• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference of the Catalan Association for Artificial Intelligence >A New Algorithm for Speech Enhancement Based on Multivariate Empirical Mode Decomposition
【24h】

A New Algorithm for Speech Enhancement Based on Multivariate Empirical Mode Decomposition

机译：一种新的语音增强算法基于多变量经验模式分解的语音增强

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

摘要

Nowadays many systems use speech as a way to interact with them. Therefore, machine learning systems are needed to perform various tasks on these recordings. But speech signals in a real environment are usually mixed with some other signals, such as noise. This may interfere with posterior signal processing applied to the signals. In this work, a new technique of data denoising is presented using Multivariate Empirical Mode Decomposition. To analyse the efficiency of the proposed technique we perform experiments with two microphones and four speakers. Different signal-to-noise ratios are checked in order to study the evolution of the improvement of the recovered data. An improvement of the analyzed data is obtained in all the cases, suggesting that this method could be used as a pre-enhancement step in speech processing algorithms.
机译：如今，许多系统使用言语作为与他们交互的方式。因此，需要机器学习系统在这些录像上执行各种任务。但是真实环境中的语音信号通常与其他一些信号混合，例如噪声。这可能干扰应用于信号的后部信号处理。在这项工作中，使用多元经验模式分解来提出一种新的数据去噪技术。分析所提出的技术的效率，我们用两个麦克风和四位扬声器进行实验。检查不同的信噪比以研究恢复数据的改进的演变。在所有情况下获得分析数据的改进，暗示该方法可以用作语音处理算法中的预增强步骤。

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