A local discontinuity based approach for monaural singing voice separation from accompanying music with multi-stage non-negative matrix factorization.
Hatem DeifWenwu WangLu GanSaadat AlhashmiPublished in: GlobalSIP (2015)
Keyphrases
- multistage
- negative matrix factorization
- music information retrieval
- matrix factorization
- nonnegative matrix factorization
- single stage
- sparse representation
- document clustering
- audio features
- principal component analysis
- dynamic programming
- lot sizing
- stochastic programming
- stochastic optimization
- computer vision
- spectral clustering
- optimal policy
- acoustic features
- natural language processing
- keywords
- machine learning
- tensor factorization