Supervised and semi-supervised speech enhancement using weighted nonnegative matrix factorization.
Xia ZouYonggang HuXiongwei ZhangPublished in: WCSP (2017)
Keyphrases
- nonnegative matrix factorization
- speech enhancement
- supervised and semi supervised
- semi supervised
- noisy environments
- noise reduction
- negative matrix factorization
- matrix factorization
- signal to noise ratio
- data representation
- single channel
- least squares
- speech signal
- principal component analysis
- unlabeled data
- spectral clustering
- document clustering
- original data
- machine learning
- pattern recognition
- objective function
- image processing
- labeled data
- unsupervised learning
- dimensionality reduction
- pairwise
- feature selection