English(EN) Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs

新的ASR方法使用熵分配来改进LLM集成并减少幻觉

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员开发了一种将大型语言模型（LLM）集成到自动语音识别（ASR）系统中的新方法，解决了延迟、开销和幻觉等挑战。所提出的方法通过熵分配的视角重新审视了基于LLM的ASR，引入了度量标准来分析训练范式如何在语音编码器和LLM之间分配熵减少。为了提高效率和对抗幻觉的鲁棒性，引入了一种多阶段训练策略，包括重新设计预训练以弥合语音-文本模态差距，以及一个迭代的异步SFT阶段，以保持功能解耦并防止编码器表示漂移。 AI

影响这项研究可能带来更高效、更可靠的ASR系统，减少幻觉，并以更少的参数提高性能。

排序理由该集群包含一篇详细介绍LLM-based ASR新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

Jiaqi Song

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; 该集群包含一篇详细介绍LLM-based ASR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: 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.CL TIER_1 English(EN) · Yuan Xie, Jiaqi Song, Guang Qiu, Xianliang Wang, Ming Lei, Jie Gao, Jie Wu · 2026-10-12 04:00

重新思考基于LLM的ASR中的熵分配：理解语音编码器与LLM之间的动态关系

arXiv:2604.08003v2 Announce Type: replace-cross Abstract: Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a dominant paradigm. Although recent LLM-based ASR models have shown promising performance on public benchmarks, it remains challe…

本文如何被排名

报道来源 [1]

重新思考基于LLM的ASR中的熵分配：理解语音编码器与LLM之间的动态关系

相关话题