• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Acoustics Speech and Signal;ICASSP 2010 >A novel feature sub-sampling method for efficient universal background model training in speaker verification
【24h】

A novel feature sub-sampling method for efficient universal background model training in speaker verification

机译：一种有效的说话人验证通用背景模型训练的特征子采样方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Speaker recognition/verification systems require an extensive universal background model (UBM), which typically requires extensive resources, especially if new channel domains are considered. In this study we propose an effective and computationally efficient algorithm for training the UBM for speaker verification. A novel method based on Euclidean distance between features is developed for effective sub-sampling of potential training feature vectors. Using only about 1.5 seconds of data from each development utterance, the proposed UBM training method drastically reduces the computation time, while improving, or at least retaining original speaker verification system performance. While methods such as factor analysis can mitigate some of the issues associated with channel/microphone/environmental mismatch, the proposed rapid UBM training scheme offers a viable alternative for rapid environment dependent UBMs.
机译：说话人识别/验证系统需要广泛的通用背景模型（UBM），通常需要大量资源，尤其是在考虑新的频道域的情况下。在这项研究中，我们提出了一种有效且计算效率高的算法，用于训练用于说话人验证的UBM。针对潜在训练特征向量的有效子采样，提出了一种基于特征之间欧氏距离的新颖方法。所提出的UBM训练方法仅使用来自每个发声的大约1.5秒的数据，就大大减少了计算时间，同时改善了或至少保留了原始说话者验证系统的性能。尽管诸如因子分析之类的方法可以缓解与通道/麦克风/环境不匹配相关的一些问题，但建议的快速UBM训练方案为依赖于环境的快速UBM提供了可行的替代方案。

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