Music Signal Analysis - ELE00134M

«Back to module search

Module summary

This module considers the production, perception and acoustic features of different musical sounds and how they can be analysed within a musical framework. You will learn about different approaches to Music Information Retrieval (MIR), how to design and implement your own MIR systems, the real-world applications of MIR, and how MIR is used in different fields of research as a tool to understand music-making and listening from different perspectives . The voice, which is inherently unique as an acoustic system, will be considered in depth within the context of current MIR frameworks and how they might be limited by musical style, instrumental characteristics, instrument combinations, and other environmental factors such as room acoustics.

Related modules

Teaching shared over 2 cohorts: MSc Audio & Music Technology & Y4 MEng Electronic Engineering with Music Technology Systems

Module will run

Occurrence	Teaching period
A	Semester 1 2024-25

Module aims

Subject content aims:

• To illustrate through demonstrations and practical sessions current Music Information Retrieval (MIR) techniques

• To provide an appropriate level of understanding of voice acoustics to approach MIR for the singing voice, including phonetics and phonetic descriptors to enable students to describe and identify vocal sounds.

• To explore current methods of MIR, including using MatLab to implement existing MIR toolboxes, identifying limitations and potential improvements to the systems being implemented

• To consider the role of MIR in the context of the ways in which people engage with music and technology, and its applications across other fields such as psychology, linguistics, and digital media.

Graduate skills aims:

• To develop skills in critically evaluating and synthesising new information based on researched information and writing concise technical reports appropriate for the target audience

• To develop advanced skills in designing, delivering and defending engaging presentations on advanced topics, appropriate for the target audience

Module learning outcomes

Subject content learning outcomes

After successful completion of this module, students will be able to:

• Explain the practical and theoretical applications of MIR
• Appropriately implement MIR toolboxes to extract relevant musical features from audio recordings
• Demonstrate their understanding of MIR techniques by analysing musical excerpts in programmes including Matlab, Praat, SonicVisualiser.
• Identify limitations of MIR toolboxes through testing of existing systems
• Explain the limitations of MIR toolboxes within the context of psychoacoustic theories
• Accurately identify and assess features of the singing voice, including phoneme labelling, based on visual inspection of spectrograms
• Design and test an MIR system
• Evaluate and present MIR in front of their peers

Graduate skills learning outcomes

After successful completion of this module, students will be able to:

• Create concise technical reports exhibiting professional written communication skills.
• Critically evaluate and synthesise new information based on research, appropriate for the target audience
• Design, deliver and defend persuasive technical presentations based on selected reliable evidence to the target audiences
• Analyse and solve problems
• Assess and review their progress
• Investigate a complex issue using independent learning research skills
• Analyse state-of-the-art audio systems
• Demonstrate autonomous task planning and implementation

Module content

The following topics will be covered in detail

• What is Music Information Retrieval?

• The applications of MIR

• MIR feature extraction and analysis

  • MIR through MIDI

  • MIR from an audio waveform

  • Time domain features (onset, offset detection, beat detection, pitch detection)

  • Frequency domain features (timbral features, pitch detection)

  • Multi-instrument analysis

• Existing MIR software

  • MATLAB toolboxes

  • Sonic Visualiser

  • Praat (Voice specific)

• Challenges of MIR for Voice

  • Singing voice acoustics

  • Acoustic phonetics

• Audio capture for successful MIR

Indicative assessment

Task	% of module mark
Essay/coursework	70
Oral presentation/seminar/exam	15
Practical	15

Special assessment rules

None

Additional assessment information

Presentation: A 3-5 minute video demonstrating the MIR tool that the student has created or implemented.

Labs: The students will write up and submit the assessed portion of the short exercises they will work on during the practicals.

MIR Implementation with report: The students will write a report in the style of a journal article on an MIR implementation they have conducted. They may choose to write their own MIR tool or systematically assess the limitations of existing software. They will submit accompanying sound files as appropriate.

Indicative reassessment

Task	% of module mark
Essay/coursework	70
Oral presentation/seminar/exam	15
Practical	15

Module feedback

'Feedback’ at a university level can be understood as any part of the learning process which is designed to guide your progress through your degree programme. We aim to help you reflect on your own learning and help you feel more clear about your progress through clarifying what is expected of you in both formative and summative assessments. A comprehensive guide to feedback and to forms of feedback is available in the Guide to Assessment Standards, Marking and Feedback.

The School of PET aims to provide some form of feedback on all formative and summative assessments that are carried out during the degree programme. In general, feedback on any written work/assignments undertaken will be sufficient so as to indicate the nature of the changes needed in order to improve the work. The School will endeavour to return all exam feedback within the timescale set out in the University's Policy on Assessment Feedback Turnaround Time. The School would normally expect to adhere to the times given, however, it is possible that exceptional circumstances may delay feedback. The School will endeavour to keep such delays to a minimum. Please note that any marks released are subject to ratification by the Board of Examiners and Senate. Meetings at the start/end of each term provide you with an opportunity to discuss and reflect with your supervisor on your overall performance to date.

Formative assessment:

The module is designed with a lot of contact time that involves short interactive practical tasks in workshops and practicals that allow you to get informal verbal feedback from the instructors to support your learning on the module. You will also work with your classmates in group exercises and receive peer feedback this way. You can also email any questions to the module leader, who will reply as soon as possible.

Summative assessments:

For each summative assessment you will receive an individual feedback sheet. The marks and feedback will be broken down as in the mark scheme to show where marks have been awarded. As well as matching descriptions from the mark scheme you will receive additional comments about your work, to support your development on the course and your skills beyond the masters.

Indicative reading

TBC