• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Spoken Language Processing; 20041004-08; Jeju(KR) >Model Quality Evaluation during Enrollment for Speaker Verification
【24h】

Model Quality Evaluation during Enrollment for Speaker Verification

机译：在注册过程中进行模型质量评估以进行演讲者验证

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The amount of data usually determines the robustness of speaker models in speaker recognition. In this sense, it is convenient to set a model quality measure for every speaker and to classify models into different categories according to their quality level. We propose a new quality measure, which uses only data from clients, based on the number of training utterances that surpass a predefined threshold. If the desired quality is not high enough, the quality measure allows for the detection of non-representative utterances. Once selected, these utterances, considered as outliers, can be removed or better replaced by new ones coming from the same speaker. A database of 184 speakers in Spanish is used to obtain empirical results with connected digits. Our experiments removing outliers and replacing them by new utterances coming from the same speaker outperform the baseline experiments by 40%.
机译：数据量通常确定说话人模型在说话人识别中的鲁棒性。从这个意义上讲，为每个说话者设置模型质量度量并将模型根据其质量水平分类到不同类别是很方便的。我们提出了一种新的质量度量标准，该度量标准基于超过预定阈值的训练话语数量，仅使用来自客户的数据。如果期望的质量不够高，则质量度量允许检测非代表性的话语。一旦选定，可以将这些话语视为异常值，或者将其替换为来自同一发言者的新话语，或者更好地代替这些话语。一个由184名西班牙语发言者组成的数据库用于获得具有关联数字的经验结果。我们的实验去除了异常值，并用同一说话者发出的新语音替换了异常值，其性能比基准实验高40％。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号