{"id":"https://openalex.org/W3196889659","doi":"https://doi.org/10.21437/interspeech.2021-165","title":"A Deliberation-Based Joint Acoustic and Text Decoder","display_name":"A Deliberation-Based Joint Acoustic and Text Decoder","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196889659","doi":"https://doi.org/10.21437/interspeech.2021-165","mag":"3196889659"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-165","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-165","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/A5060420622","display_name":"Sepand Mavandadi","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":"Sepand Mavandadi","raw_affiliation_strings":["Google Inc., U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U","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":["Google Inc., U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U","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":["Google Inc., U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035558261","display_name":"Zelin Wu","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":"Zelin Wu","raw_affiliation_strings":["Google Inc., U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., U","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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2057","last_page":"2061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994000196456909,"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":0.9969000220298767,"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":0.7308644652366638},{"id":"https://openalex.org/keywords/deliberation","display_name":"Deliberation","score":0.7032414674758911},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6894893646240234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45264768600463867},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0965401828289032},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06486442685127258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308644652366638},{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.7032414674758911},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6894893646240234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45264768600463867},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0965401828289032},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06486442685127258},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-165","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-165","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2121879602","https://openalex.org/W2271840356","https://openalex.org/W2515439472","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2752047430","https://openalex.org/W2888779557","https://openalex.org/W2928941594","https://openalex.org/W2940322076","https://openalex.org/W2952711665","https://openalex.org/W2962760690","https://openalex.org/W2963027641","https://openalex.org/W2963216553","https://openalex.org/W2963240019","https://openalex.org/W2963414781","https://openalex.org/W2963739817","https://openalex.org/W2972625221","https://openalex.org/W2972880214","https://openalex.org/W2972991710","https://openalex.org/W2973122799","https://openalex.org/W3008181812","https://openalex.org/W3011339933","https://openalex.org/W3081494755","https://openalex.org/W3096815019","https://openalex.org/W3141464856","https://openalex.org/W4287630531","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2889613074","https://openalex.org/W2030530201","https://openalex.org/W2351267244","https://openalex.org/W3011555937","https://openalex.org/W2027246577","https://openalex.org/W2778699561","https://openalex.org/W3082456152","https://openalex.org/W2397728357","https://openalex.org/W1543325588","https://openalex.org/W4385823177"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,16],"new":[3],"two-pass":[4],"E2E":[5],"speech":[6],"recognition":[7,53],"model":[8,43,82,113],"that":[9],"improves":[10],"ASR":[11],"performance":[12],"by":[13,55,103],"training":[14,44],"on":[15,93],"combination":[17],"of":[18,39,68,73],"paired":[19],"data":[20,41,76],"and":[21,28,45,106],"unpaired":[22,74],"text":[23,29,40,75],"data.Previously,":[24],"the":[25,37,46,64],"joint":[26],"acoustic":[27],"decoder":[30],"(JATD)":[31],"has":[32,51],"shown":[33],"promising":[34],"results":[35],"through":[36],"use":[38,72],"during":[42],"recently":[47],"introduced":[48],"deliberation":[49,69],"architecture":[50],"reduced":[52],"errors":[54],"leveraging":[56],"first-pass":[57],"decoding":[58],"results.Our":[59],"method,":[60],"dubbed":[61],"Deliberation-JATD,":[62],"combines":[63],"spelling":[65],"correcting":[66],"abilities":[67],"with":[70],"JATD's":[71],"to":[77],"further":[78],"improve":[79],"performance.The":[80],"proposed":[81],"produces":[83],"substantial":[84],"gains":[85],"across":[86],"multiple":[87],"test":[88],"sets,":[89],"especially":[90],"those":[91],"focused":[92],"rare":[94],"words,":[95],"where":[96],"it":[97],"reduces":[98],"word":[99],"error":[100],"rate":[101],"(WER)":[102],"between":[104],"12%":[105],"22.5%":[107],"relative.This":[108],"is":[109],"done":[110],"without":[111],"increasing":[112],"size":[114],"or":[115],"requiring":[116],"multi-stage":[117],"training,":[118],"making":[119],"Deliberation-JATD":[120],"an":[121],"efficient":[122],"candidate":[123],"for":[124],"on-device":[125],"applications.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
