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

Segmenting audio into homogeneous sections such as music and speech helps usunderstand the content of audio. It is useful as a pre-processing step toindex, store, and modify audio recordings, radio broadcasts and TV programmes.Deep learning models for segmentation are generally trained on copyrightedmaterial, which cannot be shared. Annotating these datasets is time-consumingand expensive and therefore, it significantly slows down research progress. Inthis study, we present a novel procedure that artificially synthesises datathat resembles radio signals. We replicate the workflow of a radio DJ in mixingaudio and investigate parameters like fade curves and audio ducking. We traineda Convolutional Recurrent Neural Network (CRNN) on this synthesised data andoutperformed state-of-the-art algorithms for music-speech detection. This paperdemonstrates the data synthesis procedure as a highly effective technique togenerate large datasets to train deep neural networks for audio segmentation.

Artificially Synthesising Data for Audio Classification and Segmentation to Improve Speech and Music Detection in Radio Broadcast