{"id":"https://openalex.org/W88973623","doi":"https://doi.org/10.21437/interspeech.2004-557","title":"Modeling pronunciation variation using artificial neural networks for English spontaneous speech","display_name":"Modeling pronunciation variation using artificial neural networks for English spontaneous speech","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W88973623","doi":"https://doi.org/10.21437/interspeech.2004-557","mag":"88973623"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-557","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ken Chen","raw_affiliation_strings":["Bioinformatics & Computational Biology"],"affiliations":[{"raw_affiliation_string":"Bioinformatics & Computational Biology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111477492","display_name":"Mark Hasegawa-Johnson","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100420347"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9652,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77525805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1461","last_page":"1464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.987500011920929,"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/pronunciation","display_name":"Pronunciation","score":0.8880296945571899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.807586669921875},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.7481821775436401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466253995895386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5886974930763245},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5741548538208008},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5442299246788025},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5018949508666992},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4724077582359314},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4721522331237793},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43707275390625},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16526922583580017}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8880296945571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807586669921875},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7481821775436401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466253995895386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5886974930763245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5741548538208008},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5442299246788025},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5018949508666992},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4724077582359314},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4721522331237793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43707275390625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16526922583580017},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/interspeech.2004-557","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W103827355","https://openalex.org/W1520302542","https://openalex.org/W1579089397","https://openalex.org/W1597422500","https://openalex.org/W1991431352","https://openalex.org/W2015720298","https://openalex.org/W2083620624","https://openalex.org/W2127611282","https://openalex.org/W2186659461"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497","https://openalex.org/W2376590243","https://openalex.org/W2556800355"],"abstract_inverted_index":{"Pronunciation":[0],"variation":[1,42,73,114],"in":[2,12,107],"conversational":[3],"speech":[4,16],"has":[5],"caused":[6],"significant":[7],"amount":[8],"of":[9,112,119],"word":[10],"errors":[11],"large":[13],"vocabulary":[14],"automatic":[15],"recognition.":[17],"Rule-based":[18],"approaches":[19,23],"and":[20],"decision-tree":[21],"based":[22],"have":[24,79],"been":[25,80],"previously":[26,56,81],"proposed":[27],"to":[28,93],"model":[29],"pronunciation":[30,41,72,113],"variation.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,50],"report":[36],"our":[37],"work":[38],"on":[39,59,115],"modeling":[40,71],"using":[43],"artificial":[44],"neural":[45],"networks":[46],"(ANN).":[47],"The":[48],"results":[49],"achieved":[51],"are":[52],"significantly":[53],"better":[54,68],"than":[55,74],"published":[57],"ones":[58],"two":[60],"different":[61],"corpora,":[62],"indicating":[63],"that":[64,78,86,102],"ANN":[65],"may":[66],"be":[67,91],"suited":[69],"for":[70],"other":[75],"statistical":[76],"models":[77],"investigated.":[82],"Our":[83],"experiments":[84],"indicate":[85],"binary":[87],"distinctive":[88],"features":[89],"can":[90],"used":[92],"effectively":[94],"represent":[95],"the":[96,110,120],"phonological":[97],"context.":[98],"We":[99],"also":[100],"find":[101],"including":[103],"pitch":[104],"accent":[105],"feature":[106],"input":[108],"improves":[109],"prediction":[111],"a":[116],"ToBI-labeled":[117],"subset":[118],"Switchboard":[121],"corpus.":[122]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}