Research on Hierarchical Speaker Recognition Based on Speaker Clustering Technology

LIU Wen-ju; SUN Bing; ZHONG Qiu-hai

您当前的位置：

首页 >

文章列表页 >

Research on Hierarchical Speaker Recognition Based on Speaker Clustering Technology

更新时间：2025-07-16

- Research on Hierarchical Speaker Recognition Based on Speaker Clustering Technology
- Acta Electronica Sinica Vol. 33, Issue 7, Pages: 1230-1233(2005)
- 作者机构：
  
  1. 中科院自动化所模式识别国家重点实验室,北京,100080
  2. 北京理工大学自动控制系,北京,100081
  3. 中科院自动化所模式识别国家重点实验室北京,100080
  4. 北京理工大学自动控制系北京,100081
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.34
- Published：2005
- 稿件说明：
移动端阅览
LIU Wen-ju, SUN Bing, ZHONG Qiu-hai. Research on Hierarchical Speaker Recognition Based on Speaker Clustering Technology[J]. Acta Electronica Sinica, 2005, 33(7): 1230-1233.
DOI：

LIU Wen-ju, SUN Bing, ZHONG Qiu-hai. Research on Hierarchical Speaker Recognition Based on Speaker Clustering Technology[J]. Acta Electronica Sinica, 2005, 33(7): 1230-1233. DOI：

摘要

识别正确率和抗噪性能固然是说话人识别的研究重点

但识别响应速度也是决定系统实用化的关键所在.本文成功地提出了基于说话人分类技术的分级说话人辨识方法

极大地提高了系统运行速度

随着注册说话人数的增多

较之传统的说话人辨识方法

其优势更加明显.同时在说话人确认中

该方法的使用

进一步提高了确认的正确率

有效地降低了错误接受和错误拒绝率.本文提出的可信度打分方法

也一定程度上改进了系统的性能.实验表明:基于说话人分类技术的说话人辨识方法使系统的运行速度平均提高了3.5倍

对说话人确认等误识率和最小误识率平均下降了53.75%.

Abstract

Recognition correct rate and noise robust property are indeed important for speaker recognition research

but the response rate of recognition is also a key factor for a speaker recognition system when applied in the real world.Owing to this

we propose a novel speaker identification approach based on speaker clustering

namely Hierarchical Speaker Identification (HSI).It can increase the running speed greatly for speaker identification systems

and the more the number of registered speakers is

the faster the HSI system runs than the Conventional Speaker Identification (CSI) system.Simultaneously

its counterpart for speaker verification based on speaker clustering

can reduce the rates of false rejection and false acceptance efficiently to improve the capability of verification.A new method is also presented here called reliability scoring.The experiments show that speaker clustering based algorithms can run faster 3.5 times than original approach for the speaker identification and is 53.75% deduction of equal or minimal error rates for the speaker verification on average.

关键词

Keywords

references

Views

1072

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bayesian Principal Component Analysis for I-Vector Speaker Verification

Robust Speaker Verification Under Additive Noise Condition

The Speaker Verification System Based on Neurocomputer and Its Application

Related Author

RONG Ya-feng

CHEN Chen

CHEN De-yun

HE Yong-jun

GUO Wu

LI Yi-jie

DAI Li-rong

WANG Ren-hua

Related Institution

School of Computer Science and Technology， Harbin University of Science and Technology

Postdoctoral Research Station of Computer Science and Technology， Harbin University of Science and Technology

Department of Electronic Engineering and Information Science,University of Science and Technology of China

School of Computer Science and Engineering, Nanjing University of Science and Technology

1 Institute of Semiconductors,Chinese Academy of Sciences

⁰