Information

2025年11月15日(土)・16日(日)に開かれる名古屋工業大学祭「工大祭2025」の企画として、李研から遠隔会話 CG アバターシステムを展示します。操作体験コーナーもあり、アバター越しの会話を体験いただけます。

詳しくは以下のページをご覧ください。

As part of the NITech Festival 2025 held on November 15 (Sat) and 16 (Sun), 2025, our laboratory (Lee Lab) will exhibit its remote-conversation CG Avatar System. We will also have an interactive hands-on area, where visitors can experience conversations through the avatar interface.

For more details, please see the page below (in Japanese).

https://leelabz.notion.site/2025-CG-CA-2a9d5612f79380189979f71af9438447

We’ve started uploading VRM version of our CG avatars on VRoid Hub.

• Lab’s page on VRoid Hub

“Gene” and “Uka” models are set to public, so you can use them with vroid-enabled tools.

Models are provided with CC-BY 4.0 license, and “Gene” has additional restriction for commercial use. Please consult CG avatars page for details.

We’ve updated part of the HP:

• Top
• Research
• CG avatars

Also added a new CG avatar named “Magi” to tge CG avatars page. It is a new gender-free model.

A New CG-CA “Nirva” has been released, designed by an illustrator Mai Yoneyama.

CG-CA Nirva

The CG-CA page has also been updated to have system information.

We have released MMDAgent-EX, our open-source platform for CG avatar based spoken dialogue system, multimodal dialogue and avatar communication.

Links:

• Press release (by NITech, in Japanese)
• Official site
• GitHub

A third CG dialogue agent “Uka” has been added to the CG AGENTS page.

A new “CG AGENTS” page has been added to the home page.

Assistant Professor Sei Ueno joined Lee lab in April. Together with Assist. Prof. Ueno, we will continue our research on spoken language information processing and spoken dialogue interfaces.

From December 2020, Our lab has been participating in the “Avatar Symbiotic Society” project, a moonshot-type research and development project led by Professor Ishiguro of Osaka University.

“CG-Specific Dialogue” is our research theme. We are focusing on a new conversation system with CG characters that seamlessly integrates an autonomous dialogue system and human remote control (avatars) to realize truly usable, rich-enpowered human-communication system on the next era. We are now working in collaboration with various research institutes.

Julius version 4.6 has been released. You can get it from its GitHub site.

What’s new in Julius-4.6

Julius-4.6 is a minor release with new features and fixes, including GPU integration and grammar handling updates.

GPU-based DNN-HMM computation

(Take a look at v4.6 performance comparison on YouTube!)

Now Julius can compute DNN-HMM with GPU. Total decoding will be four times faster than CPU-based computation on Julius-4.5.

Requires CUDA version 8, 9 or 10.2 and NVIDIA card. You should build Julius with nvcc to enable it. See INSTALL.txt for details.