HIGHLIGHTS
- who: Sequence-to-Sequence Emotional Voice and colleagues from the Department of Electrical Engineering, Korea Advanced Institute of Science Technology (KAIST), Daejeon, South Korea have published the paper: Sequence-to-Sequence Emotional Voice Conversion With Strength Control, in the Journal: (JOURNAL)
- what: To address this, the authors propose a novel EVC method that can synthesize emotional output speech with adjusted duration using a sequence-to-sequence network. Inspired by the controllable emotion strength in TTS, the authors propose an EVC method that controls the degree of the target emotion. The authors design the representative emotion . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.