English(EN) Causal Analysis and Mitigation of Spurious Onsets in Full-Duplex Speech LLMs

新方法抑制全双工大语言模型的虚假语音

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员已识别并解决了全双工语音大语言模型中存在的一个问题，即像 Moshi 和 PersonaPlex 这样的模型会在用户长时间沉默期间不当地启动语音。该问题源于语音概率的突然激增，而非重复采样。开发了一种新的推理时方法，通过评估在用户输入被静音的情况下模型的响应是否会发生变化来抑制这些虚假启动，成功消除了所有测试的虚假启动，且不影响真实响应。 AI

影响引入了一种无需重新训练的实时方法，以提高全双工语音大语言模型的可靠性。

排序理由学术论文，详细介绍了一种缓解语音大语言模型特定问题的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种缓解语音大语言模型特定问题的新方法。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Kento Nishi · 2026-09-15 04:00

全双工语音大语言模型中虚假起始的因果分析与缓解

arXiv:2609.13445v1 Announce Type: new Abstract: Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrently through full-duplex generation. However, they can begin speaking inappropriately during prolonged user silence: under digital-zero i…

本文如何被排名

报道来源 [1]

全双工语音大语言模型中虚假起始的因果分析与缓解

相关实体

相关话题