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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Audio segmentation and sound event detection are crucial topics in machinelistening that aim to detect acoustic classes and their respective boundaries.It is useful for audio-content analysis, speech recognition, audio-indexing,and music information retrieval. In recent years, most research articles adoptsegmentation-by-classification. This technique divides audio into small framesand individually performs classification on these frames. In this paper, wepresent a novel approach called You Only Hear Once (YOHO), which is inspired bythe YOLO algorithm popularly adopted in Computer Vision. We convert thedetection of acoustic boundaries into a regression problem instead offrame-based classification. This is done by having separate output neurons todetect the presence of an audio class and predict its start and end points. Therelative improvement for F-measure of YOHO, compared to the state-of-the-artConvolutional Recurrent Neural Network, ranged from 1% to 6% across multipledatasets for audio segmentation and sound event detection. As the output ofYOHO is more end-to-end and has fewer neurons to predict, the speed ofinference is at least 6 times faster than segmentation-by-classification. Inaddition, as this approach predicts acoustic boundaries directly, thepost-processing and smoothing is about 7 times faster.

You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection