Enhancement of Noisy Speech with Low Speech Distortion Based on Probabilistic Geometric Spectral Subtraction
This work addresses speech enhancement for noisy environments, offering a method that balances noise reduction and speech quality, though it appears incremental compared to existing spectral subtraction techniques.
The paper tackles speech enhancement by introducing a probabilistic geometric spectral subtraction method with a confidence parameter for noise estimation, which reduces speech distortion while removing noise effectively. Experimental results on the NOIZEUS database show improved performance in noise removal with minimal speech distortion.
A speech enhancement method based on probabilistic geometric approach to spectral subtraction (PGA) performed on short time magnitude spectrum is presented in this paper. A confidence parameter of noise estimation is introduced in the gain function of the proposed method to prevent subtraction of the overestimated and underestimated noise, which not only removes the noise efficiently but also prevents the speech distortion. The noise compensated magnitude spectrum is then recombined with the unchanged phase spectrum to produce a modified complex spectrum prior to synthesize an enhanced frame. Extensive simulations are carried out using the speech files available in the NOIZEUS database in order to evaluate the performance of the proposed method.