首页> 外文学位 >Efficient methods for rapid UBM training (RUT) for robust speaker verification.
【24h】

Efficient methods for rapid UBM training (RUT) for robust speaker verification.

机译:快速的UBM训练(RUT)的有效方法,用于可靠的说话人验证。

获取原文
获取原文并翻译 | 示例

摘要

This study develops a computationally faster method for training background speaker models, with the goal of contributing robust speaker verification systems. The proposed method addresses the issue of speeding up the computational process of the system without hindering overall system performance. The method presented uses a sub-sampling scheme to allow for a more rapid snapshot of the speaker acoustic space, since acoustically similar adjacent frames are skipped to achieve smaller training material. This study also proves that for an effective UBM, it is better to use smaller amounts of data from a balance across a diverse speaker population, rather than blindly using all that is possible. The main disadvantage of using the entire set of data for training UBMs is that it is possible for biases to occur if some speakers have a significantly larger amount of data in the training pool. Therefore, it becomes important to find an efficient way to balance the number and distribution of the speaker population. The method presented in this study also addresses the impact of channel variability in speaker verification systems. The database used in our experiments is the National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE) data from 04', 05', 06' and 08' data, and also a set of speakers from the FISHER database for Eigen-Channel Adaptation (for addressing channel variability). The results show a 70% significant improvement in computational speed of the system without any change in the robust speaker verification system performance. An analysis of the resulting acoustic space also provides evidence of the UBM training algorithm's advantages.
机译:这项研究开发了一种计算速度更快的方法来训练背景说话人模型,目的是提供强大的说话人验证系统。所提出的方法解决了在不影响整体系统性能的情况下加快系统计算过程的问题。由于跳过了声学上相似的相邻帧以获取更小的训练资料,因此所提出的方法使用子采样方案以允许对扬声器声学空间进行更快速的快照。这项研究还证明,对于有效的UBM,最好是使用来自不同说话者群体的均衡数据中的少量数据,而不是盲目地使用所有可能的数据。使用整个数据集来训练UBM的主要缺点是,如果某些说话者在训练池中拥有大量数据,则可能会出现偏差。因此,重要的是找到一种有效的方法来平衡说话者人数和分布。本研究中提出的方法还解决了说话人验证系统中声道可变性的影响。我们实验中使用的数据库是美国国家标准技术研究院(NIST)的说话人识别评估(SRE)数据(来自04',05',06'和08'数据)以及来自FISHER数据库的Eigen的一组说话者-通道适配(用于解决通道可变性)。结果表明,系统的计算速度显着提高了70%,而健壮的扬声器验证系统的性能没有任何变化。对产生的声学空间的分析还提供了UBM训练算法优势的证据。

著录项

  • 作者

    Chandrasekaran, Aravind.;

  • 作者单位

    The University of Texas at Dallas.;

  • 授予单位 The University of Texas at Dallas.;
  • 学科 Engineering Electronics and Electrical.;Physics Acoustics.
  • 学位 M.S.E.E.
  • 年度 2008
  • 页码 50 p.
  • 总页数 50
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 无线电电子学、电信技术;声学;
  • 关键词

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