For the purpose of quantitatively characterising polyphonic music styles, we study computational analysis of some traditionally recognised harmonic and melodic features and their statistics. While a direct computational analysis is not easy due to the need for chord and key analysis, a method for statistical analysis is developed based on relations between these features and successions of pitch-class (pc) intervals extracted from polyphonic music data. With these relations, we can explain some patterns seen in the model parameters obtained from classical pieces and reduce a significant number of model parameters (110 to five) without heavy deterioration of accuracies of discriminating composers in and around the common practice period, showing the significance of the features. The method can be applied for polyphonic music style analyses for both typed score data and performed MIDI data, and can possibly improve the state-of-the-art music style classification algorithms.
[1]
Dmitri Tymoczko.
Geometry of Music
,
2016
.
[2]
Bernard Manderick,et al.
String Quartet Classification with Monophonic Models
,
2010,
ISMIR.
[3]
Knud Jeppesen,et al.
The style of Palestrina and the dissonance
,
1946
.
[4]
Honingh,et al.
Clustering and classification of music by interval categories
,
2011
.
[5]
Rens Bod,et al.
Clustering and Classification of Music by Interval Categories
,
2011,
MCM.
[6]
Diane J. Hu.
Probabilistic Topic Models for Automatic Harmonic Analysis of Music
,
2012
.
[7]
Andie Sigler,et al.
Key Induction and Key Mapping Using Pitch-Class Set Assertions
,
2013,
MCM.
[8]
D. Conklin.
Multiple Viewpoint Systems for Music Classification
,
2013
.
[9]
Vlado Keselj,et al.
n-gram-based approach to composer recognition
,
2008
.