Automatic melodic and structural analysis of music material for enriched concert related experiences

Abstract

This PhD thesis proposal deals with the automatic analysis of musical audio, focusing on the estimation of the predominant melodic lines, which are used as a basis for extracting musical themes, and (along with other features) for structure recognition. The main focus is set on classical western music in large ensemble settings, which poses interesting research challenges to current state-of-the art algorithms. We will study the limitations of current approaches in this genre, and elaborate specific descriptors and methods, combining audio based analysis with further sources of knowledge and modalities. The creation of appropriate datasets will also be a main aspect, in order to properly evaluate the developed approaches. This work will be used to enrich musical concert related experiences, from music consumers to editors.

Wagner Ring Dataset: A Complex Opera Scenario for Music Processing and Computational Musicology

“…Among those, Western classical music has been one of the earliest focus areas (Hewlett and Selfridge-Field, 1991), which-from a technical perspective-provides interesting opportunities because of its multi-modal resources: there is a specific correspondence between what is written down in sheet music (either represented as graphical or symbolic data) and what is recorded (audio data)-typically comprising a multitude of professional performances. This not only allows for studying performance aspects (Lerch et al, 2020) but also for developing and testing algorithmic approaches to various tasks including automatic music transcription (Benetos et al, 2019), optical music recognition (Calvo-Zaragoza et al, 2020), music synchronization (Müller et al, 2021), retrieval (Müller et al, 2019), and analysis (Nieto et al, 2020;Bosch, 2013;Meredith, 2016).…”