What 1,000 Pieces of Music Can Teach Us
A Data-Driven Look at the DCMLab Corpora
Amelia Brey presents work from an academic research group that is encoding classical music to make it computer-readable for machine learning and data science research. The project is led by the Digital and Cognitive Musicology Lab (DCML) at École Polytechnique Fédérale de Lausanne.
She discusses:
- How researchers annotated over 1,200 musical scores from Bach, Beethoven, Mozart, Chopin, and Bartók
- The process of converting sheet music into machine-readable data using Roman numeral harmony analysis
- How Python parsers can identify chord tones vs. non-chord tones in classical compositions
- Statistical insights about harmonic patterns across different composers and musical periods
- The challenges and subjectivity involved in musical analysis, even among experts
Maker: Amelia Brey
Amelia Brey holds a DMA in composition from Juilliard. She is a composer by training, but wears many other hats, including as data analyst, sales representative, and audio engineer.
Meetup talk
Amelia presented at the July 10, 2025 Demo Night.
Watch on YouTube:
