{"id":"https://openalex.org/W2405329321","doi":"https://doi.org/10.21437/interspeech.2015-727","title":"Preserving word-level emphasis in speech-to-speech translation using linear regression HSMMs","display_name":"Preserving word-level emphasis in speech-to-speech translation using linear regression HSMMs","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2405329321","doi":"https://doi.org/10.21437/interspeech.2015-727","mag":"2405329321"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-727","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/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":["Nara Institute of Science & Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke Takamichi","raw_affiliation_strings":["Nara Institute of Science & Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","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 & Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]},{"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":["Nara Institute of Science & Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","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/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":"Tomoki Toda","raw_affiliation_strings":["Nara Institute of Science & Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","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 & Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3665","last_page":"3669"},"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/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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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":0.9643793106079102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8006452322006226},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.584553062915802},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5690001249313354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5412946939468384},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5397714972496033},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.513943612575531},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4808145761489868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4791550040245056},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4443356692790985},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2022615373134613}],"concepts":[{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.9643793106079102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006452322006226},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.584553062915802},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5690001249313354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5412946939468384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5397714972496033},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.513943612575531},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4808145761489868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4791550040245056},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4443356692790985},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2022615373134613},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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:10.21437/interspeech.2015-727","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W2000513720","https://openalex.org/W2048389584","https://openalex.org/W2049633694","https://openalex.org/W2049686551","https://openalex.org/W2051669046","https://openalex.org/W2069631319","https://openalex.org/W2093265061","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2147880316","https://openalex.org/W2152834109","https://openalex.org/W2154920538","https://openalex.org/W2158069733","https://openalex.org/W2158086337","https://openalex.org/W2293211712","https://openalex.org/W2295730220","https://openalex.org/W2403632467","https://openalex.org/W3044514286"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W2055105357","https://openalex.org/W3200958703","https://openalex.org/W2362773009","https://openalex.org/W2169113179","https://openalex.org/W1564107245","https://openalex.org/W2295649751"],"abstract_inverted_index":{"In":[0,76],"speech,":[1],"emphasis":[2,23,64,91,99,118,127,133,165],"is":[3,86,146],"an":[4,16],"important":[5],"type":[6],"of":[7,15,54,98],"paralinguistic":[8],"information":[9,40],"that":[10,85,129,159],"helps":[11],"convey":[12,38],"the":[13,42,52,73,90,131,135,164],"focus":[14],"utterance,":[17],"new":[18,82,115],"information,":[19],"and":[20,94,104,126,174],"emotion.":[21],"If":[22],"can":[24,162],"be":[25,35,150],"incorporated":[26],"into":[27],"a":[28,81],"speech-to-speech":[29],"(S2S)":[30],"translation":[31,53,128],"system,":[32],"it":[33],"will":[34],"possible":[36],"to":[37,88,134,149,152],"this":[39,77],"across":[41,92],"language":[43,137],"barrier.":[44],"However,":[45],"previous":[46],"related":[47],"work":[48],"focuses":[49,66],"only":[50],"on":[51,67],"particular":[55],"prosodic":[56],"features,":[57],"such":[58,71,100],"as":[59,72,101],"F0,":[60,103],"or":[61],"works":[62],"with":[63,138,167],"but":[65],"extremely":[68],"small":[69],"vocabularies,":[70],"10":[74],"digits.":[75],"paper,":[78],"we":[79],"describe":[80],"S2S":[83],"method":[84],"able":[87,151],"translate":[89,163],"languages":[93],"consider":[95],"multiple":[96],"features":[97],"power,":[102],"duration":[105],"over":[106],"larger":[107],"vocabularies.":[108],"We":[109],"do":[110],"so":[111],"by":[112],"introducing":[113],"two":[114],"components:":[116],"word-level":[117,132],"estimation":[119],"using":[120],"linear":[121],"regression":[122],"hidden":[123],"semi-Markov":[124],"models,":[125],"translates":[130],"target":[136],"conditional":[139],"random":[140],"fields.":[141],"The":[142,156],"text-to-speech":[143],"synthesis":[144],"system":[145,161],"also":[147],"modified":[148],"synthesize":[153],"emphasized":[154],"speech.":[155],"result":[157],"shows":[158],"our":[160],"correctly":[166],"91.6%":[168],"F":[169],"-measure":[170],"for":[171,176],"objective":[172],"test,":[173],"87.8%":[175],"subjective":[177],"test.":[178]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}