{"id":"https://openalex.org/W1585154421","doi":"https://doi.org/10.21437/interspeech.2013-301","title":"Formalizing expert knowledge for developing accurate speech recognizers","display_name":"Formalizing expert knowledge for developing accurate speech recognizers","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W1585154421","doi":"https://doi.org/10.21437/interspeech.2013-301","mag":"1585154421"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/Formalizing_Expert_Knowledge_for_Developing_Accurate_Speech_Recognizers/6473375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100606536","display_name":"Anuj Kumar","orcid":"https://orcid.org/0000-0002-5023-7618"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuj Kumar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354895","display_name":"Wenyi Wang","orcid":"https://orcid.org/0000-0003-1619-0294"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenyi Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108498734","display_name":"Matthew Kam","orcid":null},"institutions":[{"id":"https://openalex.org/I1293631320","display_name":"American Institutes for Research","ror":"https://ror.org/00490n048","country_code":"US","type":"funder","lineage":["https://openalex.org/I1293631320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Kam","raw_affiliation_strings":["American Institutes for Research, Alexandria, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American Institutes for Research, Alexandria, United States","institution_ids":["https://openalex.org/I1293631320"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1121","last_page":"1125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.8717331886291504},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6986743211746216},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5781595706939697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5490598082542419},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5358906984329224},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4968905746936798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4758446216583252},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.454884797334671},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.45394375920295715},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44495031237602234},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44148722290992737},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41239750385284424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38141441345214844},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3712528347969055},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3566737771034241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8717331886291504},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6986743211746216},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5781595706939697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5490598082542419},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5358906984329224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4968905746936798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4758446216583252},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.454884797334671},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.45394375920295715},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44495031237602234},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44148722290992737},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41239750385284424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38141441345214844},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3712528347969055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3566737771034241},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2013-301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/6473375","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Formalizing_Expert_Knowledge_for_Developing_Accurate_Speech_Recognizers/6473375","pdf_url":"https://figshare.com/articles/Formalizing_Expert_Knowledge_for_Developing_Accurate_Speech_Recognizers/6473375","source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:repository.cmu.edu:lti-1091","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1091&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473375","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.2567","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.2567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~anujk1/InterSpeech2013.pdf","raw_type":"text"},{"id":"doi:10.1184/r1/6473375.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473375.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473375","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Formalizing_Expert_Knowledge_for_Developing_Accurate_Speech_Recognizers/6473375","pdf_url":"https://figshare.com/articles/Formalizing_Expert_Knowledge_for_Developing_Accurate_Speech_Recognizers/6473375","source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G4229177009","display_name":"EAGER: A Research Infrastructure for Analyzing Speech-based Interfaces","funder_award_id":"1247368","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5788993370","display_name":"CI-P:Collaborative Research:The Speech Recognition Virtual Kitchen","funder_award_id":"1205589","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1585154421.pdf","grobid_xml":"https://content.openalex.org/works/W1585154421.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W26405188","https://openalex.org/W200792414","https://openalex.org/W583711304","https://openalex.org/W644665392","https://openalex.org/W1608247689","https://openalex.org/W1967452917","https://openalex.org/W1972051027","https://openalex.org/W1982723649","https://openalex.org/W1988986693","https://openalex.org/W2015786838","https://openalex.org/W2028380100","https://openalex.org/W2028878459","https://openalex.org/W2060524913","https://openalex.org/W2064890124","https://openalex.org/W2064910157","https://openalex.org/W2070504353","https://openalex.org/W2085529605","https://openalex.org/W2104499423","https://openalex.org/W2110293626","https://openalex.org/W2161386143","https://openalex.org/W2311274668","https://openalex.org/W2799202302","https://openalex.org/W2912389574","https://openalex.org/W3022607203","https://openalex.org/W3041832514","https://openalex.org/W3042359118","https://openalex.org/W3216401400","https://openalex.org/W4252160684","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2475408106","https://openalex.org/W2024736176","https://openalex.org/W2086580554","https://openalex.org/W2553860513","https://openalex.org/W3045387744","https://openalex.org/W1480876128","https://openalex.org/W32894952","https://openalex.org/W631902903","https://openalex.org/W2904591968","https://openalex.org/W2116633399"],"abstract_inverted_index":{"The":[0],"expertise":[1],"required":[2],"to":[3,44,109],"develop":[4],"a":[5,13,120,150],"speech":[6,26,66,80,116,166],"recognition":[7,27,67,101,117,167],"system":[8],"with":[9],"reasonable":[10],"accuracy":[11,49,97],"for":[12,96,135,161],"given":[14],"task":[15],"is":[16,107],"quite":[17],"significant,":[18],"and":[19,74,92,124,143,170,175],"precludes":[20],"most":[21],"non-speech":[22],"experts":[23,81],"from":[24,79],"integrating":[25],"into":[28],"their":[29],"own":[30],"research.":[31],"While":[32],"an":[33,52,89],"initial":[34],"baseline":[35],"recognizer":[36],"may":[37],"readily":[38],"be":[39,157],"available":[40],"or":[41],"relatively":[42],"simple":[43],"acquire,":[45],"identifying":[46],"the":[47,56,163],"necessary":[48],"optimizations":[50],"require":[51],"expert":[53],"understanding":[54,112],"of":[55,113,158,165],"application":[57],"domain":[58],"as":[59,61],"well":[60],"significant":[62],"experience":[63],"in":[64,76,119,141,168],"building":[65],"systems.":[68],"This":[69],"paper":[70],"describes":[71],"our":[72],"efforts":[73],"experiments":[75],"formalizing":[77],"knowledge":[78,122,127,151],"that":[82,105,125,148],"would":[83],"help":[84],"novices":[85],"by":[86],"automatically":[87],"analyzing":[88],"acoustic":[90,138,176],"context":[91],"recommending":[93],"appropriate":[94],"techniques":[95,134],"gains.":[98],"Through":[99],"two":[100],"experiments,":[102],"we":[103],"show":[104],"it":[106],"possible":[108],"model":[110],"experts'":[111],"developing":[114],"accurate":[115],"systems":[118],"rule-based":[121],"base,":[123,152],"this":[126],"base":[128],"can":[129],"accurately":[130],"predict":[131],"successful":[132],"optimization":[133],"previously":[136],"seen":[137,142],"situations,":[139],"both":[140],"unseen":[144],"datasets.":[145],"We":[146],"argue":[147],"such":[149],"once":[153],"fully":[154],"developed,":[155],"will":[156],"tremendous":[159],"value":[160],"boosting":[162],"use":[164],"research":[169],"development":[171],"on":[172],"non-mainstream":[173],"languages":[174],"conditions.":[177]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}