People
Yuma Shirahata Software Engineer
Graduated with a Master's degree from the Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, in 2021. Joined LINE Corporation as a new graduate in April of the same year. Since October 2023, I have been in my current position. I am mainly engaged in research and development of speech synthesis, working on the development of high-quality emotional speech synthesis models and foundational models for speech generation using large-scale unlabeled speech data.
Publications
-
- CONFERENCE (INTERNATIONAL)
- PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-To-Speech Using Natural Language Descriptions
- Reo Shimizu (Tohoku University), Ryuichi Yamamoto, Masaya Kawamura, Yuma Shirahata, Hironori Doi, Tatsuya Komatsu, Kentaro Tachibana
- 2024 IEEE International Conference on Acoustics, Speech and Signal Processing
- April 14, 2024
-
- CONFERENCE (INTERNATIONAL)
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
- Masaya Kawamura (The University of Tokyo), Yuma Shirahata, Ryuichi Yamamoto, Kentaro Tachibana
- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing
- June 04, 2023
-
- CONFERENCE (INTERNATIONAL)
- Period VITS: Variational Inference With Explicit Pitch Modeling For End-to-End Emotional Speech
- Yuma Shirahata, Ryuichi Yamamoto, Eunwoo Song (NAVER), Ryo Terashima, Jae-Min Kim (NAVER), Kentaro Tachibana
- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing
- June 04, 2023
-
- CONFERENCE (INTERNATIONAL)
- Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation
- Ryo Terashima, Ryuichi Yamamoto, Eunwoo Song (NAVER), Yuma Shirahata, Hyun-Wook Yoon (NAVER), Jae-Min Kim (NAVER), Kentaro Tachibana
- The 23rd Annual Conference of the International Speech Communication Association
- September 18, 2022