1999 Speaker Recognition Benchmark

<h3>Introduction</h3> <p>The 1999 speaker recognition evaluation is part of an ongoing series of yearly evaluations conducted by NIST. These evaluations provide an important contribution to the direction of research efforts and the calibration of technical capabilities. They are intended to be of interest to all researchers working on the general problem of text independent speaker recognition. </p><h3>Data</h3> <p>Technical Objectives of the 1999 speaker recognition evaluation were: </p><p>1. Exploring promising new ideas in speaker recognition 2. Developing advanced technology incorporating these ideas 3. Measuring the performance of this technology </p><p>The evaluation data was drawn from the Switchboard-2 Phase 3 corpus. Both training and test segments were constructed by concatenating consecutive turns for the desired speaker, similar to what was done in 1996. Each segment is stored as a continuous speech signal in a separate SPHERE file. The speech data is stored in 8-bit mulaw format. </p><h3>Updates</h3> There are no updates at this time. </br>
Portions © 1999 Trustees of University of Pennsylvania

<h3>引言</h3><p>1999年说话人识别评测是美国国家标准与技术研究院（National Institute of Standards and Technology, NIST）开展的年度系列评测项目的组成部分。此类评测对于明确研究方向、校准技术能力具有重要推动作用，旨在吸引所有致力于与文本无关的说话人识别通用问题研究的科研人员关注。</p><h3>数据</h3><p>1999年说话人识别评测的技术目标如下：</p><p>1. 探索说话人识别领域颇具前景的全新思路；2. 研发融合此类思路的先进技术；3. 评估该技术的性能表现。</p><p>本次评测的数据源自Switchboard-2 Phase 3语料库。训练与测试片段均通过拼接目标说话人的连续会话轮次构建而成，其处理方式与1996年的评测一致。每个片段均以连续语音信号的形式存储于独立的SPHERE文件中，语音数据采用8位mulaw格式存储。</p><h3>更新情况</h3><p>目前暂无更新内容。</br><p>部分内容 © 1999 宾夕法尼亚大学理事会</p>