A page on LabLog, a review site (not the lab's official page)
Knowledge Science Lab [Institute of Scientific and Industrial Research]
Machine-translated · View original
A lab studying dialogue systems that can talk with people, using speech recognition and natural language processing.

AboutAbout the lab
Building dialogue systems by exploring what makes conversation work
The Knowledge Science Lab (Komatani Lab) studies spoken dialogue systems that can talk with people, using speech recognition and natural language processing technologies.
It is a field with two sides: the engineering side of writing programs and building systems, and the scientific side of asking what it means for people to understand each other in conversation.
Because the lab deals with the language people use, it also draws on knowledge from linguistics and social psychology.
The lab belongs to the Institute of Scientific and Industrial Research and is positioned as a cooperating research group in the Graduate School of Engineering.
Key terms
- Speech recognition
- Technology that takes a human voice as input and converts it into text
- Spoken dialogue system
- A system that talks with people using speech recognition technology. Smartphone apps and smart speakers are familiar examples
- Multimodal dialogue system
- A system that understands the state of the person it is talking with by using not only the content of their words but also facial expressions, tone of voice, biosignals, and more
NewsLab news
The lab's research received the 2025 Paper Award from the Japanese Society for Artificial Intelligence
A student received a Student Encouragement Award at the 88th National Convention of the Information Processing Society of Japan
The lab developed a dialogue system technology that acquires unknown words while reducing the burden on users
A student received a Student Encouragement Award at the 87th National Convention of the Information Processing Society of Japan
ResearchResearch themes
The lab aims for systems that talk with people by voice to learn knowledge during conversation, pick up on the other person's state, and handle errors. Using speech recognition, natural language processing, machine learning, and other technologies, it builds new spoken dialogue systems and develops the component technologies that solve the problems they face.
Dialogue systems that get smarter the more they talk
The knowledge in dialogue systems is usually either learned from data in advance or built by hand. The lab aims for systems that learn new knowledge during conversation and get smarter as they talk.
*Illustrative imageMultimodal dialogue systems that read between the lines
Understanding dialogue requires facial expressions and tone of voice, in addition to the content of the words. The lab develops technologies that estimate how the other person feels from images, prosodic information, and biosignals such as EEG and skin potential.
Spoken dialogue that is robust to errors and breakdowns
Errors and breakdowns in dialogue arise from a mismatch at one of several layers: channel, signal, intention, or dialogue. The lab aims for spoken dialogue systems that find the cause of the mismatch, deal with it, and stay robust to errors.
*Illustrative imageSystems that become familiar with users through conversation
The lab develops dialogue systems, such as robots, that become familiar with a user through conversation. Using pattern recognition and machine learning, it works on functions that hear speech accurately and understand the meaning of the user's words without discrepancies.
MembersFaculty
Members of the Komatani Lab include faculty, administrative assistants, students in the master's program and undergraduate students, and international students.As of 2026
- ProfessorKazunori Komatani
- Associate ProfessorRyu Takeda
- Assistant ProfessorKenta Yamamoto
- Assistant ProfessorBence Mark Halpern
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Knowledge Science Lab [Institute of Scientific and Industrial Research]
Radiation Hydrodynamics Plasma Lab [Institute of Laser Engineering]Graduate School of Engineering, Department of Electrical, Electronic and Infocommunications Engineering, Cooperative ChairPioneering the electromagnetic engineering of high-density p…
Composite Photonics Lab [Institute of Laser Engineering]Graduate School of Engineering, Department of Electrical, Electronic and Infocommunications Engineering, Cooperative ChairConducts wide-ranging research including laser materials for…
Intelligent Reasoning Lab [Institute of Scientific and Industrial Research]Graduate School of Engineering, Department of Electrical, Electronic and Infocommunications Engineering, Cooperative ChairA data science and AI laboratory, characterized by research …
Quantum System Creation Lab [Institute of Scientific and Industrial Research]Graduate School of Engineering, Department of Electrical, Electronic and Infocommunications Engineering, Cooperative ChairThe Quantum System Creation research group studies quantum i…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Subvocal speech recognition” Dominic Hart, NASA / Public domain (cropped)
- Multimodal dialogue systems that read between the lines: “EEG Recording Cap” Chris Hope / CC BY 2.0 (cropped)
- Systems that become familiar with users through conversation: “A Furhat Robot Head” Guojing92 / CC0 (cropped)
- Related lab (放射流体プラズマ研究領域
[レーザー科学研究所] ): “Plasma-lamp” Luc Viatour / CC BY-SA 3.0 (cropped) - Related lab (複合フォトニクス研究領域
[レーザー科学研究所] ): “Laser LY-RGBW01 internals optical table shining in smoke PC301993” Alexey Vazhnov / CC BY-SA 4.0 (cropped) - Related lab (知能推論研究分野
[産業科学研究所] ): “Bayesian network gene” Lorenahoxhallari / CC BY-SA 4.0 (cropped) - Related lab (量子システム創成研究分野[産業科学研究所]
): “Dilution Fridge in English” OJB Quantum / CC BY 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.