Direct Speech-to-Speech Translation With Discrete Units.
Ann LeePeng-Jen ChenChanghan WangJiatao GuSravya PopuriXutai MaAdam PolyakYossi AdiQing HeYun TangJuan PinoWei-Ning HsuPublished in: ACL (1) (2022)
Keyphrases
- speech recognition
- speech signal
- text to speech
- endpoint detection
- speech synthesis
- spoken language
- audio visual
- recognition engine
- automatic speech recognition systems
- broadcast news
- speech recognizer
- speech processing
- speaker recognition
- database
- spoken dialogue systems
- language acquisition
- emotion recognition
- multi lingual
- dialogue system
- cross language information retrieval
- multi modal
- language resources
- multiscale
- feature extraction
- hearing impaired
- information retrieval