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

This paper presents an alternate representation framework to commonly usedtime-frequency representation for acoustic scene classification (ASC). A rawaudio signal is represented using a pre-trained convolutional neural network(CNN) using its various intermediate layers. The study assumes that therepresentations obtained from the intermediate layers lie in low-dimensionsintrinsically. To obtain low-dimensional embeddings, principal componentanalysis is performed, and the study analyzes that only a few principalcomponents are significant. However, the appropriate number of significantcomponents are not known. To address this, an automatic dictionary learningframework is utilized that approximates the underlying subspace. Further, thelow-dimensional embeddings are aggregated in a late-fusion manner in theensemble framework to incorporate hierarchical information learned at variousintermediate layers. The experimental evaluation is performed on publiclyavailable DCASE 2017 and 2018 ASC datasets on a pre-trained 1-D CNN, SoundNet.Empirically, it is observed that deeper layers show more compression ratio thanothers. At 70% compression ratio across different datasets, the performance issimilar to that obtained without performing any dimensionality reduction. Theproposed framework outperforms the time-frequency representation based methods.

1-D CNN based Acoustic Scene Classification via Reducing Layer-wise Dimensionality