Blind separation of underdetermined Convolutive speech mixtures by time-frequency masking with the reduction of musical noise of separated signals.
Mahbanou ZohrevandiSaeed SetayeshiAzam RabieeMidia ReshadiPublished in: Multim. Tools Appl. (2021)
Keyphrases
- blind separation
- source signals
- blind source separation
- independent component analysis
- mixing matrix
- speech signal
- signal processing
- source separation
- single channel
- speech recognition
- blind deconvolution
- nonlinear functions
- non stationary
- independent components
- additive noise
- frequency domain
- human visual system
- short time fourier transform
- negative matrix factorization
- filter responses
- neural network
- audio visual
- noise reduction
- principal component analysis
- multiscale