IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
SPE-11: Speech Synthesis: Style & Expressiveness
Sun, 8 May, 22:00 - 22:45 China Time (UTC +8)
Sun, 8 May, 14:00 - 14:45 UTC
Location: Gather Area D
Session Chair: Tomoki Toda, Nagoya University
Track: Speech and Language Processing

SPE-11.1: REFEREE: TOWARDS REFERENCE-FREE CROSS-SPEAKER STYLE TRANSFER WITH LOW-QUALITY DATA FOR EXPRESSIVE SPEECH SYNTHESIS
Songxiang Liu, Shan Yang, Dan Su, Dong Yu, Tencent, China

SPE-11.2: PVAE-TTS: ADAPTIVE TEXT-TO-SPEECH VIA PROGRESSIVE STYLE ADAPTATION
Ji-Hyun Lee, Sang-Hoon Lee, Ji-Hoon Kim, Seong-Whan Lee, Korea University, Korea, Republic of

SPE-11.3: EMOQ-TTS: EMOTION INTENSITY QUANTIZATION FOR FINE-GRAINED CONTROLLABLE EMOTIONAL TEXT-TO-SPEECH
Chae-Bin Im, Sang-Hoon Lee, Seung-Bin Kim, Seong-Whan Lee, Korea University, Korea, Republic of

SPE-11.4: JOINT AND ADVERSARIAL TRAINING WITH ASR FOR EXPRESSIVE SPEECH SYNTHESIS
Kaili Zhang, Cheng Gong, Wenhuan Lu, Longbiao Wang, Jianguo Wei, Dawei Liu, Tianjin University, China

SPE-11.5: MSDTRON: A HIGH-CAPABILITY MULTI-SPEAKER SPEECH SYNTHESIS SYSTEM FOR DIVERSE DATA USING CHARACTERISTIC INFORMATION
Qinghua Wu, Quanbo Shen, Jian Luan, Yujun Wang, Xiaomi Company, China

SPE-11.6: SPEECHSPLIT2.0: UNSUPERVISED SPEECH DISENTANGLEMENT FOR VOICE CONVERSION WITHOUT TUNING AUTOENCODER BOTTLENECKS
Chak Ho Chan, Mark Hasegawa-Johnson, University of Illinois at Urbana-Champaign, United States of America; Kaizhi Qian, Yang Zhang, MIT-IBM Watson AI Lab, United States of America