{"id":"https://openalex.org/W42019235","doi":"https://doi.org/10.21437/interspeech.2004-553","title":"Use of prosodic features for speech recognition","display_name":"Use of prosodic features for speech recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W42019235","doi":"https://doi.org/10.21437/interspeech.2004-553","mag":"42019235"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-553","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-553","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":"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/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1445","last_page":"1448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.9214527606964111},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7101050019264221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6943656206130981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6336013078689575},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5810758471488953},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5486482381820679},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48580265045166016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44143080711364746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4325796961784363},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4283992052078247},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.41791510581970215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3674154579639435}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9214527606964111},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7101050019264221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6943656206130981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6336013078689575},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5810758471488953},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5486482381820679},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48580265045166016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44143080711364746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4325796961784363},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4283992052078247},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.41791510581970215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3674154579639435},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2004-553","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-553","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.9890","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.9890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~iwano/research/papers/ieee_ws_96_10.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.588.6082","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.588.6082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2004/ICSLP_p1445-1448_t2004-10.pdf","raw_type":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00038983","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100436741","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W71699494","https://openalex.org/W197227453","https://openalex.org/W218957958","https://openalex.org/W320927564","https://openalex.org/W1590070522","https://openalex.org/W1600591519","https://openalex.org/W1606804054","https://openalex.org/W1760157887","https://openalex.org/W2078617267","https://openalex.org/W2115013739","https://openalex.org/W2166184218"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W49590631","https://openalex.org/W4298046075","https://openalex.org/W2370788932","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2474947928"],"abstract_inverted_index":{"Prosody":[0],"is":[1,15,32,49,102,119,141],"known":[2],"to":[3,19,34,42,59,110],"play":[4],"an":[5,16,87],"important":[6],"role":[7],"in":[8,62,115],"human":[9],"speech":[10,27,63],"perception":[11],"process.":[12,65],"Therefore,":[13],"there":[14],"increasing":[17],"need":[18],"use":[20],"prosodic":[21,78,139],"features":[22,122],"for":[23],"the":[24,67,95,99,112,116],"advancement":[25],"of":[26,37,89,107],"recognition":[28,64,100],"technology.":[29],"However,":[30],"prosody":[31,58,109],"related":[33],"various":[35],"levels":[36],"information,":[38],"from":[39,94],"linguistic,":[40],"para-linguistic,":[41],"non-linguistic,":[43],"and,":[44],"therefore,":[45],"its":[46],"acoustic":[47],"manifestation":[48],"rather":[50,126],"complicated":[51],"with":[52],"large":[53],"variations.":[54],"This":[55],"fact":[56],"prevents":[57],"be":[60,124],"incorporated":[61],"In":[66],"current":[68],"paper,":[69],"discussions":[70],"are":[71],"given":[72],"on":[73],"how":[74],"we":[75],"can":[76],"utilize":[77],"features,":[79],"showing":[80],"our":[81],"research":[82],"works":[83],"as":[84],"examples.":[85],"First,":[86],"idea":[88],"including":[90,138],"word":[91],"likelihood":[92],"viewed":[93],"accent":[96],"type":[97],"into":[98],"process":[101,118],"shown.":[103],"Second,":[104],"a":[105,132],"scheme":[106],"using":[108],"control":[111],"pruning":[113],"size":[114],"decoding":[117],"given.":[120],"Prosodic":[121],"should":[123],"modeled":[125],"differently":[127],"form":[128],"segmental":[129],"features.":[130],"Lastly,":[131],"new":[133],"language":[134],"model":[135],"constructed":[136],"by":[137],"events":[140],"explained.":[142],"1.":[143]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
