{"id":"https://openalex.org/W3197451691","doi":"https://doi.org/10.21437/interspeech.2021-1207","title":"Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction","display_name":"Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197451691","doi":"https://doi.org/10.21437/interspeech.2021-1207","mag":"3197451691"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1207","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030757951","display_name":"Qiujia Li","orcid":"https://orcid.org/0000-0003-3074-3692"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiujia Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187717","display_name":"Liangliang Cao","orcid":"https://orcid.org/0000-0003-0900-1512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangliang Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian McGraw","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4074","last_page":"4078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9821000099182129,"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":0.9757000207901001,"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":0.7755747437477112},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7661166191101074},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6791467070579529},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6015967726707458},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5939809679985046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5632205605506897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5085207223892212},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5061768889427185},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09973782300949097},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06099548935890198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755747437477112},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7661166191101074},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6791467070579529},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6015967726707458},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5939809679985046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5632205605506897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5085207223892212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5061768889427185},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09973782300949097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06099548935890198},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1207","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2351687372","https://openalex.org/W2383414243","https://openalex.org/W2464407842","https://openalex.org/W4307784074"],"abstract_inverted_index":{"Confidence":[0],"scores":[1,27],"are":[2],"very":[3],"useful":[4],"for":[5,28,85,99],"downstream":[6],"applications":[7],"of":[8,49,90],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"systems.":[13],"Recent":[14],"works":[15],"have":[16],"proposed":[17],"using":[18],"neural":[19,122],"networks":[20],"to":[21,56],"learn":[22,58],"word":[23,34,59,61,104],"or":[24],"utterance":[25,43,64],"confidence":[26,35,44,77,92,98],"end-to-end":[29],"ASR.":[30],"In":[31],"those":[32],"studies,":[33],"by":[36,115],"itself":[37],"does":[38,45],"not":[39,46],"model":[40,88],"deletions,":[41],"and":[42,63,111],"take":[47],"advantage":[48],"word-level":[50],"training":[51],"signals.":[52],"This":[53],"paper":[54],"proposes":[55],"jointly":[57],"confidence,":[60],"deletion,":[62],"confidence.":[65],"Empirical":[66],"results":[67],"show":[68],"that":[69],"multi-task":[70],"learning":[71],"with":[72],"all":[73],"three":[74],"objectives":[75],"improves":[76],"metrics":[78],"(NCE,":[79],"AUC,":[80],"RMSE)":[81],"without":[82,118],"the":[83,87,91,96,103],"need":[84],"increasing":[86],"size":[89],"estimation":[93],"module.":[94],"Using":[95],"utterance-level":[97],"rescoring":[100],"also":[101],"decreases":[102],"error":[105],"rates":[106],"on":[107],"Google's":[108],"Voice":[109],"Search":[110],"Long-tail":[112],"Maps":[113],"datasets":[114],"3-5%":[116],"relative,":[117],"needing":[119],"a":[120],"dedicated":[121],"rescorer.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}