What Was That Again? Certified Robustness for Automatic Speech Recognition

Computer Science > Machine Learning [Submitted on 26 Jun 2026] What Was That Again? Certified Robustness for Automatic Speech Recognition Andrew C. Cullen, Neil Marchant, Jiani Xie, Paul Montague, Benjamin I.P. Rubinstein Automatic Speech Recognition systems are notoriously both sensitive to adversarial and benign perturbations. While this has been repeatedly demonstrated using reference datasets, detecting such behaviors in deployed systems is incredibly challenging, due to the absence of oracle knowledge of the true transcription. We demonstrate that employing a certification-inspired mechanism can significantly decrease WER, increase recall, and decrease the Spearman correlation between confidence and WER. We achieve this through a dual-gate diagnostic pipeline: a Two-Sided Atomic Audit that accumulates statistical wealth to certify both token existence and adversarial exclusion, and a Rank-Based Tournament that selects the winning sequence. Our evaluations across four diverse architectures demonstrate up to a 55% relative reduction in Word Error Rate, while also providing granular word- and sentence-level certifications to enhance acoustic security. Comments: 17 pages Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Sound (cs.SD) Cite as: arXiv:2606.27698 [cs.LG]   (or arXiv:2606.27698v1 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2606.27698 Focus to learn more Submission history From: Andrew Cullen [view email] [v1] Fri, 26 Jun 2026 03:54:20 UTC (431 KB) Access Paper: HTML (experimental) view license Current browse context: cs.LG < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI cs.CR cs.SD References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)