- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents an empirical evaluation of adversarial attacks on multilingual speech recognition. Its main contribution is characterizing language-specific adversarial attacks. The results suggest that the low-resource languages suffer greater WER growth and are easier to attack. This paper also presents several defense methods and shows the trade-offs between benefits and accuracy.
Critical strengths
- This paper presents an innovative study on language-specific adversarial attacks.
- This paper proposes several defense mechanisms and demonstrates the trade-offs between benefits and accuracy in detail.
Critical weaknesses
- The perceptual evidence for trigger signals is based on PESQ values rather than human evaluation.
- In Section 4.1, the experimental results show that Hausa is more vulnerable to English, but since the two languages have different clean WERs, the conclusions drawn from this comparison are not entirely convincing.
- Table 3 shows that larger models tend to have slightly lower ASR. However, the experimental data is limited and the ASR for English does not increase monotonically.
- This paper concludes that low-resource languages are more vulnerable, but experiments were conducted on only two such languages.
Questions for authors
- Are trigger signals with low PESQ values also difficult for humans to hear? It is better to conduct human evaluations.
- Is it possible to conduct a comparative experiment in which the clean WER for the two languages in Section 4.1 is the same?