{"id":"https://openalex.org/W4319862639","doi":"https://doi.org/10.1109/slt54892.2023.10023411","title":"Context-Aware Neural Confidence Estimation for Rare Word Speech Recognition","display_name":"Context-Aware Neural Confidence Estimation for Rare Word Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862639","doi":"https://doi.org/10.1109/slt54892.2023.10023411"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023411","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5079902855","display_name":"David Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Qiu","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062473985","display_name":"Tsendsuren Munkhdalai","orcid":"https://orcid.org/0000-0002-8783-4993"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsendsuren Munkhdalai","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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":0.8322849273681641},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7109255194664001},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6968998908996582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6582928895950317},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5642201900482178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540084719657898},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4929511547088623},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47969767451286316},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.4587211608886719},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.379991352558136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3579845428466797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05990585684776306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322849273681641},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7109255194664001},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6968998908996582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6582928895950317},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5642201900482178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540084719657898},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4929511547088623},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47969767451286316},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.4587211608886719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.379991352558136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3579845428466797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05990585684776306},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023411","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W34303869","https://openalex.org/W1604697534","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1992810169","https://openalex.org/W2013598660","https://openalex.org/W2033256038","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2395440424","https://openalex.org/W2617258110","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2962824709","https://openalex.org/W2963362078","https://openalex.org/W2963414781","https://openalex.org/W2972981900","https://openalex.org/W3006752097","https://openalex.org/W3015194534","https://openalex.org/W3157998614","https://openalex.org/W3161324588","https://openalex.org/W3163169798","https://openalex.org/W3194438854","https://openalex.org/W3197451691","https://openalex.org/W3202037040","https://openalex.org/W3202725408","https://openalex.org/W3203388655","https://openalex.org/W4210424357","https://openalex.org/W4220742766","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6653897473","https://openalex.org/W6681513673","https://openalex.org/W6743477263","https://openalex.org/W6747398299","https://openalex.org/W6798110451","https://openalex.org/W6802123867","https://openalex.org/W6810734409"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W1492794944","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W4243199227"],"abstract_inverted_index":{"Confidence":[0],"estimation":[1,16],"for":[2,9,27,117,143],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"is":[7,71],"important":[8],"many":[10],"downstream":[11],"tasks.":[12],"Recently,":[13],"neural":[14,107],"confidence":[15,25,79],"models":[17,32],"(CEMs)":[18],"have":[19,85],"been":[20,86],"shown":[21],"to":[22,64,115,149],"produce":[23],"accurate":[24],"scores":[26],"predicting":[28],"word-level":[29],"errors.":[30],"These":[31],"are":[33,46],"built":[34],"on":[35],"top":[36],"of":[37,48,74,80,119],"an":[38],"end-to-end":[39],"(E2E)":[40],"ASR":[41,55],"and":[42,76,123],"the":[43,49,62,78,81,89,103,120,125,131,141],"acoustic":[44],"embeddings":[45],"part":[47],"input":[50],"features.":[51,127],"However,":[52],"practical":[53],"E2E":[54],"systems":[56],"often":[57],"incorporate":[58],"contextual":[59],"information":[60],"in":[61],"decoder":[63],"improve":[65,140],"rare":[66,82],"word":[67,144],"recognition.":[68],"The":[69],"CEM":[70,98,134],"not":[72],"aware":[73],"this":[75,92],"underestimates":[77],"words":[83],"that":[84,130],"corrected":[87],"by":[88,99],"context.":[90],"In":[91],"paper,":[93],"we":[94],"propose":[95],"a":[96,106],"context-aware":[97,133],"incorporating":[100],"context":[101],"into":[102],"encoder":[104,126],"using":[105,135],"associative":[108],"memory":[109],"(NAM)":[110],"model.":[111],"It":[112],"uses":[113],"attention":[114],"detect":[116],"presence":[118],"biasing":[121],"phrases":[122],"modify":[124],"Experiments":[128],"show":[129],"proposed":[132],"NAM":[136],"augmented":[137],"training":[138],"can":[139],"AUC-ROC":[142],"error":[145],"prediction":[146],"from":[147],"0.837":[148],"0.892.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}