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

When detecting anomalies in audio, it can often be necessary to considerconcept drift: the distribution of the data may drift over time because ofdynamically changing environments, and anomalies may become normal as timeelapses. We propose to use adaptive Huffman coding for anomaly detection inaudio with concept drift. Compared with the existing method of adaptiveGaussian mixture modeling (AGMM), adaptive Huffman coding does not require apriori information about the clusters and can adjust the number of clustersdynamically depending on the amount of variation in the audio. To control thesize of the Huffman tree, we propose to merge clusters that are close to eachother instead of replacing rare clusters with new data. This reduces redundancyin the Huffman tree while ensuring that it never forgets past information. On adataset of audio with concept drift which we have curated ourselves, ourproposed method achieves higher area under the curve (AUC) compared with AGMMand fixed-length Huffman trees. The proposed approach is also time-efficientand can be easily extended to other types of time series data (e.g., video).

Anomaly Detection in Audio with Concept Drift using Adaptive Huffman Coding