{"id":"https://openalex.org/W2242221029","doi":"https://doi.org/10.1109/taslp.2016.2643280","title":"Preserving Word-Level Emphasis in Speech-to-Speech Translation","display_name":"Preserving Word-Level Emphasis in Speech-to-Speech Translation","publication_year":2016,"publication_date":"2016-12-21","ids":{"openalex":"https://openalex.org/W2242221029","doi":"https://doi.org/10.1109/taslp.2016.2643280","mag":"2242221029"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2643280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2643280","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":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/8111","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"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":"Graham Neubig","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.739,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9213504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"25","issue":"3","first_page":"544","last_page":"556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.9300237894058228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510315179824829},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7408099174499512},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6209691166877747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5765957236289978},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5723969340324402},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.49770548939704895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47716134786605835},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4523412585258484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43179476261138916},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4314274489879608},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28634870052337646}],"concepts":[{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.9300237894058228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510315179824829},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7408099174499512},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6209691166877747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5765957236289978},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5723969340324402},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.49770548939704895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47716134786605835},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4523412585258484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43179476261138916},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4314274489879608},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28634870052337646},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2016.2643280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2643280","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"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005786562","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/8111","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"master thesis"},{"id":"pmh:oai:library.naist.jp:10061/11397","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/11397","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005786562","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/8111","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"master thesis"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3072745167","display_name":null,"funder_award_id":"24240032","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G7578374220","display_name":"Simultaneous speech translation methods for news and lectures in foreign languages","funder_award_id":"24240032","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W206967138","https://openalex.org/W1521626219","https://openalex.org/W1524333225","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W1975343484","https://openalex.org/W1992153276","https://openalex.org/W2035108931","https://openalex.org/W2039800941","https://openalex.org/W2040031823","https://openalex.org/W2048389584","https://openalex.org/W2049633694","https://openalex.org/W2049686551","https://openalex.org/W2069631319","https://openalex.org/W2093265061","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2112900913","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2133444727","https://openalex.org/W2147880316","https://openalex.org/W2152834109","https://openalex.org/W2153653739","https://openalex.org/W2154920538","https://openalex.org/W2158069733","https://openalex.org/W2158086337","https://openalex.org/W2170979168","https://openalex.org/W2226734577","https://openalex.org/W2293211712","https://openalex.org/W2295730220","https://openalex.org/W2403632467","https://openalex.org/W2404915168","https://openalex.org/W2405329321","https://openalex.org/W3044514286","https://openalex.org/W4241645538","https://openalex.org/W6608432165","https://openalex.org/W6631362777","https://openalex.org/W6676989195","https://openalex.org/W6679436768","https://openalex.org/W6679819393","https://openalex.org/W6682082992","https://openalex.org/W6689048222","https://openalex.org/W6696898479","https://openalex.org/W6697245993","https://openalex.org/W6713214878","https://openalex.org/W6713425194","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2362773009","https://openalex.org/W2169113179","https://openalex.org/W1564107245","https://openalex.org/W4391272374","https://openalex.org/W2295649751","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Speech-to-speech":[0],"translation":[1,113,166],"(S2ST)":[2],"is":[3],"a":[4,51,65,90,102,121,127],"technology":[5],"that":[6,69,110,164,193,204],"translates":[7,115],"speech":[8,27,38,144,149],"across":[9],"languages,":[10],"which":[11],"can":[12,70,168],"remove":[13],"barriers":[14],"in":[15,97,101,175],"cross-lingual":[16],"communication.":[17],"In":[18,46],"the":[19,23,37,107,111,116,133,143,155,176,197,205,208],"conventional":[20],"S2ST":[21],"systems,":[22],"linguistic":[24],"meaning":[25],"of":[26,36,64,67,78,104,135,207],"was":[28,210],"translated,":[29],"but":[30],"paralinguistic":[31,55],"information":[32],"conveying":[33],"other":[34],"features":[35,77,134],"such":[39],"as":[40],"emotion":[41],"or":[42],"emphasis":[43,73,92,112,118,124,136,157,170],"were":[44],"ignored.":[45],"this":[47],"paper,":[48],"we":[49],"propose":[50],"method":[52,62],"to":[53,88],"translate":[54,72,169],"information,":[56,171],"specifically":[57],"focusing":[58],"on":[59],"emphasis.":[60],"The":[61,161],"consists":[63],"series":[66],"components":[68],"accurately":[71],"using":[74,126],"all":[75],"acoustic":[76],"speech.":[79],"First,":[80],"linear-regression":[81],"hidden":[82],"semi-Markov":[83],"models":[84],"(LRHSMMs)":[85],"are":[86],"used":[87],"estimate":[89],"real-numbered":[91],"value":[93],"for":[94,106],"every":[95],"word":[96],"an":[98],"utterance,":[99],"resulting":[100],"sequence":[103,119,125,158],"values":[105],"utterance.":[108],"After":[109],"module":[114,146],"estimated":[117],"into":[120,153],"target":[122,177],"language":[123,178],"conditional":[128],"random":[129],"field":[130],"model":[131,167],"considering":[132],"levels,":[137],"words,":[138],"and":[139,159,203],"part-of-speech":[140],"tags.":[141],"Finally,":[142],"synthesis":[145],"synthesizes":[147],"emphasized":[148,198],"with":[150,179,188,200],"LR-HSMMs,":[151],"taking":[152],"account":[154],"translated":[156],"transcription.":[160],"results":[162],"indicate":[163],"our":[165],"correctly":[172],"emphasizing":[173],"words":[174,199],"91.6%":[180],"F-measure":[181],"by":[182],"objective":[183],"evaluation.":[184],"A":[185],"listening":[186],"test":[187],"human":[189],"subjects":[190],"further":[191],"showed":[192],"they":[194],"could":[195],"identify":[196],"87.8%":[201],"F-measure,":[202],"naturalness":[206],"audio":[209],"preserved.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}