{"id":"https://openalex.org/W2808502683","doi":"https://doi.org/10.1109/taslp.2018.2846402","title":"Sequence-to-Sequence Models for Emphasis Speech Translation","display_name":"Sequence-to-Sequence Models for Emphasis Speech Translation","publication_year":2018,"publication_date":"2018-06-11","ids":{"openalex":"https://openalex.org/W2808502683","doi":"https://doi.org/10.1109/taslp.2018.2846402","mag":"2808502683"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2846402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2846402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5102847246","display_name":"Quoc Truong","orcid":"https://orcid.org/0000-0003-1472-1370"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102847246"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.3031,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85111268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"10","first_page":"1873","last_page":"1883"},"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":0.9994999766349792,"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/emphasis","display_name":"Emphasis (telecommunications)","score":0.9387909173965454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8185797929763794},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7060673236846924},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5860055685043335},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5793548226356506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5755593776702881},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5583223104476929},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5560306906700134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.534201979637146},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5267139077186584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.51973557472229},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.503429114818573},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.4527861475944519},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.4510310888290405},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44167348742485046},{"id":"https://openalex.org/keywords/dynamic-and-formal-equivalence","display_name":"Dynamic and formal equivalence","score":0.4156811237335205},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17942872643470764},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10502877831459045}],"concepts":[{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.9387909173965454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185797929763794},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7060673236846924},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5860055685043335},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5793548226356506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5755593776702881},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5583223104476929},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5560306906700134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.534201979637146},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5267139077186584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51973557472229},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.503429114818573},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.4527861475944519},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.4510310888290405},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44167348742485046},{"id":"https://openalex.org/C98199350","wikidata":"https://www.wikidata.org/wiki/Q978442","display_name":"Dynamic and formal equivalence","level":3,"score":0.4156811237335205},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17942872643470764},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10502877831459045},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2846402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2846402","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W206967138","https://openalex.org/W222053410","https://openalex.org/W630532510","https://openalex.org/W1514535095","https://openalex.org/W1614298861","https://openalex.org/W1810943226","https://openalex.org/W1902237438","https://openalex.org/W1975343484","https://openalex.org/W2025768430","https://openalex.org/W2035108931","https://openalex.org/W2039800941","https://openalex.org/W2040031823","https://openalex.org/W2048389584","https://openalex.org/W2064675550","https://openalex.org/W2112900913","https://openalex.org/W2130942839","https://openalex.org/W2143612262","https://openalex.org/W2147880316","https://openalex.org/W2152834109","https://openalex.org/W2153653739","https://openalex.org/W2154920538","https://openalex.org/W2242221029","https://openalex.org/W2293211712","https://openalex.org/W2295730220","https://openalex.org/W2404915168","https://openalex.org/W2405329321","https://openalex.org/W2507561499","https://openalex.org/W2600702321","https://openalex.org/W2747920239","https://openalex.org/W2950577311","https://openalex.org/W2963842982","https://openalex.org/W4241645538","https://openalex.org/W6608432165","https://openalex.org/W6608792757","https://openalex.org/W6630875275","https://openalex.org/W6636510571","https://openalex.org/W6638273328","https://openalex.org/W6679436768","https://openalex.org/W6682082992","https://openalex.org/W6685145238","https://openalex.org/W6696898479","https://openalex.org/W6697245993","https://openalex.org/W6713214878","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W3044453483","https://openalex.org/W2383963481","https://openalex.org/W3169172723","https://openalex.org/W1752235915","https://openalex.org/W4210379977","https://openalex.org/W3012695376","https://openalex.org/W1555947927","https://openalex.org/W4386954442","https://openalex.org/W2183030971","https://openalex.org/W2379917486"],"abstract_inverted_index":{"Speech-to-speech":[0],"translation":[1,48,56,62,98,143,152,167,172,191,201,216],"(S2ST)":[2],"systems":[3,28],"are":[4,108],"capable":[5],"of":[6,72,82,92,202,210,218],"breaking":[7],"language":[8],"barriers":[9],"in":[10,181],"cross-lingual":[11],"communication":[12],"by":[13,42,177],"translating":[14],"speech":[15],"across":[16],"languages.":[17],"Recent":[18],"studies":[19],"have":[20],"introduced":[21],"many":[22],"improvements":[23],"that":[24,126,170,195],"allow":[25],"existing":[26],"S2ST":[27],"to":[29,66,158],"handle":[30,68,128],"not":[31,58],"only":[32],"linguistic":[33],"meaning":[34],"but":[35],"also":[36,78,193],"paralinguistic":[37],"information":[38],"such":[39],"as":[40,88],"emphasis":[41,45,55,75,83,130,142,166,205],"proposing":[43],"additional":[44],"estimation":[46],"and":[47,64,74,85,103,136,141,154,184,204],"components.":[49],"However,":[50],"the":[51,69,80,96,151,215],"approach":[52,125],"used":[53],"for":[54,60],"is":[57,100],"optimal":[59],"sequence":[61],"tasks":[63],"fails":[65],"easily":[67],"long-term":[70],"dependencies":[71],"words":[73,203],"levels.":[76],"It":[77],"requires":[79],"quantization":[81],"levels":[84,131],"treats":[86],"them":[87],"discrete":[89],"labels":[90],"instead":[91,209],"continuous":[93,129],"values.":[94],"Moreover,":[95],"whole":[97],"pipeline":[99,153],"fairly":[101],"complex":[102],"slow":[104],"because":[105],"all":[106],"components":[107],"trained":[109],"separately":[110],"without":[111],"joint":[112,160,190,200],"optimization.":[113,161],"In":[114],"this":[115],"paper,":[116],"we":[117,122,138],"make":[118,155],"two":[119],"contributions:":[120],"1)":[121],"propose":[123],"an":[124,165],"can":[127,198],"based":[132],"on":[133,164,188],"sequence-to-sequence":[134],"models,":[135],"2)":[137],"combine":[139],"machine":[140],"into":[144],"a":[145,178,189],"single":[146],"model,":[147],"which":[148],"greatly":[149],"simplifies":[150],"it":[156],"easier":[157],"perform":[159,199],"Our":[162],"results":[163],"task":[168],"indicate":[169],"our":[171,196],"models":[173,176,197],"outperform":[174],"previous":[175],"large":[179],"margin":[180],"both":[182,219],"objective":[183],"subjective":[185],"tests.":[186],"Experiments":[187],"model":[192],"show":[194],"with":[206],"one-word":[207],"delays":[208,212],"full-sentence":[211],"while":[213],"preserving":[214],"performance":[217],"tasks.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}