{"id":"https://openalex.org/W1990597496","doi":"https://doi.org/10.21437/eurospeech.2003-713","title":"Modeling linguistic features in speech recognition","display_name":"Modeling linguistic features in speech recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1990597496","doi":"https://doi.org/10.21437/eurospeech.2003-713","mag":"1990597496"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-713","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-713","pdf_url":null,"source":null,"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"},"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/A5100659889","display_name":"Min Tang","orcid":"https://orcid.org/0000-0001-7323-3698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068777363","display_name":"Stephanie Seneff","orcid":"https://orcid.org/0000-0001-8191-1049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephanie Seneff","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor W. Zue","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5538,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90269573,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2585","last_page":"2588"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7605624198913574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6162504553794861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5700854659080505},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4525623917579651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4337666630744934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605624198913574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6162504553794861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5700854659080505},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4525623917579651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4337666630744934},{"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.2003-713","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-713","pdf_url":null,"source":null,"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":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W30032985","https://openalex.org/W45736138","https://openalex.org/W123856455","https://openalex.org/W1490506669","https://openalex.org/W1556018550","https://openalex.org/W1586645951","https://openalex.org/W1604249599","https://openalex.org/W1633051326","https://openalex.org/W1904457459","https://openalex.org/W1943381225","https://openalex.org/W1949738355","https://openalex.org/W1970996882","https://openalex.org/W2022446405","https://openalex.org/W2032759346","https://openalex.org/W2111732304","https://openalex.org/W2122407890","https://openalex.org/W2130416704","https://openalex.org/W2131513205","https://openalex.org/W2158069733","https://openalex.org/W2479014774"],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W4321496520","https://openalex.org/W2293457016","https://openalex.org/W2131420137","https://openalex.org/W3169305685","https://openalex.org/W3107474891"],"abstract_inverted_index":{"This":[0,134],"paper":[1],"explores":[2],"a":[3,24,47,64,78,116],"new":[4],"approach":[5,113],"to":[6,57,76],"speech":[7,105],"recognition":[8,80,106,117],"in":[9,15,82,126,131,140],"which":[10,83],"sub-word":[11],"units":[12],"are":[13,94],"modeled":[14],"terms":[16],"of":[17,26,33,40,46,50,52],"linguistic":[18,66],"features.":[19],"Specifically,":[20],"we":[21,108],"have":[22],"adopted":[23],"scheme":[25],"modeling":[27],"separately":[28,72],"the":[29,44,84,98,127,132],"manner":[30,69],"and":[31,61,70,143],"place":[32,51,71],"articulation":[34,53],"for":[35],"these":[36],"units.":[37],"A":[38],"novelty":[39],"our":[41],"work":[42],"is":[43,87,120],"use":[45],"generalized":[48],"definition":[49],"that":[54,110,119,124],"enables":[55],"us":[56,75],"map":[58],"both":[59],"vowels":[60],"consonants":[62],"into":[63],"common":[65],"space.":[67],"Modeling":[68],"also":[73],"allows":[74],"explore":[77],"multi-stage":[79],"architecture,":[81],"search":[85,141],"space":[86,142],"successively":[88],"reduced":[89],"as":[90,146],"more":[91],"detailed":[92],"models":[93],"brought":[95],"in.":[96],"In":[97],"8,000":[99],"word":[100,103],"PhoneBook":[101],"isolated":[102],"telephone":[104],"task,":[107],"show":[109],"such":[111],"an":[112],"can":[114],"achieve":[115],"WER":[118],"10%":[121],"better":[122],"than":[123],"achieved":[125],"best":[128],"results":[129],"reported":[130],"literature.":[133],"performance":[135],"gain":[136],"comes":[137],"with":[138],"improvements":[139],"computation":[144],"time":[145],"well.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}