COMP3717: Introduction to Music Processing

• (COMP2261 Artificial Intelligence OR COMP2271 Data Science) AND COMP2221 Programming Paradigms

• None

• None

• To introduce students to the:
• computational modelling of music as applied in the field of music information retrieval;
• basics of representing music as symbolic data;
• basics of digital signal processing required to extract information from recorded music and sound;
• creative potential for computational modelling of music as data.

• Symbolic representations of pitch, rhythm, melodies, and chords
• Modelling harmony and key-finding
• Reasoning about music corpora
• Musical grammars
• Creative generation of symbolic music data
• Principles of digital audio
• Frequency-domain representations of digital audio
• Percussive onset detection, beat tracking, and tempo detection
• Pitch detection and chroma feature extraction
• Structure analysis
• Source separation
• Creative sound synthesis

Subject-specific Knowledge:

• On completion of the module, students will be able to demonstrate:
• an understanding of common computational techniques for representing, manipulating, and analysing music;
• an understanding of the difference between a variety of symbolic and non-symbolic (audio) forms of music representation from a theoretical and practical perspective;
• an awareness of the design and use of mathematical and computational techniques to manipulate and analyse musical data;
• a basic understanding of the relevant musical concepts that inform the design and use of the mathematical and computational techniques covered in the module;
• knowledge of common strategies for the design, implementation, and presentation of creative applications of mathematical and computational techniques to produce new musical art works.

Subject-specific Skills:

• On completion of the module, students will be able to demonstrate an ability to:
• use standard implementations of representing musical data for manipulation and analysis by computer as well as some understanding of their design;
• use and understand standard mathematical and computational techniques to represent, manipulate, and analyse musical data;
• correctly choose and/or combine a variety of symbolic and non-symbolic (audio) forms of music representation for a specific music processing task;
• choose and correctly deploy musical concepts that inform the design and use of the mathematical and computational techniques covered in the module;
• implement common strategies for the design, implementation, and presentation of creative applications of mathematical and computational techniques to produce new musical art works.

Key Skills:

• On completion of the module, students will:
• have implemented computational techniques that derive insight from music-related datasets, which may include audio, audio-visual multimedia, musical scores, other symbolic representations, or any combination of the above;
• be equipped to interpret and implement classic music information retrieval techniques described in the computer science, computer music, and empirical musicology literatures;
• be familiar with the representation and manipulation of symbolic and audio data in widely used Python libraries and understand the implementation and design decisions behind their most used routines.

• Lectures introduce key principles of processing symbolic representations of music and of extracting these from recorded audio, as well their applications in research and commerce.
• Practicals enable students to acquire the necessary coding skills, learn about relevant libraries and packages and receive feedback on their work.
• Workshops deepen the students understanding of the material by exploring creative applications of the principles and techniques covered in lectures and practicals.
• Summative assessments assess theoretical understanding, the knowledge of relevant libraries and application of methods and techniques.

Example formative exercises are given during the course. Feedback will be provided to the students in practical and in the summative coursework (to be applied in examination prep). Exam revision lectures will be arranged in the module's lecture slots in the 3rd term.

If you have a question about Durham's modular degree programmes, please visit our FAQ webpages, Help page or our glossary of terms. If you have a question about modular programmes that is not covered by the FAQ, or a query about the on-line Undergraduate Module Handbook, please contact us.

Prospective Students: If you have a query about a specific module or degree programme, please Ask Us.

Current Students: Please contact your department.