Students take 60 ECTS credits (one year of full-time dedication) plus up to 50 credits of complementary credits from advanced undergraduate courses (extending the program to two years). Of the 60 ECTS credits of the master, 40 correspond to courses and 20 to the thesis project. 

 Check the class schedule.

Program Structure

  • Core Courses (35 ECTS)
  • Optional Courses (5 ECTS)
  • Thesis Project (20 ECTS)
  • Complementary Courses (extra courses for up to 15 additional ECTS)

Core Courses (5 ECTS each)

  • Digital Signal Processing for Sound and Music (term 1): Covers signal processing methodologies and technologies specific for audio and music applications. Special emphasis is given to the use of spectral processing techniques for the description and transformation of sound and music signals. [syllabus]
  • Machine Learning for Sound and Music (term 1): Introduction to basic machine learning concepts and current deep learning methodologies used in sound and music applications. [syllabus]
  • Music Perception and Cognition (term 1): Goes over the principles, structures, and functions that make it possible for humans to perceive and understand sound and music, presented from empirical and computational points of view. The psychophysics of the transduction, the neural encoding of the acoustic input, the perceptual organization of audio streams, musical memory, melodic, rhythmic and tonal cognition, emotion and music, and the development and learning of musical capabilities. [syllabus]
  • Research Methods (term 1): Covers the major considerations and tasks involved in conducting scientific research, with special emphasis on those aspects related to the context of Information and Communication Technologies. [syllabus]
  • Music Information Retrieval (term 2): Survey of the field of Music Information Retrieval with a special emphasis on the well-established techniques for the automatic description of audio content in terms of different facets (e.g. melody, harmony, rhythm, timbre), temporal scopes, and abstraction levels (from low-level features to semantic descriptions such as genre or mood). [syllabus]
  • Symbolic Music Analysis and Computational Musicology (term 2): Introduction to methodologies for symbolic music processing and applications to musicological research. [syllabus]
  • Generative Algorithms for Sound and Music (term 2): Introduction to generative AI methods of relevance for sound and music creation, both using symbolic and audio representations. [syllabus]

Optional Courses (5 ECTS each)

  • Advanced Computing Techniques for Sound and Music (term 3): State-of-the-art methods and tools for the automatic processing of music content. [syllabus]
  • Practicum (any term): Individual project with a faculty of the master.
  • Sound Communication (term 3): Methods, concepts and practice of artificial intelligence, machine learning, music, sound and sonic therapies with particular emphasis on practical applications.
  • Advanced Interface Design (term 1): Paradigms, methods, and tools used in the construction of complex multimodal interfaces between people and artefacts.
  • Systems Design, Integration and Control (term 2): Paradigms within design, integration, and control of truly feasible complex systems, with special stress on neuromorphic principles underlying biological, interactive, cognitive and emotive systems. 
  • Web Intelligence (term 2): Study how to gather, process, search and mine data in the Web and its applications to search engines. Understand the basic concepts behind information retrieval and data mining. [syllabus]
  • Natural Language Interaction (term 1): The subject covers central themes related to interaction with intelligent agents through natural language. The approach will be built on models of written dialogue, analysis and generation of natural language, and implementations. [syllabus]
  • Cognitive Science and Psychology: Mind, Brain, and Behaviour (term 1): The seven central disciplines that form traditional cognitive science, showing how the concepts and paradigms of these disciplines bring complementary visions of mind, brain and behaviour. 
  • Machine Learning (term 1): The course covers the theory, definition, and implementation of various machine learning methods and algorithms. These are algorithms that generalize from labelled or unlabelled examples. [syllabus]

Thesis Project

  • Research Project (20 ECTS): Carry out a research project and write a thesis report under the supervision of a teacher. Includes a weekly class to present and discuss relevant topics to help decide, develop and present the individual thesis work [more info].

Complementary Courses

  • Courses from the undergraduate programs in engineering of the Engineering School covering topics such as: Audio Signal Processing, Software Engineering, Data Structures, Software Programming, Artificial Intelligence, Music Technology, Mathematics, and Interactive Systems.