Rong presented our paper in EUSIPCO, and recorded his talk – reference, code and links below:

Reference: Jordi Pons, Olga Slizovskaia, Rong Gong, Emilia Gómez & Xavier Serra (2017, September). Timbre Analysis of Music Audio Signals with Convolutional Neural Networks. In 25th European Signal Processing Conference (EUSIPCO2017). Publisher: IEEE.

Slides: https://doi.org/10.5281/zenodo.884444

Code. The code to reproduce each of the experiments is available online:

• Phoneme classification of Jingu singing: github.com/ronggong/EUSIPCO2017
• Musical instrument recognition: github.com/Veleslavia/EUSIPCO2017
• Music auto-tagging: github.com/jordipons/EUSIPCO2017

Datasets. This work was possible because several benchmarks/datasets are available for research purposes:

• Jingju a cappella singing dataset: github.com/MTG/jingjuPhonemeAnnotation
• IRMAS, a dataset for instrument recognition in musical audio signals: mtg.upf.edu/download/datasets/irmas
• MagnaTagATune dataset: mirg.city.ac.uk/codeapps/the-magnatagatune-dataset and github.com/keunwoochoi/magnatagatune-list