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

Supervised learning based on a deep neural network recently has achievedsubstantial improvement on speech enhancement. Denoising networks learn mappingfrom noisy speech to clean one directly, or to a spectrum mask which is theratio between clean and noisy spectra. In either case, the network is optimizedby minimizing mean square error (MSE) between ground-truth labels andtime-domain or spectrum output. However, existing schemes have either of twocritical issues: spectrum and metric mismatches. The spectrum mismatch is awell known issue that any spectrum modification after short-time Fouriertransform (STFT), in general, cannot be fully recovered after inverseshort-time Fourier transform (ISTFT). The metric mismatch is that aconventional MSE metric is sub-optimal to maximize our target metrics,signal-to-distortion ratio (SDR) and perceptual evaluation of speech quality(PESQ). This paper presents a new end-to-end denoising framework with the goalof joint SDR and PESQ optimization. First, the network optimization isperformed on the time-domain signals after ISTFT to avoid spectrum mismatch.Second, two loss functions which have improved correlations with SDR and PESQmetrics are proposed to minimize metric mismatch. The experimental resultshowed that the proposed denoising scheme significantly improved both SDR andPESQ performance over the existing methods.

End-to-End Multi-Task Denoising for joint SDR and PESQ Optimization