English(EN) Generative Testing of Automated Speech Recognition Systems

新的GATAS方法为ASR系统生成对抗性输入

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-14 04:00

研究人员开发了一种新颖的黑盒测试方法GATAS，用于自动语音识别（ASR）系统。该方法通过操纵文本到语音模型的潜在空间来生成对抗性输入，旨在诱导转录错误，同时保持语音的自然度。GATAS将攻击表述为一个多目标优化问题，平衡语义差异和感知质量。实证评估表明，与现有方法相比，GATAS在失真度较低和感知质量较好的情况下实现了高成功率，即使没有直接访问模型内部。 AI

影响这项研究引入了一种更有效的方法来测试ASR系统在对抗性攻击下的鲁棒性，有望带来更安全可靠的语音识别技术。

排序理由该集群包含一篇详细介绍测试AI系统新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍测试AI系统新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 86 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yanis Xabier Wilbrand Pe\~na, Oliver Wei{\ss}l, Andrea Stocco · 2026-07-14 04:00

生成式自动语音识别系统测试

arXiv:2607.09833v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems have achieved high accuracy with transformer-based models, enabling deployment in critical applications. However, they remain vulnerable to adversarial manipulation, particularly in black…

本文如何被排名

报道来源 [1]

生成式自动语音识别系统测试

相关实体

相关话题