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-33: Speech Synthesis 5: Prosody & Style

Session Type: Poster
Time: Thursday, 10 June, 13:00 - 13:45
Location: Gather.Town
 
SPE-33.1: SPEECH BERT EMBEDDING FOR IMPROVING PROSODY IN NEURAL TTS
         Liping Chen; Microsoft
         Yan Deng; Microsoft
         Xi Wang; Microsoft
         Frank K. Soong; Microsoft
         Lei He; Microsoft
 
SPE-33.2: BI-LEVEL STYLE AND PROSODY DECOUPLING MODELING FOR PERSONALIZED END-TO-END SPEECH SYNTHESIS
         Ruibo Fu; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
         Jianhua Tao; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
         Zhengqi Wen; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
         Jiangyan Yi; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
         Tao Wang; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
         Chunyu Qiang; National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
 
SPE-33.3: PROSODIC REPRESENTATION LEARNING AND CONTEXTUAL SAMPLING FOR NEURAL TEXT-TO-SPEECH
         Sri Karlapati; Amazon
         Ammar Abbas; Amazon
         Zack Hodari; University of Edinburgh
         Alexis Moinet; Amazon
         Arnaud Joly; Amazon
         Penny Karanasou; Amazon
         Thomas Drugman; Amazon
 
SPE-33.4: CAMP: A TWO-STAGE APPROACH TO MODELLING PROSODY IN CONTEXT
         Zack Hodari; University of Edinburgh
         Alexis Moinet; Amazon
         Sri Karlapati; Amazon
         Jaime Lorenzo-Trueba; Amazon
         Thomas Merritt; Amazon
         Arnaud Joly; Amazon
         Ammar Abbas; Amazon
         Penny Karanasou; Amazon
         Thomas Drugman; Amazon
 
SPE-33.5: UNSUPERVISED LEARNING FOR MULTI-STYLE SPEECH SYNTHESIS WITH LIMITED DATA
         Shuang Liang; Ping An Technology
         Chenfeng Miao; Ping An Technology
         Minchuan Chen; Ping An Technology
         Jun Ma; Ping An Technology
         Shaojun Wang; Ping An Technology
         Jing Xiao; Ping An Technology
 
SPE-33.6: FASTPITCH: PARALLEL TEXT-TO-SPEECH WITH PITCH PREDICTION
         Adrian Łańcucki; NVIDIA Corporation