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

Majority of the recent approaches for text-independent speaker recognitionapply attention or similar techniques for aggregation of frame-level featuredescriptors generated by a deep neural network (DNN) front-end. In this paper,we propose methods of convolutional attention for independently modellingtemporal and frequency information in a convolutional neural network (CNN)based front-end. Our system utilizes convolutional block attention modules(CBAMs) [1] appropriately modified to accommodate spectrogram inputs. Theproposed CNN front-end fitted with the proposed convolutional attention modulesoutperform the no-attention and spatial-CBAM baselines by a significant marginon the VoxCeleb [2, 3] speaker verification benchmark, and our best modelachieves an equal error rate of 2:031% on the VoxCeleb1 test set, improving theexisting state of the art result by a significant margin. For a more thoroughassessment of the effects of frequency and temporal attention in real-worldconditions, we conduct ablation experiments by randomly dropping frequency binsand temporal frames from the input spectrograms, concluding that instead ofmodelling either of the entities, simultaneously modelling temporal andfrequency attention translates to better real-world performance.

Frequency and temporal convolutional attention for text-independent speaker recognition