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

End-to-end (E2E) multi-channel ASR systems show state-of-the-art performancein far-field ASR tasks by joint training of a multi-channel front-end alongwith the ASR model. The main limitation of such systems is that they areusually trained with data from a fixed array geometry, which can lead todegradation in accuracy when a different array is used in testing. This makesit challenging to deploy these systems in practice, as it is costly to retrainand deploy different models for various array configurations. To address this,we present a simple and effective data augmentation technique, which is basedon randomly dropping channels in the multi-channel audio input during training,in order to improve the robustness to various array configurations at testtime. We call this technique ChannelAugment, in contrast to SpecAugment (SA)which drops time and/or frequency components of a single channel input audio.We apply ChannelAugment to the Spatial Filtering (SF) and Minimum VarianceDistortionless Response (MVDR) neural beamforming approaches. For SF, weobserve 10.6% WER improvement across various array configurations employingdifferent numbers of microphones. For MVDR, we achieve a 74% reduction intraining time without causing degradation of recognition accuracy.

ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization