Multiple-Translation Spotting for Mandarin-Taiwanese Speech-to-Speech Translation

Jhing-Fa Wang ； Shun-Chieh Lin ； Hsueh-Wei Yang ； Fan-Min Li

《中文計算語言學期刊》 9卷2期 (2004/08) Pp. 13-28

https://doi.org/10.30019/IJCLCLP.200408.0002

並列摘要

The critical issues involved in speech-to-speech translation are obtaining proper source segments and synthesizing accurate target speech. Therefore, this article develops a novel multiple-translation spotting method to deal with these issues efficiently. Term multiple-translation spotting refers to the task of extracting target-language synthesis patterns that correspond to a given set of source-language spotted patterns in conditional multiple pairs of speech patterns known to be translation patterns. According to the extracted synthesis patterns, the target speech can be properly synthesized by using a waveform segment concatenation-based synthesis method. Experiments were conducted with the languages of Mandarin and Taiwanese. The results reveal that the proposed approach can achieve translation understanding rates of 80% and 76% on average for Mandarin/Taiwanese translation and Taiwanese/Mandarin translation, respectively.

並列關鍵字

Multiple-Translation Spotting ； Speech-to-Speech Translation

參考文獻

(1993).Machine Translation: A View from the Lexicon.

(2000).Verbmobil: Foundations of Speech-to-Speech Translation.

Hanazawa, K.,Isotani, R.,Osada, S.,Okumura, A.,Watanabe, T.,Yamabana, K.(2003).A Speech Translation System with mobile Wireless Clients.Proceedings of the Student Research Workshop at the 41st Annual Meeting of the Association for Computational Linguistics.41(2),119-122.

Langlais, P.,Simard, M.,Macklovitch, E.(2000).TransSearch: A Free Translation Memory on the World Wide Web.Proceedings of International Conference on Language Resources and Evaluation.3(1),1201-1208.

Liu, J.(1998).A Hybrid Model for Chinese-English Machine Translation.Proceedings of IEEE International Conference on Systems, Man, and Cybernetics.2(1),1201-1206.