Exploratory Analysis of a Large Flamenco Corpus using an Ensemble of Convolutional Neural Networks as a Structural Annotation Backend

TL;DR

This paper introduces a neural network-based computational backend for analyzing large flamenco music corpora, enabling structural annotation, visualization, and musicological insights, demonstrating the feasibility of large-scale, automated flamenco music analysis.

Contribution

It presents a novel ensemble of CNNs for structural annotation of flamenco recordings, enhancing metadata and facilitating musicological research.

Findings

Automated annotations are musicologically valid and useful.

Large-scale analysis of flamenco music is feasible with CNN technology.

Identified differences in structure and instrumentation across styles.

Abstract

We present computational tools that we developed for the analysis of a large corpus of flamenco music recordings, along with the related exploratory findings. The proposed computational backend is based on a set of Convolutional Neural Networks that provide the structural annotation of each music recording with respect to the presence of vocals, guitar and hand-clapping ("palmas"). The resulting, automatically extracted annotations, allowed for the visualization of music recordings in structurally meaningful ways, the extraction of global statistics related to the instrumentation of flamenco music, the detection of a cappella and instrumental recordings for which no such information existed, the investigation of differences in structure and instrumentation across styles and the study of tonality across instrumentation and styles. The reported findings show that it is feasible to perform a large scale analysis of flamenco music with state-of-the-art classification technology and produce automatically extracted descriptors that are both musicologically valid and useful, in the sense that they can enhance conventional metadata schemes and assist bridging the semantic gap between audio recordings and high-level musicological concepts.