English(EN) Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions

新的混合搜索方法增强了基于LLM的语音识别

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

研究人员开发了一种名为混合搜索的新方法，以改进集成大型语言模型（LLM）的自动语音识别（ASR）系统。该技术利用基于LLM的ASR模型与其基础LLM之间的隐藏状态交互特征，来识别具有高度语义依赖性的词元。通过选择性地精炼这些目标词元，混合搜索在ASR性能方面超越了传统的全局纠正方法，证明了基于LLM的ASR模型可以通过利用其基础LLM来进一步提高推理时间性能。 AI

影响这项研究通过更好地整合LLM能力，有望带来更准确、更具语义意识的语音识别系统。

排序理由该集群包含一篇详细介绍语音识别新方法的学术论文。[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: 17 / 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语音识别新方法的学术论文。[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, 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: 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.AI TIER_1 English(EN) · Chan-Jan Hsu, Jaeyeon Kim, Chao-Han Huck Yang, Shinji Watanabe, Hung-yi Lee, Carlos Busso · 2026-09-04 04:00

聆听潜在表征：大型音频语言模型通过隐藏状态交互实现自我纠正语音识别

arXiv:2609.02940v1 Announce Type: cross Abstract: Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either externally through logit fusion or internally through warm initialization. However,…

本文如何被排名

报道来源 [1]

聆听潜在表征：大型音频语言模型通过隐藏状态交互实现自我纠正语音识别

相关实体

相关话题