Modules

Core Module Information
Module title: AI for Audio and Sound Design
SCQF level: 10:
SCQF credit value: 20.00
ECTS credit value: 10
Module code: IMD10113
Module leader: Callum Goddard
School School of Computing, Engineering and the Built Environment
Subject area group: Applied Informatics
Prerequisites

Requisites: Pre-requisite: [Module INF09116] User-Centred Research Methods AND Pre-requisite: [Module IMD09148] Sound Design
Description of module content:

You will learn how to use the latest artificial intelligence technologies for audio and sound design. This module will introduce students to the concepts and the skills and knowledge to understand and use these new tools effectively in their ongoing practice. Students will learn how these technologies are developed using python, as well as how to choose and use deep learning models for audio and sound design related tasks. They will integrate these technologies into creative workflows and learning how to adjust and train for bespoke tasks and evaluate their effectiveness.
Learning Outcomes for module:

Upon completion of this module you will be able to

LO1: Understand the core principles and algorithms underpinning current AI models applied to audio tasks.

LO2: Develop competencies in python, git hub and deep learning python libraries.

LO3: Learn how task specific datasets are created and used to train AI models, including how datasets are split into training, testing and validation sets.

LO4: Explore the ethical issues in developing new AI algorithms, including the legality and ethics of datasets as well as energy consuption

LO5: Evaluate the performance of AI models on their trained task.
Full Details of Teaching and Assessment
2025/6, Trimester 1, In Person,
VIEW FULL DETAILS
Occurrence: 001
Primary mode of delivery: In Person
Location of delivery: MERCHISTON
Partner:
Member of staff responsible for delivering module: Callum Goddard
Module Organiser:


Student Activity (Notional Equivalent Study Hours (NESH))
Mode of activityLearning & Teaching ActivityNESH (Study Hours)NESH Description
Face To Face Lecture 20 In person lectures exploring the the core principles and theories related to current deep learning technologies and how they are used to solve current audio realted problems and tasks. Analytical AI and generative AI tools for audio will be introduced and explained. The role of datasets will be explored and the legalities and ethical conciderations discussed as well as how to design datasets as well as evaluating the performance of AI for audio tasks.
Face To Face Tutorial 20 In person tutorials will introduce the python programming language, jupyter notebooks and github. Students will learn how to run state of the art deep learning models and integrate them into sound design workflows.
Face To Face Guided independent study 160 You will be provided with materials and resources to support ongoing independent study following up on topics explored during the taught periods. This is also opportunity for your own exploratory research on the topics to supplement the provided materials.
Total Study Hours200
Expected Total Study Hours for Module200


Assessment
Type of Assessment Weighting % LOs covered Week due Length in Hours/Words Description
Project - Practical 100 1~2~3~4~5 Week 13 HOURS= 160hours You will explore how to integrate new AI technology seamlessly into a sound design related workflow. You will outline the sound design workflow and discuss how the new AI technology can be integrated into it. You will then implement this workflow and evaluate the performance of your chosen AI technology with respect to its suitability to the workflow you have described.
Component 1 subtotal: 100
Component 2 subtotal: 0
Module subtotal: 100

Indicative References and Reading List - URL:
Contact your module leader
 

Related information