Supervised Single Channel Speech Enhancement Based on Stationary Wavelet Transforms and Non-negative Matrix Factorization with Concatenated Framing Process and Subband Smooth Ratio Mask.
Md. Shohidul IslamTarek Hasan Al MahmudWasim Ullah KhanZhongfu YePublished in: J. Signal Process. Syst. (2020)
Keyphrases
- subband
- single channel
- wavelet decomposition
- speech enhancement
- wavelet transform
- negative matrix factorization
- linear prediction
- frequency domain
- feature vectors
- wavelet coefficients
- filter bank
- image compression
- multiresolution
- multi channel
- high frequency
- wavelet domain
- image coding
- noise reduction
- multiscale
- bit rate
- noisy environments
- high quality
- hidden markov models
- information retrieval
- sar images
- sparse representation
- speech signal
- motion estimation
- feature extraction
- image sequences