{"id":"https://openalex.org/W4416799628","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249296","title":"UTRo-NAST: Non-Autoregressive Speech Translation via Understanding, Translation, and Reordering","display_name":"UTRo-NAST: Non-Autoregressive Speech Translation via Understanding, Translation, and Reordering","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799628","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249296"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5018724233","display_name":"Yu-Chen Kuan","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chen Kuan","raw_affiliation_strings":["National Taiwan University of Science and Technology,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714445","display_name":"Kuan-Yu Chen","orcid":"https://orcid.org/0000-0001-9656-7551"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["National Taiwan University of Science and Technology,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":1.6508,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89218318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"915","last_page":"920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.920199990272522,"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":0.920199990272522,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.025299999862909317,"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":0.010700000450015068,"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/speech-translation","display_name":"Speech translation","score":0.7703999876976013},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.590499997138977},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49320000410079956},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47909998893737793},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4302000105381012},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41760000586509705},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.41179999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356000185012817},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7703999876976013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.590499997138977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5436999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511900007724762},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":37,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2605131327","https://openalex.org/W2936774411","https://openalex.org/W2963532001","https://openalex.org/W2963736842","https://openalex.org/W3034571331","https://openalex.org/W3037217258","https://openalex.org/W3092424727","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3162919436","https://openalex.org/W3175164646","https://openalex.org/W3175665465","https://openalex.org/W3175809709","https://openalex.org/W3196833881","https://openalex.org/W3197140813","https://openalex.org/W4221163209","https://openalex.org/W4287890956","https://openalex.org/W4322577229","https://openalex.org/W4372267638","https://openalex.org/W4385570154","https://openalex.org/W4385571120","https://openalex.org/W4390778590","https://openalex.org/W4392902778","https://openalex.org/W4392902920","https://openalex.org/W4392902935","https://openalex.org/W4392903872","https://openalex.org/W4392904172","https://openalex.org/W4392904548","https://openalex.org/W4393147102","https://openalex.org/W4401043086","https://openalex.org/W4402667113","https://openalex.org/W4402670519","https://openalex.org/W4402671919","https://openalex.org/W4409640766","https://openalex.org/W4409642635","https://openalex.org/W4410492109"],"related_works":[],"abstract_inverted_index":{"Non-autoregressive":[0],"speech":[1,48,55,69,103,158],"translation":[2,15,49,104,133],"(NAR-ST)":[3],"has":[4],"attracted":[5],"increasing":[6],"attention":[7],"due":[8],"to":[9,12,89,136],"its":[10],"ability":[11],"deliver":[13],"competitive":[14],"quality":[16,134],"with":[17],"faster":[18,142],"inference":[19],"speed.":[20,144],"However,":[21],"further":[22],"improving":[23],"the":[24,67,85,91,97,102,116,148,153],"performance":[25],"of":[26,81,96,152],"NAR-ST":[27,44,129],"models":[28,130],"remains":[29],"a":[30,42,79],"challenging":[31],"and":[32,59,93,111,131,150],"important":[33],"research":[34],"direction.":[35],"To":[36],"this":[37],"end,":[38],"we":[39],"propose":[40],"UTRo-NAST,":[41],"novel":[43],"framework":[45,155],"that":[46,124],"decomposes":[47],"into":[50,70,78],"three":[51],"consecutive":[52],"subtasks:":[53],"source":[54,68],"understanding,":[56],"word-level":[57],"translation,":[58],"target-side":[60],"word":[61],"reordering.":[62],"The":[63],"model":[64,108],"first":[65],"encodes":[66],"high-level":[71],"acoustic":[72],"representations,":[73],"which":[74],"are":[75],"then":[76],"translated":[77],"sequence":[80,86],"target":[82,98],"words.":[83],"Finally,":[84],"is":[87],"reordered":[88],"match":[90],"syntactic":[92],"grammatical":[94],"structure":[95],"language.":[99],"By":[100],"modularizing":[101],"pipeline,":[105],"UTRo-NAST":[106,125],"enhances":[107],"interpretability,":[109],"robustness,":[110],"overall":[112],"performance.":[113],"Experiments":[114],"on":[115],"MuST-C":[117],"benchmark":[118],"across":[119],"eight":[120],"language":[121],"pairs":[122],"show":[123],"consistently":[126],"outperforms":[127],"existing":[128],"achieves":[132],"comparable":[135],"strong":[137],"autoregressive":[138],"baselines,":[139],"while":[140],"maintaining":[141],"decoding":[143],"These":[145],"results":[146],"demonstrate":[147],"effectiveness":[149],"scalability":[151],"proposed":[154],"for":[156],"practical":[157],"translation.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}