{"id":"https://openalex.org/W116380143","doi":"https://doi.org/10.21437/speechprosody.2004-134","title":"How prosody improves word recognition","display_name":"How prosody improves word recognition","publication_year":2004,"publication_date":"2004-03-23","ids":{"openalex":"https://openalex.org/W116380143","doi":"https://doi.org/10.21437/speechprosody.2004-134","mag":"116380143"},"language":"en","primary_location":{"id":"doi:10.21437/speechprosody.2004-134","doi":"https://doi.org/10.21437/speechprosody.2004-134","is_oa":true,"landing_page_url":"https://doi.org/10.21437/speechprosody.2004-134","pdf_url":"https://www.isca-archive.org/speechprosody_2004/chen04c_speechprosody.pdf","source":{"id":"https://openalex.org/S2764846564","display_name":"Speech prosody","issn_l":"2333-2042","issn":["2333-2042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"Speech Prosody 2004","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.isca-archive.org/speechprosody_2004/chen04c_speechprosody.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ken 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":true,"raw_author_name":"Ken Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign, Urbana, IL 61801"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign, Urbana, IL 61801","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","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":["Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign , Urbana , IL 61801","University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign , Urbana , IL 61801","institution_ids":["https://openalex.org/I157725225"]},{"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":1.5105,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81655014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"586"},"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":0.00039999998989515007,"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/prosody","display_name":"prosody","score":0.9789999723434448},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.9900000095367432},{"id":"https://openalex.org/keywords/bayesian-network-model","display_name":"Bayesian network model","score":0.7820000052452087},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.9169999957084656},{"id":"https://openalex.org/keywords/acoustic-observation","display_name":"acoustic observation","score":0.7799999713897705}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7192428708076477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131866216659546},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6531988382339478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6484902501106262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5213378667831421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43744680285453796},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24391880631446838},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/speechprosody.2004-134","doi":"https://doi.org/10.21437/speechprosody.2004-134","is_oa":true,"landing_page_url":"https://doi.org/10.21437/speechprosody.2004-134","pdf_url":"https://www.isca-archive.org/speechprosody_2004/chen04c_speechprosody.pdf","source":{"id":"https://openalex.org/S2764846564","display_name":"Speech prosody","issn_l":"2333-2042","issn":["2333-2042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"Speech Prosody 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.1792","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.1792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.uiuc.edu/speech/pubs/2004/Chen_PDSR_SP04.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.21437/speechprosody.2004-134","doi":"https://doi.org/10.21437/speechprosody.2004-134","is_oa":true,"landing_page_url":"https://doi.org/10.21437/speechprosody.2004-134","pdf_url":"https://www.isca-archive.org/speechprosody_2004/chen04c_speechprosody.pdf","source":{"id":"https://openalex.org/S2764846564","display_name":"Speech prosody","issn_l":"2333-2042","issn":["2333-2042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"Speech Prosody 2004","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W116380143.pdf","grobid_xml":"https://content.openalex.org/works/W116380143.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W190621901","https://openalex.org/W1501622705","https://openalex.org/W1560370201","https://openalex.org/W1577006985","https://openalex.org/W1993347555","https://openalex.org/W2039151035","https://openalex.org/W2107605728","https://openalex.org/W2115316195","https://openalex.org/W2116952749","https://openalex.org/W2125428621","https://openalex.org/W2128758093","https://openalex.org/W2165487751","https://openalex.org/W2729906263"],"related_works":["https://openalex.org/W2138435742","https://openalex.org/W2521676642","https://openalex.org/W7030530614","https://openalex.org/W7098805688","https://openalex.org/W2998208946","https://openalex.org/W2101694857","https://openalex.org/W2803516655","https://openalex.org/W7095738818","https://openalex.org/W146635250","https://openalex.org/W2060577515"],"abstract_inverted_index":{"Prosody":[0],"has":[1,88],"been":[2],"traditionally":[3],"regarded":[4],"as":[5],"useless":[6],"for":[7],"word":[8,22,60,69,90],"recognition.In":[9],"this":[10],"paper,":[11],"we":[12],"provide":[13,24],"a":[14,30,71],"schematic":[15],"view":[16,26],"describing":[17],"how":[18],"prosody":[19,64,72,87],"can":[20],"help":[21],"recognition.We":[23],"our":[25,79],"in":[27,70,85],"terms":[28],"of":[29],"Bayesian":[31],"network":[32],"that":[33,51],"models":[34],"the":[35,52],"stochastic":[36],"dependence":[37],"among":[38],"acoustic":[39,56],"observation,":[40],"word,":[41],"prosody,":[42],"syntax":[43],"and":[44,46,58],"meaning,":[45],"an":[47],"information-theoretic":[48],"analysis":[49],"proving":[50],"mutual":[53],"information":[54],"between":[55],"observation":[57],"correct":[59],"hypotheses":[61],"improves":[62],"if":[63],"is":[65],"jointly":[66],"modeled":[67],"with":[68],"dependent":[73],"speech":[74],"recognition":[75,91],"framework.We":[76],"also":[77],"report":[78],"experiment":[80],"on":[81],"Radio":[82],"News":[83],"Corpus":[84],"which":[86],"improved":[89],"accuracy":[92],"by":[93],"2.5%.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}