Biography
As a researcher at rinna Co., Ltd., I am deeply passionate about advancing the boundaries of human-AI interaction. My primary focus lies in developing innovative systems for speech synthesis and spoken dialogue modeling, aiming to create more natural and fluid conversations with AI. Recently, my interests have expanded to include the fascinating realms of multimodal Large Language Models (LLMs) and the potential of collective intelligence.
Interests
- Speech Synthesis/Recognition
- Multimodal Interaction/LLM
- Deep Learning
Education
-
Master's Degree in Information Science and Technology, 2021
The University of Tokyo
-
Bachelor’s Degree in Engineering, 2019
The University of Tokyo
Skills
Technical
Python (PyTorch, FastAPI, etc.)
Linux (Bash, Slurm, etc.)
JavaScript
Hobbies
Coffee
Music
Workout
Experience
Researcher
I have been working on speech synthesis, spoken dialogue generation, and talking head generation. Additionally, I have been involved in the development of text-to-image and speech recognition models. I also had the opportunity to mentor intern students, providing technical support and helping them integrate into the team.
Research Intern
Microsoft Development
I was engaged in improving speech synthesis quality.
Projects
*
Parallel generation of text and speech using LLM for low-latency spoken dialogue.
Integrating pretrained HuBERT and GPT for automatic speech recognition.
Natural AI-to-AI conversation with spoken content control over written dialogue.
Integrating audiovisual speech synthesis (text to speech and face) and speech-driven facial animation (speech to face) for multimodal interaction.