基本资料
金琴,美国卡内基梅隆大学博士。主要研究领域包括声纹识别,语音识别与理解,音频信息处理,多媒体信息挖掘,自然语言处理,以及统计机器学习。已在国外一流期刊和会议上发表四十多篇论文。在美国期间,作为关键研究人员参与了多项大型的科研项目,包括由美国国防部DARPA资助,美国IARPA资助,欧盟FP6资助的项目等。除此之外,还作为项目负责人成功地主持并完成了由美国空军研究所资助的两个项目。多次应邀评审国际语音研究领域一流期刊论文包括:IEEETASLP,SpeechCommunications等等。
欢迎同学们报考我的研究生,也欢迎高年级本科生加入我们的课题组,参与我们的科研工作。如果你对我们的研究方向感兴趣,请直接与我联系。
Email:qjin@ruc.edu.cn
Phone:010-62510042
详细资料
主要研究方向声纹识别,语音识别与理解,音频信息处理,多媒体信息挖掘,自然语言处理,以及统计机器学习
发表论文选列QinJin,PeterSchulam,ShourabhRawat,SusanneBurger,DuoDingandFlorianMetze.“Event-basedVideoRetrievalUsingAudio”,inProc.ofthe13thAnnualConf.oftheInternationalSpeechCommunicationAssociation(INTERSPEECH2012),Protland,USA,7thSeptember,2012.KornelLaskowskiandQinJin.“HarmonicStructureTransformforSpeakerRecognition”.InProc.ofthe12thAnnualConf.oftheInternationalSpeechCommunicationAssociation(INTERSPEECH2011),Florence,Italy,28,August2011.QinJin,ThomasFangZheng,"OverviewofFront-endFeaturesforRobustSpeakerRecognition",TheThirdAPSIPAAnnualSummitandConference(APSIPAASC2011)UdhayNallasamy,MichaelGarbus,FlorianMetze,QinJin,ThomasSchaff,TanjaSchultz.“AnalysisofDialectalInfluenceinPan-ArabicASR”.InProc.ofthe12thAnnualConf.oftheInternationalSpeechCommunicationAssociation(INTERSPEECH2011),Florence,Italy,28,August2011.QianYang,QinJin,TanjaSchultz.“InvestigationofCross-showSpeakerDiarization”.InProc.ofthe12thAnnualConf.oftheInternationalSpeechCommunicationAssociation(INTERSPEECH2011),Florence,Italy,28,August2011.StephenM.Chu,Hong-KwangKuo,LidiaMangu,QinShi,ShileiZhang,YongQin,QinJin,IanLaneandYik-CheungTam,“TowardstheStateoftheArtinAutomaticMandarinBroadcastSpeechTranscription”.HandbookofNaturalLanguageProcessingandMachineTranslation,Chapter3.5.2,pp.487-495,Springer,ISBN978-1-4419-7712-0,2011.RogerHsiao,MarkFuhs,Yik-CheungTam,QinJin,IanLane,andTanjaSchultz,“CMU-InterACTMandarinTranscriptionSystemforGALE”.HandbookofNaturalLanguageProcessingandMachineTranslation,Chapter3.5.3,pp.496-504,Springer,ISBN978-1-4419-7712-0,2011.UdhyakumarNallasamy,IanLane,MarkFuhs,MohamedNoamany,Yik-CheungTam,QinJinandTanjaSchultz,“CMU-InterACTArabicSpeechRecognitionSystemforGALE”.HandbookofNaturalLanguageProcessingandMachineTranslation,Chapter3.6.4,pp.535-540,Springer,ISBN978-1-4419-7712-0,2011.QinJin,RunxinLi,QianYang,KornelLaskowski,TanjaSchultz.“SpeakerIndeitificationwithDistantMicrophoneSpeech”,InProc.IEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP2010),Dallas,TX,USA,14-19April.KornelLaskowskiandQinJin.“ModelingProsodyforSpeakerRecognition:WhyEstimatingPitchMayBeaRedHerring”.InProc.ofthe7thISCASpeakerandLanguageRecognitionWorkshop(ODYSSEY2010),Brno,CzechRepublic,28June-01July.FlorianMetze,RogerHsiao,QinJin,UdhayNallasamy,TanjaSchultz.“The2010CMUGALESpeech-to-TextSystem”.InProc.ofthe11thAnnualConferenceoftheInternationalSpeechCommunicationAssociation(INTERSPEECH2010),Makuhari,Japan,26,September2010.QinJin,ArthurToth,TanjaSchultz,andAlanBlack,“SpeakerDe-identificationviaVoiceTransformation”,InProc.OfIEEEworkshoponAutomaticSpeechRecognitionandUnderstanding(ASRU2009),Merano,Italy.MatthiasW?lfel,QianYang,QinJin,TanjaSchultz.“SpeakerIdentificationusingWarpedMVDRCepstralFeatures”,InProc.ofInterspeech2009,Brighton,UnitedKingdom,06.September2009.RunxinLi,QinJin,TanjaSchultz.