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

Single-channel deep speech enhancement approaches often estimate a singlemultiplicative mask to extract clean speech without a measure of its accuracy.Instead, in this work, we propose to quantify the uncertainty associated withclean speech estimates in neural network-based speech enhancement. Predictiveuncertainty is typically categorized into aleatoric uncertainty and epistemicuncertainty. The former accounts for the inherent uncertainty in data and thelatter corresponds to the model uncertainty. Aiming for robust clean speechestimation and efficient predictive uncertainty quantification, we propose tointegrate statistical complex Gaussian mixture models (CGMMs) into a deepspeech enhancement framework. More specifically, we model the dependencybetween input and output stochastically by means of a conditional probabilitydensity and train a neural network to map the noisy input to the full posteriordistribution of clean speech, modeled as a mixture of multiple complex Gaussiancomponents. Experimental results on different datasets show that the proposedalgorithm effectively captures predictive uncertainty and that combiningpowerful statistical models and deep learning also delivers a superior speechenhancement performance.

Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture Models