Speaker conditioned acoustic modeling for multi-speaker conversational ASR.
Srikanth Raj ChetupalliSriram GanapathyPublished in: INTERSPEECH (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- acoustic features
- conversational speech
- speech sounds
- speaker verification
- audio visual
- acoustic models
- speaker independent
- speech recognition systems
- speaker recognition
- prosodic features
- multi modal
- speech recognizers
- noisy environments
- broadcast news
- speech signal
- speaker diarization
- visual speech
- hidden markov models
- pattern recognition
- data sets
- speech recognizer
- natural language
- speaker dependent
- emotional speech
- neural network