Dereverberation using joint estimation of dry speech signal and acoustic system.
Sanna WagerKeunwoo ChoiSimon DurandPublished in: CoRR (2020)
Keyphrases
- joint estimation
- speech signal
- acoustic features
- speech sounds
- sound source
- speech recognition
- noisy speech
- automatic speech recognition
- mel frequency cepstral coefficients
- speaker identification
- vocal tract
- linear prediction
- non stationary
- background noise
- automatic speech recognition systems
- noisy environments
- hidden markov models
- speaker verification
- speaker recognition
- spectral analysis
- visual speech
- speech quality
- audio signal
- visual features
- image quality
- computer vision