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 choice of an optimal time-frequency resolution is usually a difficult butimportant step in tasks involving speech signal classification, e.g., speechanti-spoofing. The variations of the performance with different choices oftimefrequency resolutions can be as large as those with different modelarchitectures, which makes it difficult to judge what the improvement actuallycomes from when a new network architecture is invented and introduced as theclassifier. In this paper, we propose a multi-resolution front-end for featureextraction in an end-to-end classification framework. Optimal weightedcombinations of multiple time-frequency resolutions will be learnedautomatically given the objective of a classification task. Features extractedwith different time-frequency resolutions are weighted and concatenated asinputs to the successive networks, where the weights are predicted by alearnable neural network inspired by the weighting block insqueeze-and-excitation networks (SENet). Furthermore, the refinement of thechosen timefrequency resolutions is investigated by pruning the ones withrelatively low importance, which reduces the complexity and size of the model.The proposed method is evaluated on the tasks of speech anti-spoofing inASVSpoof 2019 and its superiority has been justified by comparing with similarbaselines.

A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing