An Improved HMM for Robust Speaker Recognition

LIU Ming; DAI Bei-qian; LI Hui; LU Wei; LI Xiao-han

您当前的位置：

首页 >

文章列表页 >

An Improved HMM for Robust Speaker Recognition

更新时间：2025-07-16

- An Improved HMM for Robust Speaker Recognition
- Acta Electronica Sinica Vol. 30, Issue 1, Pages: 46-48(2002)
- 作者机构：
  
  中国科学技术大学电子科学与技术系,安徽,合肥,230026
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：2002
- 稿件说明：
移动端阅览
LIU Ming, DAI Bei-qian, LI Hui, et al. An Improved HMM for Robust Speaker Recognition[J]. Acta Electronica Sinica, 2002, 30(1): 46-48.
DOI：

LIU Ming, DAI Bei-qian, LI Hui, et al. An Improved HMM for Robust Speaker Recognition[J]. Acta Electronica Sinica, 2002, 30(1): 46-48. DOI：

摘要

为了提高话者识别系统的噪声鲁棒性

本文对CHMM 进行了改进

将每帧特征参数之间的差分参数来对应状态之间的转移

从而使帧间信息在模型中得到了体现.利用改进后的CHMM模型对不同的特征参数携带的信息进行信息融合.使得在强噪环境下

鲁棒性好的特征参数起主导作用

而在噪声比较小的环境下

精细度高的特征参数起主导作用.实验证明

这种改进的马尔可夫模型明显提高语音识别系统的鲁棒性能

这种技术具有良好的发展和应用前景.

Abstract

A modified CHMM model is proposed to improve the robustness of the speaker recognition system.In the modified model

the difference of the speech feature parameter was the observed vectors of the state-transitions of CHMM.Because of the modification

the dependence between frames was used in the modified CHMM.By the fusion of different features

the robust feature will dominate under the noisy environment and the delicate feature will dominate under clean environment.The experiments indicate that the modified CHMM have effectively improved the robustness of the speaker recognition system.

关键词

Keywords

references

Views

1214

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Robust Resource Allocation Algorithm for Secure Communication in LEO-Based Satellite Communication Systems

Robust Energy-Efficient Optimization Algorithm for Intelligent Reflecting Surface-Aided MU-MISO Communication Systems with Hardware Impairments and Discrete Phases

A Review of the Robust Technology of mMIMO Millimeter-Wave High-Speed Communication System

Dual Attention-Guided Detail and Structure Information Fusion Network for Image Dehazing

Research on Recombination Operator and Multi-Objective Optimization Based on Fitness Guided Mating Restriction Strategy

Related Author

XU Yong-jun

LU Cheng-zhuang

DONG Yi-heng

ZHAO Tao

ZHOU Ji-hua

FU Xiao-jian

XIONG Ying-xiang

XU Yong-jun

Related Institution

School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications

Aerospace New Generation Communications Co., Ltd.

State Key Laboratory of Millimeter Waves, Southeast University

School of Communications and Information Engineering， Chongqing University of Posts and Telecommunications

College of Information Science & Electronic Engineering， Zhejiang University

⁰