Convolution-based classification of audio and symbolic representations of music
| Autor: | Gissel Velarde, David Meredith, Tillman Weyde, Maarten Grachten, Carlos Eduardo Cancino Chacón |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Visual Arts and Performing Arts
InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g. HCI) Computer science Speech recognition Music analysis 02 engineering and technology audio music classification 050105 experimental psychology Style (sociolinguistics) Convolution 0202 electrical engineering electronic engineering information engineering convolution 0501 psychology and cognitive sciences composer recognition Classification algorithms genre classification 05 social sciences composer classification symbolic music classification filtering Statistical classification machine learning Music theory genre recognition 020201 artificial intelligence & image processing Music |
| Zdroj: | Velarde, G, Cancino Chacón, C, Meredith, D, Weyde, T & Grachten, M 2018, ' Convolution-based classification of audio and symbolic representations of music ', Journal of New Music Research, vol. 47, no. 3, pp. 191-205 . https://doi.org/10.1080/09298215.2018.1458885 Velarde, G, Cancino Chacón, C, Meredith, D, Weyde, T & Grachten, M 2018, ' Convolution-based classification of audio and symbolic representations of music ' Journal of New Music Research, vol. 47, no. 3, pp. 191-205 . DOI: 10.1080/09298215.2018.1458885, 10.1080/09298215.2018.1458885 |
| ISSN: | 0929-8215 |
| DOI: | 10.1080/09298215.2018.1458885 |
| Popis: | We present a novel convolution-based method for classification of audio and symbolic representations of music, which we apply to classification of music by style. Pieces of music are first sampled to pitch–time representations (piano-rolls or spectrograms) and then convolved with a Gaussian filter, before being classified by a support vector machine or by k-nearest neighbours in an ensemble of classifiers. On the well-studied task of discriminating between string quartet movements by Haydn and Mozart, we obtain accuracies that equal the state of the art on two data-sets. However, in multi-class composer identification, methods specialised for classifying symbolic representations of music are more effective. We also performed experiments on symbolic representations, synthetic audio and two different recordings of The Well-Tempered Clavier by J. S. Bach to study the method’s capacity to distinguish preludes from fugues. Our experimental results show that our approach performs similarly on symbolic representations, synthetic audio and audio recordings, setting our method apart from most previous studies that have been designed for use with either audio or symbolic data, but not both. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|