简介:Speakervariabilityisanimportantsourceofspeechvariationswhichmakescontinuousspeechrecognitionadifficulttask.Adaptingautomaticspeechrecognition(ASR)modelstothespeakervariationsisawell-knownstrategytocopewiththechallenge.AlmostallsuchtechniquesfocusondevelopingadaptationsolutionswithintheacousticmodelsoftheASRsystems.Althoughvariationsoftheacousticfeaturesconstituteanimportantportionoftheinter-speakervariations,theydonotcovervariationsatthephoneticlevel.Phoneticvariationsareknowntoformanimportantpartofvariationswhichareinfluencedbybothmicro-segmentalandsuprasegmentalfactors.Inter-speakerphoneticvariationsareinfluencedbythestructureandanatomyofaspeaker'sarticulatorysystemandalsohis/herspeakingstylewhichisdrivenbymanyspeakerbackgroundcharacteristicssuchasaccent,gender,age,socioeconomicandeducationalclass.Theeffectofinter-speakervariationsinthefeaturespacemaycauseexplicitphonerecognitionerrors.Theseerrorscanbecompensatedlaterbyhavingappropriatepronunciationvariantsforthelexiconentrieswhichconsiderlikelyphonemisclassificationsbesidespronunciation.Inthispaper,weintroducespeakeradaptivedynamicpronunciationmodels,whichgeneratedifferentlexiconsforvariousspeakerclustersanddifferentrangesofspeechrate.Themodelsarehybridsofspeakeradaptedcontextualrulesanddynamicgeneralizeddecisiontrees,whichtakeintoaccountwordphonologicalstructures,rateofspeech,unigramprobabilitiesandstresstogeneratepronunciationvariantsofwords.EmployingthesetofspeakeradapteddynamiclexiconsinaFarsi(Persian)continuousspeechrecognitiontaskresultsinworderrorratereductionsofasmuchas10.1%inaspeaker-dependentscenarioand7.4%inaspeaker-independentscenario.
简介:Inthispaper,wedescribetheestimationoflow-altituderefractivitystructurefromsimulationandrealground-basedGPSdelays.Theverticalstructureoftherefractiveenvironmentismodeledusingthreeparameters,i.e.,ductheight,ductthickness,andductslope.Therefractivitymodelisimplementedwithaprioriconstraintsontheductheight,thickness,andstrength,whichmightbederivedfromsoundingsornumericalweather-predictionmodels.Araypropagationmodelmapstherefractivitystructureintoareplicafield.Replicafieldsarecomparedwiththesimulationobserveddatausingasquarederrorobjectivefunction.Aglobalsearchforthethreeenvironmentalparametersisperformedusingageneticalgorithm.Theinversionisassessedbycomparingtherefractivityprofilesfromtheradiosondestothoseestimated.Thistechniquecouldprovidenear-real-timeestimationoftheductingeffect.Theresultssuggestthatground-basedGPSprovidessignificantatmosphericrefractivityinformation,despitecertainfundamentallimitationsofground-basedmeasurements.Radiosondesaretypicallylaunchedjustafewtimesdaily.Consequently,estimatesoftemporallyandspatiallyvaryingrefractivitythatassimilateGPSdelayscouldsubstantiallyimproveover-estimatescausedbyusingradiosondedataalone.