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

Naturally introduced perturbations in audio signal, caused by emotional andphysical states of the speaker, can significantly degrade the performance ofAutomatic Speech Recognition (ASR) systems. In this paper, we propose afront-end based on Cycle-Consistent Generative Adversarial Network (CycleGAN)which transforms naturally perturbed speech into normal speech, and henceimproves the robustness of an ASR system. The CycleGAN model is trained onnon-parallel examples of perturbed and normal speech. Experiments onspontaneous laughter-speech and creaky-speech datasets show that theperformance of four different ASR systems improve by using speech obtained fromCycleGAN based front-end, as compared to directly using the original perturbedspeech. Visualization of the features of the laughter perturbed speech andthose generated by the proposed front-end further demonstrates theeffectiveness of our approach.

A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications