Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2020 Open Preview.

SPE-L8: Speech Synthesis and Voice Conversion II

Session Type: Lecture
Time: Wednesday, 6 May, 11:30 - 13:30
Location: On-Demand
Virtual Session: View on Virtual Platform
Session Chair: Masami Akamine, Tohoku University
 
 SPE-L8.1: FULLY-HIERARCHICAL FINE-GRAINED PROSODY MODELING FOR INTERPRETABLE SPEECH SYNTHESIS
         Guangzhi Sun; Cambridge University
         Yu Zhang; Google
         Ron Weiss; Google
         Yuan Cao; Google
         Heiga Zen; Google
         Yonghui Wu; Google
 
 SPE-L8.2: TRANSFERRING NEURAL SPEECH WAVEFORM SYNTHESIZERS TO MUSICAL INSTRUMENT SOUNDS GENERATION
         Yi Zhao; National Institute of Informatics
         Xin Wang; National Institute of Informatics
         Lauri Juvela; Aalto University
         Junichi Yamagishi; National Institute of Informatics
 
 SPE-L8.3: TEACHER-STUDENT TRAINING FOR ROBUST TACOTRON-BASED TTS
         Rui Liu; Inner Mongolia University
         Berrak Sisman; National University of Singapore
         Jingdong Li; Inner Mongolia University
         Feilong Bao; Inner Mongolia University
         Guanglai Gao; Inner Mongolia University
         Haizhou Li; National University of Singapore
 
 SPE-L8.4: MANY-TO-MANY VOICE CONVERSION USING CONDITIONAL CYCLE-CONSISTENT ADVERSARIAL NETWORKS
         Shindong Lee; Korea University
         BongGu Ko; Korea University
         Keonnyeong Lee; Korea University
         In-Chul Yoo; Korea University
         Dongsuk Yook; Korea University
 
 SPE-L8.5: F0-CONSISTENT MANY-TO-MANY NON-PARALLEL VOICE CONVERSION VIA CONDITIONAL AUTOENCODER
         Kaizhi Qian; University of Illinois at Urbana-Champaign
         Zeyu Jin; Adobe
         Mark Hasegawa-Johnson; University of Illinois at Urbana-Champaign
         Gautham Mysore; Adobe
 
 SPE-L8.6: END-TO-END ACCENT CONVERSION WITHOUT USING NATIVE UTTERANCES
         Songxiang Liu; Chinese University of Hong Kong
         Disong Wang; Chinese University of Hong Kong
         Yuewen Cao; Chinese University of Hong Kong
         Lifa Sun; SpeechX Limited
         Xixin Wu; Chinese University of Hong Kong
         Shiyin Kang; Tencent
         Zhiyong Wu; Tsinghua University
         Xunying Liu; Chinese University of Hong Kong
         Dan Su; Tencent
         Dong Yu; Tencent
         Helen Meng; Chinese University of Hong Kong