{"id":"https://openalex.org/W4372267638","doi":"https://doi.org/10.1109/icassp49357.2023.10095896","title":"Align, Write, Re-Order: Explainable End-to-End Speech Translation via Operation Sequence Generation","display_name":"Align, Write, Re-Order: Explainable End-to-End Speech Translation via Operation Sequence Generation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267638","doi":"https://doi.org/10.1109/icassp49357.2023.10095896"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5088171135","display_name":"Motoi Omachi","orcid":"https://orcid.org/0000-0002-9159-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motoi Omachi","raw_affiliation_strings":["Yahoo Japan Corporation,Tokyo,Japan","Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201726","display_name":"Brian Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation,Tokyo,Japan","Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8668667078018188},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.675739049911499},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6632769107818604},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6176241040229797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6028730869293213},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5643043518066406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5514866709709167},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5313948392868042},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5242693424224854},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5163291692733765},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4843641221523285},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.48041629791259766},{"id":"https://openalex.org/keywords/word-order","display_name":"Word order","score":0.4789712727069855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4618896543979645},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09602048993110657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8668667078018188},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.675739049911499},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6632769107818604},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6176241040229797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028730869293213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5643043518066406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5514866709709167},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5313948392868042},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5242693424224854},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5163291692733765},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4843641221523285},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.48041629791259766},{"id":"https://openalex.org/C70777604","wikidata":"https://www.wikidata.org/wiki/Q257885","display_name":"Word order","level":2,"score":0.4789712727069855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4618896543979645},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09602048993110657},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2035301451","https://openalex.org/W2080373976","https://openalex.org/W2124807415","https://openalex.org/W2401449607","https://openalex.org/W2536650987","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2936969148","https://openalex.org/W2949328740","https://openalex.org/W2951456627","https://openalex.org/W2962757645","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963532001","https://openalex.org/W2964172053","https://openalex.org/W2972818416","https://openalex.org/W2985694911","https://openalex.org/W2987253016","https://openalex.org/W2998386507","https://openalex.org/W3007142233","https://openalex.org/W3007328579","https://openalex.org/W3015583403","https://openalex.org/W3021141990","https://openalex.org/W3037217258","https://openalex.org/W3096871117","https://openalex.org/W3097777922","https://openalex.org/W3102811925","https://openalex.org/W3105681039","https://openalex.org/W3113676066","https://openalex.org/W3143377973","https://openalex.org/W3148654612","https://openalex.org/W3152534858","https://openalex.org/W3156246620","https://openalex.org/W3160950270","https://openalex.org/W3162919436","https://openalex.org/W3163793923","https://openalex.org/W3172862365","https://openalex.org/W3174032041","https://openalex.org/W3175164646","https://openalex.org/W3186200218","https://openalex.org/W3186672448","https://openalex.org/W4281982771","https://openalex.org/W4285188582","https://openalex.org/W4285229778","https://openalex.org/W4285242950","https://openalex.org/W4287806332","https://openalex.org/W4386566728","https://openalex.org/W6767825573","https://openalex.org/W6776030248","https://openalex.org/W6784851026","https://openalex.org/W6839510803"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W4315705795","https://openalex.org/W2101053337","https://openalex.org/W1870651561"],"abstract_inverted_index":{"The":[0],"black-box":[1],"nature":[2,83],"of":[3,84,108,111,135,142,182],"end-to-end":[4],"speech-to-text":[5],"translation":[6,63],"(E2E":[7],"ST)":[8],"makes":[9],"it":[10,201],"difficult":[11],"to":[12,21,31,50,71,89,97,158,208],"understand":[13],"how":[14,96],"source":[15,44,113],"language":[16,45,53],"inputs":[17],"are":[18],"being":[19],"mapped":[20,49],"the":[22,60,81,115,123,128,149,178],"target":[23,52,117,129],"language.":[24],"To":[25],"solve":[26],"this":[27,78,103],"problem,":[28],"we":[29,87,166],"propose":[30,88],"simultaneously":[32],"generate":[33,90],"automatic":[34],"speech":[35,151],"recognition":[36],"(ASR)":[37],"and":[38,119,145,160,197],"ST":[39,91,198],"predictions":[40],"such":[41,136],"that":[42,62,165],"each":[43],"word":[46,72],"is":[47,64],"explicitly":[48],"a":[51,65,106,112],"word.":[54,130],"A":[55],"major":[56],"challenge":[57],"arises":[58],"from":[59,148],"fact":[61],"non-monotonic":[66,146],"sequence":[67,107],"transduction":[68],"task":[69],"due":[70],"ordering":[73],"differences":[74],"between":[75],"languages":[76],"\u2013":[77],"clashes":[79],"with":[80],"monotonic":[82,143],"ASR.":[85],"Therefore,":[86],"tokens":[92],"out-of-order":[93],"while":[94],"remembering":[95],"re-order":[98],"them":[99],"later.":[100],"We":[101,131,154],"achieve":[102],"by":[104],"predicting":[105],"tuples":[109],"consisting":[110],"word,":[114],"corresponding":[116],"words,":[118],"post-editing":[120],"operations":[121],"dictating":[122],"correct":[124],"insertion":[125],"points":[126],"for":[127],"examine":[132],"two":[133,205],"variants":[134],"operation":[137],"sequences":[138],"which":[139],"enable":[140],"generation":[141],"transcriptions":[144],"translations":[147,170],"same":[150],"input":[152],"simultaneously.":[153],"apply":[155],"our":[156,183,193],"approach":[157,184],"offline":[159],"real-time":[161],"streaming":[162],"models,":[163],"demonstrating":[164],"can":[167],"provide":[168],"explainable":[169],"without":[171],"sacrificing":[172],"quality":[173],"or":[174],"latency.":[175],"In":[176],"fact,":[177],"delayed":[179],"re-ordering":[180],"ability":[181],"improves":[185],"performance":[186],"during":[187],"streaming.":[188],"As":[189],"an":[190],"added":[191],"benefit,":[192],"method":[194],"performs":[195],"ASR":[196],"simultaneously,":[199],"making":[200],"faster":[202],"than":[203],"using":[204],"separate":[206],"systems":[207],"perform":[209],"these":[210],"tasks.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}