Undergraduate Course: Introduction to Audio Machine Learning (MUSI08085)
Course Outline
| School | Edinburgh College of Art |
College | College of Arts, Humanities and Social Sciences |
| Credit level (Normal year taken) | SCQF Level 8 (Year 2 Undergraduate) |
Availability | Available to all students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | Machine Learning is a subfield of Artificial Intelligence which uses algorithms that learn from data. Machine Learning techniques have been essential in many of the recent advances in Artificial Intelligence, which is becoming increasingly relevant in modern life. You will learn about the fundamental ideas and methods underpinning state-of-the-art Machine Learning techniques, focussing on applications to audio and music. You will also gain hands-on experience working with data and using the Python programming language. This includes the full process of a Machine Learning project, from curation/creation of datasets, pre-processing of data, fitting models using the data, and testing/evaluation of models. |
| Course description |
Machine Learning is a subfield of Artificial Intelligence, that uses algorithms trained on datasets to create predictive models. Common music and audio tasks that Machine Learning are applied to include: music genre classification, automatic music transcription, melody/music generation, and musical circuit/instrument emulation.
The course begins with the basics of Machine Learning, including: supervised learning, classification/regression, model evaluation, and feature extraction. You will apply this knowledge practically using the Python programming language, learning how to carry out all the necessary steps to create a working Machine Learning model, including loading datasets, pre-processing of data, training Machine Learning models, and testing/evaluation of models. No prior knowledge of Python or programming is required.
The course content will be delivered during weekly 2-hour class sessions, as well as weekly 1-hour workshop sessions where students will work through practical programming-based exercises exploring that week's class content. Throughout the course, you will work on a Machine Learning project in groups of 3-5 people on a topic of your choosing. This will include selecting a dataset (i.e., audio recording from musical instruments), defining a task (i.e., musical instrument identification from audio), training a Machine Learning model and evaluating its performance. Students will be assessed on one practical coding assignment, as well a project report based on the findings of the group Machine Learning project.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
| Additional Costs | This Course does not require any additional costs to be met by the Student. |
Information for Visiting Students
| Pre-requisites | None |
| High Demand Course? |
Yes |
Course Delivery Information
|
| Academic year 2025/26, Available to all students (SV1)
|
Quota: 0 |
| Course Start |
Semester 1 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 22,
Supervised Practical/Workshop/Studio Hours 11,
Summative Assessment Hours 1,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
162 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
This course has 2 assessment components.
1) Programming Challenge, a set of tasks to be completed using Python code, 50%, weeks 7-9, relating to Learning Outcomes 1 and 2. The submission will consist of Python code with comments.
2) Machine Learning Project Report, Report based on group project, 50%, December exam diet, relating to/assessed against Learning Outcomes 2 and 3.
The Machine Learning Project Report involves documenting the results of a group project in which students use machine learning to complete a technical or creative task. Students will be provided with example projects and datasets to work with. Groups will present their projects during class toward the end of the semester. The submission will consist of an individual report, that includes figures, images, and graphs, as well a description of the main findings and outcomes of the project. This should include an assessment of the strengths and limitations of the project. |
| Feedback |
Formative Feedback
Students will receive verbal formative feedback (from both staff and their peers) throughout the course during the workshops as they work through the tasks provided. Additionally, students will complete a formative programming assignment in the first half of the semester, and feedback based on these submissions will be given to the class. This feedback will feed directly into the Programming Challenge assessment.
After the presentations of the group projects, students will receive feedback on their project and presentation from the instructor as well as from their peers. The students will then have time to consider and incorporate this feedback into their final project report.
Summative Feedback
Students will receive feedback on the Programming Challenge summative assessment, in the form of brief written comments. Additionally, in the class sessions verbal feedback will be provided. Written feedback will also be provided for the project reports. Individual feedback for the summative assignments will be provided via Learn.
Summative feedback will be provided according to university regulations.
|
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Write and explain well-organised and clear Python code.
- Apply machine learning techniques to an audio-domain dataset to achieve a defined objective.
- Evaluate the performance of a machine learning algorithm when applied to a given dataset.
|
Reading List
Deisenroth, Marc Peter, A Aldo Faisal, and Cheng Soon Ong. 2020. Mathematics for Machine Learning. Cambridge University Press.
https://mml-book.github.io/book/mml-book.pdf
Jung, Alexander. 2022. Machine Learning: The Basics. Machine Learning: Foundations, Methodologies, and Applications. Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-16-8193-6.
Müller, Meinard. 2021. Fundamentals of Music Processing: Using Python and Jupyter Notebooks. Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-69808-9.
Muller, Andreas C. and Guido, Sarah. 2016. Introduction to machine learning with Python: a guide for data scientists. O'Reilly Media Inc.
Online Resources
freeCodeCamp.org, dir. 2018. Learn Python - Full Course for Beginners [Tutorial]. https://www.youtube.com/watch?v=rfscVS0vtbw. |
Additional Information
| Graduate Attributes and Skills |
Communication
By articulating the results from the group project, both as a presentation during class, and as an assessed written report, you will learn how to effectively communicate complex ideas and results.
Research and Enquiry
By completing the group project, you will develop the skills required to creatively tackle problems using machine learning methods, whilst maintaining an awareness of the merits and limitations of different approaches.
Enquiry and lifelong learning
In this course, you will learn how to approach problem solving using Machine Learning. This will provide you with a new toolset for thinking about and tackling real-world problems. |
| Keywords | Audio,Machine Learning,AI,Music |
Contacts
| Course organiser | Mr Alec Wright
Tel:
Email: Alec.Wright@ed.ac.uk |
Course secretary | Ms Rowan Paton
Tel:
Email: rpaton5@ed.ac.uk |
|
|
University Homepage