The technology we use, and even rely on, in our everyday lives –computers, radios, video, cell phones – is enabled by signal processing. Learn More »
1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.
Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this letter, we propose a novel generation-network-based approach, called symmetric saliency-based encoder-decoder (SSED), to generate adversarial voice examples to speaker identification. It contains two novel components. First, it uses a novel saliency map decoder to learn the importance of speech samples to the decision of a targeted speaker identification system, so as to make the attacker focus on generating artificial noise to the important samples. It also proposes an angular loss function to push the speaker embedding far away from the source speaker. Our experimental results demonstrate that the proposed SSED yields the state-of-the-art performance, i.e. over 97% targeted attack success rate and a signal-to-noise level of over 39 dB on both the open-set and close-set speaker identification tasks, with a low computational cost.
Speaker recognition is vulnerable to spoofing attacks . Many spoofing attack techniques to speaker recognition, including replay, voice conversion, impersonation and text-to-speech synthesis, and adversarial attacks , have been developed. On the contrary, various detection , ,  and countermeasures  against spoofing attacks are in full swing. In this letter, we focus on developing adversarial attacks to speaker identification. An adversarial attack to speaker identification aims to make an identification system wrongly recognize the adversarial voice of a source speaker as a targeted imposter speaker, where the adversarial voice, a.k.a. adversarial example, is produced by adding human-imperceptible noise to the speech of the source speaker. It shows great threat to modern speaker identification systems based on deep learning.
© Copyright 2023 IEEE – All rights reserved. Use of this website signifies your agreement to the IEEE Terms and Conditions.
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.