Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Investigating CNN-based Instrument Family Recognition for Western Classical Music Recordings

: Taenzer, Michael; Abeßer, Jakob; Mimilakis, Stylianos I.; Weiss, Christof; Müller, Meinard; Lukashevich, Hanna

Fulltext (PDF; )

Flexer, A. ; International Society for Music Information Retrieval -ISMIR-; University of Technology of Delft:
ISMIR 2019, 20th International Society for Music Information Retrieval Conference. Proceedings : Across the bridge, November 4 - 8, 2019 Delft, The Netherlands
Delft, 2019
ISBN: 978-1-7327299-1-9
International Society for Music Information Retrieval (ISMIR Conference) <20, 2019, Delft>
Conference Paper, Electronic Publication
Fraunhofer IDMT ()

Western classical music comprises a rich repertoire composed for different ensembles. Often, these ensembles consist of instruments from one or two of the families woodwinds, brass, piano, vocals, and strings. In this paper, we consider the task of automatically recognizing instrument families from music recordings. As one main contribution, we investigate the influence of data normalization, pre-processing, and augmentation techniques on the generalization capability of the models. We report on experiments using three datasets of monotimbral recordings covering different levels oft imbralcomplexity: isolated notes, isolated melodies, and polyphonic pieces. While data augmentation and the normalization of spectral patches turned outtobebeneficial,pre-processingstrategiessuchaslogarithmiccompressionandchannel-energynormalizationdid not lead to substantial improvements. Furthermore, our cross-dataset experiments indicate the necessity of further optimization routines such as domain adaptation.