{"id":"https://openalex.org/W2028825255","doi":"https://doi.org/10.1109/icassp.2013.6639103","title":"Predicting speech recognition confidence using deep learning with word identity and score features","display_name":"Predicting speech recognition confidence using deep learning with word identity and score features","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2028825255","doi":"https://doi.org/10.1109/icassp.2013.6639103","mag":"2028825255"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5076474156","display_name":"Po-Sen Huang","orcid":"https://orcid.org/0000-0003-1470-0991"},"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":"Po-Sen Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047826067","display_name":"Kshitiz Kumar","orcid":"https://orcid.org/0000-0003-2728-2493"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kshitiz Kumar","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004148430","display_name":"Chaojun Liu","orcid":"https://orcid.org/0000-0002-4676-3981"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaojun Liu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076474156"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.8854,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.91358713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7413","last_page":"7417"},"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":0.9980000257492065,"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":0.9973999857902527,"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":0.7582907676696777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6692003607749939},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6680874824523926},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5841907858848572},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5148729085922241},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47887107729911804},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4758700728416443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46479955315589905},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.46291735768318176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34257927536964417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582907676696777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6692003607749939},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6680874824523926},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5841907858848572},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5148729085922241},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47887107729911804},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4758700728416443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46479955315589905},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.46291735768318176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34257927536964417}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W55333121","https://openalex.org/W170072012","https://openalex.org/W1506806321","https://openalex.org/W1663973292","https://openalex.org/W1994935303","https://openalex.org/W2031735445","https://openalex.org/W2034537249","https://openalex.org/W2074818733","https://openalex.org/W2100495367","https://openalex.org/W2139622435","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2159391028","https://openalex.org/W2160815625","https://openalex.org/W2160840682","https://openalex.org/W2171792531","https://openalex.org/W2184045248","https://openalex.org/W2398880078","https://openalex.org/W3004219628","https://openalex.org/W6683673261","https://openalex.org/W6685152693"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W2523437662","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2766585573","https://openalex.org/W4387490624","https://openalex.org/W4286643620"],"abstract_inverted_index":{"Confidence":[0],"classifiers":[1],"for":[2,11,27],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"provide":[7],"a":[8],"quantitative":[9],"representation":[10],"the":[12,22,42,49,54,61,70,76,87,102,109,114,117,128],"reliability":[13],"of":[14,108],"ASR":[15,23],"decoding.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"improve":[21],"confidence":[24,43,62],"measure":[25,107],"performance":[26,130],"an":[28,122],"utterance":[29],"using":[30],"two":[31],"distinct":[32],"approaches:":[33],"(1)":[34],"to":[35,59,90],"define":[36],"and":[37,52,57,75,119,125],"incorporate":[38],"additional":[39,123],"predictors":[40,89],"in":[41,101,127],"classifier":[44,63,96,110],"including":[45,69],"those":[46],"based":[47],"on":[48,53,65],"word":[50],"identity":[51],"aggregated":[55],"words,":[56],"(2)":[58],"train":[60],"built":[64],"deep":[66,71,78],"learning":[67],"architectures":[68],"neural":[72],"network":[73,80],"(DNN)":[74],"kernel":[77],"convex":[79],"(K-DCN).":[81],"Our":[82],"experiments":[83],"show":[84],"that":[85],"adding":[86],"new":[88],"our":[91,106],"multi-layer":[92],"perceptron":[93],"(MLP)-based":[94],"baseline":[95],"provides":[97,121],"38.6%":[98],"relative":[99,129],"reduction":[100],"correct-reject":[103],"rate":[104],"as":[105],"performance.":[111],"Further,":[112],"replacing":[113],"MLP":[115],"with":[116],"DNN":[118],"K-DCN":[120],"14.5%":[124],"47.5%":[126],"gain,":[131],"respectively.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}