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

In speaker verification, ECAPA-TDNN has shown remarkable improvement byutilizing one-dimensional(1D) Res2Net block and squeeze-and-excitation(SE)module, along with multi-layer feature aggregation (MFA). Meanwhile, in visiontasks, ConvNet structures have been modernized by referring to Transformer,resulting in improved performance. In this paper, we present an improved blockdesign for TDNN in speaker verification. Inspired by recent ConvNet structures,we replace the SE-Res2Net block in ECAPA-TDNN with a novel 1D two-stepmulti-scale ConvNeXt block, which we call TS-ConvNeXt. The TS-ConvNeXt block isconstructed using two separated sub-modules: a temporal multi-scale convolution(MSC) and a frame-wise feed-forward network (FFN). This two-step design allowsfor flexible capturing of inter-frame and intra-frame contexts. Additionally,we introduce global response normalization (GRN) for the FFN modules to enablemore selective feature propagation, similar to the SE module in ECAPA-TDNN.Experimental results demonstrate that NeXt-TDNN, with a modernized backboneblock, significantly improved performance in speaker verification tasks whilereducing parameter size and inference time. We have released our code forfuture studies.

NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification