高斯混合模型下的残留回波抑制算法

您当前的位置：

首页 >

文章列表页 >

高斯混合模型下的残留回波抑制算法

更新时间：2025-07-09

- 高斯混合模型下的残留回波抑制算法
- Issue 4, Pages: 11-16(2013)
- 作者机构：
  
  1. 西安交通大学电子与信息工程学院
  2. 中兴通讯股份有限公司
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.3
- Published：2013
- 稿件说明：
移动端阅览
[J]. 2013, (4): 11-16.
DOI：

[J]. 2013, (4): 11-16. DOI：

摘要

为提高通话环境中的回波抑制效果

提出了基于高斯混合模型下的残留回波抑制方法。首先以线性预测系数为特征提取近端用户语音的特征向量

然后在高斯混合模型下对其进行训练

得到用户语音模板

通过对比用户语音模板和残留回波信号特征向量

判断非用户语音帧

最后将非用户语音帧予以消除。仿真实验结果表明

所提算法能正确区分用户语音帧与非用户语音帧

具有更好的回波抑制效果。在误判率约为1%～2%的情况下

可将自适应滤波器的回波消除量提高7～10dB。

Abstract

关键词

Keywords

references

{"db_type":"CJFDREF","db_name":"期刊","reference_articles":[{"unit":"计算机工程","flag":"[J]","issue":"04","year":2011,"author":"张学锋;王芳;夏萍","index":1,"title":"融合LPC与MFCC的特征参数"},{"unit":"现代电子技术","flag":"[J]","issue":"07","year":2009,"author":"曹华;李伟;谭艳梅","index":2,"title":"线性预测及其Matlab实现"},{"unit":"电子学报","flag":"[J]","issue":"02","year":2000,"author":"王永德,王春霞","index":3,"title":"一种改进的快速LMS/Newton算法及其在声回波对消中的应用"}],"articles_count":3}

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Integrated and Joint Design Optimization of Centrifugal Compressor Impeller and Casing Treatment at Multiple Working Points

Effects of Expansion Angle Crater Film Hole on the Film Cooling Characteristics of a Double-Wall Structure

Study on the Thermodynamic Properties in the Anomalous Region of Supercritical Water

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Knowledge Graph Representation Learning Driven by Semantic Discrimination and Subgraph Integration

Related Author

No data

Related Institution

No data

⁰