针对语音识别实际应用过程中的噪声问题,给出了一种新的抗噪声的特征提取算法,即先利用小波变换将语音信号进行小波子带分解,再根据人耳的听觉掩蔽效应,由谱压缩的技术,将小波变换后的子带语音信号进行压缩,从而提取其对应的语音特征.通过MATLAB软件建立实验平台,仿真实验结果表明该语音特征可以在噪声环境下得到较高的识别率.新的特征参数即充分利用了小波的抗噪声特性又有效地降低了语音识别中的训练环境和识别环境间的失配,具有抗噪声的特点.
参考文献
| [1] | Mansour D,Juang B H.Senior Member.The short-time modified coherence representation and noisy speech recognition[J].IEEE Transactions on Acoustics Speech and Signal Processing,1989,37:795-804 |
| [2] | Ning Gengxin.Research on Novel Robust Speech Recognition(抗噪声语音识别新技术的研究)[DI·Guangzhou:Doc.torial Dissertation of South China University of Technology,2006.(in Chinese). |
| [3] | Stephane M.A Wavelet Tour of Signal Processing(信号处理的小波导引)[M].Beijing:China Machine Press,2002-3-5(in Chinese). |
| [4] | Plack C J,et al.Forward masking additivity and auditory compression at low and high frequencies[J].Journal of the Association for Research in Otolaryngology,2003,4(3):405-415. |
| [5] | Yasin I,Plack C J.The role of suppression in the upward spread of masking[J].Journal of the Association for Research in Otolaryngology,2005,6(4):368-377. |
| [6] | Zwicker E,Fasti K.Psycho-acoustics,Facts and Model[M].2nd Ed.,Springer-Verlag,1999. |
| [7] | Jesteadt W,et al.Forward masking as a function of frequency,masker level,and signal delay[J].J.Acoust.Soc.Am.,1982,71(4):950-961. |
| [8] | Stevens S S.The direct estimation of sensory magnitudes:loundness[J].Am.J.Psych.,1995,69:1-25. |
| [9] | Kong Chao,Fang Yonghua,Lan Tiange.A boundary prolongation method based on orthogonal polynomial fitting in wavelet transform[J].Chinese Journal of Quantum Electronics(量子电子学报),2008,25(1):25-28(in Chinese). |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%