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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Automatic speech recognition (ASR) systems have been widely deployed inmodern smart devices to provide convenient and diverse voice-controlledservices. Since ASR systems are vulnerable to audio replay attacks that canspoof and mislead ASR systems, a number of defense systems have been proposedto identify replayed audio signals based on the speakers' unique acousticfeatures in the frequency domain. In this paper, we uncover a new type ofreplay attack called modulated replay attack, which can bypass the existingfrequency domain based defense systems. The basic idea is to compensate for thefrequency distortion of a given electronic speaker using an inverse filter thatis customized to the speaker's transform characteristics. Our experiments onreal smart devices confirm the modulated replay attacks can successfully escapethe existing detection mechanisms that rely on identifying suspicious featuresin the frequency domain. To defeat modulated replay attacks, we design andimplement a countermeasure named DualGuard. We discover and formally prove thatno matter how the replay audio signals could be modulated, the replay attackswill either leave ringing artifacts in the time domain or cause spectrumdistortion in the frequency domain. Therefore, by jointly checking suspiciousfeatures in both frequency and time domains, DualGuard can successfully detectvarious replay attacks including the modulated replay attacks. We implement aprototype of DualGuard on a popular voice interactive platform, ReSpeaker Corev2. The experimental results show DualGuard can achieve 98% accuracy ondetecting modulated replay attacks.

When the Differences in Frequency Domain are Compensated: Understanding and Defeating Modulated Replay Attacks on Automatic Speech Recognition