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

Deep learning (DL) based semantic communication methods have been exploredfor the efficient transmission of images, text, and speech in recent years. Incontrast to traditional wireless communication methods that focus on thetransmission of abstract symbols, semantic communication approaches attempt toachieve better transmission efficiency by only sending the semantic-relatedinformation of the source data. In this paper, we consider semantic-orientedspeech transmission which transmits only the semantic-relevant information overthe channel for the speech recognition task, and a compact additional set ofsemantic-irrelevant information for the speech reconstruction task. We proposea novel end-to-end DL-based transceiver which extracts and encodes the semanticinformation from the input speech spectrums at the transmitter and outputs thecorresponding transcriptions from the decoded semantic information at thereceiver. For the speech to speech transmission, we further include a CTCalignment module that extracts a small number of additional semantic-irrelevantbut speech-related information for the better reconstruction of the originalspeech signals at the receiver. The simulation results confirm that ourproposed method outperforms current methods in terms of the accuracy of thepredicted text for the speech to text transmission and the quality of therecovered speech signals for the speech to speech transmission, andsignificantly improves transmission efficiency. More specifically, the proposedmethod only sends 16% of the amount of the transmitted symbols required by theexisting methods while achieving about 10% reduction in WER for the speech totext transmission. For the speech to speech transmission, it results in an evenmore remarkable improvement in terms of transmission efficiency with only 0.2%of the amount of the transmitted symbols required by the existing method.

Semantic-preserved Communication System for Highly Efficient Speech Transmission