Speaker and Direction Inferred Dual-channel Speech Separation.
Chenxing LiJiaming XuNima MesgaraniBo XuPublished in: CoRR (2021)
Keyphrases
- dual channel
- speech recognition
- audio visual
- speaker recognition
- automatic speech recognition
- sound source
- speaker verification
- speaker identification
- speech signal
- speaker diarization
- prosodic features
- vocal tract
- speaker dependent
- automatic speech recognition systems
- speech synthesis
- synthesized speech
- hidden markov models
- multi modal
- speech sounds
- gaussian mixture model
- noisy environments
- broadcast news
- acoustic features
- text to speech
- language model
- automatic transcription
- acoustic models
- audio stream
- phoneme recognition
- visual information
- neural network
- vector quantization
- speaker adaptation
- multi stream
- visual data
- bayesian networks
- endpoint detection
- spoken language
- recognition engine
- spontaneous speech
- spoken dialogue systems
- speech recognizer