Translatotron 2: Robust direct speech-to-speech translation.
Ye JiaMichelle Tadmor RamanovichTal RemezRoi PomerantzPublished in: CoRR (2021)
Keyphrases
- speech recognition
- speech signal
- audio visual
- speech synthesis
- automatic speech recognition
- endpoint detection
- noisy environments
- speaker recognition
- broadcast news
- speaker verification
- automatic speech recognition systems
- real time
- speech recognizer
- spoken dialogue systems
- spoken language
- cross language information retrieval
- text to speech
- english text
- multimodal interfaces
- query translation
- vocal tract
- computer vision
- artificial intelligence