Abstract
Elimination of tainted noise and improving the overall quality of a speech signal is speech enhancement. To gain the advantage of individual algorithms we propose a new linear model and that is in the form of cascade adaptive filters for suppression of non-stationary noise. We have successfully deployed NLMS (Normalized Least Mean Square) algorithm, Sign LMS (Least Mean Square) and RLS (Recursive Least Square) as the main de-noising algorithms. Moreover, we are successful in demonstrating that the prior information about the noise is not required otherwise it would have been difficult to estimate for fast-varying noise in non-stationary environment. This approach estimates clean speech by recognizing the long segments of the clean speech as one whole unit. During experiment/implementation we used in-house database (includes various types of non stationary noise) for speech enhancement and proposed model results have shown improvement over conventional algorithms not only in objective but in subjective evaluations as well. Simulations present good results with a new linear model that are compared with individual algorithm results.
Highlights
The goal of speech enhancement is to improve the quality and intelligibility of speech that has been degraded by noise [11]
We propose a class of two stage www.ijacsa.thesai.org (IJACSA) International Journal of Advanced Computer Science and Applications, Vol 7, No 1, 2016 adaptive architecture to address some properties of nonstationary noise by calculating energy for original speech and calculate energy for processed speech with signal-to-noise ratio (SNR), Mean square error (MSE)
During the course of experiments, we have found that SNR tests alone can’t reflect the effectiveness of a de-noising system and results are to be confirmed with listening tests
Summary
The goal of speech enhancement is to improve the quality and intelligibility of speech that has been degraded by noise [11]. Wiener filter is used for linearity whereas spectral subtraction is used for simplified mathematical expressions [15] .Almost all the papers work on speech enhancement with added known amount of noise and use their proposed algorithm to enhance the speech or reduce the noise level In this case, mostly noise is assumed to be white, Gaussian noise and colored noise [11]. If one records speech on the road or in the market, there is no guarantee that the noise is Gaussian For this enhancement algorithm to be really useful, it must improve the quality of speech that was originally noisy due to some environmental conditions like railway station, fan, vehicle, machine gun, tank, factory etc that create distortions in clean speech signal and not due to explicit addition of noise by the researcher [13]. In the speech enhancement process, the estimation of the a priori signal-to-noise ratio (SNR), Mean square error (MSE), energy, Power Spectral Density (PSD) is one of the most important parts, especially in non-stationary environments [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
