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

This paper presents our latest investigations on improving automatic speechrecognition for noisy speech via speech enhancement. We propose a novel methodnamed Multi-discriminators CycleGAN to reduce noise of input speech andtherefore improve the automatic speech recognition performance. Our proposedmethod leverages the CycleGAN framework for speech enhancement without anyparallel data and improve it by introducing multiple discriminators that checkdifferent frequency areas. Furthermore, we show that training multiplegenerators on homogeneous subset of the training data is better than trainingone generator on all the training data. We evaluate our method on CHiME-3 dataset and observe up to 10.03% relatively WER improvement on the development setand up to 14.09% on the evaluation set.

Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN