Frequency-Domain Blind Source Separation of Many Speech Signals Using Near-Field and Far-Field Models.
Ryo MukaiHiroshi SawadaShoko ArakiShoji MakinoPublished in: EURASIP J. Adv. Signal Process. (2006)
Keyphrases
- frequency domain
- convolutive mixtures
- blind source separation
- speech signal
- spatial domain
- blind separation
- independent component analysis
- non stationary
- power spectrum
- denoising
- source separation
- negative matrix factorization
- subband
- speech recognition
- probabilistic model
- face recognition
- autoregressive
- feature space
- additive noise
- source signals
- feature extraction