LAB LOGA page on LabLog, a review site (not the lab's official page)
Makino Lab
Machine-translated · View original
A lab on acoustic signal processing that extracts the sound you want to hear from noise.
AboutAbout the lab
Giving computers the same ears as humans.
Makino Lab studies acoustic signal processing.
People take in voices, music, and the sounds of a crowd with two ears and interpret them with the brain.
The lab's question is how to achieve this mechanism on a computer.
Using both signal processing and deep learning, the lab works on extracting a target sound from a mixture of sounds.
Key terms
- Blind source separation
- A technique for separating the original sounds from a recording without knowing what sounds are mixed in it.
- Speech enhancement
- Processing that makes the voice of the person you want to hear easier to understand in a recording mixed with noise.
- Deep learning
- A method in which a computational structure with many stacked layers learns features from many examples.
NewsLab news
A master's student won the NCSP'26 Student Paper Award
Prof. Makino received the Acoustical Society of Japan Distinguished Achievement Award
A doctoral student won the IEEE Fukuoka Section Student Research Encouragement Award
A paper from a collaborative study in which Prof. Makino took part received the IEEE Signal Processing Society Japan Young Author Best Paper Award
ResearchResearch themes
How do humans hear voices, music, and the sounds of a crowd? Aiming to realize on a computer this mechanism of capturing sound with two ears and interpreting it with the brain, the lab studies blind source separation, speech enhancement, recognition and understanding of sound environments, and acoustic signal processing.
*Illustrative imageExtracting the Voice of a Moving Speaker
When a speaker walks around a room, the way the voice reaches the microphones changes, which makes it harder to extract only the voice from other sounds. The lab studies methods for separating the voice from a moving sound source while also removing the reverberation caused by reflections from the walls.
*Illustrative imageCleaning Up Voices with Generative AI
This research restores voices mixed with noise and reverberation to easily audible speech using diffusion models, which are also used for image generation. The lab explores methods such as adjusting the weighting of components inside the model to improve performance without additional training.
MembersFaculty
- ProfessorShoji Makino
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 Makino Lab
Ikenaga LabGraduate School of Information, Production and Systems, Integrated Systems FieldVideo compression systems, video recognition systems, video …
Kakitsuka LabGraduate School of Information, Production and Systems, Integrated Systems FieldSemiconductor lasers, light-emitting devices, optical circui…
Ikehashi LabGraduate School of Information, Production and Systems, Integrated Systems FieldMEMS sensors, MEMS application systems, MEMS-circuit integra…
Kimura LabGraduate School of Information, Production and Systems, Integrated Systems FieldHigh-level design and verification, application-oriented hig…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: “Cymatic” Stefaaane Shan / CC BY-SA 4.0 (cropped)
- Extracting the Voice of a Moving Speaker: “Dodecahedral-microphone-array-DHMA” Kazunobu Kondo, Yusuke Mizuno, Takanori Nishino, Kazuya Takeda / CC BY 4.0 (cropped)
- Cleaning Up Voices with Generative AI: “KSEQI410screenshot” Paulnorthyorks / CC BY-SA 4.0 (cropped)
- Related lab (Ikenaga Lab): “CMOS image sensor chip-scale package oblique” Phiarc / CC BY-SA 4.0 (cropped)
- Related lab (Kakitsuka Lab): “Laser diode chip” NASA
（PD NASA。 作者欄なし） / Public domain (cropped) - Related lab (Ikehashi Lab): “Microstructure1234” Denis Elbl, KIT / CC BY-SA 4.0 (cropped)
- Related lab (Kimura Lab): “1645RT2U-HD” ZeptoBars / CC BY 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.