基于小波分析的音頻分割與聚類

1、分類號(hào)密級(jí)公開Y1219390重慶郵電大學(xué)碩士學(xué)位論文論文題目基于小波分析的音頻分割與聚類英文題目AudioSegmentationandClassificationBasedontheWavelet1ransformation碩士研究生奎殪指導(dǎo)教師塑繾明到絲蕉學(xué)科專業(yè)計(jì)算機(jī)應(yīng)用技術(shù)論文提交日期2塑壘Z生墨日論文答辯茸期2韭盤2塋五丑墨且_論文評(píng)閱人趟墅盈煎蔓杰監(jiān)璺丕孽避丞盛型麴鱟答辯委員會(huì)主席邱玉輝教授西南大學(xué)2007年5月30日重慶

2、郵電大學(xué)碩士論文摘要AbstractWiththeincrementsofmultimediadataontheinternettheinformationquantitywhichwehavetofaceshouldbedescribedasjillionHowtOgetwhatweneedfromthelargenumberofinformationontheInteractisbecameadifficultyofinformat

3、ionretrievalBecauseofitsownlimitandthespecialfeatureofmultimediadatatext—basedretrievalisnotapplicableanymoreInthatcase，Contend—BasedRetrieval(CBR)cameforthandbecameahotspotComparingwithimageandvideetrieval，audietrievals

4、tudyisbehindhandWiththedevelopmentofwavelettechnologytheadvantageofwaveletinsignalanalysisisbecomemoreandmoreobviousIncorporatingthepastfruits，analyzethefeatureextractionaudiosegmentationandclassificationinemphasizenlere

5、searchworkandresultsoftllisdissertationcanbeconcludedasfollows：(1)Researchtheapplicationofwaveletanalysistechnologyinsignalanalysis，extractthreeaudiofeaturesinwaveletdomainMaaMsrandAzcr，analyzethedifferencebetweendiffere

6、ntaudiosonthesefeatures，andstudytheirperformancesinaudiosegmentationandclassification(2Presentamethodcalled“framecontinuance’’aimatimprovingtheabuseoftraditionalmethodhltheexperiment，thetechniquereducethesegmentsensitivi

7、tyandincreasethesegmentprecision(3)Studythekmeansalgorithmin—depth，andpresemkmeansdecisionmethodMakethekmeansalgorithmmulticlassificationtodoubleclassification，avoidtheaffectionoforiginalcentroidtoclassificationprecision