Single-channel speech dereverberation based on block-wise weighted prediction error and nonnegative matrix factorization.
Chan Woong KwakKwang Myung JeonIn Young ParkHong Kook KimJeong Eun LimJi Hyun ParkPublished in: ICCE (2018)
Keyphrases
- prediction error
- nonnegative matrix factorization
- block wise
- single channel
- linear prediction
- multi channel
- order statistics
- negative matrix factorization
- matrix factorization
- independent component analysis
- speech recognition
- frequency domain
- least squares
- principal component analysis
- bit rate
- speech signal
- spectral clustering
- inter frame
- motion vectors
- audio visual
- sound source
- signal processing
- median filter
- image segmentation
- multiresolution