An automatic speech translation system for travel conversation

Autor: kitoshi Okumura, Kiyoshi Yamabana, Ken Hanazawa, Shinichi Doi, Ken-ichi Iso, Takao Watanabe
Rok vydání: 2002
Předmět:
Zdroj: Proceedings of the second international conference on Human Language Technology Research.
DOI: 10.3115/1289189.1289241
Popis: We present a speech-to-speech translation system for notebook PC's that helps oral communication between Japanese and English speakers in the various situations in the travel abroad. Due to the high accuracy of the compact continuous speech recognition engine and our lexicalized grammar approach to machine translation that utilizes corpus but is oriented to model general linguistic phenomena as well as word-specific ones, a versatile speech-to-speech translation system for travel abroad is achieved, which is with much larger vocabulary (50,000 Japanese words and 10,000 English words) and capable of translating spoken conversations in more situations compared to previous work [1].
Databáze: OpenAIRE