语音识别 外文翻译 外文文献 英文文献.docx
- 文档编号:26388510
- 上传时间:2023-06-18
- 格式:DOCX
- 页数:13
- 大小:27.47KB
语音识别 外文翻译 外文文献 英文文献.docx
《语音识别 外文翻译 外文文献 英文文献.docx》由会员分享,可在线阅读,更多相关《语音识别 外文翻译 外文文献 英文文献.docx(13页珍藏版)》请在冰豆网上搜索。
语音识别外文翻译外文文献英文文献
SpeechRecognition
VictorZue,RonCole,&WayneWard
MITLaboratoryforComputerScience,Cambridge,Massachusetts,USAOregonGraduateInstituteofScience&Technology,Portland,Oregon,USA
CarnegieMellonUniversity,Pittsburgh,Pennsylvania,USA
1DefiningtheProblem
Speechrecognitionistheprocessofconvertinganacousticsignal,capturedbyamicrophoneoratelephone,toasetofwords.Therecognizedwordscanbethefinalresults,asforapplicationssuchascommands&control,dataentry,anddocumentpreparation.Theycanalsoserveastheinputtofurtherlinguisticprocessinginordertoachievespeechunderstanding,asubjectcoveredinsection.
Speechrecognitionsystemscanbecharacterizedbymanyparameters,someofthemoreimportantofwhichareshowninFigure.Anisolated-wordspeechrecognitionsystemrequiresthatthespeakerpausebrieflybetweenwords,whereasacontinuousspeechrecognitionsystemdoesnot.Spontaneous,orextemporaneouslygenerated,speechcontainsdisfluencies,andismuchmoredifficulttorecognizethanspeechreadfromscript.Somesystemsrequirespeakerenrollment---ausermustprovidesamplesofhisorherspeechbeforeusingthem,whereasothersystemsaresaidtobespeaker-independent,inthatnoenrollmentisnecessary.Someoftheotherparametersdependonthespecifictask.Recognitionisgenerallymoredifficultwhenvocabulariesarelargeorhavemanysimilar-soundingwords.Whenspeechisproducedinasequenceofwords,languagemodelsorartificialgrammarsareusedtorestrictthecombinationofwords.
Thesimplestlanguagemodelcanbespecifiedasafinite-statenetwork,wherethepermissiblewordsfollowingeachwordaregivenexplicitly.Moregenerallanguagemodelsapproximatingnaturallanguagearespecifiedintermsofacontext-sensitivegrammar.
Onepopularmeasureofthedifficultyofthetask,combiningthevocabularysizeandthe1languagemodel,isperplexity,looselydefinedasthegeometricmeanofthenumberofwordsthatcanfollowawordafterthelanguagemodelhasbeenapplied(seesectionforadiscussionoflanguagemodelingingeneralandperplexityinparticular).Finally,therearesomeexternalparametersthatcanaffectspeechrecognitionsystemperformance,includingthecharacteristicsoftheenvironmentalnoiseandthetypeandtheplacementofthemicrophone.
Speechrecognitionisadifficultproblem,largelybecauseofthemanysourcesofvariabilityassociatedwiththesignal.First,theacousticrealizationsofphonemes,thesmallestsoundunitsofwhichwordsarecomposed,arehighlydependentonthecontextinwhichtheyappear.Thesephoneticvariabilitiesareexemplifiedbytheacousticdifferencesofthephoneme,Atwordboundaries,contextualvariationscanbequitedramatic---makinggasshortagesoundlikegashshortageinAmericanEnglish,anddevoandaresoundlikedevandareinItalian.
Second,acousticvariabilitiescanresultfromchangesintheenvironmentaswellasinthepositionandcharacteristicsofthetransducer.Third,within-speakervariabilitiescanresultfromchangesinthespeaker'sphysicalandemotionalstate,speakingrate,orvoicequality.Finally,differencesinsociolinguisticbackground,dialect,andvocaltractsizeandshapecancontributetoacross-speakervariabilities.
Figureshowsthemajorcomponentsofatypicalspeechrecognitionsystem.Thedigitizedspeechsignalisfirsttransformedintoasetofusefulmeasurementsorfeaturesatafixedrate,2typicallyonceevery10--20msec(seesectionsand11.3forsignalrepresentationanddigitalsignalprocessing,respectively).Thesemeasurementsarethenusedtosearchforthemostlikelywordcandidate,makinguseofconstraintsimposedbytheacoustic,lexical,andlanguagemodels.Throughoutthisprocess,trainingdataareusedtodeterminethevaluesofthemodelparameters.
Speechrecognitionsystemsattempttomodelthesourcesofvariabilitydescribedaboveinseveralways.Atthelevelofsignalrepresentation,researchershavedevelopedrepresentationsthatemphasizeperceptuallyimportantspeaker-independentfeaturesofthesignal,andde-emphasizespeaker-dependentcharacteristics.Attheacousticphoneticlevel,speakervariabilityistypicallymodeledusingstatisticaltechniquesappliedtolargeamountsofdata.Speakeradaptationalgorithmshavealsobeendevelopedthatadaptspeaker-independentacousticmodelstothoseofthecurrentspeakerduringsystemuse,(seesection).Effectsoflinguisticcontextattheacousticphoneticlevelaretypicallyhandledbytrainingseparatemodelsforphonemesindifferentcontexts;thisiscalledcontextdependentacousticmodeling.
