{"id":"https://openalex.org/W272647413","doi":"https://doi.org/10.21437/eurospeech.2003-153","title":"Prosody dependent speech recognition with explicit duration modelling at intonational phrase boundaries","display_name":"Prosody dependent speech recognition with explicit duration modelling at intonational phrase boundaries","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W272647413","doi":"https://doi.org/10.21437/eurospeech.2003-153","mag":"272647413"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-153","doi":"https://doi.org/10.21437/eurospeech.2003-153","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-153","pdf_url":null,"source":{"id":"https://openalex.org/S7407089324","display_name":"European Conference on Speech Communication and Technology (Eurospeech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"K. Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Chen","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050462311","display_name":"Sarah Borys","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Borys","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893","observed_orcids":["https://orcid.org/0000-0002-5631-2893"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001457934","display_name":"Jennifer Cole","orcid":"https://orcid.org/0000-0002-0465-4920","observed_orcids":["https://orcid.org/0000-0002-0465-4920"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Cole","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.5722,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82224486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0003000000142492354,"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/T10860","display_name":"Speech and Audio Processing","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/intonational-phrase-boundaries","display_name":"intonational phrase boundaries","score":0.9779999852180481},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.5529999732971191},{"id":"https://openalex.org/keywords/boundary-detection","display_name":"boundary detection","score":0.5950000286102295},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.917452871799469},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7830938100814819},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7600297331809998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7324395179748535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249748706817627},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5966838002204895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5573002099990845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5291978120803833},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5087729096412659},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17390650510787964},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10810533165931702},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07371905446052551},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-153","doi":"https://doi.org/10.21437/eurospeech.2003-153","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-153","pdf_url":null,"source":{"id":"https://openalex.org/S7407089324","display_name":"European Conference on Speech Communication and Technology (Eurospeech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W82292940","https://openalex.org/W190621901","https://openalex.org/W1481826355","https://openalex.org/W1577006985","https://openalex.org/W1988000972","https://openalex.org/W1993347555","https://openalex.org/W1997485640","https://openalex.org/W2064218608","https://openalex.org/W2116952749"],"related_works":["https://openalex.org/W7095738818","https://openalex.org/W7099385961","https://openalex.org/W7098805688","https://openalex.org/W2138435742","https://openalex.org/W2521676642","https://openalex.org/W2107605728","https://openalex.org/W1568653222","https://openalex.org/W116380143","https://openalex.org/W146635250","https://openalex.org/W1582730572"],"abstract_inverted_index":{"Does":[0],"prosody":[1,22,31,107,123,149],"help":[2],"word":[3,16,28,135],"recognition?":[4],"In":[5],"this":[6,37],"paper,":[7],"we":[8,34],"propose":[9],"a":[10,24],"novel":[11],"probabilistic":[12],"framework":[13],"in":[14,23,36,48,126],"which":[15,103],"and":[17,131,138],"phoneme":[18,67],"are":[19,142],"dependent":[20,108],"on":[21,74],"way":[25],"that":[26,33,90],"improves":[27,105],"recognition.":[29],"The":[30],"attribute":[32],"investigate":[35],"study":[38,71],"is":[39,61,72,116],"the":[40,45,49,93,106],"duration":[41,68,114],"lengthening":[42,91],"effects":[43],"of":[44,51,92],"speech":[46],"segments":[47],"vicinity":[50],"intonational":[52],"phrase":[53,94,119],"boundaries.":[54],"Explicit":[55],"Duration":[56],"Hidden":[57],"Markov":[58],"Model":[59],"(EDHMM)":[60],"implemented":[62,125],"to":[63],"provide":[64],"an":[65],"accurate":[66],"model.":[69],"This":[70],"conducted":[73],"Boston":[75],"University":[76],"Radio":[77],"New":[78],"Corpus":[79],"with":[80],"prosodic":[81],"boundaries":[82],"marked":[83],"using":[84],"ToBI":[85],"labelling":[86],"system.":[87],"We":[88],"found":[89,117],"final":[95],"rhymes":[96],"can":[97],"be":[98],"reliably":[99],"modelled":[100],"by":[101,144],"EDHMM,":[102],"significantly":[104],"acoustic":[109,127],"modelling.":[110],"Conversely,":[111],"no":[112],"systematic":[113],"variation":[115],"at":[118],"initial":[120],"position.":[121],"With":[122],"dependence":[124],"model,":[128,133],"pronunciation":[129],"model":[130],"language":[132],"both":[134],"recognition":[136,140],"accuracy":[137,141],"boundary":[139],"improved":[143],"1%":[145],"over":[146],"systems":[147],"without":[148],"dependence.":[150]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}