Some results with a trainable speech translation and understanding system
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference（1995）
摘要
The problems of limited-domain spoken language translation and understanding are considered. A standard continuous speech recognizer is extended for using automatically learnt finite-state transducers as translation models. Understanding is considered as a particular case of translation where the target language is a formal language. From the different approaches compared, the best results are obtained with a fully integrated approach, in which the input language acoustic and lexical models, and (N-gram) language models of input and output languages, are embedded into the learnt transducers. Optimal search through this global network obtains the best translation for a given input acoustic signal
更多查看译文
关键词
acoustic signal processing,finite state machines,formal languages,grammars,language translation,natural languages,speech recognition,transducers,N-gram language models,automatically learnt finite-state transducers,continuous speech recognizer,formal language,global network,input acoustic signal,input language acoustic model,input language lexical model,limited-domain spoken language translation,optimal search,output languages,speech understanding system,spoken language understanding,target language,trainable speech translation system,translation model
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