Research on Natural Language Recognition Algorithm Based on Sample Entropy

Juan Lai

doi:10.4028/www.scientific.net/AMM.539.185

Paper Titles

Design of Quantum Communication Broadband Amplifier Based on Photoelectric Diode
p.169

Application and Research of Land Changes Based on GIS and RS
p.173

Design of High Precision Temperature Sensor Based on Platinum Resistance
p.177

Study on Consistency Analysis in Text Categorization
p.181

Research on Natural Language Recognition Algorithm Based on Sample Entropy
p.185

Research on Multi-Fuze Co-Channel Interference Suppression Based on Pseudorandom Code Phase Modulation
p.190

Research on the Application of Chaotic Iteration Function of Heterogeneous Populations Mining Algorithm in Computer Based on Co-Evolution
p.194

Study on Composite Electromagnetic Scattering from 1D Weierstrass Fractal Land Surface with Buried Target Using FDTD
p.199

Based on ZigBee Technology Intelligent Sensor Network Design and Implementation
p.207

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 539Research on Natural Language Recognition Algorithm...

Research on Natural Language Recognition Algorithm Based on Sample Entropy

Abstract:

Sample entropy can reflect the change of level of new information in signal sequence as well as the size of the new information. Based on the sample entropy as the features of speech classification, the paper firstly extract the sample entropy of mixed signal, mean and variance to calculate each signal sample entropy, finally uses the K mean clustering to recognize. The simulation results show that: the recognition rate can be increased to 89.2% based on sample entropy.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 539)

Pages:

185-189

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.539.185

Citation:

Cite this paper

Online since:

July 2014

Authors:

Juan Lai

Keywords:

Sample Entropy, Speech Processing, Voice Activity Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Yan Nan, Wang Jue, Wei Na, et al. Feature exaction and classification of attention related electroencephalographic signals based on sample entropy [J]. Journal of Xipan Jiaotong University, 2007, 41 (10): 1237-1241 2006, 25 (5): 527-531.

Google Scholar

[2] Ei M M S, Moe P. An efficient approach for classification of speech and music[C]. In: Multimedia Information Processing, Berlin. 2008: 50-60.

Google Scholar

[3] Hu Guangrui, Wei Xiaodong. Endpoint detection of noisy speech based on cepstum [J]. Acta Electronica Sinica, 2000, 28 (10): 95-97.

Google Scholar

[4] Fan Yingle, Wu Chuanyan, Li Yi, et al. Application of C0 complexity measure in detecting speech [J]. Chinese Journalof Sensors and Actuators, 2006, 19 (3): 750-753.

Google Scholar

[5] Lei Xiongguo, Zeng Yicheng, Li Ling. Noisy speech endpoint detection based on approximate entropy [J]. Technical Acoustics, 2007, 26 (1): 121-125.

Google Scholar