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

Deep neural networks (DNNs) have greatly benefited direction of arrival (DoA)estimation methods for speech source localization in noisy environments.However, their localization accuracy is still far from satisfactory due to thevulnerability to nonspeech interference. To improve the robustness againstinterference, we propose a DNN based normalized time-frequency (T-F) weightedcriterion which minimizes the distance between the candidate steering vectorsand the filtered snapshots in the T-F domain. Our method requires noeigendecomposition and uses a simple normalization to prevent the optimizationobjective from being misled by noisy filtered snapshots. We also studydifferent designs of T-F weights guided by a DNN. We find that duplicating theHadamard product of speech ratio masks is highly effective and better thanother techniques such as direct masking and taking the mean in the proposedapproach. However, the best-performing design of T-F weights iscriterion-dependent in general. Experiments show that the proposed methodoutperforms popular DNN based DoA estimation methods including widely usedsubspace methods in noisy and reverberant environments.

A DNN based Normalized Time-frequency Weighted Criterion for Robust Wideband DoA Estimation