Probabilistic Generative Models Applied to Musical Audio Data

情報理工学英語特別講義Ⅳ（Probabilistic Generative Models Applied to Musical Audio Data）

education program·university course·active·also: 情報理工学英語特別講義Ⅳ（Probabilistic Generative Models Applied to Musical Audio Data）, Jōhō Rikōgaku Eigo Tokubetsu Kōgi IV

English-language graduate course covering probabilistic and deep generative models for musical audio, from latent models to diffusion.

Verified facts

Official site	https://catalog.he.u-tokyo.ac.jp/detail?code=4893-1004&year=2026 ↗
Geography	Japan / Tokyo
price	included in university tuition
title	情報理工学英語特別講義Ⅳ（Probabilistic Generative Models Applied to Musical Audio Data）
format	in person lecture and project report
topics	musical information; machine learning; Bayesian inference; VAEs; GANs; diffusion models
duration	13 classes; 2 credits; S1–S2
end date	unknown
language	English
location	The University of Tokyo
provider	The University of Tokyo Graduate School of Information Science and Technology
recurrence	2026 offering; recurrence not established
start date	unknown
instructors	Philippe Esling (Qosmo)
program type	graduate special lecture
prerequisites	Notebook computer required; Graduate enrollment; other-faculty enrollment not permitted
program state	active
target audience	University of Tokyo information-science graduate students
learning outcomes	Understand major probabilistic and deep generative model families; Apply them in a musical-audio project
application deadline	institutional registration; exact date not public
credential or outcome	2 academic credits; application project and report
scholarship and funding	not publicly disclosed