Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Ensemble size classification in Colombian Andean string music recordings

: Grollmisch, Sascha; Cano, Estefanía; Mora-Ãngel, Fernando; López Gil, Gustavo A.

Fulltext (PDF; )
Fulltext (PDF; - Gesamtes Dokument)

Aramaki, M.:
14th International Symposium on Computer Music Multidisciplinary Research, CMMR 2019. Proceedings : 14th-18th October 2019, Marseille, France
Marseille: Laboratory PRISM, 2019
ISBN: 979-10-97-498-01-6
International Symposium on Computer Music Multidisciplinary Research (CMMR) <14, 2019, Marseille>
Conference Paper, Electronic Publication
Fraunhofer IDMT ()

Reliable methods for automatic retrieval of semantic information from large digital music archives can play a critical role in musicological research and musical heritage preservation. With the advancement of machine learning techniques, new possibilities for information retrieval in scenarios where ground-truth data is scarce are now available. This work investigates the problem of counting the number of instruments in music recordings as a classification task. For this purpose, a new data set of Colombian Andean string music was compiled and annotated by expert musicologists. Different neural network architectures, as well as pre-processing steps and data augmentation techniques were systematically evaluated and optimized. The best deep neural network architecture achieved 80.7% file-wise accuracy using only feed forward layers with linear magnitude spectrograms as input representation. This model will serve as a baseline for future research on ensemble size classification.