Speaker Recognition Based on Improved Mel Hybrid Parameters

HUANG Ting; ZHOU Ping; JING Xin-xing; YANG Qing

Chinese

您当前的位置：

首页 >

文章列表页 >

Speaker Recognition Based on Improved Mel Hybrid Parameters

更新时间：2026-09-04

- Speaker Recognition Based on Improved Mel Hybrid Parameters
- Vol. 33, Issue 4, Pages: 60-63(2016)
- 作者机构：
  
  1. 桂林电子科技大学机构电子工程与自动化学院,广西,桂林,541004
  2. 桂林电子科技大学信息与通信学院,广西,桂林,541004
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2016
- 稿件说明：
移动端阅览
黄婷, 周萍, 景新幸, 杨青. 改进型Mel混合参数应用于说话人识别[J]. 微电子学与计算机, 2016, 33(4): 60-63, 68.

HUANG Ting, ZHOU Ping, JING Xin-xing, et al. Speaker Recognition Based on Improved Mel Hybrid Parameters[J]. 2016, 33(4): 60-63.
黄婷, 周萍, 景新幸, 杨青. 改进型Mel混合参数应用于说话人识别[J]. 微电子学与计算机, 2016, 33(4): 60-63, 68. DOI：

HUANG Ting, ZHOU Ping, JING Xin-xing, et al. Speaker Recognition Based on Improved Mel Hybrid Parameters[J]. 2016, 33(4): 60-63. DOI：

摘要

在实验室录音设备条件下

提取基于Mel的特征参数及其差分倒谱系数(DCC)和差分频谱倒谱系数(DSCC)

利用增减分量法进行有效融合

建立基于VQ的说话人识别模型

采用LBG算法设计不同码本容量进行说话人识别实验

并在各类噪声环境下验证混合参数性能.实验结果表明

与单一参数及其他融合参数相比该混合特征参数具有更高的识别率和鲁棒性.

Abstract

With the recording voice library in the laboratory

we extract Mel frequency cepstral coefficient

its delta-cepstral coefficient and delta-spectral cepstral coefficient

and fuse them with change component method effectively. And a speaker recognition model is established based on VQ model using LGB algorithm to design different codebook capacity for the experiment and we evaluate the hybrid feature parameters in noise environments. Experimental results show that by applying the fusion hybrid feature parameters the recognition system rate and robustness are obviously improved compared with other parameters.

关键词

Keywords

references

蒋晔. 基于短语音和信道变化的说话人识别研究[D]. 南京: 南京理工大学, 2013.

毛旭. 说话人检索系统的研究与实现[D]. 大连: 大连理工大学, 2009.

宋乐. 基于说话人识别中改进特征提取算法的研究[D]. 太原: 太原理工大学, 2014.

张宇. 基于倒谱特征的说话人识别方法研究[D]. 大连: 大连海事大学, 2010.

Chanwoo Kim, Richard M Stern. Power-normalized cepstral coefficients (PNCC) for robust speech recognition[C]//IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings. [s. l. ]: IEEE, 2012: 4101-4104.

Kshitiz Kumar, Chanwoo Kim, Richard M Stern. Delta-spectral cepstral cofefficents robust speech recognition[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. [s. l. ]: IEEE, 2011: 4784-4787.

胡政权, 曾毓敏, 宗原, 等. 说话人识别中MFCC参数提取的改进[J]. 计算机工程与应用, 2014, 50(7): 217-220. DOI: 217

姜占才, 孙燕, 姚刚. 模糊聚类与LBG级联的VQ算法[J]. 计算机工程与科学, 2011, 33(5) : 155-159. DOI: 155

王书诏, 邱天爽. 说话人识别研究综述[J]. 电声技术, 2007, 31(1): 51-55. DOI: 51

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Steganography model guided by attention mechanism and improved dense convolution

Efficient parameter fine-tuning of prefix label embedding and prediction score-guided Mixup text classification method

Adaptive robust watermarking based on AKAZE algorithm

Reversible watermarking algorithm based on ciphertext domain extension and DNA bidirectional coding

A Watermarking Method in Wavelet Domain Optimized by Firefly Algorithm

Related Author

ZHAO Li

WANG Libin

WANG Shumei

LIU Zhenshuai

HUANG Yuxin

XIANG Yan

XIAN Yantuan

PANG Yuhong

Related Institution

College of Computer Science and Technology, Jiangsu Normal University

Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology

Faculty of Information Engineering and Automation, Kunming University of Science and Technology

College of Physical Science and Technology, Central China Normal University

School of Statistics and Data Science, Xinjiang University of Finance and Economics

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