Improving Stability of LS-GANs for Audio and Speech Signals.
Mohammad EsmaeilpourRaymel Alfonso SalloOlivier St-GeorgesPatrick CardinalAlessandro Lameiras KoerichPublished in: CoRR (2020)
Keyphrases
- speech signal
- speaker identification
- speech recognition
- automatic speech recognition
- acoustic features
- automatic speech recognition systems
- linear prediction
- broadcast news
- background noise
- additive noise
- noisy environments
- hidden markov models
- vocal tract
- mel frequency cepstral coefficients
- sound source
- spectral analysis
- speech enhancement
- computer vision
- neural network
- audio features
- blind source separation
- feature extraction
- audio signal
- speaker recognition
- image processing
- audio visual