基于GFCC与RLS的说话人识别抗噪系统研究

计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (10): 215-218.

基于GFCC与RLS的说话人识别抗噪系统研究

茅正冲，王正创，黄芳

江南大学轻工过程先进控制教育部重点实验室，江苏无锡 214122

出版日期:2015-05-15 发布日期:2015-05-15

Speaker recognition anti-noise system research based on RLS and GFCC

MAO Zhengchong, WANG Zhengchuang, HUANG Fang

Key Laboratory of Advanced Process Control for Light Industry（Ministry of Education）, Jiangnan University, Wuxi, Jiangsu 214122, China

Online:2015-05-15 Published:2015-05-15

摘要/Abstract

摘要： 为了提高说话人识别抗噪系统的性能，提出了将RLS自适应滤波器作为语音信号去噪的预处理器，进一步提高语音信号的信噪比，再通过Gammatone滤波器组，对去噪后的说话人语音信号进行处理，提取说话人语音信号的特征参数GFCC，进而将特征参数GFCC用于说话人识别系统中。仿真实验在高斯混合模型识别系统中进行。实验结果表明，采用这种方法应用于说话人识别抗噪系统，系统的识别率及鲁棒性都有明显的提高。

关键词: 抗噪系统, 递归式最小均方（RLS）, Grammatone频率倒谱系数（GFCC）, 识别率

Abstract: In order to improve the performance of speaker recognition system in noisy environment, a RLS adaptive filter as preprocessor to remove noise is presented, to further improve the SNR of speech signal, and then through the Gammatone filter bank to deal with the speech signal after denoising, extracting the feature parameter GFCC, which is used for speaker recognition. Simulation experiment is conducted with Gaussian mixture?model based speaker recognition system. The experimental results show that the proposed algorithm significantly improves system recognition rate and robustness in noisy environment.

Key words: anti-noise system, Recursivel East Squares（RLS）, Gammatone Frequency Cepstrum Confficient（GFCC）, recognition rate

茅正冲，王正创，黄芳. 基于GFCC与RLS的说话人识别抗噪系统研究[J]. 计算机工程与应用, 2015, 51(10): 215-218.

MAO Zhengchong, WANG Zhengchuang, HUANG Fang. Speaker recognition anti-noise system research based on RLS and GFCC[J]. Computer Engineering and Applications, 2015, 51(10): 215-218.

[1]	邹柏贤1，3，苗军2，许少武2，逯燕玲1. 基于ELM算法的光纤振动信号识别研究[J]. 计算机工程与应用, 2017, 53(16): 126-133.
[2]	满蔚仕，王建华，张志禹. 基于二维快速广义S变换的人脸识别研究[J]. 计算机工程与应用, 2017, 53(11): 199-205.
[3]	闫喜亮1，王黎明2. 卷积深度神经网络的手写汉字识别系统[J]. 计算机工程与应用, 2017, 53(10): 246-250.
[4]	茅正冲，王正创，王丹. 基于Gammatone滤波器组的说话人识别算法研究[J]. 计算机工程与应用, 2015, 51(1): 200-203.
[5]	毛建鑫，刘炜，侯秋华，孙红彬. 一种改进的水果特征提取算法[J]. 计算机工程与应用, 2013, 49(6): 225-228.
[6]	李孟歆^1,2,吴成东¹,夏兴华². 一种基于分级RBF网络的车牌字符识别方法[J]. 计算机工程与应用, 2008, 44(30): 213-216.