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-34: Speech Synthesis 6: Data Augmentation & Adaptation

Session Type: Poster
Time: Thursday, 10 June, 13:00 - 13:45
Location: Gather.Town
Session Chair: Hung-yi Lee, National Taiwan University
 
SPE-34.1: LOW-RESOURCE EXPRESSIVE TEXT-TO-SPEECH USING DATA AUGMENTATION
         Goeric Huybrechts; Amazon
         Thomas Merritt; Amazon
         Giulia Comini; Amazon
         Bartek Perz; Amazon
         Raahil Shah; Amazon
         Jaime Lorenzo-Trueba; Amazon
 
SPE-34.2: TTS-BY-TTS: TTS-DRIVEN DATA AUGMENTATION FOR FAST AND HIGH-QUALITY SPEECH SYNTHESIS
         Min-Jae Hwang; Search Solutions Inc.
         Ryuichi Yamamoto; LINE Corporation
         Eunwoo Song; Naver corporation
         Jae-Min Kim; Naver corporation
 
SPE-34.3: A NEURAL TEXT-TO-SPEECH MODEL UTILIZING BROADCAST DATA MIXED WITH BACKGROUND MUSIC
         Hanbin Bae; NCSOFT
         Jae-Sung Bae; NCSOFT
         Young-Sun Joo; NCSOFT
         Young-Ik Kim; NCSOFT
         Hoon-Young Cho; NCSOFT
 
SPE-34.4: DISENTANGLED SPEAKER AND LANGUAGE REPRESENTATIONS USING MUTUAL INFORMATION MINIMIZATION AND DOMAIN ADAPTATION FOR CROSS-LINGUAL TTS
         Detai Xin; University of Tokyo
         Tatsuya Komatsu; LINE Corporation
         Shinnosuke Takamichi; University of Tokyo
         Hiroshi Saruwatari; University of Tokyo
 
SPE-34.5: ADASPEECH 2: ADAPTIVE TEXT TO SPEECH WITH UNTRANSCRIBED DATA
         Yuzi Yan; Tsinghua University
         Xu Tan; Microsoft Research Asia
         Bohan Li; Microsoft Azure Speech
         Tao Qin; Microsoft Research Asia
         Sheng Zhao; Microsoft Azure Speech
         Yuan Shen; Tsinghua University
         Tie-Yan Liu; Microsoft Research Asia
 
SPE-34.6: INVESTIGATION OF FAST AND EFFICIENT METHODS FOR MULTI-SPEAKER MODELING AND SPEAKER ADAPTATION
         Yibin Zheng; Tencent Inc
         Xinhui Li; Tencent Inc
         Li Lu; Tencent Inc