PulseAugur
中
实时 08:57:35
实体 Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions

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

PulseAugur coverage of Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions — every cluster mentioning Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions across labs, papers, and developer communities, ranked by signal.

Show in brief
总计 · 30天
1
90 天内 1
发布 · 30天
0
90 天内 0
论文 · 30天
1
90 天内 1
层级分布 · 90 天
主题
情绪 · 30 天

1 天有情绪数据

最近 · 第 1/1 页 · 共 1 条
  1. TOOL · CL_235421 ·

    新的混合搜索方法增强了基于LLM的语音识别

    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。