基于瑞利混合隐马尔科夫模型的语音幅度谱分布估计

›› 2012, Vol. 42 ›› Issue (05): 1327-1330.

基于瑞利混合隐马尔科夫模型的语音幅度谱分布估计

王海艳, 赵晓晖, 顾海军

吉林大学通信工程学院信息科学实验室,长春 130012

收稿日期:2011-08-23 出版日期:2012-09-01 发布日期:2012-09-01
通讯作者: 赵晓晖(1957-),男,教授,博士生导师.研究方向:自适应信号处理理论与应用. E-mail:xhzhao@jlu.edu.cn E-mail:xhzhao@jlu.edu.cn
基金资助:
高等学校博士学科点专项科研基金项目(200801830037).

Probability distribution estimation of speech amplitude spectrum based on Rayleigh mixture hidden Markov model

WANG Hai-yan, ZHAO Xiao-hui, GU Hai-jun

Laboratory of Information Science, College of Communication Engineering, Jilin University, Changchun 130012, China

Received:2011-08-23 Online:2012-09-01 Published:2012-09-01

摘要/Abstract

摘要： 针对语音信号处理中语音短时幅度谱分布模型过于单一的问题,提出了一种基于隐马尔科夫模型的语音幅度谱分布估计算法。该算法利用瑞利混合模型作为语音幅度谱分布,采用隐马尔科夫模型将语音分成不同的状态,在每一状态中有一组瑞利混合模型参数与之相对应,通过把语音信号分成不同的状态对语音进行分类,为语音短时谱幅度建立更为准确的模型。

关键词: 语音信号处理, 瑞利混合模型, 隐马尔科夫模型

Abstract: To solve the problem of oversimplified speech short-time spectral amplitude distribution model in speech signal processing, an estimation method of speech amplitude spectrum based on hidden Markov model is proposed. This estimation method uses Rayleigh mixture model as speech amplitude spectrum distribution and employs hidden Markov model to divide speech signal into different states. In each state, there is accordingly a group of Rayleigh mixture model parameters. By the division of speech signal into different states, this method can achieve speech classification and build more accurate model for speech signal short term spectrum.

Key words: speech signal processing, Rayleigh mixture model, hidden Markov model

中图分类号:

TN912.3

王海艳, 赵晓晖, 顾海军. 基于瑞利混合隐马尔科夫模型的语音幅度谱分布估计[J]. , 2012, 42(05): 1327-1330.

WANG Hai-yan, ZHAO Xiao-hui, GU Hai-jun. Probability distribution estimation of speech amplitude spectrum based on Rayleigh mixture hidden Markov model[J]. , 2012, 42(05): 1327-1330.

参考文献

[1] 欧世峰,王显云,高颖,等. 基于两步噪声消除技术与高斯统计模型的语音增强算法[J].信号处理,2011,27(8):1171-1178. Ou Shi-feng, Wang Xian-yun, Gao Ying, et al.Speech enhancement based on two-step noise reduction and Gaussian statistical model[J]. Signal Processing,2011,27(8):1171-1178.
[2] 王海艳,赵晓晖. 基于语音清浊音分离的语音增强算法[J]. 吉林大学学报:工学版, 2011, 41 (4) : 1135-1139. Wang Hai-yan, Zhao Xiao-hui. Speech enhancement algorithm based on voiced/unvoiced discrimination[J]. Jilin University(Engineering and Technology Edition), 2011, 41 (4) : 1135-1139.
[3] Ephrain Yariv, Malah David. Speech enhancement using a minimum mean square error short-time spectral amplitude estimator[J]. IEEE Transaction on Acoustics, Speech, and Signal Processing, 1984,32(6):443-445.
[4] Lotter Thomas, Vary Peter. Speech enhancement by MAP spectral Amplitude estimation using a super Gauss speech model[J].EURASIP Journal on Applied Signal Processing, 2005,7:1110-1126.
[5] Erkelens J S, Jensen J, Heusdens R. Speech enhancement based on rayleigh mixture modeling of speech spectral amplitude distributions//EURASIP, Poznań, Poland, 2007.
[6] Karsten Vandborg Srensen, Sren Vang Andersen. Rayleigh mixture modeling and estimation of noise in noisy speech signals[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2007,15(3):901-917.
[7] Huang Xue-dong, Acero Alex, Hon Hsiao-Wuen. Spoken Language Processing: a Guide to Theory, Algorithm, and System Development[M]. New Jersey:Prentice Hall PTR, 2001.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed