Research on Information Technology with Voiceprint Authentication Algorithm and its Implementation on Mobile Terminal

Article Preview

Abstract:

Mobile internet and its application is hot information technology. The study integrates and improves some speech processing algorithms to make them suitable for the mobile terminal environment and to realize user identity authentication. It uses one body's unique voiceprint information which has the characteristics of convenient, concise, efficient and safe. By studying pre-emphasis, hamming window and other speech signal pretreatment, the voiceprint feature extraction technique of Mel cepstrum parameters, pattern matching algorithm DTW, a algorithm scheme is established. The scheme has been implemented and verified. It is suitable for treating small amount of words voice authentication.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

698-701

Citation:

Online since:

January 2014

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] Tian Li: Research for Automatic Speech Recognition Based on Wave1et and ANN (2005).

Google Scholar

[2] Guo Feng: Research on Chinese Audio CAPTCHA technique and application (2010).

Google Scholar

[3] Ren Xiaolin, Hu Guangrui and Xu Xiong: Speech Recognition Method Based on Chaotic Neural Network, edtied by JOURNAL OF SHANGHAI JIAOTONG UNIVERSITY, Vol. 33 (1999), pp.1517-1520.

Google Scholar

[4] Zhang Xianda: Modern Signal Processing, edited by Tsinghua University Press, Beijing (1995).

Google Scholar

[5] Jin Kyung Ryeu and Ho Sun Chung: Chaotic recurrent neural networks and their application to speech recognition, edtied by Neurocomputing, Vol. 13 (1996), pp.281-294.

DOI: 10.1016/0925-2312(95)00093-3

Google Scholar

[6] Cai Lianhong, Huang Dezhi and Cai Rui: Modern Speech Technology Fundamentals and Applications, edtied by Tsinghua University Press, Beijing (2003).

Google Scholar

[7] He Jun: Research on strategies against abnormal speech in voiceprint recognition system (2012).

Google Scholar

[8] Wang Di, Fu Qiang and Yang Lin: Automatic pathological voice evaluation based on auditory model, edtied by ACTA PHYSICA SINICA, Vol. 57 (2008), pp.4244-4250.

Google Scholar

[9] Lv Cheng-guo, Han Ji-qing and Wang Cheng-fa, Stressful speech recognition method based on difference subspace integrated with dynamic time warping, ACT ACUSTICA, vol. 30, May 2005, pp.229-234.

Google Scholar