Direct speech-to-speech translation with discrete units.
Ann LeePeng-Jen ChenChanghan WangJiatao GuXutai MaAdam PolyakYossi AdiQing HeYun TangJuan Miguel PinoWei-Ning HsuPublished in: CoRR (2021)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- endpoint detection
- recognition engine
- audio visual
- automatic speech recognition
- text to speech
- speaker identification
- broadcast news
- text to speech synthesis
- spoken language
- language acquisition
- pattern recognition
- data sets
- spoken dialogue systems
- speaker recognition
- cross language information retrieval
- speech recognizer
- spontaneous speech
- information retrieval systems
- machine learning