2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

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