Tristan CARSAULT has defended his thesis called:
Introduction of musical knowledge and qualitative analysis in chord extraction and prediction tasks with machine learning
This thesis can be seen with the link there
Abstract:
This thesis investigates the impact of introducing musical properties in machine learning models for the extraction and inference of musical features. Furthermore, it discusses the use of musical knowledge to perform qualitative evaluations of the results. In this work, we focus on musical chords since these mid-level features are frequently used to describe harmonic progressions in Western music. Hence, amongst the variety of tasks encountered in the field of Music Information Retrieval (MIR), the two main tasks that we address are the Automatic Chord Extraction (ACE) and the inference of symbolic chord sequences.
In the case of musical chords, there exists inherent strong hierarchical and functional relationships. Indeed, even if two chords do not belong to the same class, they can share the same harmonic function within a chord progression. Hence, we developed a specifically-tailored analyzer that focuses on the functional relations between chords to distinguish strong and weak errors. Here, we define weak errors as a misclassification that still preserves the relevance in terms of harmonic function.
Finally, along with other musical applications, we present the development of a software that interacts with a musician in real-time by inferring expected chord progression
with the jury:
Thèse thesis made under the direction of:
Gérard ASSAYAG - Directeur de recherche, IRCAM
Philippe ESLING - Maitre de conférences, IRCAM
Jérôme NIKA - Chercheur, IRCAM
Jury :
Nicolas BREDECHE - Professeur, CNRS
Pierre COUPRIE - Professeur, CHCSC
Dorien HERREMANS - Professeur, Singapore University
Florence LEVÉ - Maitre de conférences, Université de Picardie
Brian MCFEE - Professeur, New York University
(invité) Kazuyoshi YOSHII, Professeur, Kyoto University