A Maximum Likelihood Approach to Masking-based Speech Enhancement Using Deep Neural Network.
Qing WangJun DuLi ChaiLi-Rong DaiChin-Hui LeePublished in: ISCSLP (2018)
Keyphrases
- speech enhancement
- single channel
- neural network
- multi channel
- noisy environments
- independent component analysis
- signal to noise ratio
- wiener filter
- prior information
- noise reduction
- frequency domain
- speech signal
- vocal tract
- wavelet decomposition
- pattern recognition
- linear prediction
- principal component analysis
- sound source
- background noise
- brain activity
- wavelet transform
- signal processing
- edge detection