{"id":"https://openalex.org/W17294665","doi":"https://doi.org/10.21437/eurospeech.2003-336","title":"Time adjustable mixture weights for speaking rate fluctuation","display_name":"Time adjustable mixture weights for speaking rate fluctuation","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W17294665","doi":"https://doi.org/10.21437/eurospeech.2003-336","mag":"17294665"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-336","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sadaoki Furui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"973","last_page":"976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8203191161155701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6917340755462646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6625391244888306},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6313295364379883},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5862133502960205},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5038396716117859},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4940626919269562},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48086482286453247},{"id":"https://openalex.org/keywords/hidden-variable-theory","display_name":"Hidden variable theory","score":0.47430944442749023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4690535366535187},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4498908519744873},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41860267519950867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3553197383880615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.355260968208313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30255067348480225}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8203191161155701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6917340755462646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625391244888306},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6313295364379883},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5862133502960205},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5038396716117859},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4940626919269562},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48086482286453247},{"id":"https://openalex.org/C137002209","wikidata":"https://www.wikidata.org/wiki/Q898521","display_name":"Hidden variable theory","level":3,"score":0.47430944442749023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4690535366535187},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4498908519744873},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41860267519950867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3553197383880615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.355260968208313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30255067348480225},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-336","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1493898446","https://openalex.org/W2096044236","https://openalex.org/W2102637746","https://openalex.org/W2122678358"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Abstract":[0],"Oneof":[1],"themostseriousproblemsin":[2],"spontaneousspeechrecog-nition":[3],"is":[4,63,103,126,143,172,182,237,263,273,283,296,323,340,346],"the":[5,33,42,45,57,67,93,120,123,127,146,157,166,169,187,190,205,232,240,267,280,300,313,332,343,350,361],"degradation":[6],"of":[7,26,44,48,56,119,130,185,200,204,226,247],"recognition":[8,124,351],"accuracy":[9,83],"due":[10],"to":[11,65,140,155,161,243,265,312,325],"thespeaking":[12],"rate":[13,95,114,125,148,159,171,315,355],"\ufb02uctuation":[14],"in":[15,72,165,305,328,336,358],"an":[16,27,179,292],"utterance.":[17,136],"This":[18,195],"paper":[19,196,272,362],"proposesa":[20],"method":[21,80,199,236,262,282,322,345],"for":[22,86,115,256],"adjusting":[23,186],"mixture":[24,202],"weights":[25,203],"HMM":[28,102,206,248],"frame":[29,209],"byframe":[30],"depending":[31],"on":[32,89],"local":[34],"speaking":[35,94,147,158,170,191,212,314],"rate.":[36,213],"The":[37,258,320],"proposedmethodisimplementedusingtheBayesiannetworkframework.A":[38],"hidden":[39,215],"variable":[40,128,216],"representing":[41],"variation":[43],"\u201cmode\u201d":[46],"ofthespeakingrateisintroducedanditsvaluecontrolsthemixtureweights":[47],"Gaussian":[49],"mixtures.":[50],"Model":[51],"training":[52],"and":[53,149,177,255,308,331],"maximumprobability":[54],"assignment":[55],"variablesare":[58],"conducted":[59],"usingtheEM/GEMandinferencealgorithmsforBayesiannetworks.":[60],"TheBayesian":[61],"network":[62,259,302],"used":[64,264],"rescore":[66,266],"acoustic":[68,227,268],"likelihood":[69],"ofthe":[70],"hypotheses":[71],"N-best":[73,270],"lists.":[74],"Experimental":[75],"results":[76,333],"show":[77],"thatthe":[78],"proposed":[79,235,261,321,344],"improves":[81],"word":[82],"by":[84,99],"1.6%":[85],"theabsolute":[87],"value":[88],"meeting":[90,326],"speech":[91],"given":[92],"in-formation,":[96],"whereas":[97],"improvement":[98],"a":[100,111,174,198,219,286],"regression":[101],"lesssigni\ufb01cant.":[104],"1.":[105],"Introduction":[106],"Conventional":[107],"HMM-based":[108],"recognizers":[109],"suffer":[110],"lower":[112],"recogni-tion":[113],"spontaneous":[116],"speech.":[117],"One":[118],"signi\ufb01cant":[121],"factorsreducing":[122],"nature":[129],"sponta-neousutterances[1].":[131],"For":[132],"example,thespeakingratecanchangeeven":[133],"within":[134],"one":[135],"A":[137,214],"possible":[138],"strategy":[139],"manage":[141],"thisproblem":[142],"\ufb01rst":[144],"estimating":[145,168],"then":[150],"adjustingarecognizer":[151],"basedonthe":[152],"speakingrate.":[153],"Thispaperinvestigateshow":[154],"use":[156],"information":[160],"control":[162,246],"probabilitydensity":[163],"functions":[164],"HMM.Since":[167],"itself":[173],"dif\ufb01cult":[175],"prob-lem":[176],"assuming":[178],"accurate":[180],"detection":[181],"unrealistic,":[183],"themethod":[184],"decoder":[188],"accordingto":[189],"rateshould":[192],"be":[193],"probabilistic.":[194],"proposes":[197],"ad-justing":[201],"at":[207],"every":[208],"based":[210],"onthe":[211],"that":[217,342],"represents":[218],"\u201cmode\u201dofthespeakingratecontrolsthemixtureweights.":[220],"Theproposedmethod":[221],"can":[222],"model":[223],"complex":[224],"changes":[225],"characteristicswith":[228],"only":[229],"asmall":[230],"increaseof":[231],"numberof":[233],"parameters.The":[234],"implemented":[238],"using":[239],"Bayesiannetwork":[241],"framework":[242],"realize":[244],"detailed":[245],"param-eters[2].":[249],"WeuseGMTK[3]for":[250],"modelparametertraining":[251],"usingthe":[252],"EM/GEM":[253],"algorithms":[254],"decoding.":[257],"ac-ceptsthespeakingrateinadditiontotheusualacousticfeatures.The":[260],"likelihoodof":[269],"hypotheses.This":[271],"organized":[274],"as":[275,285],"follows.":[276],"In":[277,289],"Section":[278,306,329,359],"2,":[279],"pro-posed":[281],"formulated":[284],"Bayesian":[287,301],"network.":[288],"Sec-tion":[290,337],"3,":[291],"experimental":[293],"set":[294],"up":[295],"described.":[297],"Training":[298],"processesof":[299],"are":[303,316,334],"described":[304],"4,":[307],"ob-tained":[309],"parameters":[310],"related":[311],"analyzed":[317],"inSection":[318],"5.":[319],"applied":[324],"speechrecognition":[327],"6":[330],"discussed":[335],"7.":[338],"It":[339],"shown":[341],"more":[347],"effectivein":[348],"improving":[349],"ratethan":[352],"aregressionHMM":[353],"givenspeaking":[354],"information.":[356],"Finally,":[357],"8,":[360],"isconcluded.":[363]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}