Generative adversarial networks for single channel separation of convolutive mixed speech signals.
Yang LiWei-Tao ZhangShun-Tian LouPublished in: Neurocomputing (2021)
Keyphrases
- single channel
- speech enhancement
- sound source
- speech signal
- multi channel
- independent component analysis
- speech recognition
- noisy environments
- noise reduction
- signal to noise ratio
- vocal tract
- frequency domain
- wavelet decomposition
- blind source separation
- linear prediction
- wiener filter
- additive noise
- audio visual
- non stationary
- hidden markov models
- automatic speech recognition
- machine learning
- image compression
- background noise
- feature extraction
- face recognition
- image processing