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

Estimating a time-varying spatial covariance matrix for a beamformingalgorithm is a challenging task, especially for wearable devices, as thealgorithm must compensate for time-varying signal statistics due to rapidpose-changes. In this paper, we propose Neural Integrated Covariance Estimatorsfor Beamformers, NICE-Beam. NICE-Beam is a general technique for learning howto estimate time-varying spatial covariance matrices, which we apply to jointspeech enhancement and dereverberation. It is based on training a neuralnetwork module to non-linearly track and leverage scene information acrosstime. We integrate our solution into a beamforming pipeline, which enablessimple training, faster than real-time inference, and a variety of test-timeadaptation options. We evaluate the proposed model against a suite of baselinesin scenes with both stationary and moving microphones. Our results show thatthe proposed method can outperform a hand-tuned estimator, despite thehand-tuned estimator using oracle source separation knowledge.

NICE-Beam: Neural Integrated Covariance Estimators for Time-Varying Beamformers