2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-50: Voice Conversion & Speech Synthesis: Singing Voice & Other Topics |
| Session Type: Poster |
| Time: Friday, 11 June, 11:30 - 12:15 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Erica Cooper, National Institute of Informatics |
| SPE-50.1: NON-AUTOREGRESSIVE SEQUENCE-TO-SEQUENCE VOICE CONVERSION |
| Tomoki Hayashi; TARVO Inc. |
| Wen-Chin Huang; Nagoya University |
| Kazuhiro Kobayashi; TARVO Inc. |
| Tomoki Toda; Nagoya University |
| SPE-50.2: PPG-BASED SINGING VOICE CONVERSION WITH ADVERSARIAL REPRESENTATION LEARNING |
| Zhonghao Li; ByteDance AI Lab |
| Benlai Tang; ByteDance AI Lab |
| Xiang Yin; ByteDance AI Lab |
| Yuan Wan; ByteDance AI Lab |
| Ling Xu; ByteDance AI Lab |
| Chen Shen; ByteDance AI Lab |
| Zejun Ma; ByteDance AI Lab |
| SPE-50.3: LITESING: TOWARDS FAST, LIGHTWEIGHT AND EXPRESSIVE SINGING VOICE SYNTHESIS |
| Xiaobin Zhuang; Tencent Music Entertainment |
| Tao Jiang; Tencent Music Entertainment |
| Szu-Yu Chou; Tencent Music Entertainment |
| Bin Wu; Tencent Music Entertainment |
| Peng Hu; Tencent Music Entertainment |
| Simon Lui; Tencent Music Entertainment |
| SPE-50.4: SEMI-SUPERVISED LEARNING FOR SINGING SYNTHESIS TIMBRE |
| Jordi Bonada; Universitat Pompeu Fabra |
| Merlijn Blaauw; Universitat Pompeu Fabra |
| SPE-50.5: RECURRENT PHASE RECONSTRUCTION USING ESTIMATED PHASE DERIVATIVES FROM DEEP NEURAL NETWORKS |
| Lars Thieling; Institute of Communication Systems, RWTH Aachen University |
| Daniel Wilhelm; Institute of Communication Systems, RWTH Aachen University |
| Peter Jax; Institute of Communication Systems, RWTH Aachen University |
| SPE-50.6: STABLE CHECKPOINT SELECTION AND EVALUATION IN SEQUENCE TO SEQUENCE SPEECH SYNTHESIS |
| Slava Shechtman; IBM Research |
| David Haws; IBM Research |
| Raul Fernandez; IBM Research |