ISCA Archive SPSC 2021
ISCA Archive SPSC 2021

Language Dependencies in Adversarial Attacks on Speech Recognition Systems

Karla Markert, Donika Mirdita, Konstantin Böttinger

Automatic speech recognition (ASR) systems are ubiquitously present in our daily devices. They are vulnerable to adversarial attacks, where manipulated input samples fool the ASR system’s recognition. While adversarial examples for various English ASR systems have already been analyzed, there exists no inter-language comparative vulnerability analysis. We compare the attackability of a German and an English ASR system, taking Deepspeech as an example. We investigate if one of the language models is more susceptible to manipulations than the other. The results of our experiments suggest statistically significant differences between English and German in terms of computational effort necessary for the successful generation of adversarial examples. This result encourages further research in language-dependent characteristics in the robustness analysis of ASR.


doi: 10.21437/SPSC.2021-6

Cite as: Markert, K., Mirdita, D., Böttinger, K. (2021) Language Dependencies in Adversarial Attacks on Speech Recognition Systems. Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication, 25-31, doi: 10.21437/SPSC.2021-6

@inproceedings{markert21b_spsc,
  author={Karla Markert and Donika Mirdita and Konstantin Böttinger},
  title={{Language Dependencies in Adversarial Attacks on Speech Recognition Systems}},
  year=2021,
  booktitle={Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication},
  pages={25--31},
  doi={10.21437/SPSC.2021-6}
}