本文提出一种鲁棒语音特征提取框架。通过使用一种基于子带能量分布的噪声估计方法,无需静音段,就可以估计出带噪语音的子带噪声,同时提出结合谱减和谱加权方法对特征进行处理,最终生成具有较高鲁棒性的特征。
实验证明,在语音识别系统中,这种特征可以有效提高语音识别的鲁棒性,在噪声较强(信噪比0dB到15dB)的情况下,识别率可以提高20%以上;并且,在干净语音的情况下又能保证识别率没有大的下降;同时,这种特征上的处理方法对各种噪声的适应能力都很强,无需对噪声进行预先分类即可得到很好的抗噪效果。
Abstract
In this paper ,we propose a new method to integrate the sub - band information into features via both the sub - band weighting and the spectral subtraction for robust speech recognition. In this method ,just simple on - line noise estimation and sub - band processing where the sub - bands divided by the filter banks of common MFCC Calculation are added into the traditional MFCC calculation algorithm to achieve the robust MFCC ,without any prior knowledge of the noise. Furthermore ,other robust methods after the feature extraction step can be used together with this method to obtain high recognition performance in adverse environments. Experiments show that the new robust MFCC yields good recognition results compared with the traditional feature. Forexample ,at 5 to 10dB SNR , it can reduce the error rate by over 20% compared with the traditional MFCC.
关键词
语言识别 /
噪声估计 /
鲁棒语音特征
{{custom_keyword}} /
Key words
Speech Recognition /
Noise Estimation /
Robust feature
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] H. Hermansky , S. Tibrewala ,and M. Pavel , Towards ASR on partially corrupted speech , International Conference on Spoken Language Processing ,Philadelphia ,October 1996
[2] Okawa ,S. ,E.Bocchieri and A. Potamianos ,Multi-band speech recognition in noisy environments ,in Proceedings of ICASSP’98 ,pp. 641 - 644 ,Seattle ,Washington ,USA ,1998
[3] H. Fletcher ,Speech and Hearing in Communication ,Krieger ,New York ,1953
[4] M. Cooke ,A. Morris ,and P. Green ,Recognising occluded speech ,in Proceedings of the ESCA Workshop on the auditory basis of speech perception ,1996 ,297 - 300
[5] L. Deng ,A. Acero ,M. Plumpe and X. Huang ,Large-Vocabulary Speech Recognition under Adverse Acoustic Environments , Int. Conf. on Spoken Language Processing ,Beijing ,China ,Oct 2000
[6] H. G. Hirsch ,and C. Ehrlicher ,Noise Estimation Technique for Robust Speech Recognition ,in Proc. ICASSP’95 ,May 1995 ,153 - 156
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(319 KB)
