{"id":"https://openalex.org/W3162919436","doi":"https://doi.org/10.1109/icassp39728.2021.9415093","title":"ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder","display_name":"ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162919436","doi":"https://doi.org/10.1109/icassp39728.2021.9415093","mag":"3162919436"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415093","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":"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/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University,Japan","Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Duh","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Japan","Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7503","last_page":"7507"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.8207211494445801},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.765386700630188},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7229529619216919},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7078673839569092},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6597952842712402},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6380017995834351},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6282545924186707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6121835708618164},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5480976700782776},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5041369199752808},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4519495666027069},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43383458256721497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38772881031036377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2746533751487732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0830528736114502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207211494445801},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.765386700630188},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7229529619216919},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7078673839569092},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6597952842712402},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6380017995834351},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6282545924186707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6121835708618164},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5480976700782776},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5041369199752808},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4519495666027069},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43383458256721497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38772881031036377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2746533751487732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0830528736114502},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415093","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":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2101105183","https://openalex.org/W2113106066","https://openalex.org/W2124807415","https://openalex.org/W2407080277","https://openalex.org/W2512593609","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2766219058","https://openalex.org/W2767206889","https://openalex.org/W2785350307","https://openalex.org/W2789543585","https://openalex.org/W2892213699","https://openalex.org/W2896457183","https://openalex.org/W2899716505","https://openalex.org/W2920538220","https://openalex.org/W2936774411","https://openalex.org/W2945700568","https://openalex.org/W2946200149","https://openalex.org/W2946375144","https://openalex.org/W2949328740","https://openalex.org/W2949644922","https://openalex.org/W2952167535","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2963736842","https://openalex.org/W2963782041","https://openalex.org/W2963819008","https://openalex.org/W2963979492","https://openalex.org/W2964026424","https://openalex.org/W2964089333","https://openalex.org/W2964121744","https://openalex.org/W2964172053","https://openalex.org/W2970730223","https://openalex.org/W2970832665","https://openalex.org/W2971167892","https://openalex.org/W2972448360","https://openalex.org/W2982129078","https://openalex.org/W2988975212","https://openalex.org/W2995999067","https://openalex.org/W2997436923","https://openalex.org/W3000840023","https://openalex.org/W3008125272","https://openalex.org/W3008549139","https://openalex.org/W3012492057","https://openalex.org/W3014413043","https://openalex.org/W3015162217","https://openalex.org/W3015633994","https://openalex.org/W3034363136","https://openalex.org/W3034571331","https://openalex.org/W3035289598","https://openalex.org/W3035445001","https://openalex.org/W3035490255","https://openalex.org/W3037217258","https://openalex.org/W3096160024","https://openalex.org/W3096490862","https://openalex.org/W3097625183","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3100753857","https://openalex.org/W4294619240","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W4394649814","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6748215858","https://openalex.org/W6748381668","https://openalex.org/W6755207826","https://openalex.org/W6760017253","https://openalex.org/W6762471145","https://openalex.org/W6763832098","https://openalex.org/W6769269733","https://openalex.org/W6769921281","https://openalex.org/W6773383770","https://openalex.org/W6774835902","https://openalex.org/W6775187155","https://openalex.org/W6775291257","https://openalex.org/W6776039324","https://openalex.org/W6776353054","https://openalex.org/W6776541132","https://openalex.org/W6777996268","https://openalex.org/W6843673214","https://openalex.org/W6898505805","https://openalex.org/W6898634591"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W4399356803","https://openalex.org/W3177132412","https://openalex.org/W3198731777"],"abstract_inverted_index":{"Fast":[0],"inference":[1,157],"speed":[2,38,158],"is":[3,101],"an":[4],"important":[5],"goal":[6,28],"towards":[7],"real-world":[8],"deployment":[9],"of":[10,70,120,141,151],"speech":[11,97,136],"translation":[12,106,162],"(ST)":[13],"systems.":[14,169],"End-to-end":[15],"(E2E)":[16],"models":[17],"based":[18],"on":[19,94,145],"the":[20,68,95,113,118,139,149,152],"encoder-decoder":[21],"architecture":[22],"are":[23,91],"more":[24],"suitable":[25],"for":[26,73,103],"this":[27],"than":[29],"traditional":[30],"cascaded":[31],"systems,":[32],"but":[33],"their":[34],"effectiveness":[35,119,150],"regarding":[36],"decoding":[37,72],"has":[39],"not":[40],"been":[41],"explored":[42],"so":[43],"far.":[44],"Inspired":[45],"by":[46,62],"recent":[47],"progress":[48],"in":[49,53,60,83,155],"non-autoregressive":[50],"(NAR)":[51],"methods":[52,134],"text-based":[54],"translation,":[55],"which":[56,84,115],"generates":[57],"target":[58],"tokens":[59],"parallel":[61],"eliminating":[63],"conditional":[64],"dependencies,":[65],"we":[66],"study":[67],"problem":[69],"NAR":[71,79,86],"E2E-ST.":[74],"We":[75,128],"propose":[76],"a":[77,121],"novel":[78],"E2E-ST":[80,168],"framework,":[81],"Orthros,":[82],"both":[85],"and":[87,138],"autoregressive":[88],"(AR)":[89],"decoders":[90],"jointly":[92],"trained":[93],"shared":[96],"encoder.":[98],"The":[99],"latter":[100],"used":[102],"selecting":[104],"better":[105],"among":[107],"various":[108],"length":[109,123,132],"candidates":[110],"generated":[111],"from":[112,135],"former,":[114],"dramatically":[116],"improves":[117],"large":[122],"beam":[124],"with":[125],"negligible":[126],"overhead.":[127],"further":[129],"investigate":[130],"effective":[131],"prediction":[133],"inputs":[137],"impact":[140],"vocabulary":[142],"sizes.":[143],"Experiments":[144],"four":[146],"benchmarks":[147],"show":[148],"proposed":[153],"method":[154],"improving":[156],"while":[159],"maintaining":[160],"competitive":[161],"quality":[163],"compared":[164],"to":[165],"state-of-the-art":[166],"AR":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}