Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization.
Yoshiaki BandoMasato MimuraKatsutoshi ItoyamaKazuyoshi YoshiiTatsuya KawaharaPublished in: ICASSP (2018)
Keyphrases
- negative matrix factorization
- speech enhancement
- matrix factorization
- noisy environments
- document clustering
- sparse representation
- noise reduction
- probabilistic model
- speech signal
- signal to noise ratio
- single channel
- generative model
- bayesian networks
- principal component analysis
- spectral clustering
- multi channel
- pattern recognition
- vocal tract
- data mining
- image classification
- image retrieval
- wiener filter