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

Radio speech echo is a specific phenomenon in the air traffic control (ATC)domain, which degrades speech quality and further impacts automatic speechrecognition (ASR) accuracy. In this work, a recognition-oriented speechenhancement (ROSE) framework is proposed to improve speech intelligibility andalso advance ASR accuracy, which serves as a plug-and-play tool in ATCscenarios and does not require additional retraining of the ASR model.Specifically, an encoder-decoder-based U-Net framework is proposed to eliminatethe radio speech echo based on the real-world collected corpus. Byincorporating the SE-oriented and ASR-oriented loss, ROSE is implemented in amulti-objective manner by learning shared representations across the twooptimization objectives. An attention-based skip-fusion (ABSF) mechanism isapplied to skip connections to refine the features. A channel and sequenceattention (CSAtt) block is innovatively designed to guide the model to focus oninformative representations and suppress disturbing features. The experimentalresults show that the ROSE significantly outperforms other state-of-the-artmethods for both the SE and ASR tasks. In addition, the proposed approach cancontribute to the desired performance improvements on public datasets.

ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning