基于小波變換的語(yǔ)音分析訓(xùn)練系統(tǒng).pdf

1、Y103S359分類(lèi)號(hào)：塑2ij：23UDC：Q堡密級(jí)：公玨學(xué)號(hào)；照!!魚(yú)!⑨東南大掌碩士學(xué)位論文基于小波變換的語(yǔ)音分析訓(xùn)練系統(tǒng)研究生姓名：塞墻筻導(dǎo)師姓名：趙卷登熬授申請(qǐng)學(xué)位級(jí)別王堂殛論文提交日期窒嫂曼生曼最!呈旦學(xué)位授予單位盔畝太堂答辯委員會(huì)主席翌蜩重羔：學(xué)科專(zhuān)業(yè)名稱(chēng)塞蟄醫(yī)坐王蕉論文答辯日期至鯉魚(yú)生曼履22自學(xué)位授予日期至鯉璺生丑一。臣一評(píng)閱人鹽土i羔塹△翌2006年6月東南大學(xué)碩士學(xué)位論文AbstractChinaiSoueofth

2、ecountrieswherethespeechdiseaseoccupiesahighproportionofthepopulationIfthosespeechdiseaseshavenotreceivedspecialspeechtrainingtheyarclikelytolosethenaturalabilityofspeechcommunicationIfdevelopingthespecialsoftwarebythemu

3、ltimediaofcomputerwecantrainandcurespeechdiseasepatientByusingspeechprocesstechnologyspeechsigrlalchangedtodifferentimagesn艟patientc月1njudgetheaccuracyratingofpronouncebytheseimagesandcorrectpronounceInthisthesisitisfⅡst

4、lysununarizcdthatsomebaseknowledgeofspeechsignalandthenitisintroducedthatthespeechanalysismethodsintimeandfrequencydomainn玲t(yī)imedomainanalysisismostsimpleandintuitionisticn璩shorttimeenergytheshorttimezerocrossingrateandth

5、eshorttimeselfcorrelationaremainanalysismethodintimedomain11圮frequencydomainanalysis∞ngetmanycharacterswhichCannotgetbythetimedomainanalysisWeCangetfrequencyinformationofspeechthroughtheanalysisofthespectrogramandspeetru

6、nlwhichgetbyusingtheshorttermFouriertransform111espectrogramconexpresstherelationshipbetweentimeandfrequencydomainanalysis，anditismainanalysismethodWeintroducethatthespectrogramCangetbyusingthewavelettransform11圮spectrog

7、ramwhichgetbyusingthewaveletWansformhasgoodfrequencyresolutioninlowfrequencyandgoodtimeresolutionillhighfrequencythismoreaccordwiththecharactersofspeechWeanalyzedalotofspeechandtheresultsshowthewavelettransformhasmoreadv

8、antageAtlastitisintroducedthattherealizationofaspeechanalyzingandtrainingsystemnesystemisbasedonwavelettransformandothertimeandfrequencydomainanalysismethod耵圮controlmenuisdevelopedinVisualC60andtheanalysisprogramisdevelo

9、pedinMauab6511lcanalysisprogramiscalledinVisual()andthedevelopingtimeisshortenedThesystemCancontroltheplayingrecordingandpausingandCandisplayfigureformsoftheinputspeechbothintimedomainandfrequencydomain玎豫usercanSetupdiff

10、erentparameterbecauseofdifferentneeds，SOtheyCangetmoreexactresultThoseinarticulatetraineescancarryoutspeechtrainingbycomparingspectrogramasvisualfeedbackKeywords：SpeechSignal；SignalProcess；TheFourierTransform；TheWaveletT