To access the full text documents, please follow this link: http://hdl.handle.net/10230/27038

Title:	Experimenting with musically motivated convolutional neural networks
Author:	Pons Puig, Jordi; Lidy, Thomas; Serra, Xavier
Abstract:	Paper presented at 14th International Workshop on Content-Based Multimedia Indexing (CBMI 2016)
Abstract:	A common criticism of deep learning relates to the difficulty in understanding the underlying relationships that/nthe neural networks are learning, thus behaving like a black-box. In this article we explore various architectural choices of relevance for music signals classification tasks in order to start understanding what the chosen networks are learning. We first discuss how convolutional filters with different shapes can fit specific musical concepts and based on that we propose several musically motivated architectures. These architectures are then assessed by measuring the accuracy of the deep learning model in the prediction of various music classes using a known dataset of audio recordings of ballroom music. The classes in this dataset have a strong correlation with tempo, what allows assessing if the proposed architectures are learning frequency and/or time dependencies. Additionally, a black-box model is proposed as a baseline for comparison. With these experiments we have been able to understand what some deep learning based algorithms can learn from a particular set of data.
Abstract:	This work is partly supported by the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).
Rights:	© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works./nThe final published article can be found at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7496233
Document type:	Conference Object Article - Accepted version
Published by:	Institute of Electrical and Electronics Engineers (IEEE)
Share:

Show full item record