Audio Source Separation in Reverberant Environments Using β-Divergence-Based Nonnegative Factorization.
Mahmoud FakhryPiergiorgio SvaizerMaurizio OmologoPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2017)
Keyphrases
- source separation
- audio features
- blind source separation
- independent component analysis
- multimedia
- tensor factorization
- audio visual
- single channel
- dynamic environments
- speech signal
- denoising
- low level
- feature set
- matrix factorization
- temporal structure
- signal processing
- noise reduction
- visual features
- audio signal
- gaussian process
- visual data
- speech recognition
- negative matrix factorization
- non stationary
- music information retrieval
- collaborative filtering
- probabilistic model
- multiscale