基于卷积神经网络分类的说话人识别算法

doi:10.3969/j.issn.1671-1122.2016.04.009

信息网络安全 ›› 2016, Vol. 16 ›› Issue (4): 55-60.doi: 10.3969/j.issn.1671-1122.2016.04.009

基于卷积神经网络分类的说话人识别算法

胡青¹, 刘本永^1,²()

1. 贵州大学大数据与信息工程学院,贵州贵阳 550025
2. 贵州大学智能信息处理研究所,贵州贵阳 550025

收稿日期:2016-01-18 出版日期:2016-04-20 发布日期:2020-05-13
作者简介:
作者简介：胡青（1989—）,男,安徽,硕士研究生,主要研究方向为声纹识别;刘本永（1966—）,男,贵州,教授,博士,主要研究方向为图像处理、模式识别。
基金资助:
国家自然科学基金[60862003];科技部国际合作项目[2009DFR10530];贵州大学研究生创新基金[2015081]

Speaker Recognition Algorithm Based on Convolutional Neural Networks

Qing HU¹, Benyong LIU^1,²()

1. College of Big Data and Information Engineering, Guizhou University, Guiyang Guizhou 550025, China
2. Institute of Intelligent Information Processing, Guizhou University, Guiyang Guizhou 550025, China

Received:2016-01-18 Online:2016-04-20 Published:2020-05-13

摘要/Abstract

摘要：

由于经典的说话人识别算法都是将特征提取和模式分类分开进行的,这导致特征的选取对分类影响很大,更增加了算法的复杂度。利用卷积神经网络（CNN）的结构优势,文章提出一种基于卷积神经网络分类的说话人识别算法。算法首先对原始语音信号计算语谱图,对获得的语谱图采用卷积神经网络进行分类,分类的结果即为类别。通过真实语音库和TIMIT库测试表明,本算法取得了较高的识别率,说明这是一种有效的说话人识别方法。

关键词: 卷积神经网络, 说话人识别, 语谱图

Abstract:

Feature extraction and pattern classification are two separated part in classical algorithms for speaker recognition, wherein the choice of features has much influence on classification, and thus algorithm complexity is generally increased. In this manuscript we propose to use the structure advantage of convolutional neural network(CNN) to form a new speaker recognition algorithm. The algorithm firstly computes the spectrograms of a speech signal, then using CNN for classification. Experimental results based on self-built database and the TIMIT database show that the presented algorithm is effective in speaker recognition.

Key words: convolutional neural network, speaker recognition, spectrogram

中图分类号:

TP309

胡青, 刘本永. 基于卷积神经网络分类的说话人识别算法[J]. 信息网络安全, 2016, 16(4): 55-60.

Qing HU, Benyong LIU. Speaker Recognition Algorithm Based on Convolutional Neural Networks[J]. Netinfo Security, 2016, 16(4): 55-60.

