Speech Endpoint Detection Based on Fractal Dimension with Adaptive Threshold

被引：3
|
作者：
Zheng Y. [1 ]
Gao S. [1 ]
机构：
[1] School of Information Science & Engineering, Northeastern University, Shenyang
来源：
Dongbei Daxue Xuebao/Journal of Northeastern University | 2020年 / 41卷 / 01期
关键词：
Adaptive threshold; Fractal dimension; Low SNR(signal noise ratio); Robustness; Speech endpoint detection;
D O I：
10.12068/j.issn.1005-3026.2020.01.002
中图分类号：
学科分类号：
摘要：
Considering the limitation of fixed threshold method in speech endpoint detection, in order to improve the robustness and accuracy of speech endpoint detection under low SNR(signal noise ratio), a novel speech detection algorithm was proposed based on adaptive threshold in fractal dimension. By analyzing the mechanism of speech signal generation, the fractal dimension was applied to the detection of speech starting and ending points, and an adaptive threshold was designed to avoid noise interference and to achieve real-time detection. The simulation results show that, compared with the traditional short-term energy detection algorithm, the proposed algorithm can effectively realize the endpoint detection of noisy speech under the low SNR, and has better robustness to noise interference. © 2020, Editorial Department of Journal of Northeastern University. All right reserved.
引用
收藏
页码：7 / 11
页数：4
相关论文
共 14 条
  • [1] Seman N., Bakar Z.A., Bakar N.A., An evaluation of endpoint detection measures for Malay speech recognition of an isolated words, Information Technology, 10, pp. 1628-1635, (2010)
  • [2] Morita S., Unoki M., Lu X., Et al., Robust voice activity detection based on concept of modulation transfer function in noisy reverberant environments, Journal of Signal Processing Systems, 82, 2, pp. 163-173, (2016)
  • [3] Wu D., Zhao H., Huang C., Et al., Speech endpoint detection in low-SNRs environment based on perception spectrogram structure boundary parameter, Chinese Journal of Acoustics, 39, 4, pp. 392-399, (2014)
  • [4] Li J.-J., An D., Wang J., Speech denoising method based on the EEMD and ICA approaches, Journal of Northeastern University(Natural Science), 32, 11, pp. 1554-1557, (2011)
  • [5] Eshaghi M., Mollaei M.R.K., Voice activity detection based on using wavelet packet, Digital Signal Processing, 20, 4, pp. 1102-1115, (2010)
  • [6] Lu Y.Y., Zhou N., Xiao K., Et al., Improved speech endpoint detection algorithm in strong noise environment, Journal of Computer Applications, 34, 5, pp. 1386-1390, (2014)
  • [7] Liang Y.S., Su W.Y., Fractal dimensions of fractional integral of continuous functions, Acta Mathematica Sinica: English Series, 32, 12, pp. 1494-1508, (2016)
  • [8] Liu Y., Wang X.-T., A speech endpoint detection algorithm based on fractal in short-term frequency domain, Microelectronics and Computer, 32, 9, pp. 82-84, (2015)
  • [9] Ali Z., Elamvazuthi I., Alsulaiman M., Et al., Detection of voice pathology using fractal dimension in a multiresolution analysis of normal and disordered speech signals, Journal of Medical Systems, 40, 1, pp. 20-21, (2016)
  • [10] Shen X.-B., Wei R., Yang Y., Study on the extraction of fractal dimension based on frequency domain energy distribution, Control Engineering of China, 23, 6, pp. 834-838, (2016)
12