2019 Vol.2 Dec. No.6

• Title: Denoising method for intelligent image and speech signals based on blind source separation
• Name: Sheral Heinrich
• Company: Dalhousie University
• Abstract:

  After the noise reduction of smart images and voice signals using traditional noise reduction methods, the sharpness of smart images is lower and the signal-to-noise ratio of voice signals is too large. The noise reduction effect is not good. Regarding the issue above. This paper proposes a method for denoising intelligent images and speech signals based on blind source separation. First use the signal acquisition device to collect intelligent image and voice signals, and then use them to pre-process: Mean value and whitening, and finally use symmetric orthogonalization method for independent component extraction, that is to achieve noise reduction. The results show that after using this noise reduction method to reduce noise, the sharpness of the intelligent image is higher, and the signal-to-noise ratio of the speech signal is larger, reaching 28dB, which proves that the method has better noise reduction effect than the traditional method.

• Keyword: blind source separation; independent component analysis; intelligent image; speech signal; noise reduction
• DOI: 10.12250/jpciams2019060642
• Citation form: Sheral Heinrich.Denoising method for intelligent image and speech signals based on blind source separation[J]. Computer Informatization and Mechanical System, 2019, vol. 2, pp. 12-17.

[1] Meng Zong, Ma Zhao, Liu Dong, et al. Blind Source Separation Based on Wavelet Semi-soft Threshold Denoising[J]. China Mechanical Engineering, 2016, 27 (3): 337-342.

[2] Cai Weihua, He Xuesen. Noisy blind source separation based on undecimated wavelet transform and independent component analysis [J].Computer Engineering and Applications, 2016,52(16): 180-185.

[3] Liu Jiahui, Dong Xinmin, Li Jianfei. Fault Feature Extraction of Rolling Bearings Based on Noises Reduced by Full Vector Spectrum ITD-ICA Blind Source Separation[J]. Chinese mechanical engineering, 2018, 29 (8): 943-948.

[4] Xu Chao, Feng Fuzhou, Min Qingxu, et al. Blind Source Separation of Thermal Image Sequences Using Principal Component Analysis [J]. Infrared Spectroscopy, 2017, 39 (11): 1018-1023.

[5] Shenjiang River, Gaofeng, Qujianling, et al. Blind source separation of helicopter vibration signal based on improved particle swarm algorithm[J] Journal of Electronic Measurement and Instrumentation,2016, 30(9): 1372-1378.

[6] Wang Yu, Li Xiaobo, Mao Yunxiang, et al. Radar Signal Research Based on JADE Blind Source Separation Algorithm[J]. Modern defense technology, 2017, 45 (1).

[7] Liu Bin, He Zhicheng, Ji Yan Jun. Simulation study on optimal control of vehicle running noise reduction [J]. computer simulation, 2018,35 (06): 151-155+171