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

While the use of deep neural networks has significantly boosted speakerrecognition performance, it is still challenging to separate speakers in pooracoustic environments. To improve robustness of speaker recognition systemperformance in noise, a novel two-stage attention mechanism which can be usedin existing architectures such as Time Delay Neural Networks (TDNNs) andConvolutional Neural Networks (CNNs) is proposed. Noise is known to often maskimportant information in both time and frequency domain. The proposed mechanismallows the models to concentrate on reliable time/frequency components of thesignal. The proposed approach is evaluated using the Voxceleb1 dataset, whichaims at assessment of speaker recognition in real world situations. In additionthree types of noise at different signal-noise-ratios (SNRs) were added forthis work. The proposed mechanism is compared with three strong baselines:X-vectors, Attentive X-vector, and Resnet-34. Results on both identificationand verification tasks show that the two-stage attention mechanism consistentlyimproves upon these for all noise conditions.

Improving Noise Robustness In Speaker Identification Using A Two-Stage Attention Model