PulseAugur
中
实时 10:44:00
English(EN) Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations

新的ASR纠错方法利用本体记忆处理长对话

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了一种新颖的本体记忆增强型框架，用于改进长文本与语音交织对话的自动语音识别（ASR）纠错。该方法将交互历史组织成一个动态本体记忆，将实体、术语和语义关系存储为可检索节点。使用新构建的RAMC-Corr数据集进行的实验表明，与直接纠错方法相比，该方法显著提高了纠错准确性。 AI

影响 这种新的ASR纠错框架可以提高语音转文本系统在复杂、长篇对话场景中的准确性。

排序理由 该集群包含一篇详细介绍ASR纠错新方法的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Xinxin Li, Huiyao Chen, Meishan Zhang, Yunxin Li, Zulong Chen, Zhibo Ren, Xiaoqing Dong Baotian Hu, Min Zhang ·

    Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations

    arXiv:2606.13464v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) correction has traditionally focused on isolated utterances or short local contexts. However, as text and speech become increasingly interleaved in long interactions, ASR correction requires conv…

  2. arXiv cs.AI TIER_1 English(EN) · Min Zhang ·

    Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations

    Automatic speech recognition (ASR) correction has traditionally focused on isolated utterances or short local contexts. However, as text and speech become increasingly interleaved in long interactions, ASR correction requires conversation-level contextual evidence. Existing ASR c…

相关话题