JANUS-II-translation of spontaneous conversational speech.

A. Waibel,M. Finke,D. Gates,M. Gavalda,T. Kemp,A. Lavie,L. Levin,M. Maier,L. Mayfield,A. McNair,I. Rogina,K. Shima,T. Sloboda, M. Woszczyna,T. Zeppenfeld, P. Zhan

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference（1996）

引用 25|浏览0

暂无评分

摘要

JANUS-II is a research system to design and test components of speech-to-speech translation systems as well as a research prototype for such a system. We focus on two aspects of the system: (1) the new features of the speech recognition component JANUS-SR, and (2) the end-to-end performance of JANUS-II, including a comparison of two machine translation strategies used for JANUS-MT (PHOENIX and GLR*).

查看译文

关键词

machine translation strategy,test component,research system,research prototype,end-to-end performance,spontaneous conversational speech,speech recognition component janus-sr,new feature,speech-to-speech translation system,performance,databases,machine translation,speech recognition,crosstalk,natural languages,switches,language translation,prototypes

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要