Back Sergio Giraldo defends his PhD thesis on September 16th

Sergio Giraldo defends his PhD thesis on September 16th

15.09.2016

 

16 Sep 2016

Sergio GIraldo defends his PhD thesis entitled "Computational Modelling of Expressive Music Performance in Jazz Guitar: A Machine Learning Approach" on Friday September 16th 2016 at 15:00h in room 55.309 of the Communication Campus of the UPF.

The jury of the defense is: Jose Manuel Iñesta (Alicante University), Hendrik Purwins (Aalborg University), Enric Guaus (UPF)

Thesis abstract:
Computational modelling of expressive music performance deals with the analysis and characterization of performance deviations from the score that a musician may introduce when playing a piece in order to add expression. Most of the work in expressive performance analysis has focused on expressive duration and energy transformations, and has been mainly conducted in the context of classical piano music. However, relatively little work has been dedicated to study expression in popular music where expressive performance involves other kinds of transformations. For instance in jazz mu- sic, ornamentation is an important part of expressive performance but is seldom indicated in the score, i.e. it is up to the interpreter to decide how to ornament a piece based on the melodic, harmonic and rhythmic contexts, as well as on his/her musical background. In this dissertation we investigate the computational modelling of expressive music performance in jazz music, using the guitar as a case study. High-level features are extracted from music scores, and expressive transformations (including timing, energy and ornamentation transformations) are obtained from the corresponding audio recordings. Once each note is characterized by its musical context description and expressive deviations, several machine learning techniques are explored to induce both, black-box and interpretable rule-based predictive models for duration, onset, dynamics and ornamentation transformations. The models are used to both, render expressive performances of new pieces, and attempt to understand expressive performance. We report on the relative importance of the considered music features, quantitatively evaluate the accuracy of the induced models, and discuss some of the learnt expressive performance rules. Furthermore, we present different approaches to semi-automatic data extraction-analysis, as well as some applications in other research fields. The findings, methods, data extracted, and libraries developed for this work are a contribution to expressive music performance field.

Multimedia

Categories:

SDG - Sustainable Development Goals:

Els ODS a la UPF

Contact