SPE-23.6
CONTROLLABLE SPEECH REPRESENTATION LEARNING VIA VOICE CONVERSION AND AIC LOSS
Yunyun Wang, Jiaqi Su, Adam Finkelstein, Princeton University, United States of America; Zeyu Jin, Adobe Research, United States of America
Session:
Voice Conversion: Singing Voice and Others
Track:
Speech and Language Processing
Location:
Gather Area D
Presentation Time:
Mon, 9 May, 21:00 - 21:45 China Time (UTC +8)
Mon, 9 May, 13:00 - 13:45 UTC
Mon, 9 May, 13:00 - 13:45 UTC
Session Chair:
Mark Hasegawa-Johnson, University of Illinois
Session SPE-23
SPE-23.1: IMPROVING ADVERSARIAL WAVEFORM GENERATION BASED SINGING VOICE CONVERSION WITH HARMONIC SIGNALS
Haohan Guo, Chinese University of Hong Kong, Hong Kong; Zhiping Zhou, Fanbo Meng, Kai Liu, Sogou, China
SPE-23.2: K-Converter: An unsupervised Singing Voice Conversion System
Ying Zhang, Peng Yang, Jinba Xiao, Ye Bai, Hao Che, Xiaorui Wang, kwai, China
SPE-23.3: HIFI-SVC: FAST HIGH FIDELITY CROSS-DOMAIN SINGING VOICE CONVERSION
Yong Zhou, Xiangju Lu, iQIYI Inc., China
SPE-23.4: TOWARDS IDENTITY PRESERVING NORMAL TO DYSARTHRIC VOICE CONVERSION
Wen-Chin Huang, Lester Phillip Violeta, Tomoki Toda, Nagoya University, Japan; Bence Mark Halpern, Odette Scharenborg, Delft University of Technology, Netherlands
SPE-23.5: SPEAKER IDENTITY PRESERVATION IN DYSARTHRIC SPEECH RECONSTRUCTION BY ADVERSARIAL SPEAKER ADAPTATION
Disong Wang, Songxiang Liu, Xixin Wu, Hui Lu, Xunying Liu, Helen Meng, The Chinese University of Hong Kong, Hong Kong; Lifa Sun, SpeechX Limited, China
SPE-23.6: CONTROLLABLE SPEECH REPRESENTATION LEARNING VIA VOICE CONVERSION AND AIC LOSS
Yunyun Wang, Jiaqi Su, Adam Finkelstein, Princeton University, United States of America; Zeyu Jin, Adobe Research, United States of America