SLP-L8: Speech Synthesis I |
Session Type: Lecture |
Time: Thursday, May 16, 15:30 - 17:30 |
Location: Auditorium 1 |
Session Chairs: Junichi Yamagishi, University of Edinburgh and Lei Xie, Northwestern Polytechnical University
|
|
SLP-L8.1: LPCNET: IMPROVING NEURAL SPEECH SYNTHESIS THROUGH LINEAR PREDICTION |
Jean-Marc Valin; Mozilla |
Jan Skoglund; Google, Inc. |
|
SLP-L8.2: PHONEMIC-LEVEL DURATION CONTROL USING ATTENTION ALIGNMENT FOR NATURAL SPEECH SYNTHESIS |
Jungbae Park; Humelo Inc. / Korea Advanced Institute of Science and Technology (KAIST) |
Kijong Han; Korea Advanced Institute of Science and Technology |
Yuneui Jeong; Humelo Inc. |
Sang Wan Lee; Humelo Inc. / Korea Advanced Institute of Science and Technology (KAIST) / KI Institute for Artificial Intelligence |
|
SLP-L8.3: DISENTANGLING CORRELATED SPEAKER AND NOISE FOR SPEECH SYNTHESIS VIA DATA AUGMENTATION AND ADVERSARIAL FACTORIZATION |
Wei-Ning Hsu; Massachusetts Institute of Technology |
Yu Zhang; Google, Inc. |
Ron J. Weiss; Google, Inc. |
Yu-An Chung; Massachusetts Institute of Technology |
Yuxuan Wang; Google, Inc. |
Yonghui Wu; Google, Inc. |
James Glass; Massachusetts Institute of Technology |
|
SLP-L8.4: REPRESENTATION MIXING FOR TTS SYNTHESIS |
Kyle Kastner; University of Montreal |
Joao Santos; University of Montreal |
Yoshua Bengio; University of Montreal |
Aaron Courville; University of Montreal |
|
SLP-L8.5: ROBUST AND FINE-GRAINED PROSODY CONTROL OF END-TO-END SPEECH SYNTHESIS |
Younggun Lee; Neosapience, Inc. |
Taesu Kim; Neosapience, Inc. |
|
SLP-L8.6: NEURAL SOURCE-FILTER-BASED WAVEFORM MODEL FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS |
Xin Wang; National Institute of Informatics |
Shinji Takaki; National Institute of Informatics |
Junichi Yamagishi; National Institute of Informatics |
|