<?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>动态时间规整 on 语音/音频论文速递</title>
    <link>https://nanless.github.io/audio-paper-digest-blog/tags/%E5%8A%A8%E6%80%81%E6%97%B6%E9%97%B4%E8%A7%84%E6%95%B4/</link>
    <description>Recent content in 动态时间规整 on 语音/音频论文速递</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Mon, 20 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://nanless.github.io/audio-paper-digest-blog/tags/%E5%8A%A8%E6%80%81%E6%97%B6%E9%97%B4%E8%A7%84%E6%95%B4/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing</title>
      <link>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-ps-tts-phonetic-synchronization-in-text-to-speech/</link>
      <pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-ps-tts-phonetic-synchronization-in-text-to-speech/</guid>
      <description>这篇论文旨在解决自动配音（AD）中目标语音与源语音在时长和唇形上的同步难题。其核心贡献是提出了一套两阶段的文本改写方法，并集成到TTS系统中：首先通过语言模型进行**等时性**改写，确保目标语音时长匹配源语音；其次引入**音素同步（PS）**，使用动态时间规整（DTW）和从训练数据中学习的元音距离，</description>
    </item>
    <item>
      <title>语音/音频论文速递 2026-04-20</title>
      <link>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20/</link>
      <pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20/</guid>
      <description>共分析 24 篇语音/AI 论文</description>
    </item>
  </channel>
</rss>
