SPE-84.4
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy, Amazon, Canada
Session:
Speech Synthesis: Vocoder and Evaluation
Track:
Speech and Language Processing
Location:
Gather Area D
Presentation Time:
Fri, 13 May, 21:00 - 21:45 China Time (UTC +8)
Fri, 13 May, 13:00 - 13:45 UTC
Fri, 13 May, 13:00 - 13:45 UTC
Session Chair:
Esther Klabbers, ReadSpeaker
Session SPE-84
SPE-84.1: ITOWAVE: ITO STOCHASTIC DIFFERENTIAL EQUATION IS ALL YOU NEED FOR WAVE GENERATION
Shoule Wu, Yangzhou University, China; Ziqiang Shi, Fujitsu R & D Center, China
SPE-84.2: MULTI-SAMPLE SUBBAND WAVERNN VIA MULTIVARIATE GAUSSIAN
Hiroki Kanagawa, Yusuke Ijima, NTT Corporation, Japan
SPE-84.3: INFERGRAD: IMPROVING DIFFUSION MODELS FOR VOCODER BY CONSIDERING INFERENCE IN TRAINING
Zehua Chen, Danilo Mandic, Imperial College London, United Kingdom of Great Britain and Northern Ireland; Xu Tan, Ke Wang, Shifeng Pan, Lei He, Sheng Zhao, Microsoft, China
SPE-84.4: Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy, Amazon, Canada
SPE-84.5: GENERALIZATION ABILITY OF MOS PREDICTION NETWORKS
Erica Cooper, Junichi Yamagishi, National Institute of Informatics, Japan; Wen-Chin Huang, Tomoki Toda, Nagoya University, Japan
SPE-84.6: ON THE INTERPLAY BETWEEN SPARSITY, NATURALNESS, INTELLIGIBILITY, AND PROSODY IN SPEECH SYNTHESIS
Cheng-I Lai, Yi-Lun Liao, Yung-Sung Chuang, Alexander Liu, James Glass, MIT CSAIL, United States of America; Erica Cooper, Junichi Yamagishi, National Institute of Informatics, Japan; Yang Zhang, Shiyu Chang, Kaizhi Qian, David Cox, MIT-IBM Watson AI Lab, United States of America