A New Robust Hybrid Approach to Enhance Speech in Mobile Communication Systems | Science Publications

American Journal of Applied Sciences

Keppana G. Thanuskodi¹  Manimegalai G. Sumithra¹  Bharathi Deepa¹ 

关键词: Speech enhancement;    dual band spectral subtraction;    Wavelet Packet Decomposition (WPT);    stein's unbiased risk estimate (SURE);   

DOI  :  10.3844/ajassp.2011.332.342

学科分类：自然科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: The received voice signal in mobile communication is often disturbedby background noise and hence there is a need for good noise reduction methods for enhancingSpeech. It is well known that denoising is a compromise between the removal of the largest possibleamount of noise and the preservation of signal integrity. To address this issue, a new method forenhancing speech from background interference is presented in this study by fusing dual band spectralsubtraction with adaptive noise estimator and wavelet packet based thresholding method. Approach:The proposed system uses the combination of dual band Spectral Subtraction method with adaptivenoise estimator for pre-processing, in order to initially reduce the noise level and further the quality ofspeech is improved by Wavelet Packet Transform (WPT) based level dependent thresholding method.The threshold value is determined by using Steins Unbiased Risk Estimator (SURE) and hard, soft,Garrotte, µ-law and a proposed modified soft thresholding functions are considered for denoising.Results: The proposed method was investigated by ten different clean speech samples (five male andfive female) taken from TIMIT database and thirteen different noise sources to degrade the speechartificially and the energy level of the noise is scaled such that the overall SNR of the noisy speech ismaintained at -5, 0,5,10 and 15 dB and finally the results are evaluated using objective and subjectivemeasures. Conclusion/Recommendations: It is suggested from the experimental results that theproposed scheme gives improved spectral performance, reflects in better speech quality in all types ofnoisy environment. For better speech enhancement in noise dominated regions, the system efficiency isfurther improved by fusing threshold values for wavelet denoising.

【 授权许可】

Unknown