Learning Sonata Form Structure on Mozart’s String Quartets

Abstract

The musical analysis of large-scale structures, such as the classical sonata form, requires to integrate multiple analyses of local musical events into a global coherent analysis. Modelling large-scale structures is still a challenging task for the research community. It includes building large and accurate annotated corpora, as well as developing practical and efficient tools in order to visualize the analyses of these corpora. It finally requires the conception of effective and properly evaluated MIR algorithms. We propose a machine learning approach for the sonata form structure on 32 movements from Mozart's string quartets. We release an open dataset, encoding two reference analyses of these 32 movements, totaling more than 1800 curated annotations, as well as flexible visualizations of these analyses. We discuss the occurrence in this corpus of melodic, harmonic, and rhythmic features induced by pitches, durations, and rests. We investigate whether the presence or the absence of these features can be characteristic of the different sections forming a sonata form. We then compute the emission and transition probabilities of several Hidden Markov Models intended to match the structure of sonata forms at several resolutions. Our results confirm that the sonata form is better identified when the parameters are learned rather than manually set up. These results open perspectives on the computational analysis of musical forms by mixing human knowledge and machine learning from annotated scores.

The Mozart Expositional Punctuation Corpus: A Dataset of Interthematic Cadences in Mozart's Sonata-Allegro Exposition

“…Cadence detection is a highly topical research object of quantitative and computational musicology, and represents a crucial part of a broader effort to model musical form using data-driven methods (see, e.g., Allegraud et al, 2019;Ito, 2014;Sears, Pearce, Caplin & McAdams, 2018). Whereas musical corpus studies may now draw on an ever-growing body of datasets of harmonic analyses, explicit cadential labels are, by and large, rare.…”

I Keep Counting: An Experiment in Human/AI Co-creative Songwriting

“…The team is composed of five MIR researchers working on music modeling (especially music analysis), with a focus on structure, harmony, and texture. Previous work of the team includes form analysis of fugues (Giraud et al, 2015) and sonata forms (Allegraud et al, 2019). Most members of the team have pursued academic studies in classical music and some have experience also in folk, choral, or electronic music.…”

Structural Segmentation of Alap in Dhrupad Vocal Concerts

“…Another widely used feature to characterize the global timbre of audio is the set of Mel Frequency Cepstral Coeffients (MFCCs) that parameterize relative sound levels in critical frequency bands (Logan, 2000;Foote and Cooper, 2003). Recently, Allegraud et al (2019) reviewed the challenges inherent in the segmentation of largescale structure in the classical sonata form and proposed methods exploiting music theory with computed melodic, harmonic and rhythmic features to characterize the evolving structure as a sequence of recurring states. Rhythmic cues have been exploited for segmentation of Chinese popular music by Jensen et al (2005).…”