Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment

Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment

ID:40848683

大小:597.34 KB

页数:7页

时间:2019-08-08

Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment_第1页
Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment_第2页
Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment_第3页
Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment_第4页
Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment_第5页
资源描述:

《Two Methods of Automatic Evaluation of Speech Signal Enhancement Recorded in the Open-Air MRI Environment》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、MEASUREMENTSCIENCEREVIEW,17,(2017),No.6,257-263Journalhomepage:http://www.degruyter.com/view/j/msrTwoMethodsofAutomaticEvaluationofSpeechSignalEnhancementRecordedintheOpen-AirMRIEnvironmentJiříPřibil1,AnnaPřibilová2,IvanFrollo11InstituteofMeasurementScience,SAS,Dúbravsk

2、ácesta9,SK-84104Bratislava,Slovakia,Jiri.Pribil@savba.sk2InstituteofElectronicsandPhotonics,FEE&IT,SUT,Ilkovičova3,SK-81219Bratislava,SlovakiaThepaperfocusesontwomethodsofevaluationofsuccessfulnessofspeechsignalenhancementrecordedintheopen-airmagneticresonanceimagerduri

3、ngphonationforthe3Dhumanvocaltractmodeling.ThefirstapproachenablestoobtainacomparisonbasedonstatisticalanalysisbyANOVAandhypothesistests.ThesecondmethodisbasedonclassificationbyGaussianmixturemodels(GMM).TheperformedexperimentshaveconfirmedthattheproposedANOVAandGMMclas

4、sifiersforautomaticevaluationofthespeechqualityarefunctionalandproducefullycomparableresultswiththestandardevaluationbasedonthelisteningtestmethod.Keywords:Acousticnoisesuppression,magneticresonanceimaging,speechprocessing,statisticalanalysis.1.INTRODUCTIONannotationoft

5、hespeechcorpus,etc.[13]).Theobjectiveapproachesformeasuringthespeechsignalquality[14]Constructionof3Darticulatorymodelsisnecessaryforcomprise,forexample,evaluationofdifferencesbetweenthebetterrepresentationofthehumanvocaltractfunctionandspeechspectralenvelopes[11]orspec

6、traldistances[12],etc.thesubsequentarticulatoryspeechsynthesis.Forthisreason,Thesefeaturesmaybecomparedandmatchedusingthetheaudiosignalmustberecordedsimultaneouslywiththestatisticalapproaches,liketheanalysisofvariancesimagescanning[1].Themagneticresonanceimaging(MRI)(AN

7、OVA)[15],[16]orhypothesistests[17],[18].ThefinaldeviceisusedtoobtainthevocaltractimagesoftheevaluationintheseapproachesbearstheformofaarticulatingpersonthatliesinthescanningareawhiletherecognitionscorethatcanbeobtainedbythemethodsbasedMRsequenceisrunning[2],[3].TheMRIeq

8、uipmentonartificialneuralnetworks,thenearestneighbor[19],consistsofagradientcoilsystemproducingthreeorthogonal

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。