Voice Activity Detection Based on Nonlinear Processing Techniques

Abstract:

Hilbert-Huang transform is developed in recent years dealing with nonlinear, non-stationary signal analysis of the complete local time-frequency method, recurrence plot method is a recursive nonlinear dynamic behavior of time series method of reconstruction. In this paper, Hilbert-Huang Transform empirical mode decomposition (EMD) and the recurrence plot (RP) method, a new voice activity detection algorithm. Firstly, through the speech and noise based on the empirical mode decomposition and multi-scale features of the different intrinsic mode function (IMF) on a time scale filtering and nonlinear dynamic behavior of the recurrence plot method, quantitative Recursive analysis of statistical uncertainty for endpoint detection. Simulation results show that the method has a strong non-steady-state dynamic analysis capabilities, in low SNR environment more accurately than the traditional method to extract the start and end point of the speech signal, robustness.

• Periodical: Applied Mechanics and Materials (Volumes 198-199)
• Pages: 1560-1566
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.198-199.1560
• Online since: September 2012
• Authors: Wen Lian Zhan, Jing Fang Wang
• Keywords: Empirical Mode Decomposition (EMD), Endpoint Detection, Nonlinear Processing, Recurrence Plot (RP)

References

[1] Junqua J C. Robustness and cooperative multimodel manmachine communication application[C]. Proc Second Venaco Workshop and ESCA ETRW. (1991).

[2] Tang Jingtian, Cliff Choi, Yong Ren G, et al. Hilbert-Huang Transform and Time-frequency magnetotelluric signal analysis [J]. Central South University (Natural Science), 2009, 40(5): 1399-1405.

[3] Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-station time series analysis [C]. Proceeding of the Royal Society of London, 1998: 903-995.

[4] Marwan N, Thiel M, Nowaczyk N R. Cross recurrence plot based synchronization of time series [J]. Nonlinear. Proc. Geophys, 2002, 9: 325-331.

DOI: 10.5194/npg-9-325-2002

[5] Yan Yun-Qiang, Yi-Sheng Zhu. recursion based on signal analysis of the speech endpoint detection method [J]. Communications, 2007, 28 (1): 35- 39.

[6] Yong, Xu Jin Wu, Rong Li. recurrence plot and approximate entropy of the complexity of the equipment failure signal analysis [J]. Mechanical Strength, 2006, 28 (3) : 317-321.

[7] Tan Shanwen, Qin Shuren, Tang Baoping. Hilbert-Huang Transform and Its Application filtering characteristics [J]. Chongqing University (Natural Science), 2004, 27 (2) : 9-12.

[8] Zbilut JP, Webber J, Charles L. Embeddings and delays as derived from quantification of recurrence plots [J]. Physics Letters A. 1992, 171 (1) : 199-203.

DOI: 10.1016/0375-9601(92)90426-m

[9] Songqian Qian, Feng-Qin Yu. based on EMD and improved double threshold method of endpoint detection [J]. electro-acoustic technology, 2009, 33 (8): 60-63.

[10] Boudraa AO, Cexus JC, Saidi Z. EMD-based signal noise reduction [J]. International Journal of Signal Processing, 2004, 1 (1) : 33-37.

[11] Marzinzik M, Kollmeier B Speech pause detection for noise spectrum estimation by tracking power envelopedynamics [J]. IEEE Trans on Speech and Audio Processing, 2002, 10: 109-118.

DOI: 10.1109/89.985548