Joint noise and mask aware training for DNN-based speech enhancement with SUB-band features.
Qing WangJun DuLi-Rong DaiChin-Hui LeePublished in: HSCMA (2017)
Keyphrases
- subband
- speech enhancement
- feature vectors
- noisy environments
- low frequency
- signal to noise ratio
- high frequency
- noise reduction
- feature extraction
- filter bank
- multiresolution
- wavelet decomposition
- high pass
- wavelet transform
- discrete wavelet transform
- image compression
- wavelet coefficients
- feature space
- low pass
- image sequences
- vocal tract
- single channel
- wiener filter
- multiscale
- speech signal
- image coding
- feature set