An Auditory Feature Extraction Algorithm Based on γ-Tone Filter-Banks

WANG Yue; QIAN Zhi-hong; WANG Xue; CHENG Guang-ming

您当前的位置：

首页 >

文章列表页 >

An Auditory Feature Extraction Algorithm Based on γ-Tone Filter-Banks

更新时间：2025-07-16

- An Auditory Feature Extraction Algorithm Based on γ-Tone Filter-Banks
- Acta Electronica Sinica Vol. 38, Issue 3, Pages: 525-528(2010)
- 作者机构：
  
  1. 吉林大学,吉林,长春,130025
  2. 国家知识产权局,北京,100190
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN912.3
- Published：2010
- 稿件说明：
移动端阅览
WANG Yue, QIAN Zhi-hong, WANG Xue, et al. An Auditory Feature Extraction Algorithm Based on γ-Tone Filter-Banks[J]. Acta Electronica Sinica, 2010, 38(3): 525-528.
DOI：

WANG Yue, QIAN Zhi-hong, WANG Xue, et al. An Auditory Feature Extraction Algorithm Based on γ-Tone Filter-Banks[J]. Acta Electronica Sinica, 2010, 38(3): 525-528. DOI：

摘要

本文从模拟人类听觉角度出发

给出了基于人耳耳蜗听觉模型的伽马通滤波器组模型

测试语音通过该滤波器组输出得到了高维听觉特征向量.经过主成分分析和离散余弦变换

分别得到了可用于表征说话人的伽马通系数和伽马通滤波器倒谱系数及其衍生特征.实验证明

与传统梅尔倒谱特征相比

采用本文提出特征的说话人识别系统在识别率及鲁棒性上均有明显提高.

Abstract

By means of emulating human auditory

γ-Tone filter-banks models based on the auditory system in human cochlea are presented. The speech to be detected goes through the γ-Tone filter-banks

thereby multi-dimension eigenvectors are obtained. By PCA (principal component analysis) and DCT (discrete cosine transform)

it is yielded to represent a speaker’s γ-Tone coefficients

γ-Tone filter-banks cepstral coefficients respectively and their derivative features as well. Compared to the ordinary Mel-frequency cepstral coefficients

the speaker recognition system presented turns out to have better recognition rate and robustness characteristics.

关键词

Keywords

references

Views

1804

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A New Consolidated Speech VBR Coding Method

Speech Enhancement Based on Minimum Mean-Square Error Short-Time Spectral Estimation and Residual Noise Reduction

Speech Enhancement Algorithms Using MMSE Estimation with Interframe Constraints

Chaos and Fractal Theories for Speech Signal Processing

A Method to Estimate the Parameters of the Vocal－Tract Area Function from Formant Frequencies of Speech Signal

Related Author

YANG Zhen

ZHENG Bao-yu

Cao Zbigang

Zheng Wentao

田滨

曹志刚

韦岗

陆以勤

Related Institution

南京邮电学院165信箱

Dept. of Electronic Engineering, Tsinghua Univ.

清华大学电子工程系北京 100084

Dept.of Electronic Engineering,Tsinghua University

Institute of Radio Engineering & Automatic Control.South China University ofTechnology

⁰