LAB LOGA page on LabLog, a review site (not the lab's official page)
Nakashika Lab
Machine-translated · View original
A lab that applies machine learning to speech, music, acoustics, and EEG signals.
AboutAbout the lab
Modeling the structure of sound to learn from small amounts of data
The Nakashika Lab conducts research using machine learning and AI (deep learning) on speech, music, acoustics, and EEG (brain waves).
It works on speech synthesis, voice conversion, automatic music composition, automatic music transcription, sound source separation, and synthesizing speech from EEG.
By making use of prior knowledge such as the data structures specific to speech and acoustics and music theory, the lab aims to develop AI that performs well even with small amounts of data.
Research themes are, in principle, set freely by each student individually.
Key terms
- Voice conversion
- Technology that changes one person's voice into another's, or changes only the emotion or impression of a voice
- Automatic music transcription
- Technology that automatically generates sheet music from audio
- Sound source separation
- Technology that separates audio in which multiple types of sounds are mixed into sounds of each type
- Deep learning
- A type of machine learning method that uses artificial neural networks stacked in many layers
ResearchResearch themes
This lab studies machine learning and AI methods for data such as speech, music, acoustics, and EEG (brain waves). Using prior knowledge such as the data structures specific to speech and acoustics and music theory, it aims for models that perform well even with small amounts of data.
*Illustrative imageSpeech Synthesis and Voice Conversion
The lab studies speech synthesis, which artificially generates speech from text, and voice conversion, which turns one person's voice into another's. By modeling the data structures specific to speech, it works on technology that can generate high-quality speech even from small amounts of data.
*Illustrative imageAutomatic Music Composition and Automatic Music Transcription
The lab works on automatic music composition, which automatically generates music that meets given conditions, and automatic music transcription, which automatically generates sheet music from audio. It also covers melody analysis and chord estimation, and uses prior knowledge such as music theory to aim for AI that performs well even with small amounts of data.
*Illustrative imageSound Source Separation
The lab studies sound source separation, which splits audio in which multiple types of sounds are mixed into sounds of each type. As in its speech research, it models the data structures specific to acoustics and works on technology that separates sound sources more efficiently.
*Illustrative imageSynthesizing Speech from EEG
The lab studies direct speech synthesis from EEG (electroencephalography), which can be measured noninvasively. By synthesizing speech that also conveys non-linguistic information such as the speaker's individuality and emotion, it aims to establish next-generation communication technology.
MembersFaculty
The lab's members consist of faculty, collaborators, doctoral, master's, and undergraduate students, and a secretary.As of 2026
- Associate ProfessorToru Nakashika
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 Nakashika Lab
Takagi LabSchool of Informatics and Engineering, Class I (Informatics)Spoken language information processing / pattern recognition…
Ueno LabSchool of Informatics and Engineering, Class I (Informatics)Artificial intelligence / Machine learning / Data science
Minami LabSchool of Informatics and Engineering, Class I (Informatics)Artificial intelligence / Spoken dialogue processing / Speec…
Kaneiwa LabSchool of Informatics and Engineering, Class I (Informatics)Artificial intelligence / Machine learning / Semantic WebThe 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: “Siemens Studio for Electronic Music - Console, Signal generator, Tape recorders - Deutsches Museum, 2010” pixabay: Stefan Schweihofer / CC0 (cropped)
- Speech Synthesis and Voice Conversion: “Vocal recording setup & IYE - Studio B, In Your Ear Studios” Will Fisher from Richmond, VA, United States / CC BY-SA 2.0 (cropped)
- Automatic Music Composition and Automatic Music Transcription: “Chopin polonaise Op. 53” Frédéric Chopin / Public domain (cropped)
- Sound Source Separation: “ADT Mixing Console” Prof. Pod / CC BY-SA 4.0 (cropped)
- Synthesizing Speech from EEG: “EEG Recording Cap” Chris Hope / CC BY 2.0 (cropped)
- Related lab (高木 一幸 研究室): “Utaco recording with Blue Snowball Microphone 20111101” Danny Choo / CC BY-SA 2.0 (cropped)
- Related lab (植野 真臣 研究室): “Bayesian network” Sachs K, Gifford D, Jaakkola T, Sorger P, Lauffenburger DA. / CC BY-SA 4.0 (cropped)
- Related lab (南 泰浩 研究室): “Toddler with book - Picture Primer (circa 1910)” 作者不詳 / Public domain (cropped)
- Related lab (兼岩 憲 研究室): “Bookshelves in Faculty of Arts Library, Chulalongkorn University” Geonuch / CC BY-SA 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.