The ATR multilingual speech-to-speech translation system.
Satoshi NakamuraKonstantin MarkovHiromi NakaiwaGen-ichiro KikuiHisashi KawaiTakatoshi JitsuhiroJinsong ZhangHirofumi YamamotoEiichiro SumitaSeiichi YamamotoPublished in: IEEE Trans. Speech Audio Process. (2006)
Keyphrases
- speech recognition
- multi lingual
- speech signal
- language resources
- automatic speech recognition
- broadcast news
- cross language information retrieval
- endpoint detection
- recognition engine
- text to speech
- dialogue system
- speaker recognition
- spoken language
- speech synthesis
- digital libraries
- speaker identification
- query translation
- neural network