{"id":"https://openalex.org/W3044996015","doi":"https://doi.org/10.1162/tacl_a_00340","title":"Consistent Transcription and Translation of Speech","display_name":"Consistent Transcription and Translation of Speech","publication_year":2020,"publication_date":"2020-11-13","ids":{"openalex":"https://openalex.org/W3044996015","doi":"https://doi.org/10.1162/tacl_a_00340","mag":"3044996015"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00340","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00340","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00340/1923479/tacl_a_00340.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00340/1923479/tacl_a_00340.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024736091","display_name":"Matthias Sperber","orcid":null},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Matthias Sperber","raw_affiliation_strings":["Apple","Apple (Israel), Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046770326","display_name":"Hendra Setiawan","orcid":"https://orcid.org/0000-0001-7417-6699"},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Hendra Setiawan","raw_affiliation_strings":["Apple","Apple (Israel), Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084597617","display_name":"Christian Gollan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Christian Gollan","raw_affiliation_strings":["Apple","Apple (Israel), Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012623245","display_name":"Udhyakumar Nallasamy","orcid":null},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Udhyakumar Nallasamy","raw_affiliation_strings":["Apple","Apple (Israel), Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002419451","display_name":"Matthias Paulik","orcid":null},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Matthias Paulik","raw_affiliation_strings":["Apple","Apple (Israel), Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08293685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"695","last_page":"709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.8130975961685181},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7389198541641235},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7309498190879822},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6920437216758728},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6891428232192993},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5968285799026489},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48343905806541443},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4718582332134247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44422852993011475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43020790815353394},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.36449718475341797},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07715809345245361},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06751564145088196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130975961685181},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7389198541641235},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7309498190879822},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6920437216758728},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6891428232192993},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5968285799026489},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48343905806541443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4718582332134247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44422852993011475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43020790815353394},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.36449718475341797},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07715809345245361},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06751564145088196},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1162/tacl_a_00340","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00340","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00340/1923479/tacl_a_00340.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.12741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.12741","pdf_url":"https://arxiv.org/pdf/2007.12741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3044996015","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.12741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:8c52ff0fb5944971ac2c3488d0e4e677","is_oa":false,"landing_page_url":"https://doaj.org/article/8c52ff0fb5944971ac2c3488d0e4e677","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 8 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2007.12741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.12741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3160861497","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/corr/corr2007.html#abs-2007-12741","pdf_url":null,"source":{"id":"https://openalex.org/S4306418267","display_name":"Empirical Methods in Natural Language Processing","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00340","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00340","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00340/1923479/tacl_a_00340.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3044996015.pdf","grobid_xml":"https://content.openalex.org/works/W3044996015.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1506371579","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W2050552609","https://openalex.org/W2061141931","https://openalex.org/W2063692070","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2113106066","https://openalex.org/W2114483840","https://openalex.org/W2127452865","https://openalex.org/W2148708890","https://openalex.org/W2150955799","https://openalex.org/W2168995909","https://openalex.org/W2183341477","https://openalex.org/W2404511972","https://openalex.org/W2493041683","https://openalex.org/W2605131327","https://openalex.org/W2798761464","https://openalex.org/W2936969148","https://openalex.org/W2945700568","https://openalex.org/W2953039212","https://openalex.org/W2962680099","https://openalex.org/W2963250244","https://openalex.org/W2963266340","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2963779652","https://openalex.org/W2964308564","https://openalex.org/W2971120958","https://openalex.org/W2998386507"],"related_works":["https://openalex.org/W3105681039","https://openalex.org/W2115479746","https://openalex.org/W2808502683","https://openalex.org/W114239111","https://openalex.org/W3096871117","https://openalex.org/W2251347599","https://openalex.org/W49622573","https://openalex.org/W2184842915","https://openalex.org/W3027945255","https://openalex.org/W1982895372","https://openalex.org/W2557853562","https://openalex.org/W2807535859","https://openalex.org/W3046643869","https://openalex.org/W3143808257","https://openalex.org/W2992229580","https://openalex.org/W2898412432","https://openalex.org/W3022822895","https://openalex.org/W2995304149","https://openalex.org/W2529548870","https://openalex.org/W120225049"],"abstract_inverted_index":{"The":[0],"conventional":[1],"paradigm":[2],"in":[3,51],"speech":[4,9],"translation":[5,18,85,173],"starts":[6],"with":[7,20],"a":[8,17,106,143],"recognition":[10],"step":[11,19],"to":[12,61,108,132,149],"generate":[13],"transcripts,":[14],"followed":[15],"by":[16],"the":[21,59,71,101,117,133,165],"automatic":[22],"transcripts":[23,45,57],"as":[24],"input.":[25],"To":[26],"address":[27],"various":[28],"shortcomings":[29],"of":[30,73,82],"this":[31,65],"paradigm,":[32],"recent":[33],"work":[34],"explores":[35],"end-to-end":[36,122,139],"trainable":[37],"direct":[38,127],"models":[39,128,140],"that":[40,99,126,138,141],"translate":[41],"without":[42],"transcribing.":[43],"However,":[44],"can":[46,92],"be":[47],"an":[48],"indispensable":[49],"output":[50],"practical":[52],"applications,":[53],"which":[54],"often":[55],"display":[56],"alongside":[58],"translations":[60],"users.":[62],"We":[63,104,124,153],"make":[64],"common":[66],"requirement":[67],"explicit":[68],"and":[69,76,84,111,121,163,172],"explore":[70],"task":[72],"jointly":[74],"transcribing":[75],"translating":[77],"speech.":[78],"Although":[79],"high":[80],"accuracy":[81],"transcript":[83],"are":[86,129,147],"crucial,":[87],"even":[88],"highly":[89],"accurate":[90],"systems":[91],"suffer":[93],"from":[94],"inconsistencies":[95],"between":[96,168],"both":[97],"outputs":[98],"degrade":[100],"user":[102],"experience.":[103],"introduce":[105,155],"methodology":[107],"evaluate":[109],"consistency":[110],"compare":[112],"several":[113],"modeling":[114],"approaches,":[115],"including":[116],"traditional":[118],"cascaded":[119],"approach":[120],"models.":[123],"find":[125],"poorly":[130],"suited":[131],"joint":[134],"transcription/translation":[135],"task,":[136],"but":[137],"feature":[142],"coupled":[144],"inference":[145],"procedure":[146],"able":[148],"achieve":[150],"strong":[151],"consistency.":[152],"further":[154],"simple":[156],"techniques":[157],"for":[158,161],"directly":[159],"optimizing":[160],"consistency,":[162,169],"analyze":[164],"resulting":[166],"trade-offs":[167],"transcription":[170],"accuracy,":[171],"accuracy.":[174],"1":[175]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
