Streaming Parrotron for on-device speech-to-speech conversion.
Oleg RybakovFadi BiadsyXia ZhangLiyang JiangPhoenix MeadowlarkShivani AgrawalPublished in: CoRR (2022)
Keyphrases
- speech recognition
- text to speech
- speech signal
- recognition engine
- audio visual
- neural network
- endpoint detection
- automatic speech recognition
- speech processing
- spoken language
- broadcast news
- automatic speech recognition systems
- audio stream
- speaker recognition
- language acquisition
- human communication
- multi stream
- spontaneous speech
- dialogue system
- data acquisition
- mobile devices
- text to speech synthesis
- data streams