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

Most of the recent state-of-the-art results for speaker verification areachieved by X-vector and its subsequent variants. In this paper, we propose anew network architecture which aggregates the channel and contextinterdependence features from multi aspect based on Time Delay Neural Network(TDNN). Firstly, we use the SE-Res2Blocks as in ECAPA-TDNN to explicitly modelthe channel interdependence to realize adaptive calibration of channelfeatures, and process local context features in a multi-scale way at a moregranular level compared with conventional TDNN-based methods. Secondly, weexplore to use the encoder structure of Transformer to model the global contextinterdependence features at an utterance level which can capture better longterm temporal characteristics. Before the pooling layer, we aggregate theoutputs of SE-Res2Blocks and Transformer encoder to leverage the complementarychannel and context interdependence features learned by themself respectively.Finally, instead of performing a single attentive statistics pooling, we alsofind it beneficial to extend the pooling method in a multi-head way which candiscriminate features from multiple aspect. The proposed MACCIF-TDNNarchitecture can outperform most of the state-of-the-art TDNN-based systems onVoxCeleb1 test sets.

MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification