Enhancing Speech-To-Speech Translation with Multiple TTS Targets.
Jiatong ShiYun TangAnn LeeHirofumi InagumaChanghan WangJuan PinoShinji WatanabePublished in: ICASSP (2023)
Keyphrases
- text to speech
- speech synthesis
- speech recognition
- speech signal
- prosodic features
- audio visual
- endpoint detection
- automatic speech recognition
- noisy environments
- text to speech synthesis
- speaker identification
- automatic speech recognition systems
- speech recognizer
- multi lingual
- speaker recognition
- speaker verification
- real time
- broadcast news
- spoken language
- multiple targets
- feature extraction