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

Multi-channel multi-talker automatic speech recognition (ASR) presentsongoing challenges within the speech community, particularly when confrontedwith significant reverberation effects. In this study, we introduce a novelapproach involving the convolution of overlapping speech signals with the roomimpulse response (RIR) corresponding to the target speaker's transmission to amicrophone array. This innovative technique yields a novel spatial featureknown as the RIR-SF. Through a comprehensive comparison with the previouslyestablished state-of-the-art 3D spatial feature, both theoretical analysis andexperimental results substantiate the superiority of our proposed RIR-SF. Wedemonstrate that the RIR-SF outperforms existing methods, leading to aremarkable 21.3\% relative reduction in the Character Error Rate (CER) inmulti-channel multi-talker ASR systems. Importantly, this novel featureexhibits robustness in the face of strong reverberation, surpassing thelimitations of previous approaches.

RIR-SF: Room Impulse Response Based Spatial Feature for Multi-channel Multi-talker ASR