mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
188 lines
9.3 KiB
HTML
188 lines
9.3 KiB
HTML
|
||
<!DOCTYPE html>
|
||
|
||
<html lang="zh-CN">
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
|
||
|
||
|
||
<!-- Licensed under the Apache 2.0 License -->
|
||
<link rel="stylesheet" type="text/css" href="_static/fonts/open-sans/stylesheet.css" />
|
||
<!-- Licensed under the SIL Open Font License -->
|
||
<link rel="stylesheet" type="text/css" href="_static/fonts/source-serif-pro/source-serif-pro.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap.min.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/css/bootstrap-theme.min.css" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
|
||
<title>基线 — m2met2 文档</title>
|
||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/guzzle.css" />
|
||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||
<script src="_static/jquery.js"></script>
|
||
<script src="_static/underscore.js"></script>
|
||
<script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
|
||
<script src="_static/doctools.js"></script>
|
||
<script src="_static/sphinx_highlight.js"></script>
|
||
<script src="_static/translations.js"></script>
|
||
<link rel="index" title="索引" href="genindex.html" />
|
||
<link rel="search" title="搜索" href="search.html" />
|
||
<link rel="next" title="竞赛规则" href="%E8%A7%84%E5%88%99.html" />
|
||
<link rel="prev" title="赛道设置与评估" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html" />
|
||
|
||
|
||
|
||
</head><body>
|
||
<div class="related" role="navigation" aria-label="related navigation">
|
||
<h3>导航</h3>
|
||
<ul>
|
||
<li class="right" style="margin-right: 10px">
|
||
<a href="genindex.html" title="总索引"
|
||
accesskey="I">索引</a></li>
|
||
<li class="right" >
|
||
<a href="%E8%A7%84%E5%88%99.html" title="竞赛规则"
|
||
accesskey="N">下一页</a> |</li>
|
||
<li class="right" >
|
||
<a href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html" title="赛道设置与评估"
|
||
accesskey="P">上一页</a> |</li>
|
||
<li class="nav-item nav-item-0"><a href="index.html">m2met2 文档</a> »</li>
|
||
<li class="nav-item nav-item-this"><a href="">基线</a></li>
|
||
</ul>
|
||
</div>
|
||
<div class="container-wrapper">
|
||
|
||
<div id="mobile-toggle">
|
||
<a href="#"><span class="glyphicon glyphicon-align-justify" aria-hidden="true"></span></a>
|
||
</div>
|
||
<div id="left-column">
|
||
<div class="sphinxsidebar"><a href="
|
||
index.html" class="text-logo">m2met2 文档</a>
|
||
<div class="sidebar-block">
|
||
<div class="sidebar-wrapper">
|
||
<div id="main-search">
|
||
<form class="form-inline" action="search.html" method="GET" role="form">
|
||
<div class="input-group">
|
||
<input name="q" type="text" class="form-control" placeholder="Search...">
|
||
</div>
|
||
<input type="hidden" name="check_keywords" value="yes" />
|
||
<input type="hidden" name="area" value="default" />
|
||
</form>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<div class="sidebar-block">
|
||
<div class="sidebar-toc">
|
||
|
||
|
||
<p class="caption" role="heading"><span class="caption-text">目录:</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html">简介</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html#id2">竞赛介绍</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html#aoe">时间安排(AOE时间)</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E7%AE%80%E4%BB%8B.html#id3">竞赛报名</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html">数据集</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html#id2">数据集概述</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html#alimeeting">Alimeeting数据集介绍</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E6%95%B0%E6%8D%AE%E9%9B%86.html#id3">获取数据</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html">赛道设置与评估</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html#id2">说话