{"id":"https://openalex.org/W4372260052","doi":"https://doi.org/10.1109/icassp49357.2023.10095973","title":"Enhancing Speech-To-Speech Translation with Multiple TTS Targets","display_name":"Enhancing Speech-To-Speech Translation with Multiple TTS Targets","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260052","doi":"https://doi.org/10.1109/icassp49357.2023.10095973"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052049405","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0003-2340-1109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ann Lee","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhan Wang","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"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/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5008336983"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7785025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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":0.8820258378982544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8679587841033936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6824913024902344},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6073527336120605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5735687613487244},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5066278576850891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49354708194732666},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4605428874492645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.443476140499115},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.41008704900741577}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8820258378982544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8679587841033936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6824913024902344},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6073527336120605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5735687613487244},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5066278576850891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49354708194732666},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4605428874492645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.443476140499115},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.41008704900741577},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W206967138","https://openalex.org/W2058094241","https://openalex.org/W2139647714","https://openalex.org/W2152834109","https://openalex.org/W2154304575","https://openalex.org/W2242221029","https://openalex.org/W2908510526","https://openalex.org/W2963532001","https://openalex.org/W2964243274","https://openalex.org/W2972495969","https://openalex.org/W3001434439","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3024605872","https://openalex.org/W3033411150","https://openalex.org/W3091928890","https://openalex.org/W3092028330","https://openalex.org/W3140429000","https://openalex.org/W3142316150","https://openalex.org/W3161236344","https://openalex.org/W3169905056","https://openalex.org/W3175871055","https://openalex.org/W3180374548","https://openalex.org/W3197580070","https://openalex.org/W3206375275","https://openalex.org/W3207300132","https://openalex.org/W3207738474","https://openalex.org/W3209059054","https://openalex.org/W4221153524","https://openalex.org/W4224821740","https://openalex.org/W4226444650","https://openalex.org/W4285250921","https://openalex.org/W4287072252","https://openalex.org/W4287854499","https://openalex.org/W4296070387","https://openalex.org/W4394671563","https://openalex.org/W6757817989","https://openalex.org/W6777028661","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6784545093","https://openalex.org/W6790356757","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6802857679","https://openalex.org/W6810701745","https://openalex.org/W6810778535","https://openalex.org/W6841035593","https://openalex.org/W6917585676","https://openalex.org/W7061659707"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W1540615732","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W4360995948"],"abstract_inverted_index":{"It":[0],"has":[1],"been":[2],"known":[3],"that":[4,94,118,134],"direct":[5,34,89],"speech-to-speech":[6],"translation":[7,57],"(S2ST)":[8],"models":[9],"usually":[10,39],"suffer":[11],"from":[12,55,100,127],"the":[13,19,48,53,67,73,81,97,107,121,144,147],"data":[14,54],"scarcity":[15],"issue":[16],"because":[17],"of":[18,83],"limited":[20,63],"existing":[21],"parallel":[22],"materials":[23],"for":[24,88],"both":[25],"source":[26],"and":[27],"target":[28,49,69,86,98],"speech.":[29],"Therefore":[30],"to":[31,44],"train":[32],"a":[33,62,115],"S2ST":[35,74,90,108,122],"system,":[36],"previous":[37],"works":[38],"utilize":[40],"text-to-speech":[41],"(TTS)":[42],"systems":[43,103],"generate":[45],"samples":[46],"in":[47],"language":[50],"by":[51],"augmenting":[52],"speech-to-text":[56],"(S2TT).":[58],"However,":[59],"there":[60],"is":[61],"investigation":[64],"into":[65],"how":[66],"synthesized":[68,85],"speech":[70,87,99],"would":[71],"affect":[72],"models.":[75,91],"In":[76],"this":[77],"work,":[78],"we":[79,112],"analyze":[80],"effect":[82],"changing":[84],"We":[92],"find":[93],"simply":[95],"combining":[96],"different":[101,128],"TTS":[102,129],"can":[104],"potentially":[105],"improve":[106],"performances.":[109],"Following":[110],"that,":[111],"also":[113],"propose":[114],"multi-task":[116],"framework":[117,137],"jointly":[119],"optimizes":[120],"system":[123],"with":[124],"multiple":[125],"targets":[126],"systems.":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"our":[135],"proposed":[136],"achieves":[138],"consistent":[139],"improvements":[140],"(2.8":[141],"BLEU)":[142],"over":[143],"baselines":[145],"on":[146],"Fisher":[148],"Spanish-English":[149],"dataset.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
