{"id":"https://openalex.org/W42120822","doi":"https://doi.org/10.21437/icslp.2000-299","title":"Using bayesian belief networks for model duration in text-to-speech systems","display_name":"Using bayesian belief networks for model duration in text-to-speech systems","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W42120822","doi":"https://doi.org/10.21437/icslp.2000-299","mag":"42120822"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-299","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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/A5060900351","display_name":"Olga Goubanova","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Olga Goubanova","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089724584","display_name":"Paul Taylor","orcid":"https://orcid.org/0000-0002-8213-0380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Taylor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1485,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91538462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"vol. 2, 427","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7418760061264038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324858903884888},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5627756714820862},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5572088956832886},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.5465663075447083},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5370411276817322},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5264718532562256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4933296740055084},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.48288798332214355},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4355596601963043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4348587393760681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43327462673187256},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43175289034843445}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7418760061264038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324858903884888},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5627756714820862},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5572088956832886},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.5465663075447083},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5370411276817322},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5264718532562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4933296740055084},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.48288798332214355},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4355596601963043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4348587393760681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43327462673187256},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43175289034843445},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2000-299","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W12485773","https://openalex.org/W1993533823","https://openalex.org/W2049073556","https://openalex.org/W2049510512","https://openalex.org/W2152024332","https://openalex.org/W3085162807"],"related_works":["https://openalex.org/W3183113072","https://openalex.org/W2126934800","https://openalex.org/W2187019487","https://openalex.org/W1715419791","https://openalex.org/W643788828","https://openalex.org/W2158940596","https://openalex.org/W4200510307","https://openalex.org/W3125134981","https://openalex.org/W2188106786","https://openalex.org/W1554198325"],"abstract_inverted_index":{"We":[0,86,174,204],"present":[1],"a":[2,12,20,34,38,42,58,88,111,127,158],"new":[3,221,258,268],"Bayesian-based":[4],"probabilistic":[5,89],"approach":[6,94],"to":[7,70,95,245,253,265,267],"modelling":[8],"segmental":[9,51,132],"duration":[10,16,52,80,109],"in":[11,57,123,145,199,229],"text-to-speech":[13,202],"system.":[14,203],"Segment":[15],"is":[17,139,250],"influenced":[18],"by":[19,191],"number":[21],"of":[22,37,62,72,78,116,152,160,169,178,184,187],"contextual":[23],"factors":[24,48,138],"such":[25],"as":[26,110,141],"segment":[27,40,79,108],"identity,":[28],"stress,":[29],"accent,":[30],"local":[31],"context":[32],"within":[33,41],"syllable,":[35,43],"position":[36],"target":[39],"word,":[44],"and":[45,99,118,171,194,206,255],"utterance.":[46],"The":[47,134,215],"that":[49,130,219],"affect":[50],"interact":[53],"with":[54,68,182,231,257],"each":[55,121],"other":[56,242],"complex":[59],"way.":[60],"Databases":[61],"speech":[63],"data":[64,97],"are":[65],"often":[66],"imbalanced":[67],"respect":[69],"frequencies":[71],"different":[73],"factors\u2019":[74],"combinations.":[75],"A":[76],"model":[77,107,181,190,197,222,239],"should":[81,261],"account":[82],"for":[83,247],"these":[84],"problems.":[85,102],"propose":[87],"Bayesian":[90,113],"belief":[91],"network":[92,114,125],"(BN)":[93],"tackle":[96],"sparsity":[98],"factor":[100,129],"interaction":[101,135],"In":[103],"our":[104,220,238],"work,":[105],"we":[106,156,236],"hybrid":[112],"consisting":[115],"discrete":[117],"continuous":[119],"nodes;":[120],"node":[122],"the":[124,137,146,150,153,167,176,179,185,195,200,212,224,232],"represents":[126],"linguistic":[128],"affects":[131],"duration.":[133],"between":[136],"represented":[140],"conditional":[142],"dependence":[143],"relations":[144],"graphical":[147],"model.":[148,234],"For":[149],"purposes":[151],"current":[154],"research":[155],"used":[157],"database":[159],"over":[161],"1000":[162],"prosodically":[163],"rich":[164],"sentences":[165],"from":[166],"speakers":[168],"American":[170],"RP":[172],"English.":[173],"contrasted":[175],"results":[177,216],"BN":[180],"those":[183],"sums":[186],"products":[188],"(SoP)":[189],"van":[192],"Santen":[193],"CART":[196,225],"implemented":[198],"Festival":[201],"trained":[205],"tested":[207],"all":[208],"three":[209],"models":[210],"on":[211],"same":[213],"data.":[214],"have":[217],"shown":[218],"outperforms":[223],"model;":[226],"it":[227,249,263],"compares":[228],"performance":[230],"SoP":[233],"However,":[235],"think":[237],"has":[240],"many":[241],"advantages":[243],"compared":[244],"SoP,":[246],"instance":[248],"much":[251],"easier":[252,264],"configure":[254],"experiment":[256],"features.":[259],"This":[260],"make":[262],"adapt":[266],"languages.":[269]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}