Pons Puig, JordiSerra, Xavier2019-10-312019-10-312018Pons J, Serra X. Randomly weighted CNNs for (music) audio classification. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2019 May 12-17; Brighton, United Kingdom. New Jersey: Institute of Electrical and Electronics Engineers; 2019. p. 336-40. DOI: 10.1109/ICASSP.2019.8682912978-1-4799-8131-12379-190Xhttp://hdl.handle.net/10230/42575Comunicació presentada a: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing celebrat de 12 al 17 de maig de 2019 a Brighton, Regne Unit.The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature extractors for (music) audio classification tasks. We use features extracted from the embeddings of deep architectures as input to a classifier - with the goal to compare classification accuracies when using different randomly weighted architectures. By following this methodology, we run a comprehensive evaluation of the current architectures for audio classification, and provide evidence that the architectures alone are an important piece for resolving (music) audio problems using deep neural networks.application/pdfeng© Jordi Pons, Xavier Serra. Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: Jordi Pons, Xavier Serra. “Randomly weighted CNNs for (music) audio classificationRandomly weighted CNNs for (music) audio classificationinfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/ICASSP.2019.8682912RandomNeural networksAudioELMSVMinfo:eu-repo/semantics/openAccess