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-3: Speech Synthesis 1: Architecture

Session Type: Poster
Time: Tuesday, 8 June, 13:00 - 13:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Yu Zhang, Google
 
 SPE-3.1: WAVE-TACOTRON: SPECTROGRAM-FREE END-TO-END TEXT-TO-SPEECH SYNTHESIS
         Ron Weiss; Google
         RJ Skerry-Ryan; Google
         Eric Battenberg; Google
         Soroosh Mariooryad; Google
         Diederik Kingma; Google
 
 SPE-3.2: PATNET : A PHONEME-LEVEL AUTOREGRESSIVE TRANSFORMER NETWORK FOR SPEECH SYNTHESIS
         Shiming Wang; University of Science and Technology of China
         Zhenhua Ling; University of Science and Technology of China
         Ruibo Fu; Institute of Automation, Chinese Academy of Sciences
         Jiangyan Yi; Institute of Automation, Chinese Academy of Sciences
         Jianhua Tao; Institute of Automation, Chinese Academy of Sciences
 
 SPE-3.3: MULTI-RATE ATTENTION ARCHITECTURE FOR FAST STREAMABLE TEXT-TO-SPEECH SPECTRUM MODELING
         Qing He; Facebook Inc
         Zhiping Xiu; Facebook Inc
         Thilo Koehler; Facebook Inc
         Jilong Wu; Facebook Inc
 
 SPE-3.4: END-TO-END TEXT-TO-SPEECH USING LATENT DURATION BASED ON VQ-VAE
         Yusuke Yasuda; National Institute of Informatics
         Xin Wang; National Institute of Informatics
         Junichi Yamagishi; National Institute of Informatics
 
 SPE-3.5: LIGHTSPEECH: LIGHTWEIGHT AND FAST TEXT TO SPEECH WITH NEURAL ARCHITECTURE SEARCH
         Renqian Luo; University of Science and Technology of China
         Xu Tan; Microsoft Research Asia
         Rui Wang; Microsoft Research Asia
         Tao Qin; Microsoft Research Asia
         Jinzhu Li; Microsoft Azure Speech
         Sheng Zhao; Microsoft Azure Speech
         Enhong Chen; University of Science and Technology of China
         Tie-Yan Liu; Microsoft Research Asia
 
 SPE-3.6: A NEW HIGH QUALITY TRAJECTORY TILING BASED HYBRID TTS IN REAL TIME
         Feng-Long Xie; Tencent
         Xin-Hui Li; Tencent
         Wen-Chao Su; Tencent
         Li Lu; Tencent
         Frank K. Soong; Microsoft