Tonal complexity features for style classification of classical music. Weiß, C. & Muller, M. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pages 688–692, 2015. doi abstract bibtex We propose a set of novel audio features for classifying the style of classical music. The features rely on statistical measures based on a chroma feature representation of the audio data and describe the tonal complexity of the music, independently from the orchestration or timbre of the music. To analyze this property, we use a dataset containing piano and orchestral music from four general historical periods including Baroque, Classical, Romantic, and Modern. By applying dimensionality reduction techniques, we derive visualizations that demonstrate the discriminative power of the features with regard to the music styles. In classification experiments, we evaluate the features' performance using an SVM classifier. We investigate the influence of artist filtering with respect to the individual composers on the classification performance. In all experiments, we compare the results to the performance of standard features. We show that the introduced features capture meaningful properties of musical style and are robust to timbral variations. © 2015 IEEE.
@InProceedings{ wei.ea2015-tonal,
author = {Wei{\ss}, Christof and Muller, Meinard},
year = {2015},
title = {Tonal complexity features for style classification of
classical music},
abstract = {We propose a set of novel audio features for classifying
the style of classical music. The features rely on
statistical measures based on a chroma feature
representation of the audio data and describe the tonal
complexity of the music, independently from the
orchestration or timbre of the music. To analyze this
property, we use a dataset containing piano and orchestral
music from four general historical periods including
Baroque, Classical, Romantic, and Modern. By applying
dimensionality reduction techniques, we derive
visualizations that demonstrate the discriminative power
of the features with regard to the music styles. In
classification experiments, we evaluate the features'
performance using an SVM classifier. We investigate the
influence of artist filtering with respect to the
individual composers on the classification performance. In
all experiments, we compare the results to the performance
of standard features. We show that the introduced features
capture meaningful properties of musical style and are
robust to timbral variations. {\textcopyright} 2015 IEEE.},
booktitle = {ICASSP, IEEE International Conference on Acoustics,
Speech and Signal Processing - Proceedings},
doi = {10.1109/ICASSP.2015.7178057},
isbn = {9781467369978},
issn = {15206149},
keywords = {Musical Style Classification,Tonal Features,music
analysis with computers},
mendeley-tags= {music analysis with computers},
number = {June 2016},
pages = {688--692}
}
Downloads: 0
{"_id":"YyEqg7mHTWrqRFjjb","bibbaseid":"wei-muller-tonalcomplexityfeaturesforstyleclassificationofclassicalmusic-2015","authorIDs":[],"author_short":["Weiß, C.","Muller, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Weiß"],"firstnames":["Christof"],"suffixes":[]},{"propositions":[],"lastnames":["Muller"],"firstnames":["Meinard"],"suffixes":[]}],"year":"2015","title":"Tonal complexity features for style classification of classical music","abstract":"We propose a set of novel audio features for classifying the style of classical music. The features rely on statistical measures based on a chroma feature representation of the audio data and describe the tonal complexity of the music, independently from the orchestration or timbre of the music. To analyze this property, we use a dataset containing piano and orchestral music from four general historical periods including Baroque, Classical, Romantic, and Modern. By applying dimensionality reduction techniques, we derive visualizations that demonstrate the discriminative power of the features with regard to the music styles. In classification experiments, we evaluate the features' performance using an SVM classifier. We investigate the influence of artist filtering with respect to the individual composers on the classification performance. In all experiments, we compare the results to the performance of standard features. We show that the introduced features capture meaningful properties of musical style and are robust to timbral variations. © 2015 IEEE.","booktitle":"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings","doi":"10.1109/ICASSP.2015.7178057","isbn":"9781467369978","issn":"15206149","keywords":"Musical Style Classification,Tonal Features,music analysis with computers","mendeley-tags":"music analysis with computers","number":"June 2016","pages":"688–692","bibtex":"@InProceedings{ wei.ea2015-tonal,\n author = {Wei{\\ss}, Christof and Muller, Meinard},\n year = {2015},\n title = {Tonal complexity features for style classification of\n classical music},\n abstract = {We propose a set of novel audio features for classifying\n the style of classical music. The features rely on\n statistical measures based on a chroma feature\n representation of the audio data and describe the tonal\n complexity of the music, independently from the\n orchestration or timbre of the music. To analyze this\n property, we use a dataset containing piano and orchestral\n music from four general historical periods including\n Baroque, Classical, Romantic, and Modern. By applying\n dimensionality reduction techniques, we derive\n visualizations that demonstrate the discriminative power\n of the features with regard to the music styles. In\n classification experiments, we evaluate the features'\n performance using an SVM classifier. We investigate the\n influence of artist filtering with respect to the\n individual composers on the classification performance. In\n all experiments, we compare the results to the performance\n of standard features. We show that the introduced features\n capture meaningful properties of musical style and are\n robust to timbral variations. {\\textcopyright} 2015 IEEE.},\n booktitle = {ICASSP, IEEE International Conference on Acoustics,\n Speech and Signal Processing - Proceedings},\n doi = {10.1109/ICASSP.2015.7178057},\n isbn = {9781467369978},\n issn = {15206149},\n keywords = {Musical Style Classification,Tonal Features,music\n analysis with computers},\n mendeley-tags= {music analysis with computers},\n number = {June 2016},\n pages = {688--692}\n}\n\n","author_short":["Weiß, C.","Muller, M."],"key":"wei.ea2015-tonal","id":"wei.ea2015-tonal","bibbaseid":"wei-muller-tonalcomplexityfeaturesforstyleclassificationofclassicalmusic-2015","role":"author","urls":{},"keyword":["Musical Style Classification","Tonal Features","music analysis with computers"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://hmb.sampaio.me/bibliografia.bib.txt","creationDate":"2019-04-22T13:04:36.134Z","downloads":0,"keywords":["musical style classification","tonal features","music analysis with computers"],"search_terms":["tonal","complexity","features","style","classification","classical","music","weiß","muller"],"title":"Tonal complexity features for style classification of classical music","year":2015,"dataSources":["n6MFY2CscQLDpJ7nT","RFLDZw5KyJdadDXDm"]}