Titulo Estágio
MOODetector Reloaded
Áreas de especialidade
Sistemas Inteligentes
Engenharia de Software
Local do Estágio
DEI
Enquadramento
The area of Music Emotion Recognition (MER), a sub-area of the Music Information Retrieval (MIR), is attracting increasing interest by the international scientific community, both academic and industrial. In fact, companies such as Spotify, Pandora, Google, Sony, Philips Research, Gracenote, among others, have invested strongly in the area in recent years.
In particular, MER enables a broad set of applications in fields such as automatic music classification, emotion-based playlist generation and similarity analysis, music therapy, as well as application in the gaming, film and advertising industries, among others.
In this context, the MIR group at the Center of Informatics and Systems of the University of Coimbra (CISUC) developed a computational prototype entitled MOODetector, which can be found at http://mir.dei.uc.pt/downloads.html#indextag2. The prototype (standalone monolithic application) is based on audio-based music emotion recognition through the use of emotionally-relevant acoustic descriptors (already developed). The prototype is currently functional, although it shows a number of limitations, namely regarding computational performance and the need to integrate currently created acoustic features/descriptors.
Objetivo
The objectives to be achieved in this project are the following:
1. To update the current system via:
1.1. The integration of audio-based acoustic features (already developed, but still to integrate)
1.2. Code cleaning and optimization, to make it publicly available, possibly including code refactoring and/or migration of components developed in Matlab
2. To develop a web front-end to the current system
3. To extend an already available emotion-based audio dataset, to use in the validation of system’s classification accuracy
4. To evaluate the complete solution, both in terms of software quality requirements (e.g., computational performance) and classification accuracy
5. To write a scientific paper and present it at an international conference
Plano de Trabalhos - Semestre 1
1. Familiarization with the application and code (1 month; Sep/2019)
2. State of the art review (1 month; Oct/2019)
3. Integration of the current emotion-based audio features (2 months; Nov-Dec/2019)
4. Writing of the intermediate report (1 month; Dec 2019)
Plano de Trabalhos - Semestre 2
4. System optimization and refactoring (3 months; Jan-Mar/2020)
5. Development of the web front-end (2 months; Abr-Mai/2020)
6. Dataset acquisition (1 month; Abr /2020)
7. Complete system evaluation (1 month; May/2020)
8. Writing of a scientific paper and thesis (1 month; June/2020)
Condições
Nothing to add.
Orientador
Rui Pedro Paiva, Renato Panda
ruipedro@dei.uc.pt 📩