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

The speech representations learned from large-scale unlabeled data have shownbetter generalizability than those from supervised learning and thus attract alot of interest to be applied for various downstream tasks. In this paper, weexplore the limits of speech representations learned by differentself-supervised objectives and datasets for automatic speaker verification(ASV), especially with a well-recognized SOTA ASV model, ECAPA-TDNN [1], as adownstream model. The representations from all hidden layers of the pre-trainedmodel are firstly averaged with learnable weights and then fed into theECAPA-TDNN as input features. The experimental results on Voxceleb dataset showthat the weighted average representation is significantly superior to FBank, aconventional handcrafted feature for ASV. Our best single system achieves0.537%, 0.569%, and 1.180% equal error rate (EER) on the three official trialsof VoxCeleb1, separately. Accordingly, the ensemble system with threepre-trained models can further improve the EER to 0.479%, 0.536% and 1.023%.Among the three evaluation trials, our best system outperforms the winnersystem [2] of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC2021) onthe VoxCeleb1-E trial.

Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification