On-Line NMF-Based Stereo Up-Mixing of Speech Improves Perceived Reduction of Non-Stationary Noise.
Christian KirstFelix WeningerCyril JoderPeter GroscheJürgen T. GeigerBjörn W. SchullerPublished in: Semantic Audio (2014)
Keyphrases
- non stationary
- speech signal
- blind source separation
- white noise
- noisy environments
- negative matrix factorization
- biomedical signals
- nonnegative matrix factorization
- adaptive algorithms
- computer vision
- speech recognition
- random noise
- autoregressive
- depth map
- matrix factorization
- noise level
- signal to noise ratio
- temporal evolution
- missing data
- three dimensional
- noise reduction
- noise model
- stock market
- stereo matching
- multiresolution