...
首页> 外文期刊>The Journal of the Acoustical Society of America >Phonetically optimized speaker modeling for robust speaker recognition
【24h】

Phonetically optimized speaker modeling for robust speaker recognition

机译:通过语音优化的说话人建模,可实现可靠的说话人识别

获取原文
获取原文并翻译 | 示例
           

摘要

This paper proposes an efficient method to improve speaker rec_ognition performance by dynamically controlling the ratio of phoneme class information. It utilizes the fact that each phoneme contains different amounts of speaker discriminative information that can be measured by mutual infor_mation. After classifying phonemes into five classes, the optimal ratio of each class in both training and testing processes is adjusted using a non-linear op_timization technique, i.e., the Nelder_Mead method. Speaker identification results verify that the proposed method achieves 18% improvement in terms of error rate compared to a baseline system.
机译:本文提出了一种通过动态控制音素类别信息的比率来提高说话人识别性能的有效方法。它利用了以下事实:每个音素包含不同数量的说话者区分信息,这些信息可以通过相互信息来衡量。将音素分为五类后,使用非线性优化技术(即Nelder_Mead方法)调整训练和测试过程中各类的最佳比例。说话人识别结果证明,与基线系统相比,该方法的错误率提高了18%。

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