Comparing pitch spelling algorithms on a large corpus of tonal music

Authors:
David Meredith
Affiliations:
Centre for Computational Creativity, City University, London, London, United Kingdom
Venue:
CMMR'04 Proceedings of the Second international conference on Computer Music Modeling and Retrieval
Year:
2004

Citing 5
Cited 3

The perception of melodies

Machine models of music
MuseData: multipurpose representation

Beyond MIDI
Approximate statistical tests for comparing supervised classification learning algorithms

Neural Computation
Mental Processes: Studies in Cognitive Science

Mental Processes: Studies in Cognitive Science
The Cognition of Basic Musical Structures

The Cognition of Basic Musical Structures

Real-Time Pitch Spelling Using the Spiral Array

Computer Music Journal
Slicing It All Ways: Mathematical Models for Tonal Induction, Approximation, and Segmentation Using the Spiral Array

INFORMS Journal on Computing
Optimizing Chew and Chen's Pitch-Spelling Algorithm

Computer Music Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper focuses on the problem of constructing a reliable pitch spelling algorithm—that is, an algorithm that computes the correct pitch names (e.g., C$\sharp$4, B$\flat$5 etc.) of the notes in a passage of tonal music, when given only the onset-time, MIDI note number and possibly the duration of each note. The author's ps13 algorithm and the pitch spelling algorithms of Cambouropoulos, Temperley and Longuet-Higgins were run on a corpus of tonal music containing 1.73 million notes. ps13 spelt significantly more of the notes in this corpus correctly than the other algorithms (99.33% correct). However, Temperley's algorithm spelt significantly more intervals between consecutive notes correctly than the other algorithms (99.45% correct). All the algorithms performed less well on classical music than baroque music. However, ps13 performed more consistently across the various composers and styles than the other algorithms.