图/表 11

图1

图2

图3

图4

图5

表1

表2

图6

表3

表4

图7

参考文献 23

[1]	王韵琪,俞一彪.自适应高斯混合模型及说话人识别应用[J]. 通信技术, 2014, 47(7): 738-739.
[2]	鲁晓倩. 基于VP树和GMM的说话人识别研究[D].合肥:中国科学技术大学,2014.
[3]	ATAL B S.Automatic Recognition of Speaker from Their Voices[J]. IEEE Transaction on Acoustics, Speech, and Signal Processing, 1976, 64(4): 460-475.
[4]	DAVIS S B, MERMELSTEIN P.Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1980, 28(4): 357-366.
[5]	LAWRENCE R.Fundamentals of Speech Recognition[M]. India:Pearson Education India, 2008.
[6]	DAVENPORT M R, GARUDADRI H.A Neural Net Acoustic Phonetic Feature Extractor Based on Wavelets[C]// IEEE. Pacific Rim Conference on Communications, Computers and Signal Processing, May 9-10, 1991, Victoria, B. C., CANADA. NJ: IEEE, 1991: 449-452.
[7]	刘鸣,戴蓓倩,李辉,等.基于离散小波变换和感知频域滤波的语音特征参数.[J]电路与系统学报,2000,10(1):21-25.
[8]	NÁDAS A, NAHAMOO D, PICHENY M A. Speech Recognition Using Noise-adaptive Prototypes[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1989, 37(10): 1495-1503.
[9]	COLOMBI J M, RUCK D W, ANDERSON T R, et al.Cohort Selection and Word Grammar Effects for Speaker Recognition[C]//IEEE. International Conference on Acoustics, Speech and Signal Processing, May 7-10, 1996, Atlanta, Georgia. NJ: IEEE, 1996: 85-88.
[10]	REYNOLDS D A, CARLSON B A.Text-dependent Speaker Verification Using Decoupled and Integrated Speaker and Speech Recognizers[C]//IEEE. 4th European Conference on Speech Communication and Technology. September 18-21, 1995, Madrid, Spain.NJ: IEEE, 1995: 2201-2204.
[11]	SEO J, HONG S, GU J, et al.New Speaker Recognition Feature Using Correlation Dimension[C]// IEEE. International Symposium on Industrial Electronics, June 12-16, 2001,Pusan, Korea.NJ: IEEE, 2001: 505-507.
[12]	HOSSAN M A, MEMON S, GREGORY M A.A Novel Approach for MFCC Feature Extraction[C]// IEEE. 4th International Conference on Signal Processing and Communication Systems, December 13-15, 2010, Gold Coast, Australia. NJ: IEEE, 2010: 1-5.
[13]	SAKOE H, CHIBA S.Dynamic Programming Algorithm Optimization for Spoken Word Recognition[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1978, 26(1): 43-49.
[14]	SOONG F K, ROSENBERG A E, JUANG B H, et al.Report: A Vector Quantization Approach to Speaker Recognition[J]. AT&T Technical Journal, 1987, 66(2): 14-26.
[15]	RABINER L R.A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition[J]. Proceedings of the IEEE, 1989, 77(2): 257-286.
[16]	OGLESBY J, MASON J S.Optimisation of Neural Models for Speaker Identification[C]//IEEE. International Conference on Acoustics, Speech and Signal Processing, April 3-6, 1990, Albuquerque, New Mexico. NJ: IEEE, 1990: 261-264.
[17]	REYNOLDS D A, ROSE R C.Robust Text-independent Speaker Identification Using Gaussian Mixture Speaker Models[J]. IEEE Transactions on Speech and Audio Processing, 1995, 3(1): 72-83.
[18]	AUCKENTHALER R, PARRIS E S, CAREY M J.Improving a GMM Speaker Verification System by Phonetic Weighting[C]// IEEE, International Conference on Acoustics, Speech and Signal Processing, March 15-19, 1999, Phoenix, Arizona. NJ: IEEE, 1999: 313-316.
[19]	REYNOLDS D A, QUATIERI T F, DUNN R B.Speaker Verification Using Adapted Gaussian Mixture Models[J]. Digital Signal Processing, 2000, 10(1): 19-41.
[20]	WU D, LI J, WU H.α-gaussian Mixture Modelling for Speaker Recognition[J]. Pattern Recognition Letters, 2009, 30(6): 589-594.
[21]	VENTURINI A, ZAO L, COELHO R.On Speech Features Fusion, α-integration Gaussian Modeling and Multi-Style Training for Noise Robust Speaker Classification[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014, 22(12): 1951-1964.
[22]	WAN V, CAMPBELL W M.Support Vector Machines for Speaker Verification and Identification[C]//IEEE. Signal Processing Society Workshop, December 11-13, 2000, Sydney, Australia. NJ: IEEE, 2000: 775-784.
[23]	蔡娟,蔡坚勇,廖晓东,等.基于卷积神经网络的手势识别初探[J]. 计算机系统应用,2015,24(4):113-117.

基于卷积神经网络分类的说话人识别算法

Speaker Recognition Algorithm Based on Convolutional Neural Networks

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 23

相关文章 3

编辑推荐

Metrics

本文评价

[1]	王蓉, 马春光, 武朋. 基于联邦学习和卷积神经网络的入侵检测方法[J]. 信息网络安全, 2020, 20(4): 47-54.
[2]	龙敏, 龙啸海, 马莉. 基于深度卷积神经网络的指纹活体检测算法研究[J]. 信息网络安全, 2018, 18(6): 28-35.
[3]	夏玉明, 胡绍勇, 朱少民, 刘丽丽. 基于卷积神经网络的网络攻击检测方法研究[J]. 信息网络安全, 2017, 17(11): 32-36.