Effective Features for Finding Chord Interpretation Paths
DOI:
https://doi.org/10.52731/liir.v003.079Keywords:
Distance model, harmony analysis, tonal musicAbstract
We humans naturally feel tonality when we hear music, but its actual mechanism is still unknown.
There have been many approaches to understand this mechanism, but one promising method is to measure the distance between chords, as was proposed in Tonal Pitch Space (TPS).
Although the theory seems theoretically convincing, we could not know which features contribute most and which others are useless in an objective manner.
In this study, we try to define a new distance model by clarifying the effective set of features among them.
Based on the principle of the shortest distance, which is claimed by TPS, we estimate each distance by optimizing features to obtain the most plausible chord interpretation (i.e., a degree/key pair for a chord name).
We propose the set of functions based on these features and we evaluate all simple combinations of them exhaustively.
It turns out that accuracies almost max out with around 20 effective parameters in the functions, achieving about 80--90\% accuracy, that outperforms the original TPS.
References
J. D. Heinichen, General-bass in der composition. Dresden: J. D. Heinichen, 1728.
D. Kellner, Treulicher Unterricht im General-Bass. Hamburg: C. Herold, 1737
G. Weber, Versuch einer geordneten theorie der tonsetzkunst. Mainz: B. Schotts Sohne, ¨
-24.
H. Riemann, Grosse kompositionslehre, Vol. 1. Berlin: W. Spemann, 1902.
L. Euler, Tentamen novae theoriae musicae. St. Petersburg Academy, 1739.
J. Bharucha and C. Krumhansl, “The representation of harmonic structures in music:
Hierarchies of stability as a functions of context”, Cognition, 13(1), pp.63-103, 1983.
D. Deutsch, “The processing of pitch combinations”, in The Psychology of Music,
Chapter 10, Academic Press, New York, 1999.
F. Lerdahl, Tonal pitch space. New York, Oxford University Press, 2001.
S. Sakamoto, S. Arn, M. Matsubara, S. Tojo, “Harmonic analysis based on tonal pitch
space”, in Proc. of the 8th International Conference on Knowledge and Systems Engineering (KSE), pp.230-233, 2016.
H. Yamamoto, S. Tojo, “Generalized tonal pitch space with empirical training”, in
Proc. of the 18th Sound and Music Computing Conference (SMC), pp.300-307, 2021.
F. Lerdahl, R. Jackendoff, A Generative Theory of tonal music. Cambridge, MA,
B. Catteau, J. Martens, M. Leman, “A probabilistic framework for audio-based tonal
key and chord recognition”, in Advancesin Data Analysis, pp.637-644, 2007.
D. Temperley, “What ’s Key for Key? The Krumhansl-Schmuckler Key-Finding Algorithm Reconsidered”, in Music Perception 17, 1, pp.65-100, 1999.
T. Rocher, M. Robine, P. Hanna, L. Oudre, “Concurrent estimation of chords and keys
from audio”, in Proc. of the 11th International Society for Music Information Retrieval
Conference (ISMIR), pp.141-146, 2010.
M. Matsubara, T. Kodama, S. Tojo, “Revisiting cadential retention in GTTM”, in Proc.
of the 8th International Conference on Knowledge and Systems Engineering (KSE),
pp.218-223, 2016.
D. Tymoczko, M. Gotham, M. S. Cuthbert, C. Ariza, “The romantext format: a flexible
and standard method for representing Roman numeral analyses”, in Proc. of the 20th International Society for Music Information Retrieval Conference (ISMIR), pp.123-129,
M. Gotham, R. Kleinertz, C. Weiss, M. Muller, S. Klauk. “What if the ’When’ implies ¨
the ’What’?: human harmonic analysis datasets clarify the relative role of the separate
steps in automatic tonal analysis”, in Proc. of the 22nd International Society for Music
Information Retrieval Conference (ISMIR), pp.229–236, 2021
H. Yamamoto, Y. Uehara, S. Tojo, “Jazz harmony analysis with ε-transition and cadential shortcut”, in Proc. of the 17th Sound and Music Computing Conference (SMC),
pp.316-322, 2020.
