English(EN) Merging the Knowledge of LLMs for Automatic Speech Recognition

大型语言模型融合可提升自动语音识别性能且无额外计算成本

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

研究人员开发了一种新颖的方法，可以将大型语言模型（LLMs）集成到自动语音识别（ASR）系统中，而不会增加计算成本。该方法利用LoRA（低秩适配）技术将LLMs直接融合到ASR模型的参数中。在CSJ和LibriSpeech数据集上的实验表明，这种语言模型融合在领域适应方面一致地提高了ASR性能，且不影响推理速度或内存使用。 AI

影响该方法可以实现将先进的语言理解更有效地集成到语音处理任务中。

排序理由该集群包含一篇详细介绍改进ASR系统新方法的学术论文。[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: 15 / 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改进ASR系统新方法的学术论文。[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.CL TIER_1 English(EN) · Hayato Futami, Tatsuya Kawahara · 2026-09-15 04:00

融合大型语言模型的知识以实现自动语音识别

arXiv:2609.15743v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data. LM fusion methods such as shallow fusion and density ratio are well-es…

本文如何被排名

报道来源 [1]

融合大型语言模型的知识以实现自动语音识别

相关实体

相关话题