Thesis Open Access

Genre Classification based on Predominant Melodic Pitch Contours

Rocha, Bruno M

Thesis supervisor(s)

Gómez, Emilia; Salamon, Justin

We present an automatic genre classification system based on melodic features. First a ground truth genre dataset composed of polyphonic music excerpts is compiled. Predominant melodic pitch contours are then estimated, from which a series of descriptors is extracted. These features are related to melody pitch, variation and expressiveness (e.g. vibrato characteristics, pitch distributions, contour shape classes). We compare different standard classification algorithms to automatically classify genre using the extracted features. Finally, the model is evaluated and refined, and a working prototype is implemented. The results show that the set of melody descriptors developed is robust and reliable. They also reveal that complementing low level timbre features with high level melody features is a promising direction for genre classification.

Files (2.2 MB)
Name Size
2.2 MB Download
All versions This version
Views 5151
Downloads 9191
Data volume 204.0 MB204.0 MB
Unique views 4545
Unique downloads 8080


Cite as