling to Symbolic Machine Translation. In Proceedings of the Sixth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-95), pages 221--239.
• 7: Ralf D. Brown, Example-Based Machine Translation in the Pangloss system, Proceedings of the 16th conference on Computational linguistics, August 05-09, 1996, Copenhagen, Denmark [doi>10.3115/992628.992660]
• 8: Robert Frederking , Sergei Nirenburg, Three heads are better than one, Proceedings of the fourth conference on Applied natural language processing, October 13-15, 1994, Stuttgart, Germany [doi>10.3115/974358.974380]
• 9: Robert Frederking , Alexander Rudnicky , Christopher Hogan , Kevin Lenzo, Interactive Speech Translation in the Diplomat Project, Machine Translation, v.15 n.1-2, p.27-42, June 2000 [doi>10.1023/A:1011172330853]
• 10: R. Frederking, A. Black, R. Brown, J. Moody, and E. Steinbrecher. 2002. Field Testing the Tongues Speech-to-Speech Machine Translation System. LREC 2002.
• 11: Keiko Horiguchi and Alexander Franz. 1997. A formal basis for spoken language translation by analogy. In Steven Krauwer et al., editors, Proceedings of the Spoken Language Translation Workshop, pages 32--39, Madrid, Spain, July. ELSNET.
• 12: X. Huang, F. Alleva, H.-W. Hon, K.-F. Hwang, M.-Y. Lee, and R. Rosenfeld. 1992. The SPHINX-II Speech Recognition System: an overview. Computer Speech and Language, 7(2):137--148.
• 13: Lori Levin , Alon Lavie , Monika Woszczyna , Donna Gates , Marsal Gavaldá , Detlef Koll , Alex Waibel, The Janus-III Translation System: Speech-to-Speech Translation in Multiple Domains, Machine Translation, v.15 n.1-2, p.3-25, June 2000 [doi>10.1023/A:1011186420821]
• 14: M. Rayner , D. Carter, Hybrid Language Processing in the Spoken Language Translator, Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1, p.107, April 21-24, 1997
• 15: Alex Waibel, Interactive Translation of Conversational Speech, Computer, v.29 n.7, p.41-48, July 1996 [doi>10.1109/2.511967]