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

SPE-15: Speech Synthesis 3: Vocoder

Session Type: Poster
Time: Wednesday, 9 June, 13:00 - 13:45
Location: Gather.Town
 
SPE-15.1: NOISE LEVEL LIMITED SUB-MODELING FOR DIFFUSION PROBABILISTIC VOCODERS
         Takuma Okamoto; National Institute of Information and Communications Technology
         Tomoki Toda; Nagoya University
         Yoshinori Shiga; National Institute of Information and Communications Technology
         Hisashi Kawai; National Institute of Information and Communications Technology
 
SPE-15.2: STYLEMELGAN: AN EFFICIENT HIGH-FIDELITY ADVERSARIAL VOCODER WITH TEMPORAL ADAPTIVE NORMALIZATION
         Ahmed Mustafa; Fraunhofer-Institut für Integrierte Schaltungen IIS
         Nicola Pia; Fraunhofer-Institut für Integrierte Schaltungen IIS
         Guillaume Fuchs; Fraunhofer-Institut für Integrierte Schaltungen IIS
 
SPE-15.3: PARALLEL WAVEFORM SYNTHESIS BASED ON GENERATIVE ADVERSARIAL NETWORKS WITH VOICING-AWARE CONDITIONAL DISCRIMINATORS
         Ryuichi Yamamoto; LINE Corp.
         Eunwoo Song; NAVER Corp.
         Min-Jae Hwang; Search Solutions Inc.
         Jae-Min Kim; NAVER Corp.
 
SPE-15.4: UNIVERSAL NEURAL VOCODING WITH PARALLEL WAVENET
         Yunlong Jiao; Amazon
         Adam Gabrys; Amazon
         Georgi Tinchev; University of Oxford
         Bartosz Putrycz; Amazon
         Daniel Korzekwa; Amazon
         Viacheslav Klimkov; Amazon
 
SPE-15.5: PERIODNET: A NON-AUTOREGRESSIVE WAVEFORM GENERATION MODEL WITH A STRUCTURE SEPARATING PERIODIC AND APERIODIC COMPONENTS
         Yukiya Hono; Nagoya Institute of Technology
         Shinji Takaki; Nagoya Institute of Technology
         Kei Hashimoto; Nagoya Institute of Technology
         Keiichiro Oura; Nagoya Institute of Technology
         Yoshihiko Nankaku; Nagoya Institute of Technology
         Keiichi Tokuda; Nagoya Institute of Technology
 
SPE-15.6: LVCNET: EFFICIENT CONDITION-DEPENDENT MODELING NETWORK FOR WAVEFORM GENERATION
         Zhen Zeng; Ping An Technology (Shenzhen) Co., Ltd.
         Jianzong Wang; Ping An Technology (Shenzhen) Co., Ltd.
         Ning Cheng; Ping An Technology (Shenzhen) Co., Ltd.
         Jing Xiao; Ping An Technology (Shenzhen) Co., Ltd.