Reverberation as Supervision for Speech Separation.
Rohith AralikattiChristoph BöddekerGordon WichernAswin Shanmugam SubramanianJonathan Le RouxPublished in: CoRR (2022)
Keyphrases
- sound source
- speech signal
- speech recognition
- audio visual
- speech synthesis
- broadcast news
- multi modal
- vocal tract
- audio features
- spoken language
- text to speech
- automatic speech recognition
- endpoint detection
- speaker recognition
- automatic speech recognition systems
- neural network
- spectral features
- speaker verification
- emotion recognition
- dialogue system
- machine learning