Already purchased this program?
Login to View
This video program is a part of the Premium package:
The Sound Of My Voice: Speaker Representation Loss For Target Voice Separation
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
The Sound Of My Voice: Speaker Representation Loss For Target Voice Separation
Content and style representations have been widely studied in the field of style transfer. In this paper, we propose a new loss function using speaker content representation for audio source separation, and we call it speaker representation loss. The obje
Content and style representations have been widely studied in the field of style transfer. In this paper, we propose a new loss function using speaker content representation for audio source separation, and we call it speaker representation loss. The obje