| Paper ID | SPE-P19.5 |
| Paper Title |
SEMI-SUPERVISED SPEAKER ADAPTATION FOR END-TO-END SPEECH SYNTHESIS WITH PRETRAINED MODELS |
| Authors |
Katsuki Inoue, Sunao Hara, Masanobu Abe, Okayama university, Japan; Tomoki Hayashi, Nagoya university, Japan; Ryuichi Yamamoto, LINE Corporation, Japan; Shinji Watanabe, Johns Hopkins university, United States |
| Session | SPE-P19: Machine Learning for Speech Synthesis III |
| Location | On-Demand |
| Session Time: | Friday, 08 May, 11:45 - 13:45 |
| Presentation Time: | Friday, 08 May, 11:45 - 13:45 |
| Presentation |
Poster
|
| Topic |
Speech Processing: [SPE-SYNT] Speech Synthesis and Generation |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |