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

The combined electric and acoustic stimulation (EAS) has demonstrated betterspeech recognition than conventional cochlear implant (CI) and yieldedsatisfactory performance under quiet conditions. However, when noise signalsare involved, both the electric signal and the acoustic signal may bedistorted, thereby resulting in poor recognition performance. To suppress noiseeffects, speech enhancement (SE) is a necessary unit in EAS devices. Recently,a time-domain speech enhancement algorithm based on the fully convolutionalneural networks (FCN) with a short-time objective intelligibility (STOI)-basedobjective function (termed FCN(S) in short) has received increasing attentiondue to its simple structure and effectiveness of restoring clean speech signalsfrom noisy counterparts. With evidence showing the benefits of FCN(S) fornormal speech, this study sets out to assess its ability to improve theintelligibility of EAS simulated speech. Objective evaluations and listeningtests were conducted to examine the performance of FCN(S) in improving thespeech intelligibility of normal and vocoded speech in noisy environments. Theexperimental results show that, compared with the traditional minimum-meansquare-error SE method and the deep denoising autoencoder SE method, FCN(S) canobtain better gain in the speech intelligibility for normal as well as vocodedspeech. This study, being the first to evaluate deep learning SE approaches forEAS, confirms that FCN(S) is an effective SE approach that may potentially beintegrated into an EAS processor to benefit users in noisy environments.

Improving the Intelligibility of Electric and Acoustic Stimulation Speech Using Fully Convolutional Networks Based Speech Enhancement