<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>层次分类 on 语音/音频论文速递</title>
    <link>https://nanless.github.io/audio-paper-digest-blog/tags/%E5%B1%82%E6%AC%A1%E5%88%86%E7%B1%BB/</link>
    <description>Recent content in 层次分类 on 语音/音频论文速递</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Thu, 23 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://nanless.github.io/audio-paper-digest-blog/tags/%E5%B1%82%E6%AC%A1%E5%88%86%E7%B1%BB/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Deep Hierarchical Knowledge Loss for Fault Intensity Diagnosis</title>
      <link>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-deep-hierarchical-knowledge-loss-for-fault/</link>
      <pubDate>Thu, 23 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-deep-hierarchical-knowledge-loss-for-fault/</guid>
      <description>1.  **要解决什么问题**：传统故障强度诊断方法将各类故障视为独立标签，忽略了物理状态之间固有的层次依赖关系（如“空化”是“初期空化”、“稳定空化”等的父类），这限制了模型的性能和鲁棒性。 2.  **方法核心是什么**：提出一个名为DHK的通用框架，其核心是设计两个新的损失函数：**层次树损失</description>
    </item>
  </channel>
</rss>
