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

In this paper, we propose the multi-perspective information fusion (MPIF)Res2Net with random Specmix for fake speech detection (FSD). The main purposeof this system is to improve the model's ability to learn precise forgeryinformation for FSD task in low-quality scenarios. The task of random Specmix,a data augmentation, is to improve the generalization ability of the model andenhance the model's ability to locate discriminative information. Specmix cutsand pastes the frequency dimension information of the spectrogram in the samebatch of samples without introducing other data, which helps the model tolocate the really useful information. At the same time, we randomly selectsamples for augmentation to reduce the impact of data augmentation directlychanging all the data. Once the purpose of helping the model to locateinformation is achieved, it is also important to reduce unnecessaryinformation. The role of MPIF-Res2Net is to reduce redundant interferenceinformation. Deceptive information from a single perspective is always similar,so the model learning this similar information will produce redundant spoofingclues and interfere with truly discriminative information. The proposedMPIF-Res2Net fuses information from different perspectives, making theinformation learned by the model more diverse, thereby reducing the redundancycaused by similar information and avoiding interference with the learning ofdiscriminative information. The results on the ASVspoof 2021 LA datasetdemonstrate the effectiveness of our proposed method, achieving EER andmin-tDCF of 3.29% and 0.2557, respectively.

Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection