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

ECAPA-TDNN is currently the most popular TDNN-series model for speakerverification, which refreshed the state-of-the-art(SOTA) performance of TDNNmodels. However, one-dimensional convolution has a global receptive field overthe feature channel. It destroys the time-frequency relevance of thespectrogram. Besides, as ECAPA-TDNN only has five layers, a much shallowerstructure compared to ResNet restricts the capability to generate deeprepresentations. To further improve ECAPA-TDNN, we propose a progressivechannel fusion strategy that splits the spectrogram across the feature channeland gradually expands the receptive field through the network. Secondly, weenlarge the model by extending the depth and adding branches. Our proposedmodel achieves EER with 0.718 and minDCF(0.01) with 0.0858 on vox1o, relativelyimproved 16.1\% and 19.5\% compared with ECAPA-TDNN-large.

PCF: ECAPA-TDNN with Progressive Channel Fusion for Speaker Verification