Representations of Sound in Deep Learning of Audio Features from Music

Shuvaev, Sergey, Giaffar, Hamza, Koulakov, Alexei A (December 2017) Representations of Sound in Deep Learning of Audio Features from Music. arXiv. (Submitted)

[thumbnail of 1712.02898v1.pdf] PDF
1712.02898v1.pdf - Submitted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (929kB)

Abstract

The work of a single musician, group or composer can vary widely in terms of musical style. Indeed, different stylistic elements, from performance medium and rhythm to harmony and texture, are typically exploited and developed across an artist's lifetime. Yet, there is often a discernable character to the work of, for instance, individual composers at the perceptual level - an experienced listener can often pick up on subtle clues in the music to identify the composer or performer. Here we suggest that a convolutional network may learn these subtle clues or features given an appropriate representation of the music. In this paper, we apply a deep convolutional neural network to a large audio dataset and empirically evaluate its performance on audio classification tasks. Our trained network demonstrates accurate performance on such classification tasks when presented with 5 s examples of music obtained by simple transformations of the raw audio waveform. A particularly interesting example is the spectral representation of music obtained by application of a logarithmically spaced filter bank, mirroring the early stages of auditory signal transduction in mammals. The most successful representation of music to facilitate discrimination was obtained via a random matrix transform (RMT). Networks based on logarithmic filter banks and RMT were able to correctly guess the one composer out of 31 possibilities in 68 and 84 percent of cases respectively.

Item Type: Paper
Subjects: organism description > animal > mammal
organs, tissues, organelles, cell types and functions > tissues types and functions > neural networks
CSHL Authors:
Communities: CSHL labs > Koulakov lab
School of Biological Sciences > Publications
SWORD Depositor: CSHL Elements
Depositing User: CSHL Elements
Date: 7 December 2017
Date Deposited: 13 Oct 2023 14:17
Last Modified: 29 Feb 2024 19:53
Related URLs:
URI: https://repository.cshl.edu/id/eprint/41226

Actions (login required)

Administrator's edit/view item Administrator's edit/view item