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: CoRR (2022)
Keyphrases
- speech recognition
- speech synthesis
- speech signal
- recognition engine
- audio visual
- database
- spoken language
- automatic speech recognition systems
- machine learning
- case study
- hidden markov models
- speech processing
- automatic speech recognition
- speech quality
- multi stream
- speaker recognition
- broadcast news
- neural network
- data sets
- real time