首页> 中文期刊> 《黑龙江科学》 >基于声诊的煤矿工人健康状态分析的关键技术研究

基于声诊的煤矿工人健康状态分析的关键技术研究

         

摘要

In this paper, acoustic parameters are analyzed by phonological phonetic representation of coal worker′s pneumoconiosis, and the characteristics of Mel S transform coefficients are used to describe the non-stationary characteristics of mutated speech signals.In this paper, we propose a nonlinear feature to describe the speech variation caused by the variation of vocal cords.At the same time, aiming at the redundancy problem of high dimensional feature, the feature set is proposed to be fused with auditory processing model.%本文通过病理语音代表煤工尘肺等疾病状态下的语音进行声学参数分析,提出梅尔S变换系数特征来描述变异语音信号的非平稳特性.针对声带形状变异造成的语音变异,提出非线性特征来描述,同时针对高维特征的冗余问题,提出利用听觉加工模型对特征集进行融合.

著录项

相似文献

  • 中文文献
  • 外文文献
  • 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