Monaural Singing Voice Separation Using Fusion-Net with Time-Frequency Masking.
Feng LiKaizhi QianMark Hasegawa-JohnsonMasato AkagiPublished in: APSIPA (2019)
Keyphrases
- data fusion
- human visual system
- information fusion
- fusion method
- multi sensor
- frequency domain
- fusion process
- wavelet transform
- empirically derived
- signal analysis
- sensor fusion
- emotion recognition
- information loss
- image fusion
- search engine
- non stationary
- multiple features
- wavelet packet
- multi modal
- image registration
- fusion algorithm
- pattern recognition
- database programming
- music information retrieval
- feature selection
- information retrieval