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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep generative models for Speech Enhancement (SE) received increasingattention in recent years. The most prominent example are GenerativeAdversarial Networks (GANs), while normalizing flows (NF) received lessattention despite their potential. Building on previous work, architecturalmodifications are proposed, along with an investigation of differentconditional input representations. Despite being a common choice in relatedworks, Mel-spectrograms demonstrate to be inadequate for the given scenario.Alternatively, a novel All-Pole Gammatone filterbank (APG) with high temporalresolution is proposed. Although computational evaluation metric results wouldsuggest that state-of-the-art GAN-based methods perform best, a perceptualevaluation via a listening test indicates that the presented NF approach (basedon time domain and APG) performs best, especially at lower SNRs. On average,APG outputs are rated as having good quality, which is unmatched by the othermethods, including GAN.

Improved Normalizing Flow-Based Speech Enhancement using an All-pole Gammatone Filterbank for Conditional Input Representation