{"id":"https://openalex.org/W3142316150","doi":"https://doi.org/10.1109/slt48900.2021.9383496","title":"Transformer-Based Direct Speech-To-Speech Translation with Transcoder","display_name":"Transformer-Based Direct Speech-To-Speech Translation with Transcoder","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3142316150","doi":"https://doi.org/10.1109/slt48900.2021.9383496","mag":"3142316150"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5042592085","display_name":"Takatomo Kano","orcid":"https://orcid.org/0000-0001-9693-3785"},"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":"Takatomo Kano","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, 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"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"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/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"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, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042592085"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":6.9384,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97329692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"958","last_page":"965"},"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":0.9991000294685364,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8684431910514832},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.8177989721298218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7081019878387451},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6539554595947266},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5781707167625427},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5591017603874207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5292341709136963},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5264949202537537},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4262196719646454},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41772398352622986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8684431910514832},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8177989721298218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7081019878387451},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6539554595947266},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5781707167625427},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5591017603874207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5292341709136963},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5264949202537537},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4262196719646454},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41772398352622986},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":30,"referenced_works":["https://openalex.org/W206967138","https://openalex.org/W854541894","https://openalex.org/W2101105183","https://openalex.org/W2116492146","https://openalex.org/W2133564696","https://openalex.org/W2136545725","https://openalex.org/W2153653739","https://openalex.org/W2161742089","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2605202026","https://openalex.org/W2936969148","https://openalex.org/W2949328740","https://openalex.org/W2962680099","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2964308564","https://openalex.org/W2972495969","https://openalex.org/W3017535695","https://openalex.org/W3037217258","https://openalex.org/W4241645538","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W6608432165","https://openalex.org/W6623517193","https://openalex.org/W6677328238","https://openalex.org/W6679434410","https://openalex.org/W6736996214","https://openalex.org/W6739901393","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4385571610","https://openalex.org/W4200068392","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W2772686614","https://openalex.org/W2293738010","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W1489621819","https://openalex.org/W2251328660"],"abstract_inverted_index":{"Traditional":[0],"speech":[1,10,22,59,79,113,122,182],"translation":[2,14,50,60,114,140,177,183],"systems":[3],"use":[4],"a":[5,30,62,68,132,158,169,173,180],"cascade":[6],"manner":[7],"that":[8,71,94],"concatenates":[9],"recognition":[11],"(ASR),":[12],"machine":[13],"(MT),":[15],"and":[16,86,105,119,178,190,196],"text-to-speech":[17],"(TTS)":[18],"synthesis":[19],"to":[20,26,43,56,73,130,172],"translate":[21],"from":[23],"one":[24,53],"language":[25,28,100,111,198],"another":[27],"in":[29,48,61],"step-by-step":[31,139,170],"manner.":[32],"Unfortunately,":[33],"since":[34],"those":[35],"components":[36],"are":[37],"trained":[38],"separately,":[39],"MT":[40],"often":[41],"struggles":[42],"handle":[44],"ASR":[45],"errors,":[46],"resulting":[47],"unnatural":[49],"results.":[51],"Recently,":[52],"work":[54,95],"attempted":[55],"construct":[57,131],"direct":[58,121],"single":[63,133],"model.":[64,163],"The":[65],"model":[66,192],"used":[67],"multi-task":[69,191],"scheme":[70,171],"learns":[72],"predict":[74],"not":[75],"only":[76,97,146],"the":[77,84,138],"target":[78,87],"spectrograms":[80],"directly":[81],"but":[82],"also":[83],"source":[85],"phoneme":[88],"transcription":[89],"as":[90],"auxiliary":[91],"tasks.":[92],"However,":[93,142],"was":[96,129],"evaluated":[98],"Spanish-English":[99],"pairs":[101],"with":[102],"similar":[103,195],"syntax":[104],"word":[106,117],"order.":[107],"With":[108],"syntactically":[109,194],"distant":[110,116,197],"pairs,":[112],"requires":[115],"order,":[118],"thus":[120],"frame-to-frame":[123],"alignments":[124],"become":[125],"difficult.":[126],"Another":[127],"direction":[128],"deep-learning":[134],"framework":[135],"while":[136],"keeping":[137],"process.":[141],"such":[143],"studies":[144],"focused":[145],"on":[147,157],"speech-to-text":[148],"translation.":[149],"Furthermore,":[150],"all":[151],"of":[152],"these":[153],"works":[154],"were":[155],"based":[156],"recurrent":[159],"neural":[160],"net-work":[161],"(RNN)":[162],"In":[164],"this":[165],"work,":[166],"we":[167],"propose":[168,179],"complete":[174],"end-to-end":[175],"speech-to-speech":[176],"Transformer-based":[181],"using":[184,193],"Transcoder.":[185],"We":[186],"compare":[187],"our":[188],"proposed":[189],"pairs.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
