Research on the Speaker Identification Based on Short Utterance

JIANG Ye; TANG Zhen-min

您当前的位置：

首页 >

文章列表页 >

Research on the Speaker Identification Based on Short Utterance

更新时间：2025-07-16

- Research on the Speaker Identification Based on Short Utterance
- Acta Electronica Sinica Vol. 39, Issue 4, Pages: 953-957(2011)
- 作者机构：
  
  南京理工大学计算机科学与技术学院,江苏,南京,210094
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN913.2
- Published：2011
- 稿件说明：
移动端阅览
JIANG Ye, TANG Zhen-min. Research on the Speaker Identification Based on Short Utterance[J]. Acta Electronica Sinica, 2011, 39(4): 953-957.
DOI：

JIANG Ye, TANG Zhen-min. Research on the Speaker Identification Based on Short Utterance[J]. Acta Electronica Sinica, 2011, 39(4): 953-957. DOI：

摘要

针对短语音说话人辨认训练语料不充分的特点

对特征参数和GMM模型进行优化和改进

提出一种基于局部模糊PCA的GMM说话人辨认方法.该方法采用特征组合代替单一特征

以提高有效特征维数来弥补特征样本的不足

并用局部模糊PCA对组合特征进行有效降维

在对识别率影响很小的前提下

降低了系统的时空复杂度.本文还对GMM参数初始化方法进行改进

采用分裂法与模糊k均值聚类相结合方法.实验表明

与传统初始化方法相比该方法能有效提高短语音说话人辨认性能.

Abstract

For the inadequate training speech data of speaker identification based on short utterance

feature vectors and GMM models are optimized and improved

an efficient GMM based on local PCA with fuzzy clustering is presented.To compensate for the limited feature samples

the effective feature dimensions are increased with feature combinations instead of single feature.Furthermore

the time and space complexity of the system can be compressed by reducing dimensions of feature combinations with local fuzzy PCA in the premise of little effect on recognition rate.Finally

a new approach which combines division and fuzzy k-means clustering is used

in order to optimize GMM initialization parameters.The experiments show that the improved method is more effective in improving performance of the system than traditional initialization methods.

关键词

Keywords

references

Views

1330

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

TFA-Conformer Based Network for Short Utterance Speaker Recognition

Application of Hadamard ECOC in Multi-Class Problems Based on SVM

Related Author

YANG Lu

ZHANG Bang-cheng

YANG Jun-mei

ZENG De-lu

YIN An-rong

XIE Xiang

KUANG Jing-ming

Related Institution

School of Electronics and Information Technology, South China University of Technology

Department of Electronics Engineering,Beijing Institute of Technology

⁰