Orthonormal Embedding-based Deep Clustering for Single-channel Speech Separation.
Soyeon ChoeSoo-Whan ChungYouna JiHong-Goo KangPublished in: CoRR (2019)
Keyphrases
- single channel
- speech enhancement
- multi channel
- sound source
- speech signal
- independent component analysis
- speech recognition
- clustering algorithm
- denoising
- noisy environments
- vocal tract
- high frequency
- cluster analysis
- frequency domain
- image quality
- automatic speech recognition
- similarity measure
- image segmentation
- image processing