“ImprovingSpeakerSegmentationviaSpeakerIdentificationandTextSegmentation”,InProc.OfInterspeech2009,Brighton,UnitedKingdom,06.September2009.QinJin,ArthurR.Toth,TanjaSchultz,AlanWBlack.“VoiceConvergin:SpeakerDe-IdentificationbyVoiceTransformation”,Inproceedingsofthe34thIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP2009),Taipei,Taiwan,19-24April,pp3909-3912.KornelLaskowskiandQinJin,“ModelingInstantaneousIntonationforSpeakerIdentificationUsingtheFundamentalFrequencyVariationSpectrum”.Inproceedingsofthe34thIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP2009),Taipei,Taiwan,19-24April,pp4541-4544.MarkC.Fuhs,QinJin,andTanjaSchultz.“DetectingBandlimitedAudioinBroadcastTelevisionShows”.Inproceedingsofthe34thIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP2009),Taipei,Taiwan,19-24April,pp4589-4592.HaizhouLi,BinMa,K-A.Lee,HanwuSun,DonglaiZhu,KheChaiSim,ChanghuaiYou,RongTong,IsmoKarkkainen,Chien-LinHuang,VladimirPervouchine,WuGuo,YijieLi,LirongDai,M.Nosratighods,T.Tharmarajah,JulienEpps,E.Ambikairajah,E.-S.Chng,QinJin,TanjaSchultz.“TheI4USystemInNIST2008SpeakerRecognitionEvaluation”.Inproceedingsofthe34thIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP2009),Taipei,Taiwan,19-24April,pp4201-4204.QinJin,TanjaSchultz.“RobustFar-FieldSpeakerIdentificationUnderMismatchedConditions”,inproceedingsofInterSpeech2008,Brisbane,Australia,22.September2008.QinJin,KshitizKumar,TanjaSchultz,RichardMStern,“CompensationApproachesforFar-fieldSpeakerIdentification”,NISTSREWorkshop2008,NISTSRE2008,Montreal,Canada,17.June2008.QinJin,ArthurToth,AlanBlack,andTanjaSchultz.“IsVoiceTransformationaThreattoSpeakerIdentification?”,inproceedingsoftheIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP-2008),LasVagas,April,2008.RogerHsiao,MarkFuhs,Yik-CheungTam,QinJin,TanjaSchultz.“TheCMU-InterACT2008MandarinTranscriptionSystem”,inproceedingsofInterSpeech2008,Brisbane,Australia,22.September2008.QinJin,Szu-ChenStanJou,andTanjaSchultz.“WhisperingSpeakerIdentification”,inproceedingsofInternationalConferenceonMultimedia&Expo(ICME),Beijing,P.R.China,July2007.QinJin,TanjaSchultz,andAlexWaibel.“Far-fieldSpeakerRecognition”.InIEEEtransactionsonAudio,Speech,andLanguageProcessing(TASL),Vol.15,No.7,September,2007.HazimK.EkenelandQinJin.“ISLPersonIdentificationSystemsintheCLEAREvaluations”.InMultimodalTechnologiesforPerceptionofHumansofLectureNotesinComputerScience,SpringerBerlin/Heidelberg,May18,2007.QinJin,YuePan,andTanjaSchultz.“Far-fieldSpeakerRecognition”,inProceedingsoftheIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP-2006),Toulouse,France,May2006.HazimKemalandQinJin.“ISLPersonIdentificationSystemsintheCLEAREvaluations”,intheProceedingsofCLEAREvaluationWorkshop(CLEAR-2006),Southampton,UK,April2006.SebastianStüker,ChristianFügen,RogerHsiao,ShajithIkbal,QinJin,FlorianKraft,MatthiasPaulik,MartinRaab,Yik-CheungTam,andMatthiasW?lfel.