Monaural Speech Enhancement using Deep Neural Network with Cross-Speech Dataset.
Norezmi JamalNorfaiza FuadShahnoor ShantaMohd Nurul Al-Hafiz Sha'abaniPublished in: ICSIPA (2021)
Keyphrases
- spectral analysis
- speech signal
- speech enhancement
- neural network
- speech recognition
- linear prediction
- vocal tract
- noisy environments
- automatic speech recognition
- noisy speech
- additive noise
- background noise
- noise reduction
- hidden markov models
- single channel
- pattern recognition
- signal to noise ratio
- speech synthesis
- edge preserving
- wavelet transform
- sound source
- motion estimation
- smoothing algorithm
- feature vectors