A speech enhancement method based on Kalman filtering |
| |
作者姓名: | SHEN Yaqiang |
| |
作者单位: | Zhejiang Normal Universily,Zhejiang 321004 |
| |
摘 要: | I.IntroductionKa1manfilteringisjustamethodtoestimatestatistica1lythestateoftheobservedsystemfromthecorruptedsigna1s,andthiskindofcstimationisarecurrcneeestimationbasedon1inear,nonbiasandminimumvariance.Moreover,Ka1manfilteringisapplicabletonon-sta-honarysignalsandtime-variantdynamicsystem.Therefore,Kalmanfilteringisveryapplica-bletoenhancingthespeechsigna1sthatarecorruptedbynoise.ThispaperreportStheconcretcmethodofenhanccmentofnoisyspccchanditscxperimentresults.Experimentsindicate:Afterthes…
|
A speech enhancement method based on Kalman filtering |
| |
Authors: | SHEN Yaqiang |
| |
Abstract: | In this paper, we research the enhancement of noisy specch signals by use of Kalman Filtering. The corrupted speech signal by adding noises, which have +5 to -5dB low SNR, was used as filter object. The adding noises to be processed are broadband white noise and color noise and without correlation to speech signal. The improvement of SNR about 7 to 10 dB have been achieved. |
| |
Keywords: | Kalman filtering Speech enhancement |
本文献已被 CNKI 等数据库收录! |