Reverberation as Supervision For Speech Separation.
Rohith AralikattiChristoph BöddekerGordon WichernAswin Shanmugam SubramanianJonathan Le RouxPublished in: ICASSP (2023)
Keyphrases
- sound source
- speech signal
- speech recognition
- audio visual
- recognition engine
- speech synthesis
- text to speech
- automatic speech recognition
- audio features
- spoken language
- active learning
- hidden markov models
- speaker identification
- language acquisition
- speaker recognition
- audio stream
- multi lingual
- speech processing
- data sets
- speaker verification
- broadcast news
- visual features
- probabilistic model
- pattern recognition
- knowledge base
- genetic algorithm