• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of information and computational science >Adaptive Linear Prediction Based on Compressed Sensing Algorithm for Speech Data
【24h】

Adaptive Linear Prediction Based on Compressed Sensing Algorithm for Speech Data

机译：基于压缩感知算法的语音数据自适应线性预测

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 the linear residual domain, the characteristics of linear prediction based on compressed sensing and analytical methods for the speech data are studied. Here we put forward a compressed sensing algorithm based on adaptive distribution of observed points in linear residual domain. The observed points are distributed in proportion to be occupied energy of each frame speech for overall speech data, so the features of speech data can be differentiated by energy among each speech frames. Simulation results demonstrate that reconstruction performance of speech data with the proposed algorithm in linear residual domain is better than that of the traditional compressed sensing algorithm. The algorithm not only has relatively high segmental Signal to Noise Ratio (SNR) but also provides better mean opinion score.
机译：在线性残差域中，研究了基于压缩感知和分析方法的语音数据线性预测的特征。这里我们提出了一种基于线性残差域中观测点自适应分布的压缩感知算法。观测点按比例分配，以占整体语音数据的每个帧语音所占的能量，因此可以通过每个语音帧之间的能量来区分语音数据的特征。仿真结果表明，该算法在线性残差域中的语音数据重建性能优于传统的压缩感知算法。该算法不仅具有较高的分段信噪比（SNR），而且还提供了更好的平均意见评分。

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