• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Audio, Speech, and Language Processing, IEEE Transactions on >Speaker Model Clustering for Efficient Speaker Identification in Large Population Applications
【24h】

Speaker Model Clustering for Efficient Speaker Identification in Large Population Applications

机译：扬声器模型聚类，可在大量应用中实现高效的说话人识别

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

In large population speaker identification (SI) systems, likelihood computations between an unknown speaker's feature vectors and the registered speaker models can be very time-consuming and impose a bottleneck. For applications requiring fast SI, this is a recognized problem and improvements in efficiency would be beneficial. In this paper, we propose a method whereby GMM-based speaker models are clustered using a simple k-means algorithm. Then, during the test stage, only a small proportion of speaker models in selected clusters are used in the likelihood computations resulting in a significant speed-up with little to no loss in accuracy. In general, as the number of selected clusters is reduced, the identification accuracy decreases; however, this loss can be controlled through proper tradeoff. The proposed method may also be combined with other test stage speed-up techniques resulting in even greater speed-up gains without additional sacrifices in accuracy.
机译：在人口众多的说话人识别（SI）系统中，未知说话人的特征向量与注册的说话人模型之间的似然计算可能非常耗时，并且会造成瓶颈。对于需要快速SI的应用程序，这是一个公认的问题，提高效率将是有益的。在本文中，我们提出了一种使用简单k均值算法对基于GMM的说话人模型进行聚类的方法。然后，在测试阶段，在似然计算中仅使用了选定簇中的一小部分说话人模型，从而显着提高了速度，而准确性几乎没有损失。通常，随着所选簇的数量减少，识别精度会降低；但是，可以通过适当的权衡来控制这种损失。所提出的方法也可以与其他测试阶段加速技术相结合，从而获得更大的加速增益，而不会牺牲准确性。

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