一键破解语音模型？新研究系统优化多模态越狱攻击，直指spoken language model安全漏洞。
arXiv:2603.19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vul…
探讨翻译增强预训练对语音大模型的实际影响，为语音AI研究提供实证依据。
arXiv:2606.25444v1 Announce Type: cross Abstract: Connecting a pre-trained speech encoder to a Large Language Model (LLM) is the standard architecture…
端到端口语对话状态追踪新突破：联合语音与文本训练，显著提升LLM在语音场景下的跟踪准确率。
arXiv:2511.22503v2 Announce Type: replace Abstract: End-to-end spoken dialogue state tracking (DST) is made difficult by the tandem of having to handl…
视频大语言模型是否真的需要音频？这篇被Interspeech 2026接收的研究给出了基准审计与可扩展修复方案。
arXiv:2509.17901v4 Announce Type: replace Abstract: Speech and audio encoders developed over years of community effort are routinely excluded from vid…
最新研究量化了语音LLM中的交叉偏见，揭示声音特征与种族、性别等多重因素的交互影响，为AI公平性提供关键评估方法。
arXiv:2603.16941v2 Announce Type: replace-cross Abstract: Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such…
利用Audio-LLMs智能过滤低质量数据，大幅提升语音到语音翻译模型的训练效率与效果，INTERSPEECH 2026录用论文。
arXiv:2606.13507v1 Announce Type: new Abstract: Large-scale mined corpora provide abundant training data for end-to-end speech-to-speech translation (…
利用参考语音增强训练，提出RAT方法有效提升ASV反欺骗性能，已被Interspeech 2026接收。
arXiv:2606.10908v1 Announce Type: cross Abstract: We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but…
用LLM生成近似错误进行对比训练，显著提升语种混合语音识别的鲁棒性，INTERSPEECH 2026收录。
arXiv:2606.06985v1 Announce Type: new Abstract: Code-switching (CS), the alternation between multiple languages within a single utterance, remains cha…
面向语音理解的开源可复现实验框架，统一评估标准，加速研究迭代。
arXiv:2605.30899v1 Announce Type: cross Abstract: Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented…