LAB LOGA page on LabLog, a review site (not the lab's official page)
Sound Media Informatics (Saruwatari-Saito Lab)
Machine-translated · View original
The lab processes speech, acoustic, and music signals using statistics and machine learning to advance the study of sound media.
AboutAbout the lab
Handling sound phenomena with mathematics and machine learning
The Saruwatari-Saito Lab studies signal processing and information processing for sound media such as speech, acoustics, and music.
Focusing on the constraints imposed by where sounds are produced and the environments they travel through, as well as on the statistical properties of sound, the lab develops new statistical models and machine learning theory.
Through this work, the lab aims to expand human abilities in processing sound information and to make engineering contributions to the creation of new art.
Key terms
- Statistical model
- A representation of the variability and tendencies of data using probability and statistical equations. It forms the foundation for handling the properties of sound on computers.
- Sound source separation
- A technology for extracting each original sound from a mixture of sounds. When it is done without any prior clues about the sources, it is called blind separation.
- Speech synthesis
- A technology for artificially creating a voice on a computer from input such as text or another voice.
NewsLab news
A paper by doctoral students and others won first place in Track 2 of The VoiceMOS Challenge 2026
A doctoral student received the Awaya Prize Young Researcher Award
A doctoral student received the Student Presentation Award from the Acoustical Society of Japan
A master's student received the Outstanding Presentation Award at Ongaku Symposium 2026
A master's student received the Student Research Encouragement Award from the Applied Acoustics Committee
ResearchResearch themes
The lab aims to understand, process information from, and control sound media such as speech, acoustics, and music. It develops new signal processing methods that take into account how sound waves spread, and studies how to build information processing systems that apply them.
*Illustrative imageUnsupervised sound source separation
In acoustic signal processing, it is often possible to use only a small amount of one-off data in which unknown sound sources and complex sound fields are involved. The lab proposes blind (unsupervised) sound source separation methods that work under such conditions. It also applies them to build human interfaces for robots and systems that support communication.
*Illustrative imageMusic information processing tailored to the user
The lab applies machine learning methods to a variety of music media, analyzing signals based on patterns that frequently appear in time and space, to achieve high-quality music signal processing. Building on this, it creates music information processing mechanisms tailored to the user, aiming to make engineering contributions to the creation of new art.
*Illustrative imageExpanding conversation through speech synthesis and voice conversion
By generating speech artificially, the lab makes it possible to produce speech beyond human ability and to communicate with computers by voice. It aims for "super-communication" that goes beyond the differences between people, and between people and computers.
MembersFaculty
The Saruwatari-Saito Lab consists of faculty members, project researchers, academic specialist staff, visiting researchers, and doctoral and master's students.As of 2026
- ProfessorHiroshi SaruwatariPublications ↗
- LecturerYuki SaitoPublications ↗
- Assistant Professor山岡 洸瑛
- Project Assistant Professor岡本 悠希
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 Sound Media Informatics (Saruwatari-Saito Lab)
Computational Informatics LabFaculty of Engineering, Department of Mathematical Engineering and Information PhysicsFundamental theory of discrete optimization algorithms and t…
Computing Systems Lab (Nakamura-Takase)Faculty of Engineering, Department of Mathematical Engineering and Information PhysicsResearch on acceleration techniques for computer architectur…
Statistical Informatics LabFaculty of Engineering, Department of Mathematical Engineering and Information PhysicsFundamental theory of statistics; statistical modeling and d…
Cryptography and Mathematical Informatics LabFaculty of Engineering, Department of Mathematical Engineering and Information PhysicsCryptography and information security supporting a secure in…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: “Anechoic chamber-3” Togabi / CC BY-SA 4.0 (cropped)
- Unsupervised sound source separation: “ADT Mixing Console” Prof. Pod / CC BY-SA 4.0 (cropped)
- Music information processing tailored to the user: “Kraftwerk Vocoder custom made in early1970s” GoodOmens at English Wikipedia / Public domain (cropped)
- Expanding conversation through speech synthesis and voice conversion: “Human voice spectrogram” Dvortygirl, Mysid / CC BY-SA 3.0 (cropped)
- Related lab (Computational Informatics Lab): “SocialNetworkAnalysis” Martin Grandjean / CC BY-SA 4.0 (cropped)
- Related lab (Computing Systems Lab (Nakamura-Takase)): “Pleiades two row” NASA Ames Research Center / Public domain (cropped)
- Related lab (Statistical Informatics Lab): “Beta distribution for 3 different prior probability functions - J. Rodal” Dr. J. Rodal / CC BY-SA 3.0 (cropped)
- Related lab (Cryptography and Mathematical Informatics Lab): “Enigma-IMG 0487-black” Rama / CC BY-SA 2.0 fr (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.