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

In this work, we propose the use of dropout as a Bayesian estimator forincreasing the generalizability of a deep neural network (DNN) for speechenhancement. By using Monte Carlo (MC) dropout, we show that the DNN performsbetter enhancement in unseen noise and SNR conditions. The DNN is trained onspeech corrupted with Factory2, M109, Babble, Leopard and Volvo noises at SNRsof 0, 5 and 10 dB. Speech samples are obtained from the TIMIT database andnoises from NOISEX-92. In another experiment, we train five DNN modelsseparately on speech corrupted with Factory2, M109, Babble, Leopard and Volvonoises, at 0, 5 and 10 dB SNRs. The model precision (estimated using MCdropout) is used as a proxy for squared error to dynamically select the best ofthe DNN models based on their performance on each frame of test data. Wepropose an algorithm with a threshold on the model precision to switch betweenclassifier based model selection scheme and model precision based selectionscheme. Testing is done on speech corrupted with unseen noises White, Pink andFactory1 and all five seen noises.

Using Monte Carlo dropout for non-stationary noise reduction from speech