SPE-3.5
PERCEPTUAL-SIMILARITY-AWARE DEEP SPEAKER REPRESENTATION LEARNING FOR MULTI-SPEAKER GENERATIVE MODELING
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari, The University of Tokyo, Japan
Session:
Speech Synthesis: General Topics I
Track:
Speech and Language Processing
Location:
Gather Area D
Presentation Time:
Sun, 8 May, 20:00 - 20:45 China Time (UTC +8)
Sun, 8 May, 12:00 - 12:45 UTC
Sun, 8 May, 12:00 - 12:45 UTC
Session Chair:
Lei Xie, Northwestern Polytechnical University
Presentation
Discussion
Resources
No resources available.
Session SPE-3
SPE-3.1: IMPROVING CROSS-LINGUAL SPEECH SYNTHESIS WITH TRIPLET TRAINING SCHEME
Jianhao Ye, Hongbin Zhou, Zhiba Su, Wendi He, Kaimeng Ren, Lin Li, Heng Lu, Ximalaya Inc., China
SPE-3.2: IMPROVING PHONETIC REALIZATIONS IN TTS BY USING PHONEME-ALIGNED GRAPHEMES
Manish Sharma, Yizhi Hong, Emily Kaplan, Siamak Tazari, Rob Clark, Google, United Kingdom of Great Britain and Northern Ireland
SPE-3.3: CONTEXT-AWARE MASK PREDICTION NETWORK FOR END-TO-END TEXT-BASED SPEECH EDITING
Tao Wang, Jiangyan Yi, Ruibo Fu, Jianhua Tao, Zhengqi Wen, Institute of Automation, Chinese Academy of Sciences, China; Liqun Deng, Huawei Noah's Ark Lab, Shenzhen, China, China
SPE-3.4: A study on the efficacy of model pre-training in developing neural text-to-speech system
Guangyan Zhang, Daxin Tan, Tan Lee, Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong; Yichong Leng, University of Science and Technology of China, China; Ying Qin, Institute of Information Science, Beijing Jiaotong University, China; Kaitao Song, Xu Tan, Microsoft Research Asia, China; Sheng Zhao, Microsoft Azure Speech, China
SPE-3.5: PERCEPTUAL-SIMILARITY-AWARE DEEP SPEAKER REPRESENTATION LEARNING FOR MULTI-SPEAKER GENERATIVE MODELING
Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari, The University of Tokyo, Japan
SPE-3.6: ONE TTS ALIGNMENT TO RULE THEM ALL
Rohan Badlani, Adrian Lancucki, Kevin J. Shih, Rafael Valle, Wei Ping, Bryan Catanzaro, NVIDIA, United States of America