Enhancing Automatic Speech Recognition Quality with a Second-Stage Speech Enhancement Generative Adversarial Network.
Soha A. NossierJulie A. WallMansour MoniriCornelius GlackinNigel CanningsPublished in: ICTAI (2023)
Keyphrases
- automatic speech recognition
- speech signal
- speech enhancement
- noisy environments
- speech recognition
- vocal tract
- background noise
- speech sounds
- conversational speech
- broadcast news
- additive noise
- noise reduction
- signal to noise ratio
- non stationary
- language model
- speaker identification
- word error rate
- pattern recognition
- spectral subtraction
- neural network
- speaker verification
- acoustic features
- hidden markov models
- smoothing algorithm
- feature selection