“TheISLTC-STARSpring2006ASREvaluationSystems”,inProceedingsoftheTC-STARWorkshoponSpeech-to-SpeechTranslation,Barcelona,Spain,2006,ELDA.QinJinandTanjaSchultz."SpeakerSegmentationandClusteringinMeetings".InproceedingsofInternationalConferenceofSpokenLanguageProcessing(ICSLP-2004),JejuIsland,SouthKorea,October2004.KornelLaskowski,QinJin,andTanjaSchultz."Crosscorrelation-basedMultispeakerSpeechActivityDetection".InproceedingsofInternationalConferenceofSpokenLanguageProcessing(ICSLP-2004),JejuIsland,SouthKorea,October2004.KornelLaskowski,QinJin,andTanjaSchultz."Crosscorrelation-basedMultispeakerSpeechActivityDetection".InproceedingsofInternationalConferenceofSpokenLanguageProcessing(ICSLP-2004),JejuIsland,SouthKorea,October2004.FlorianMetze,QinJin,ChristianFügen,KornelLaskowski,YuePan,andTanjaSchultz."IssuesinMeetingTranscription-TheISLMeetingTranscriptionSystem".InproceedingsofInternationalConferenceofSpokenLanguageProcessing(ICSLP-2004),JejuIsland,SouthKorea,October2004.HuaYu,Yik-CheungTam,ThomasSchaaf,SebastianStüker,QinJin,MohamedNoamany,andTanjaSchultz."TheISLRT04MandarinBroadcastNewsEvaluationSystem".EARSRichTranscriptionWorkshop,Palisades,NY,November2004.QinJin,JiriNavratil,DouglasReynolds,Joseph.Campbell,Walter.Andrews,andJoyAbramson."CombiningCross-StreamandTimeDimensionsinPhoneticSpeakerRecognition".InproceedingsoftheIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP-2003),HongKong,China,April2003.JiriNavratil,QinJin,WalterAndrews,andJosephCampbell."PhoneticSpeakerRecognitionUsingMaximum-likelihoodBinary-DecisionTreeMothods".InproceedingsoftheIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP-2003),HongKong,China,April2003.D.Reynolds,W.Andrews,J.Campbell,J.Navratil,B.Peskin,A.Adami,Q.Jin,D.Klusacek,J.Abramson,R.Mihaescu,J.Godfrey,D.Jones,andB.Xiang."TheSuperSIDProject:ExploitingHigh-levelInformationforHigh-accuracySpeakerRecognition".InproceedingsoftheIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP-2003),HongKong,China,April2003.QinJin,TanjaSchultz,andAlexWaibel."PhoneticSpeakerIdentification".InproceedingsoftheInternationalConferenceofSpokenLanguageProcessing(ICSLP-2002),Denver,CO,September2002.QinJin,TanjaSchultzandAlexWaibel."SpeakerIdentificationUsingMultilingualPhoneStrings".InproceedingsoftheIEEEInternationalConferenceonAcoustics,Speech,andSignalProcessing(ICASSP-2002),Orlando,Florida,May2002.TanjaSchultz,QinJin,KornelLaskowski,AliciaTribble,andAlexWaibel."ImprovementsinNon-verbalCueIdentificationusingMultilingualPhoneStrings".InproceedingsoftheSpeech-to-SpeechTranslationWorkshoponthe40thAnniversaryMeetingoftheAssociationforComputationalLinguistics(ACL-2002),Philadelphia,July6-12,2002.TanjaSchultz,QinJin,KornelLaskowski,AliciaTribbleandAlexWaibel.Speaker,AccentandLanguageIdentificationUsingMultilingualPhoneStrings".InproceedingsoftheHumanLanguageTechnologyMeeting(HLT-2002),SanDiego,March2002.QinJinANaiveDe-lambingMethodforSpeakerIdentification".InproceedingsofInternationalConferenceonSpokenLanguageProcessing(ICSLP-2000),Beijing,P.R.China,October2000.QinJinandAlexWaibel."ApplicationofLDAtoSpeakerRecognition".InproceedingsofInternationalConferenceonSpokenLanguageProcessing(ICSLP-2000),Beijing,P.R.China,October2000.
主要工作经历- 2013.01-今,中国人民大学,副教授
- 2012.04-2012.12,IBM中国研究院,研究员
- 2008.06-2012.03,美国卡内基梅隆大学,研究员,教师
- 2007.02-2008.05,美国卡内基梅隆大学,博士后
- 1999.08-2007.01,美国卡内基梅隆大学,博士