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 performance of speaker-related systems usually degrades heavily inpractical applications largely due to the presence of background noise. Toimprove the robustness of such systems in unknown noisy environments, thispaper proposes a simple pre-processing method called Noise Invariant FrameSelection (NIFS). Based on several noisy constraints, it selects noiseinvariant frames from utterances to represent speakers. Experiments conductedon the TIMIT database showed that the NIFS can significantly improve theperformance of Vector Quantization (VQ), Gaussian Mixture Model-UniversalBackground Model (GMM-UBM) and i-vector-based speaker verification systems indifferent unknown noisy environments with different SNRs, in comparison totheir baselines. Meanwhile, the proposed NIFS-based speaker verificationsystems achieves similar performance when we change the constraints(hyper-parameters) or features, which indicates that it is robust and easy toreproduce. Since NIFS is designed as a general algorithm, it could be furtherapplied to other similar tasks.

Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification