English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The work of a single musician, group or composer can vary widely in terms ofmusical style. Indeed, different stylistic elements, from performance mediumand rhythm to harmony and texture, are typically exploited and developed acrossan artist's lifetime. Yet, there is often a discernable character to the workof, for instance, individual composers at the perceptual level - an experiencedlistener can often pick up on subtle clues in the music to identify thecomposer or performer. Here we suggest that a convolutional network may learnthese subtle clues or features given an appropriate representation of themusic. In this paper, we apply a deep convolutional neural network to a largeaudio dataset and empirically evaluate its performance on audio classificationtasks. Our trained network demonstrates accurate performance on suchclassification tasks when presented with 5 s examples of music obtained bysimple transformations of the raw audio waveform. A particularly interestingexample is the spectral representation of music obtained by application of alogarithmically spaced filter bank, mirroring the early stages of auditorysignal transduction in mammals. The most successful representation of music tofacilitate discrimination was obtained via a random matrix transform (RMT).Networks based on logarithmic filter banks and RMT were able to correctly guessthe one composer out of 31 possibilities in 68 and 84 percent of casesrespectively.

Representations of Sound in Deep Learning of Audio Features from Music