{"id":"https://openalex.org/W2166317648","doi":"https://doi.org/10.1109/icassp.2004.1326034","title":"An automatic prosody labeling system using ANN-based syntactic-prosodic model and GMM-based acoustic-prosodic model","display_name":"An automatic prosody labeling system using ANN-based syntactic-prosodic model and GMM-based acoustic-prosodic model","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2166317648","doi":"https://doi.org/10.1109/icassp.2004.1326034","mag":"2166317648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5100420347","display_name":"Ken Chen","orcid":"https://orcid.org/0000-0003-4013-5279"},"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":"Ken Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","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"},"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":"M. Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109271145","display_name":"A. S. Cohen","orcid":"https://orcid.org/0009-0009-3843-0368"},"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":"A. Cohen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","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":3.9692,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.94886771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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/prosody","display_name":"Prosody","score":0.8956887722015381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.731683075428009},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.6839674711227417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6605522632598877},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5480241775512695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5476788282394409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4983632564544678},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.471230149269104},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.4657018780708313},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4405604600906372},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.42944058775901794},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17758971452713013}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8956887722015381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.731683075428009},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.6839674711227417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6605522632598877},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5480241775512695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476788282394409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4983632564544678},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.471230149269104},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.4657018780708313},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4405604600906372},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.42944058775901794},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17758971452713013},{"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:10.1109/icassp.2004.1326034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1535015163","https://openalex.org/W1577006985","https://openalex.org/W1993347555","https://openalex.org/W2088965663","https://openalex.org/W2093476462","https://openalex.org/W2107605728","https://openalex.org/W2166820052","https://openalex.org/W6632145054","https://openalex.org/W6634560542"],"related_works":["https://openalex.org/W4212971584","https://openalex.org/W2088008556","https://openalex.org/W1965454423","https://openalex.org/W2071315723","https://openalex.org/W2381837697","https://openalex.org/W2474947928","https://openalex.org/W2332932563","https://openalex.org/W2530248338","https://openalex.org/W2967415048","https://openalex.org/W4301230705"],"abstract_inverted_index":{"Automatic":[0],"prosody":[1,26,44,54,83],"labeling":[2,93],"is":[3,68],"important":[4],"for":[5,27,90,96,140,157],"both":[6,15],"speech":[7,11],"synthesis":[8],"and":[9,18,47,94,105,128,142,144],"automatic":[10],"understanding.":[12],"Humans":[13],"use":[14],"syntactic":[16,77],"cues":[17,20],"acoustic":[19,103],"to":[21,82],"develop":[22],"their":[23],"prediction":[24],"of":[25,79,88,160],"a":[28,48,112],"given":[29],"utterance.":[30],"This":[31],"process":[32],"can":[33,121],"be":[34],"effectively":[35],"modeled":[36],"by":[37],"an":[38,86],"ANN-based":[39],"syntactic-prosodic":[40],"model":[41,51],"that":[42,52,66],"predicts":[43,53],"from":[45,55,75],"syntax":[46],"GMM-based":[49,113],"acoustic-prosodic":[50,56,114],"observations.":[57],"Our":[58],"experiments":[59],"on":[60,152],"the":[61,72,76,118,153,158],"Radio":[62],"News":[63],"Corpus":[64],"show":[65],"ANN":[67],"effective":[69],"in":[70],"learning":[71],"stochastic":[73],"mapping":[74],"representation":[78],"word":[80],"strings":[81],"labels,":[84],"with":[85,117],"accuracy":[87,127],"82.7%":[89],"pitch":[91,124],"accent":[92,125],"90.5%":[95],"intonational":[97],"phrase":[98],"boundary":[99],"(IPB)":[100],"labeling.":[101],"When":[102],"observations":[104],"reasonably":[106],"accurate":[107],"phoneme":[108],"transcriptions":[109],"are":[110,135],"given,":[111],"model,":[115,120],"coupled":[116],"syntactical-prosodic":[119],"achieve":[122],"84%":[123],"recognition":[126,131],"93%":[129],"IPB":[130,161],"accuracy.":[132],"These":[133],"results":[134,151],"obtained":[136],"using":[137],"different":[138],"speakers":[139],"training":[141],"testing":[143],"have":[145],"considerably":[146],"exceeded":[147],"all":[148],"previously":[149],"reported":[150],"same":[154],"corpus,":[155],"especially":[156],"task":[159],"detection.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}