Speech recognition based on combined enhancement of Symlets wavelet and subspace

Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (5): 141-145.

• 数据库、信号与信息处理 • Previous Articles Next Articles

Speech recognition based on combined enhancement of Symlets wavelet and subspace

WU Hao，LU Zhouxun

College of Electronics and Information Engineering，Nanjing University of Technology，Nanjing 210009，China

Received:1900-01-01 Revised:1900-01-01 Online:2011-02-11 Published:2011-02-11

Symlets小波和子空间联合增强下的语音识别

吴昊，鲁周迅

南京工业大学电子与信息工程学院，南京 210009

Abstract

Abstract: A combined method of Symlets wavelet and subspace is proposed based on experimental robustness comparison in Chinese speaker-dependent isolated word recognition against wavelet threshold diversification.The experiment built on Matlab utilizes VQ（Vector Quantization） and GMM（Gaussian Mixture Models） respectively based on MFCC（Mel Frequency Cepstrum Coefficient）.The way Symlets wavelet before subspace performs much better than the other order.Robustness of VQ system is strengthened distinctly after utilizing advantages of both methods.Aesthesis of auditory sense is improved，while the effect on GMM system is not so well as expectation.

Key words: Symlets wavelet, subspace, speech enhancement, speech recognition

摘要： 针对小波阈值选择的多样性，主要研究了小波自适应阈值消噪联合子空间增强对特定人汉语孤立词识别系统的鲁棒性提升。采用Mel倒谱系数，在基于矢量量化（VQ）和高斯混合模型（GMM）的两个系统上，检验采用联合Symlets小波多阈值消噪和子空间增强算法在互为先后顺序作用下系统的识别率，给出一个先Symlets小波阈值消噪再子空间增强的语音增强方法。人耳感官和Matlab实验证实该方法结合了两者的优点，不但平衡了语音失真和噪声抑制，亦可提高VQ系统的顽健性，而对于GMM系统作用有限。

关键词: Symlets小波, 子空间, 语音增强, 语音识别

WU Hao，LU Zhouxun. Speech recognition based on combined enhancement of Symlets wavelet and subspace[J]. Computer Engineering and Applications, 2011, 47(5): 141-145.

吴昊，鲁周迅. Symlets小波和子空间联合增强下的语音识别[J]. 计算机工程与应用, 2011, 47(5): 141-145.

[1]	SANG Jianghui, JIANG Haiyan. Multi-label Transfer Learning Algorithm Based on Joint Distribution Alignment [J]. Computer Engineering and Applications, 2021, 57(9): 154-161.
[2]	WANG Shiqi, ZENG Qingning, LONG Chao, XIONG Songling, QI Xiaoxiao. Multi-task Learning for Speech Enhancement and Detection [J]. Computer Engineering and Applications, 2021, 57(20): 197-202.
[3]	MA Yang, ZHAO Xujun. Multi-source Outlier Detection Algorithm Based on Relevant Subspace [J]. Computer Engineering and Applications, 2021, 57(17): 88-95.
[4]	HU Wentao, CHEN Xiuhong. Robust Sparse Subspace Learning Based on Locality Preserving Projections [J]. Computer Engineering and Applications, 2021, 57(10): 194-199.
[5]	DONG Yanhua, ZHANG Shumei, ZHAO Junli. Review of Occlusion Face Recognition Method [J]. Computer Engineering and Applications, 2020, 56(9): 1-12.
[6]	WANG Yusi, LU Deyang, LI Haiyang. Sparse Subspace Clustering Method Based on Fractional Function Constraints [J]. Computer Engineering and Applications, 2020, 56(7): 39-47.
[7]	WANG Yiwu, YANG Yuwang. Research and Application of Spatial Projection in [K]-means Algorithm [J]. Computer Engineering and Applications, 2020, 56(7): 200-204.
[8]	ZHENG Yi, MA Yingcang, YANG Xiaofei, XU Qiuxia. Sparse Subspace Clustering Based on [k]-Nearest Neighbors and Local Similarity [J]. Computer Engineering and Applications, 2020, 56(4): 99-108.
[9]	JIN Hongqi, CHEN Xindu, WU Lei. Defect Detection Combining Random Subspace and Cascade Residual Network [J]. Computer Engineering and Applications, 2020, 56(23): 265-269.
[10]	ZHU Dan, CHEN Xiaohong, WU Qingyuan, LI Shunming. Subspace Clustering Induced by Adaptive Graph Learning [J]. Computer Engineering and Applications, 2020, 56(21): 30-37.
[11]	QIN Fengting, YANG Youlong, QIU Haiquan. Sparse Subspace-Based Method for Local Outlier Detection [J]. Computer Engineering and Applications, 2020, 56(19): 152-159.
[12]	GUO Sheng, ZHONG Zhaoman, LI Cunhua. Multi-view Subspace Clustering Network Based on Deep Autoencoder [J]. Computer Engineering and Applications, 2020, 56(17): 60-68.
[13]	LIU Wenfen, MU Xiaodong, HUANG Yuehua. Anomaly Detection Method Based on Multi-resolution Grid [J]. Computer Engineering and Applications, 2020, 56(17): 78-85.
[14]	YANG Ying, WANG Jun, WANG Gang. Customer Complaints Classification Method Based on Improved Random Subspace [J]. Computer Engineering and Applications, 2020, 56(13): 230-235.
[15]	LI Dan. Structured Weighted Correlation Adaptive Subspace Clustering [J]. Computer Engineering and Applications, 2020, 56(13): 137-142.

Speech recognition based on combined enhancement of Symlets wavelet and subspace

Symlets小波和子空间联合增强下的语音识别

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics