{"id":"https://openalex.org/W3161324588","doi":"https://doi.org/10.1109/icassp39728.2021.9413966","title":"Learning Word-Level Confidence for Subword End-To-End ASR","display_name":"Learning Word-Level Confidence for Subword End-To-End ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161324588","doi":"https://doi.org/10.1109/icassp39728.2021.9413966","mag":"3161324588"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"raw_author_name":"David Qiu","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5030757951","display_name":"Qiujia Li","orcid":"https://orcid.org/0000-0003-3074-3692"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiujia Li","raw_affiliation_strings":["University of Cambridge,UK","University of Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"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":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"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":"Yu Zhang","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"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":"Bo Li","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5103187717","display_name":"Liangliang Cao","orcid":"https://orcid.org/0000-0003-0900-1512"},"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":"Liangliang Cao","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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":"Rohit Prabhavalkar","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5075099055","display_name":"Deepti Bhatia","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":"Deepti Bhatia","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5100318291","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-8278-1765"},"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":"Wei Li","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5029338576","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-1599-1519"},"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":"Ke Hu","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,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/A5048236120","display_name":"Ian McGraw","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":"Ian McGraw","raw_affiliation_strings":["LLC,Google,USA","Google, LLC, USA"],"affiliations":[{"raw_affiliation_string":"LLC,Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5079902855"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.2632,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93188137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6393","last_page":"6397"},"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.835669994354248},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6948648691177368},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6873560547828674},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6356068849563599},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5488874316215515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5442327857017517},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47906073927879333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46667659282684326},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44769421219825745},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3824799656867981},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32053565979003906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13438686728477478},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07524120807647705},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06972575187683105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835669994354248},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6948648691177368},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6873560547828674},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6356068849563599},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5488874316215515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5442327857017517},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47906073927879333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46667659282684326},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44769421219825745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3824799656867981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32053565979003906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13438686728477478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07524120807647705},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06972575187683105},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W34303869","https://openalex.org/W173561343","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1795658042","https://openalex.org/W1904457459","https://openalex.org/W2013598660","https://openalex.org/W2033256038","https://openalex.org/W2034537249","https://openalex.org/W2129334286","https://openalex.org/W2134659216","https://openalex.org/W2135241496","https://openalex.org/W2143577772","https://openalex.org/W2159391028","https://openalex.org/W2161391345","https://openalex.org/W2280141299","https://openalex.org/W2507771204","https://openalex.org/W2515439472","https://openalex.org/W2577366047","https://openalex.org/W2594610113","https://openalex.org/W2617258110","https://openalex.org/W2626967530","https://openalex.org/W2898630520","https://openalex.org/W2928941594","https://openalex.org/W2950170869","https://openalex.org/W2962760690","https://openalex.org/W2963403868","https://openalex.org/W2963505832","https://openalex.org/W2964121744","https://openalex.org/W2964212410","https://openalex.org/W2970859221","https://openalex.org/W2972981900","https://openalex.org/W2982413405","https://openalex.org/W3011339933","https://openalex.org/W3015194534","https://openalex.org/W3016010032","https://openalex.org/W3026041220","https://openalex.org/W3035207248","https://openalex.org/W3094667432","https://openalex.org/W3095994005","https://openalex.org/W3097777922","https://openalex.org/W3163169798","https://openalex.org/W4234016251","https://openalex.org/W4288088457","https://openalex.org/W4385245566","https://openalex.org/W6607114211","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6653897473","https://openalex.org/W6739651123","https://openalex.org/W6739901393","https://openalex.org/W6760633627","https://openalex.org/W6769806307","https://openalex.org/W6775002949","https://openalex.org/W6784657998"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W4287816966","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W2944691285","https://openalex.org/W3015650676","https://openalex.org/W4387800341","https://openalex.org/W2802566028","https://openalex.org/W2121178211","https://openalex.org/W3213130020"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,59,151,155,161],"problem":[3,159],"of":[4,80],"word-level":[5,95],"confidence":[6,25,56,78,96,111,132],"estimation":[7],"in":[8],"subword-based":[9],"end-to-end":[10],"(E2E)":[11],"models":[12,26,79],"for":[13,27,54,160],"automatic":[14],"speech":[15],"recognition":[16,158],"(ASR).":[17],"Although":[18],"prior":[19],"works":[20],"have":[21],"proposed":[22,131],"training":[23,55],"auxiliary":[24],"ASR":[28],"systems,":[29],"they":[30],"do":[31],"not":[32],"extend":[33],"naturally":[34],"to":[35,64,69,83,92,109,140,153],"systems":[36],"that":[37],"operate":[38],"on":[39,114,150],"word-pieces":[40],"(WP)":[41],"as":[42],"their":[43],"vocabulary.":[44],"In":[45],"particular,":[46],"ground":[47],"truth":[48],"WP":[49,65],"correctness":[50],"labels":[51,68],"are":[52],"needed":[53],"models,":[57],"but":[58],"non-unique":[60],"tokenization":[61],"from":[62,106],"word":[63,157],"causes":[66],"inaccurate":[67],"be":[70],"generated.":[71],"This":[72],"paper":[73],"proposes":[74],"and":[75,101,117],"studies":[76],"two":[77],"increasing":[81],"complexity":[82],"solve":[84],"this":[85],"problem.":[86],"The":[87,130],"final":[88],"model":[89,137,145,149],"uses":[90],"self-attention":[91],"directly":[93],"learn":[94],"without":[97],"needing":[98],"subword":[99],"tokenization,":[100],"exploits":[102],"full":[103],"context":[104],"features":[105],"multiple":[107],"hypotheses":[108],"improve":[110],"accuracy.":[112],"Experiments":[113],"Voice":[115],"Search":[116],"long-tail":[118],"test":[119],"sets":[120],"show":[121],"standard":[122],"metrics":[123],"(e.g.,":[124],"NCE,":[125],"AUC,":[126],"RMSE)":[127],"improving":[128],"substantially.":[129],"module":[133],"also":[134],"enables":[135],"a":[136,147],"selection":[138],"approach":[139],"combine":[141],"an":[142],"on-device":[143],"E2E":[144,162],"with":[146],"hybrid":[148],"server":[152],"address":[154],"rare":[156],"model.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}