Adaptively compensated multiband spectral subtraction for robust noise reduction

An adaptively compensated multiband spectral subtraction (MBSS) is presented in this paper. In this research, the adaptive compensation in the MBSS utilizes artificial neural network. The purpose of this compensation is to improve the quality of speech signal after denoising of MBSS step. This compensation is calculated adaptively depend on the MBSS parameters, estimated noise, and difference between input and estimated speech signal. The neural network used was Multi-Layer Perceptron consisted of three hidden layers. The proposed neural network was trained by three speech signals contaminated by white gaussian noises with SNR 0dB and 30dB. For investigating the performance, the proposed method was tested by five noised speech signals with SNR 0dB to 10dB. The result of experiment is examined and evaluated by SNR and PESQ scores. Based on the examination, the proposed speech enhancement method exposed the better performance than the origin MBSS algorithm.

[1]  Chen Yi,et al.  Multi-band spectral subtraction method combined with auditory masking properties for speech enhancement , 2012, 2012 5th International Congress on Image and Signal Processing.

[2]  Richard M. Schwartz,et al.  Enhancement of speech corrupted by acoustic noise , 1979, ICASSP.

[3]  Chao Li,et al.  A novel multi-band spectral subtraction method based on phase modification and magnitude compensation , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  S. Boll,et al.  Suppression of acoustic noise in speech using spectral subtraction , 1979 .

[5]  Jenq-Neng Hwang,et al.  Handbook of Neural Network Signal Processing , 2000, IEEE Transactions on Neural Networks.

[6]  Md. Fasiul Alam,et al.  Perceptually weighted multi-band spectral subtraction speech enhancement technique , 2008, 2008 International Conference on Electrical and Computer Engineering.

[7]  Abhijit Karmakar,et al.  Single channel speech enhancement utilizing iterative processing of multi-band spectral subtraction algorithm , 2012, 2012 2nd International Conference on Power, Control and Embedded Systems.

[8]  M.N.S. Swamy,et al.  Neural Networks and Statistical Learning , 2013 .

[9]  Philipos C. Loizou,et al.  A multi-band spectral subtraction method for enhancing speech corrupted by colored noise , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[10]  S. Ciochina,et al.  Multi-band Bark scale spectral over-subtraction for colored noise reduction , 2005, International Symposium on Signals, Circuits and Systems, 2005. ISSCS 2005..