SUSAS

<h3>Introduction</h3><br>
<p>Speech Under Simulated and Actual Stress (SUSAS) was created by the Robust Speech Processing Laboratory at the University of Colorado-Boulder under the direction of Professor John H. L. Hansen and sponsored by the Air Force Research Laboratory.</p><br>
<h3>Data</h3><br>
<p>The database is partitioned into four domains, encompassing a wide variety of stresses and emotions. A total of 32 speakers (13 female, 19 male), with ages ranging from 22 to 76 years were employed to generate in excess of 16,000 utterances.</p><br>
<p>SUSAS also contains several longer speech files from four Apache helicopter pilots. Those helicopter speech files were transcribed by the Linguistic Data Consortium and are available in SUSAS Transcripts (<a href="../../../LDC99T33">LDC99T33</a>).</p><br>
<p>A common highly confusable vocabulary set of 35 aircraft communication words make up the database. All speech tokens were sampled using a 16-bit A/D converter at a sample rate of 8kHz.</p><br>
<h3>Samples</h3><br>
<p>Please listen to the following four audio samples:</p><br>
<ul><br>
<li><a href="desc/addenda/LDC99S78.1.sph">Sample 1</a></li><br>
<li><a href="desc/addenda/LDC99S78.2.sph">Sample 2</a></li><br>
<li><a href="desc/addenda/LDC99S78.3.sph">Sample 3</a></li><br>
<li><a href="desc/addenda/LDC99S78.4.sph">Sample 4</a></li><br>
</ul><br>
<h3>Updates</h3><br>
<p>There are no updates at this time.</p></br>
Portions © 1999 Trustees of the University of Pennsylvania

<h3>简介</h3><br>
<p>模拟与真实压力下语音（Speech Under Simulated and Actual Stress, SUSAS）由科罗拉多大学博尔德分校鲁棒语音处理实验室在约翰·H·L·汉森教授指导下研发，并由美国空军研究实验室资助。</p><br>
<h3>数据</h3><br>
<p>该数据集划分为四个领域，涵盖多种压力状态与情感类型。共招募32名发音者（13名女性，19名男性），年龄介于22至76岁之间，累计生成超过16000条语音语段。</p><br>
<p>SUSAS还收录了4名阿帕奇直升机飞行员的若干长语音文件。这些直升机语音语料已由语言数据联盟（Linguistic Data Consortium, LDC）完成转写，相关转写文件可在SUSAS转写集（<a href="../../../LDC99T33">LDC99T33</a>）中获取。</p><br>
<p>本数据集采用35个航空通信常用词汇构建易混淆通用词表。所有语音Token均采用16位模数转换器以8kHz采样率完成采样。</p><br>
<h3>样本</h3><br>
<p>请收听以下四段语音样本：</p><br>
<ul><br>
<li><a href="desc/addenda/LDC99S78.1.sph">样本1</a></li><br>
<li><a href="desc/addenda/LDC99S78.2.sph">样本2</a></li><br>
<li><a href="desc/addenda/LDC99S78.3.sph">样本3</a></li><br>
<li><a href="desc/addenda/LDC99S78.4.sph">样本4</a></li><br>
</ul><br>
<h3>更新</h3><br>
<p>目前暂无更新内容。</p><br>
<p>部分内容 © 1999 宾夕法尼亚大学托管会</p>

搜集汇总

背景与挑战

背景概述

SUSAS是一个包含模拟和实际压力下语音的数据集，适用于语音识别研究。数据集包含32位说话者的16,000多条语音样本，以及四位直升机飞行员的语音文件，采样率为8kHz，词汇为35个航空通信词汇。