Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix Factorization Based on Multivariate Complex Sub-Gaussian Distribution.
Keigo KamoYuki KuboNorihiro TakamuneDaichi KitamuraHiroshi SaruwatariYu TakahashiKazunobu KondoPublished in: EUSIPCO (2020)
Keyphrases
- gaussian distribution
- nonnegative matrix factorization
- negative matrix factorization
- matrix factorization
- data representation
- maximum likelihood
- gaussian mixture model
- expectation maximization
- nonnegative matrix
- principal component analysis
- spectral clustering
- probabilistic latent semantic indexing
- machine learning
- information retrieval
- training data
- bag of words