| Paper ID | AUD-L2.6 |
| Paper Title |
UNSUPERVISED TRAINING FOR DEEP SPEECH SOURCE SEPARATION WITH KULLBACK-LEIBLER DIVERGENCE BASED PROBABILISTIC LOSS FUNCTION |
| Authors |
Masahito Togami, LINE Corporation, Japan; Yoshiki Masuyama, Waseda University, Japan; Tatsuya Komatsu, LINE Corporation, Japan; Yu Nakagome, Waseda University, Japan |
| Session | AUD-L2: Deep Learning for Source Separation |
| Location | On-Demand |
| Session Time: | Tuesday, 05 May, 16:30 - 18:30 |
| Presentation Time: | Tuesday, 05 May, 18:10 - 18:30 |
| Presentation |
Lecture
|
| Topic |
Audio and Acoustic Signal Processing: [AUD-SEP] Audio and Speech Source Separation |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |