Combining statistical models using modified spectral subtraction method for embedded system

Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile devices increased usage, the demand for algorithms processing also increases. As the microphones that capture the voice of the speaker are at considerable distance in most of the devices, noise are getting added thereby degrading the quality of the speech signal. No single theorist's stone or minimization standard has been discovered so far for speech enhancement. In this work, we have combined the statistical models along with machine learning algorithm to improve the results thereby resulting in robust communication. Experimentation results on AURORA 2 database shows us improved results over the state of the art methods discussed in the literature.