Wordlevelvariabilitycanbehandledbyallowingalternatepronunciationsofwordsinrepresentationsknownaspronunciationnetworks.Commonalternatepronunciationsofwords,aswellaseffectsofdialectandaccentarehandledbyallowingsearchalgorithmstofindalternatepathsofphonemesthroughthesenetworks.Statisticallanguagemodels,basedonestimatesofthefrequencyofoccurrenceofwordsequences,areoftenusedtoguidethesearchthroughthemostprobablesequenceofwords.
ThedominantrecognitionparadigminthepastfifteenyearsisknownashiddenMarkovmodels(HMM).AnHMMisadoublystochasticmodel,inwhichthegenerationoftheunderlyingphonemestringandtheframe-by-frame,surfaceacousticrealizationsarebothrepresentedprobabilisticallyasMarkovprocesses,asdiscussedinsections,and11.2.Neuralnetworkshavealsobeenusedtoestimatetheframebasedscores;thesescoresarethenintegratedintoHMM-basedsystemarchitectures,inwhathascometobeknownashybridsystems,asdescribedinsection11.5.
Aninterestingfeatureofframe-basedHMMsystemsisthatspeechsegmentsareidentifiedduringthesearchprocess,ratherthanexplicitly.Analternateapproachistofirstidentifyspeechsegments,thenclassifythesegmentsandusethesegmentscorestorecognizewords.Thisapproachhasproducedcompetitiverecognitionperformanceinseveraltasks.
2StateoftheArt
Commentsaboutthestate-of-the-artneedtobemadeinthecontextofspecificapplicationswhichreflecttheconstraintsonthetask.Moreover,differenttechnologiesaresometimesappropriatefordifferenttasks.Forexample,whenthevocabularyissmall,theentirewordcanbemodeledasasingleunit.Suchanapproachisnotpracticalforlargevocabularies,wherewordmodelsmustbebuiltupfromsubwordunits.
Thepastdecadehaswitnessedsignificantprogressinspeechrecognitiontechnology.Worderrorratescontinuetodropbyafactorof2everytwoyears.Substantialprogresshasbeenmadeinthebasictechnology,leadingtotheloweringofbarrierstospeakerindependence,continuousspeech,andlargevocabularies.Thereareseveralfactorsthathavecontributedtothisrapidprogress.First,thereisthecomingofageoftheHMM.HMMispowerfulinthat,withtheavailabilityoftrainingdata,theparametersofthemodelcanbetrainedautomaticallytogiveoptimalperformance.
Second,muchefforthasgoneintothedevelopmentoflargespeechcorporaforsystemdevelopment,training,andtesting.Someofthesecorporaaredesignedforacousticphoneticresearch,whileothersarehighlytaskspecific.Nowadays,itisnotuncommontohavetensofthousandsofsentencesavailableforsystemtrainingandtesting.Thesecorporapermitresearcherstoquantifytheacousticcuesimportantforphoneticcontrastsandtodetermineparametersoftherecognizersinastatisticallymeaningfulway.Whilemanyofthesecorpora(e.g.,TIMIT,RM,ATIS,andWSJ;seesection12.3)wereoriginallycollectedunderthesponsorshipoftheU.S.DefenseAdvancedResearchProjectsAgency(ARPA)tospurhumanlanguagetechnologydevelopmentamongitscontractors,theyhaveneverthelessgainedworld-wideacceptance(e.g.,inCanada,France,Germany,Japan,andtheU.K.)asstandardsonwhichtoevaluatespeechrecognition.
Third,progresshasbeenbroughtaboutbytheestablishmentofstandardsforperformanceevaluation.Onlyadecadeago,researcherstrainedandtestedtheirsystemsusinglocallycollecteddata,andhadnotbeenverycarefulindelineatingtrainingandtestingsets.Asaresult,itwasverydifficulttocompareperformanceacrosssystems,andasystem'sperformancetypicallydegradedwhenitwaspresentedwithpreviouslyunseendata.Therecentavailabilityofalargebodyofdatainthepublicdomain,coupledwiththespecificationofevaluationstandards,hasresultedinuniformdocumentationoftestresults,thuscontributingtogreaterreliabilityinmonitoringprogress(corpusdevelopmentactivitiesandevaluationmethodologiesaresummarizedinchapters12and13respectively).
Finally,advancesincomputertechnologyhavealsoindirectlyinfluencedourprogress.Theavailabilityoffastcomputerswithinexpensivemassstoragecapabilitieshasenabledresearcherstorunmanylargescaleexperimentsinashortamountoftime.Thismeansthattheelapsedtimebetweenanideaanditsimplementationandevaluationisgreatlyreduced.Infact,speechrecognitionsystemswithreasonableperformancecannowruninrealtimeusinghigh-endworkstationswithoutadditionalhardware---afeatunimaginableonlyafewyearsago.
Oneofthemostpopular,andpotentiallymostusefultaskswithlowperplexity(PP=11)istherecognitionofdigits.ForAmericanEnglish,speaker-independentrecognitionofdigitstringsspokencontinuouslyandrestrictedtotelephonebandwidthcanachieveanerrorrateof0.3%whenthestringlengthisknown.
Oneofthebestknownmoderate-perplexitytasksisthe1,000-wordso-calledResource5Management(RM)task,inwhichinquiriescanbema
- 配套讲稿:
如PPT文件的首页显示word图标,表示该PPT已包含配套word讲稿。双击word图标可打开word文档。
- 特殊限制:
部分文档作品中含有的国旗、国徽等图片,仅作为作品整体效果示例展示,禁止商用。设计者仅对作品中独创性部分享有著作权。
- 关 键 词:
- 语音识别 外文翻译 外文文献 英文文献 语音 识别 外文 翻译 文献 英文