LAB LOGA page on LabLog, a review site (not the lab's official page)
Minematsu-Saito Lab
Machine-translated · View original
The lab supports human voice communication with computers that speak, listen, and teach.
AboutAbout the lab
Focusing on speech, the foundation of human communication
The Minematsu-Saito Lab studies spoken language, which lies at the foundation of human communication.
The lab considers both humans and computers as the producer and the receiver of speech, and takes every combination of the two as its research subject.
Its work ranges from basic research on speech analysis, synthesis, recognition, and perception to applied research such as spoken dialogue systems and computer-assisted language learning.
To close the gap with the flexibility of human communication, the lab explores new ways of modeling speech.
Key terms
- Speech recognition
- Technology in which a computer listens to human speech and converts it into text
- Voice conversion
- Technology that changes only the characteristics of a voice into those of another person's voice or speaking style, while keeping the spoken content the same
- Shadowing
- A practice method in which the learner repeats aloud the foreign-language speech they hear, following slightly behind it like a shadow
ResearchResearch themes
The lab conducts research to realize more flexible spoken communication, both between humans and between humans and computers. Centered on technologies such as speech recognition and speech synthesis, it works on supporting foreign language pronunciation learning and on linking multiple media, such as speech and video.
*Illustrative imageSpeech recognition robust to differences in speakers and environments
The lab develops speech recognition technology that is not affected by differences between speakers or in the surrounding environment, approaching the problem from a variety of perspectives and methods, and explores its applications.
*Illustrative imageForeign language pronunciation assessment and its use in education
The lab builds pronunciation assessment systems for foreign language learners that are not affected by the speaker's age, gender, or body size. It also focuses on shadowing, a practice method in which learners listen and repeat aloud.
*Illustrative imageFlexible speech synthesis and voice conversion
The lab develops speech synthesis technology, centered on voice conversion. This involves extracting information such as speaker identity and spoken content, then reassembling it to change the speaker or speaking style while preserving what is said.
*Illustrative imageAssociating speech with video and other media
This research handles multiple media, such as speech, video, and behavioral data, at the same time and links them together. In recent years, the lab has also been analyzing the relationship between a robot's appearance and its voice.
MembersFaculty
The Minematsu-Saito Lab consists of faculty, technical specialists, administrative assistants, postdoctoral researchers, doctoral, master's, and undergraduate students, research students, and exchange students.As of 2026
- ProfessorNobuaki MinematsuPublications ↗
- Associate ProfessorDaisuke SaitoPublications ↗
VoicesStudent voices
Compiled from answers by students who were in the lab. Ratings and reviews reflect individual students' experiences, not the lab's official views.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Who is this lab for?
What's great about this lab?
What did you learn after joining?
What's the vibe, and what is the professor like?
Where do graduates go?
RelatedLabs similar to Minematsu-Saito Lab
Yamasaki LabFaculty of Engineering, Department of Information and Communication EngineeringA broad range of fields including artificial intelligence, m…
IIS LabFaculty of Engineering, Department of Information and Communication EngineeringSupporting people's intellectual activities and healthy livi…
Irie-Kadomoto LabFaculty of Engineering, Department of Information and Communication EngineeringResearch centered on processor architecture, encompassing la…
Matsuura LabFaculty of Engineering, Department of Information and Communication EngineeringInformation security research, from cryptography to networks…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: “Long-window reassigned spectrogram of speech” Kelly Fitz / CC BY-SA 3.0 (cropped)
- Speech recognition robust to differences in speakers and environments: “Studio microphone with pop-shield crop” Galak76 / CC BY-SA 3.0 (cropped)
- Foreign language pronunciation assessment and its use in education: “Headphones with Microphone” Zephyris at English Wikipedia / CC BY-SA 3.0 (cropped)
- Flexible speech synthesis and voice conversion: “Waveform Closeup Image” Bob3Studios / CC BY-SA 4.0 (cropped)
- Associating speech with video and other media: “Open-Source 3D printed Poppy humanoid robot (head)” Inria / Poppy-project.org / Photo H. Raguet. / CC BY-SA 4.0 (cropped)
- Related lab (Yamasaki Lab): “Artificial Neural Network with Chip” mikemacmarketing / photo on flickr / CC BY 2.0 (cropped)
- Related lab (IIS Lab): “Piqsels.com-id-zbxec” piqsels / CC0 (cropped)
- Related lab (Irie-Kadomoto Lab): “12-inch silicon wafer” Peellden / CC BY-SA 3.0 (cropped)
- Related lab (Matsuura Lab): “BalticServers data center” BalticServers.com / CC BY-SA 3.0 (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.