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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present a method to develop low-complexity convolutional neural networks(CNNs) for acoustic scene classification (ASC). The large size and highcomputational complexity of typical CNNs is a bottleneck for their deploymenton resource-constrained devices. We propose a passive filter pruning framework,where a few convolutional filters from the CNNs are eliminated to yieldcompressed CNNs. Our hypothesis is that similar filters produce similarresponses and give redundant information allowing such filters to be eliminatedfrom the network. To identify similar filters, a cosine distance based greedyalgorithm is proposed. A fine-tuning process is then performed to regain muchof the performance lost due to filter elimination. To perform efficientfine-tuning, we analyze how the performance varies as the number of fine-tuningtraining examples changes. An experimental evaluation of the proposed frameworkis performed on the publicly available DCASE 2021 Task 1A baseline networktrained for ASC. The proposed method is simple, reduces computations perinference by 27%, with 25% fewer parameters, with less than 1% drop inaccuracy.

A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification