UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units.
Hirofumi InagumaSravya PopuriIlia KulikovPeng-Jen ChenChanghan WangYu-An ChungYun TangAnn LeeShinji WatanabeJuan PinoPublished in: ACL (1) (2023)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- endpoint detection
- recognition engine
- automatic speech recognition
- emotion recognition
- spoken language
- language acquisition
- speech processing
- speaker identification
- broadcast news
- spoken dialogue systems
- speaker recognition
- discrete space
- speech recognizer
- fundamental frequency
- hearing impaired
- automatic speech recognition systems
- database
- linear prediction
- noisy environments
- hidden markov models
- natural language
- bayesian networks