資源描述:
《基于波原子變換的語音信號去噪畢業(yè)論文》由會員上傳分享,免費在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫。
1、Contents1.INTRODUCTION12.WAVEATOMTRANSFORM42.1DefinitionofWaveAtomTransform42.21-DCharacteristicsinWaveAtomTransform62.3TheStructureof1-Dfilter-bankinWaveAtom……………………………….…103.THRESHOLDINGMETHODFORNOISEREDUCTION173.1HardandSoftThresholdings173.2Determi
2、nationofThreshold204.EXPERIMENTSANDDISCUSSIONS……………………………………………..274.1ExperimentalConditions…………………………………………………………..274.2ResultsandDiscussions285.CONCLUSION37REFERENCE38ABSTRACT(INKOREAN)40i401.INTRODUCTIONSpeechisoneofthemostnaturalandconvenientwaysof
3、intercommunication.Thus,speechsignalprocessingtechniquesforaman-machineinterfacelikespeechrecognition,speechsynthesisandspeechcodinghavedrawnmuchattention.Asspeechprocessingmovedfromthelaboratorytothefield,ithasbecomeincreasinglyimportanttodealwiththea
4、mbientnoise.Sincethequalityandintelligibilityaredegradedbytheambientnoise,theproblemofreducingnoisecomponentsofthenoisyspeechisstillregardedasanimportantissueinthefieldofspeechresearch[1-3].Mostclassicalmethodsforhandlingambientwidebandnoisewerevariant
5、sofanapproachbasedonsubtractinganestimateofthespectrumofthenoisefromthatofthenoisyspeech[4-7].AndthenanovelapproachfornoisereductionusingthewavelettransformhasbeenproposedbyD.L.Donoho[8].Itemploysthethresholdingtechniqueinthewaveletdomainandhasshowntoh
6、avegoodpropertiesforawideclassofsignalscorruptedbyadditivewhiteGaussiannoise.Overthepasttwodecades,numeroussignalprocessingtechniqueswiththewavelettransformhavebeendevelopedtomakeuseofitssuperioritytotheconventionalFouriertransform.Recently,waveatomtra
7、nsformhasbeenproposed,andhasshownits40potentialindenoisingexperimentsonbothseismicandfingerprintimages[1].Waveatomwasintroducedasavariantof2Dwaveletpacketsobeyingtheparabolicscaling.Inanutshell,waveatomsinterpolateexactlybetweendirectionalwaveletsandGa
8、bor,inthesensethattheperiodofoscillationsofeachwavepacket(wavelength)islinkedtothesizeoftheessentialsupport(diameter)bytheparabolicscaling,i.e.,wavelength~(diameter)2[1,2].Inthisthesis,weapplythe1Dwaveatomtransformtonoisyspeechsignalsfo