人相关的语音识别</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html#id3">评估方法</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html#id4">子赛道设置</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">基线</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#id2">基线概述</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#id3">快速开始</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#id4">基线结果</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="%E8%A7%84%E5%88%99.html">竞赛规则</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="%E7%BB%84%E5%A7%94%E4%BC%9A.html">组委会</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="%E8%81%94%E7%B3%BB%E6%96%B9%E5%BC%8F.html">联系方式</a></li>
|
||
</ul>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
</div>
|
||
</div>
|
||
<div id="right-column">
|
||
|
||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||
<ol class="breadcrumb">
|
||
<li><a href="index.html">Docs</a></li>
|
||
|
||
<li>基线</li>
|
||
</ol>
|
||
</div>
|
||
|
||
<div class="document clearer body">
|
||
|
||
<section id="id1">
|
||
<h1>基线<a class="headerlink" href="#id1" title="此标题的永久链接">¶</a></h1>
|
||
<section id="id2">
|
||
<h2>基线概述<a class="headerlink" href="#id2" title="此标题的永久链接">¶</a></h2>
|
||
<p>我们将提供一个在<a class="reference external" href="https://github.com/alibaba-damo-academy/FunASR">FunASR</a>上实现的端到端SA-ASR系统作为基线。该模型的结构如图3所示。SpeakerEncoder用<a class="reference external" href="https://modelscope.cn/home">ModelScope</a>中预先训练好的<a class="reference external" href="https://modelscope.cn/models/damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch/summary">说话人确认模型</a>作为初始化。这个说话人确认模型也被用来提取说话人档案中的说话人嵌入。</p>
|
||
<p><img alt="model archietecture" src="_images/sa_asr_arch.png" /></p>
|
||
</section>
|
||
<section id="id3">
|
||
<h2>快速开始<a class="headerlink" href="#id3" title="此标题的永久链接">¶</a></h2>
|
||
<p>#TODO: fill with the README.md of the baseline</p>
|
||
</section>
|
||
<section id="id4">
|
||
<h2>基线结果<a class="headerlink" href="#id4" title="此标题的永久链接">¶</a></h2>
|
||
<p>基线系统的结果如表3所示。在训练期间，说话人档案采用了真实说话人嵌入。然而由于在评估过程中缺乏真实说话人标签，因此使用了由额外的谱聚类提供的说话人特征。同时我们还提供了在评估和测试集上使用真实说话人档案的结果，以显示说话人档案准确性的影响。
|
||
<img alt="baseline result" src="_images/baseline_result.png" /></p>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
|
||
<div class="footer-relations">
|
||
|
||
<div class="pull-left">
|
||
<a class="btn btn-default" href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html" title="上一章 (use the left arrow)">赛道设置与评估</a>
|
||
</div>
|
||
|
||
<div class="pull-right">
|
||
<a class="btn btn-default" href="%E8%A7%84%E5%88%99.html" title="下一章 (use the right arrow)">竞赛规则</a>
|
||
</div>
|
||
</div>
|
||
<div class="clearer"></div>
|
||
|
||
</div>
|
||
<div class="clearfix"></div>
|
||
</div>
|
||
<div class="related" role="navigation" aria-label="related navigation">
|
||
<h3>导航</h3>
|
||
<ul>
|
||
<li class="right" style="margin-right: 10px">
|
||
<a href="genindex.html" title="总索引"
|
||
>索引</a></li>
|
||
<li class="right" >
|
||
<a href="%E8%A7%84%E5%88%99.html" title="竞赛规则"
|
||
>下一页</a> |</li>
|
||
<li class="right" >
|
||
<a href="%E8%B5%9B%E9%81%93%E8%AE%BE%E7%BD%AE%E4%B8%8E%E8%AF%84%E4%BC%B0.html" title="赛道设置与评估"
|
||
>上一页</a> |</li>
|
||
<li class="nav-item nav-item-0"><a href="index.html">m2met2 文档</a> »</li>
|
||
<li class="nav-item nav-item-this"><a href="">基线</a></li>
|
||
</ul>
|
||
</div>
|
||
<script type="text/javascript">
|
||
$("#mobile-toggle a").click(function () {
|
||
$("#left-column").toggle();
|
||
});
|
||
</script>
|
||
<script type="text/javascript" src="_static/js/bootstrap.js"></script>
|
||
<div class="footer">
|
||
© Copyright 2023, Speech Lab, Alibaba Group; ASLP Group, Northwestern Polytechnical University. Created using <a href="http://sphinx.pocoo.org/">Sphinx</a>.
|
||
</div>
|
||
</body>
|
||
</html> |