Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Music Information Retrieval on Representative Mexican Folk Vocal Melodies Through MIDI Feature Extraction

Mario Alberto Vallejo Reyes

TL;DR

This work applies MIDI feature extraction to Mexican folk vocal melodies to quantify ambitus, pitch-class entropy, and interval distribution, using a MATLAB/MIDI Toolbox workflow. It investigates whether these musical features correlate with popularity as measured by Spotify plays, finding a moderate, non-significant negative link for ambitus and no significant link for entropy. Entropy highlights melodic complexity differences (e.g., Somos Novios vs La Bamba), while interval distributions reveal a preference for compact intervals (P1, M2, m2) that may enhance accessibility. The study demonstrates a reproducible, key-independent, data-driven framework for computational musicology in folk repertoires and calls for broader datasets and integration of cultural factors to better understand digital-age music consumption.

Abstract

This study analyzes representative Mexican folk vocal melodies using MIDI feature extraction, examining ambitus, pitch-class entropy, and interval distribution. It also explores the relationship between these features and song popularity, as measured by Spotify plays. The study employs MATLAB and the MIDI Toolbox for extracting musical features and performing statistical analysis. The findings reveal a significant variation in ambitus, with values ranging from 8 to 27 semitones, indicating a diverse compositional style and vocal demand across the genre. The analysis of pitch-class entropy showcases a broad spectrum of melodic complexity, with Armando Manzanero's `Somos Novios' displaying the highest entropy, suggesting varied and complex melodic structures, while traditional pieces like `La Bamba' exhibit lower entropy, indicating simpler, more repetitive patterns. The interval distribution predominantly features prime intervals (P1), major and minor seconds (M2, m2), pointing to a compositional preference for close, contiguous intervals that contribute to the melodies' accessibility and appeal. Statistical analysis do not establish a significant correlation between the ambitus or entropy and the number of Spotify plays.

Music Information Retrieval on Representative Mexican Folk Vocal Melodies Through MIDI Feature Extraction

TL;DR

This work applies MIDI feature extraction to Mexican folk vocal melodies to quantify ambitus, pitch-class entropy, and interval distribution, using a MATLAB/MIDI Toolbox workflow. It investigates whether these musical features correlate with popularity as measured by Spotify plays, finding a moderate, non-significant negative link for ambitus and no significant link for entropy. Entropy highlights melodic complexity differences (e.g., Somos Novios vs La Bamba), while interval distributions reveal a preference for compact intervals (P1, M2, m2) that may enhance accessibility. The study demonstrates a reproducible, key-independent, data-driven framework for computational musicology in folk repertoires and calls for broader datasets and integration of cultural factors to better understand digital-age music consumption.

Abstract

This study analyzes representative Mexican folk vocal melodies using MIDI feature extraction, examining ambitus, pitch-class entropy, and interval distribution. It also explores the relationship between these features and song popularity, as measured by Spotify plays. The study employs MATLAB and the MIDI Toolbox for extracting musical features and performing statistical analysis. The findings reveal a significant variation in ambitus, with values ranging from 8 to 27 semitones, indicating a diverse compositional style and vocal demand across the genre. The analysis of pitch-class entropy showcases a broad spectrum of melodic complexity, with Armando Manzanero's `Somos Novios' displaying the highest entropy, suggesting varied and complex melodic structures, while traditional pieces like `La Bamba' exhibit lower entropy, indicating simpler, more repetitive patterns. The interval distribution predominantly features prime intervals (P1), major and minor seconds (M2, m2), pointing to a compositional preference for close, contiguous intervals that contribute to the melodies' accessibility and appeal. Statistical analysis do not establish a significant correlation between the ambitus or entropy and the number of Spotify plays.

Paper Structure

This paper contains 22 sections, 6 figures, 2 tables.

Table of Contents

  1. Introduction and Background
  2. Research Objectives and Significance
  3. Review of Recent Methods
  4. Succinct Introduction to the Chosen Approach
  5. Methodology and Implementation
  6. MIR Pipeline Design
  7. Feature Extraction and Normalisation
  8. Selection of Features
  9. Ambitus
  10. Pitch-class Entropy
  11. Interval Distribution
  12. Statistical Analysis Methods
  13. Experimentation and Results
  14. Dataset Creation
  15. Dataset Pre-processing
  16. ...and 7 more sections

Figures (6)

  • Figure 1: Schematic Overview of the Music Information Retrieval Process
  • Figure 2: Average Ambitus of Selected Mexican Vocal Melodies
  • Figure 3: Correlation Between Spotify Plays and Ambitus
  • Figure 4: Average Pitch Class Entropy of Representative Mexican Vocal Melodies
  • Figure 5: Correlation Between Spotify Plays and Pitch-Class Entropy
  • ...and 1 more figures