Pilot case

Deep Learning with Audio

Students will learn recent deep learning & artificial intelligence (AI) models and network architectures for audio, work on course exercises and start building AI music/audio applications for their own purposes.
Deep Learning with Audio

Pilot leader

Koray Tahiroglu


School of Arts Design and Architecture


12 students


Feb 2020 – Jun 2020


During the pilot period, we will develop free and open source teaching materials and code for the course, to make contemporary work in deep learning and audio more accessible to students who may not have advanced knowledge of programming or experience with setting up computational environments.

Students will learn the basic architecture of deep learning and artificial intelligence models for audio, work on course exercises and start building AI applications for their own purposes. The exercises and projects will be based on the Pure Data platform, which students are familiar with from previous courses. We will provide code templates that integrate the functionality from open source deep learning audio projects, such as Google’s Magenta, into Pure Data’s visual programming paradigm. We will also provide detailed setup instructions and automated scripts to make installation of the required tools as easy as possible (such as for Pure Data, Python, Conda, Magenta, PyExt).

The realisation of the pilot will improve students’ learning by involving them deeply in the implementation of their artistic and design ideas. Deep Learning with Audio is a project based course, where students will be working on specific projects, receiving instant and personalised feedback on their work. This inquiry-based hands-on experience, incorporating technology and literacy, will help students to learn the foundations of deep learning and procedural audio content generation, it will help them to understand how to build an AI, make a case study to determine how AI functions in music and sound design; utilising computational tools that perceive their own states and the state of the surrounding environment and are able to make decisions related to content generation processes. By the end of the course, students will know powerful ways to use advanced deep learning methods to manipulate and generate audio for sonic interaction as well as creating AI models for interactive music practices.

Platforms and tools

Python: a programming language popular in deep learning applications.
Conda: a tool for managing multiple Python environments, each of which may use a different version and different sets of libraries. This is to simplify dealing with the possibly conflicting requirements between the various deep learning models.
Magenta: Google’s TensorFlow-based library for Music and Art Generation with Machine Intelligence.
Pure Data: a visual programming language for audio processing, originally developed by Miller Puckette.

Pedagogical methods

In similarly structured courses in the Department of Media, because of the technical, project-based, hands-on teaching, we have to limit the number of students accepted to these courses. The implementation of the new Deep Learning with Audio course, with the advanced code template applications, which will already be interfaced with other computational tools that the students are familiar with or learned in previous courses, will make it possible to apply online learning practice to this course teaching methodology, which will change the teaching structure of relevant courses with hands-on teaching methodologies and enable to accept wider range of students to this course.

Involved courses

DOM-E5KT01 – Deep Learning with Audio (3 ECTS)


Koray Tahiroglu
School of Arts, Design and Architecture,  Department of Media / Media Lab
Pilot leader

Miranda Kastemaa
School of Arts, Design and Architecture,  Department of Media / Media Lab
Research assistant

Oskar Koli
School of Arts, Design and Architecture,  Department of Media / Media Lab
Research assistant

Contact us

Got a great idea on how to support learning via online means?
We help make it reality!

Find out more