SLP-P22: Speech Synthesis III |
| Session Type: Poster |
| Time: Friday, May 17, 13:30 - 15:30 |
| Location: Poster Area B, Ground Floor |
| Session Chair: Dong Yu, Tencent AI Lab |
| SLP-P22.1: DNN-BASED SPECTRAL ENHANCEMENT FOR NEURAL WAVEFORM GENERATORS WITH LOW-BIT QUANTIZATION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Yang Ai; University of Science and Technology of China |
| Jing-Xuan Zhang; University of Science and Technology of China |
| Liang Chen; Anhui Science and Technology Research Institute |
| Zhen-Hua Ling; University of Science and Technology of China |
| SLP-P22.2: DNN-BASED SPEAKER-ADAPTIVE POSTFILTERING WITH LIMITED ADAPTATION DATA FOR STATISTICAL SPEECH SYNTHESIS SYSTEMS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Miraç Göksu Öztürk; Boğaziçi University |
| Okan Ulusoy; Boğaziçi University |
| Cenk Demiroglu; Özyeğin University |
| SLP-P22.3: SELF-ATTENTION BASED PROSODIC BOUNDARY PREDICTION FOR CHINESE SPEECH SYNTHESIS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Chunhui Lu; Institute of Acoustics, Chinese Academy of Sciences |
| Pengyuan Zhang; Institute of Acoustics, Chinese Academy of Sciences |
| Yonghong Yan; Institute of Acoustics, Chinese Academy of Sciences |
| SLP-P22.4: AN END-TO-END NETWORK TO SYNTHESIZE INTONATION USING A GENERALIZED COMMAND RESPONSE MODEL |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| François Marelli; Idiap Research Institute |
| Bastian Schnell; Idiap Research Institute |
| Hervé Bourlard; Idiap Research Institute |
| Thierry Dutoit; Université de Mons |
| Philip N. Garner; Idiap Research Institute |
| SLP-P22.5: SPEECH WAVEFORM RECONSTRUCTION USING CONVOLUTIONAL NEURAL NETWORKS WITH NOISE AND PERIODIC INPUTS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Oliver Watts; Edinburgh University |
| Cassia Valentini-Botinhao; Edinburgh University |
| Simon King; Edinburgh University |
| SLP-P22.6: IMPLEMENTING PROSODIC PHRASING IN CHINESE END-TO-END SPEECH SYNTHESIS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Yanfeng Lu; Institute for Infocomm Research |
| Minghui Dong; Institute for Infocomm Research |
| Ying Chen; Nanjing University of Science and Technology |
| SLP-P22.7: QUASI-FULLY CONVOLUTIONAL NEURAL NETWORK WITH VARIATIONAL INFERENCE FOR SPEECH SYNTHESIS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Mu Wang; Tsinghua University |
| Xixin Wu; The Chinese University of Hong Kong |
| Zhiyong Wu; Tsinghua University |
| Shiyin Kang; Tencent |
| Deyi Tuo; Tencent |
| Guangzhi Li; Tencent |
| Dan Su; Tencent |
| Dong Yu; Tencent |
| Helen Meng; The Chinese University of Hong Kong |
| SLP-P22.8: STFT SPECTRAL LOSS FOR TRAINING A NEURAL SPEECH WAVEFORM MODEL |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Shinji Takaki; National Institute of Informatics |
| Toru Nakashika; The University of Electro-Communications |
| Xin Wang; National Institute of Informatics |
| Junichi Yamagishi; National Institute of Informatics |
| SLP-P22.9: GENERATIVE MOMENT MATCHING NETWORK-BASED RANDOM MODULATION POST-FILTER FOR DNN-BASED SINGING VOICE SYNTHESIS AND NEURAL DOUBLE-TRACKING |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Hiroki Tamaru; The University of Tokyo |
| Yuki Saito; The University of Tokyo |
| Shinnosuke Takamichi; The University of Tokyo |
| Tomoki Koriyama; Tokyo Institute of Technology |
| Hiroshi Saruwatari; The University of Tokyo |
| SLP-P22.10: EFFECT OF DATA REDUCTION ON SEQUENCE-TO-SEQUENCE NEURAL TTS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Javier Latorre; Amazon |
| Jakub Lachowicz; Amazon |
| Jaime Lorenzo-Trueba; Amazon |
| Thomas Merritt; Amazon |
| Thomas Drugman; Amazon |
| Srikanth Ronanki; Amazon |
| Viacheslav Klimkov; Amazon |