[1]刘菁华.一种改进的语音识别抗噪算法[J].华侨大学学报(自然科学版),2009,30(1):117-118.[doi:10.11830/ISSN.1000-5013.2009.01.0117]
　LIU Jing-hua.A Improved Method for Robust Speech Recognition[J].Journal of Huaqiao University(Natural Science),2009,30(1):117-118.[doi:10.11830/ISSN.1000-5013.2009.01.0117]
点击复制

一种改进的语音识别抗噪算法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第30卷
期数:
2009年第1期
页码:
117-118
栏目:
出版日期:
2009-01-20

文章信息/Info

Title:
A Improved Method for Robust Speech Recognition
文章编号:
1000-5013(2009)01-0117-02
作者:
刘菁华
华侨大学信息科学与工程学院
Author(s):
LIU Jing-hua
College of Information Science and Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
语音识别;  抗噪算法;  语音增强;  信噪比
Keywords:
speech recognition;  antinoise arithmetic;  speech enhancement;  signal-to-noise ratio
分类号:
TN912.34
DOI:
10.11830/ISSN.1000-5013.2009.01.0117
文献标志码:
A
摘要:
为了提高在噪声环境下的语音识别性能,提出一种融合信号级和特征参数级抗噪的抗噪算法.该算法首先对带噪语音用最小均方误差估计法进行语音增强,后端对原始的带噪语音运用自相关法,以有效抑制加性和卷积噪声.实验结果表明,该算法能有效提高系统在噪声环境下,特别是低信噪比情况下的识别率.
Abstract:
In order to improve the speech recognition accuracy in noisy environments,an algorithm proposed,which combines the signal level with the characteristic parameter level antinoise algorithm.At first,MMSE algorithm is used for the speech enhacement module,and then,new robust features RAS-MFCC effectively suppressed the additive and convolutional noise.The results show that this algorithm effectively improves the speech recognition accuracy in noisy environments,especially in low signal-to-noise ratio(SNR) conditions.

参考文献/References:

[1] DONOHO D L. De-noising by soft-thresholding [J]. IEEE Transactions on Information theory, 1995(3):613-627.doi:10.1109/18.382009.
[2] VIIKI O, BYE D, LAYRUKA K. A recursive feature vector normalization approach for robust speech recognition in noise [A]. 1998.733-736.
[3] YOU K H, WANG H C. Robust features derived from temporal trajectory filtering for speech recognition under the corruption of additive and convolutional noises [A]. 1998.577-580.
[4] VAN COMPERNOLLE D. Noise adaptation in the hidden markov model speech recognition system [J]. Computer Speech and Language, 1987.151-168.
[5] GALES M J F, YOUNG S J. Robust continuous speech recognition using parallel model combination [J]. IEEE Transations on Speech and Audio Processing, 1996(5):352-359.
[6] 丁沛, 曹志刚. 融合语音增强与后续补偿的抗噪声语音识别方法 [J]. 清华大学学报(自然科学版), 2003(7):919-922.doi:10.3321/j.issn:1000-0054.2003.07.017.

更新日期/Last Update: 2014-03-23