Titulo Estágio
MOODetector v2 - Music Mood Analysis for Automatic Playlist Generation and Mood Tracking
Área Tecnológica
Multimédia
Local do Estágio
DEI
Enquadramento
Audio music mood-based classification is a research area of increasing interest in Music Information Retrieval (MIR). It has a wide range of applications in fields such us automatic music classification, automatic playlist generation and similarity analysis.
In fact, recent studies identify music mood/emotion as an important criterion used by people in music retrieval and organization. Moreover, music psychology and education recognize the emotion component of music as the one most strongly associated with music expressivity.
The analysis of audio music in terms of mood/emotion is challenging in its very nature: mood is a subjective notion, techniques are still in an embryonic stage and a uniform evaluation framework is yet to be agreed upon. Nevertheless, the Music Information Retrieval Evaluation eXchange (MIREX, a small “competition” that takes place every year), has in 2007 (and for the first time) a track on audio music mood classification, which will certainly give a strong impulse towards the improvement of techniques and creation of evaluation standards.
Objetivo
The main objective of this thesis is to continue current work in our research group on mood-based automatic playlist generation and mood tracking (i.e., detect mood variations throughout an audio musical clip). This involves the study and derivation of mood-like features and mood-based similarity metrics and ranking.
References:
- Juslin P.N., Karlsson J., Lindström E., Friberg A. and Schoonderwaldt E. (2006) “Play It Again With Feeling: Computer Feedback in Musical Communication of Emotions”, Journal of Experimental Psychology: Applied, Vol. 12, No.2, pp. 79-95.
- Lu, Liu and Zhang (2006), “Automatic Mood Detection and Tracking of Music Audio Signals”, IEEE Transaction on Audio, Speech and Language Processing, Vol. 14, No. 1., pp. 5-18.
Plano de Trabalhos - Semestre 1
1. Study and summarization of the state-of-the art.
2. Requirements analysis.
3. Review of mood-based feature extraction.
4. Review of similarity metrics.
5. Review of mood tracking.
6. Documentation (in each stage) and intermediate report.
Plano de Trabalhos - Semestre 2
1. Implementation of mood-based feature extraction and selection. Proposal of novel features are a plus.
2. Improvements to mood tracking and similarity analysis.
4. System evaluation: accuracy, computational efficiency and subjective tests.
5. Software tests.
6. Documentation (in each stage) and thesis writing.
7. Writing of a scientific article.
Condições
Estágio não remunerado
Orientador
Rui Pedro Paiva
ruipedro@dei.uc.pt 📩