English(EN) Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript

DuplexJev让冻结的LLM在理解超越文本的语音方面取得突破

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-05 04:00

研究人员开发了DuplexJev，一个新颖的系统，使冻结的大型语言模型（LLMs）能够处理超越简单转录的语音音频。通过将音频编码器的隐藏状态通过一个小型连接器直接馈送到LLM中，DuplexJev可以在约0.1秒内使用8个GPU节点回答关于八个语音片段的问题。这种方法不仅能让LLM理解语音内容，还能以高达90%的准确率辨别说话者的情绪和性别。 AI

影响使LLM能够处理语音音频以完成超越转录的任务，可能提高语音代理能力和实时决策能力。

排序理由该集群描述了一篇在arXiv上发表的研究论文，详细介绍了一种用LLM进行语音处理的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇在arXiv上发表的研究论文，详细介绍了一种用LLM进行语音处理的新方法。[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, model release; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jie Jin, Ziyin Ma, Min Yin, Jinyu Chen, Haigang Song, Zhikun Pang, Xiaowen Zhang · 2026-10-05 04:00

无需解码的批量语音决策：单Token监督让冻结LLM听懂超越文本的内容

arXiv:2610.02638v1 Announce Type: new Abstract: Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden states through a small connector into a frozen LLM and re…

本文如何被排名

报道来源 [1]

无需解码的批量语音决策：单Token监督让冻结LLM听懂超越文本的内容

相关实体

相关话题