{"id":"https://openalex.org/W4221153524","doi":"https://doi.org/10.21437/interspeech.2022-10938","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","display_name":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221153524","doi":"https://doi.org/10.21437/interspeech.2022-10938"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10938","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10938","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5101778490","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-7242-6065"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ye Jia","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107006573","display_name":"Yifan Ding","orcid":"https://orcid.org/0009-0001-4352-5427"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Ding","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Bapna","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048302740","display_name":"Colin Cherry","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Cherry","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433533","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-3250-4284"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068394403","display_name":"Alexis Conneau","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexis Conneau","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5097328971","display_name":"Nobu Morioka","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nobu Morioka","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101778490"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.4568,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83569466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1721","last_page":"1725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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":0.9983999729156494,"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":0.9961000084877014,"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":0.7820422649383545},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7371780872344971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6574856042861938},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5088117718696594},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4766750633716583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4689473807811737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4667516052722931},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4396190643310547},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.34311169385910034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820422649383545},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7371780872344971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6574856042861938},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5088117718696594},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4766750633716583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4689473807811737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4667516052722931},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4396190643310547},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.34311169385910034},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/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.2022-10938","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10938","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2257408573","https://openalex.org/W2292087804","https://openalex.org/W2560647685","https://openalex.org/W2605131327","https://openalex.org/W2903193068","https://openalex.org/W2914120296","https://openalex.org/W2928941594","https://openalex.org/W2958953787","https://openalex.org/W2963779652","https://openalex.org/W2964085268","https://openalex.org/W2964161387","https://openalex.org/W2964172053","https://openalex.org/W2970279348","https://openalex.org/W2972448360","https://openalex.org/W3007068036","https://openalex.org/W3011411500","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3091928890","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3097787369","https://openalex.org/W3119308075","https://openalex.org/W3142316150","https://openalex.org/W3169320628","https://openalex.org/W3169483174","https://openalex.org/W3173767661","https://openalex.org/W3175871055","https://openalex.org/W3196509775","https://openalex.org/W3197324626","https://openalex.org/W3207222250","https://openalex.org/W3207738474","https://openalex.org/W3213018012","https://openalex.org/W3213029956","https://openalex.org/W4221155340","https://openalex.org/W4226033575","https://openalex.org/W4226444650","https://openalex.org/W4285158119","https://openalex.org/W4287072252","https://openalex.org/W4287213456","https://openalex.org/W4287329822","https://openalex.org/W4287854499","https://openalex.org/W4297808394","https://openalex.org/W4300558631","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W1540615732","https://openalex.org/W2293738010","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971"],"abstract_inverted_index":{"End-to-end":[0],"speech-to-speech":[1],"translation":[2,94],"(S2ST)":[3],"without":[4,122],"relying":[5],"on":[6,37,84,99,103,126,135],"intermediate":[7],"text":[8,74],"representations":[9],"is":[10,28,47,107],"a":[11],"rapidly":[12],"emerging":[13],"frontier":[14],"of":[15,23,31,44,52,80,96],"research.Recent":[16],"works":[17],"have":[18],"demonstrated":[19],"that":[20,30],"the":[21,42,50,78,92,104,118],"performance":[22,43,79],"such":[24],"direct":[25,45,81,97],"S2ST":[26,34,46,54,82,98,144],"systems":[27],"approaching":[29],"conventional":[32],"cascade":[33],"when":[35],"trained":[36,121],"comparable":[38],"datasets.However,":[39],"in":[40],"practice,":[41],"bounded":[48],"by":[49,109],"availability":[51],"paired":[53],"training":[55],"data.In":[56],"this":[57],"work,":[58],"we":[59],"explore":[60],"multiple":[61],"approaches":[62],"for":[63,143],"leveraging":[64],"much":[65],"more":[66,131],"widely":[67],"available":[68],"unsupervised":[69],"and":[70,73,145],"weakly-supervised":[71],"speech":[72,146],"data":[75],"to":[76,117],"improve":[77],"based":[83],"Translatotron":[85],"2.":[86],"With":[87],"our":[88],"most":[89],"effective":[90],"approaches,":[91],"average":[93],"quality":[95],"21":[100],"language":[101,128],"pairs":[102],"CVSS-C":[105],"corpus":[106],"improved":[108],"+13.6":[110],"BLEU":[111],"(or":[112],"+113%":[113],"relatively),":[114],"as":[115],"compared":[116],"previous":[119],"state-of-the-art":[120],"additional":[123],"data.The":[124],"improvements":[125],"low-resource":[127],"are":[129],"even":[130],"significant":[132],"(+398%":[133],"relatively":[134],"average).Our":[136],"comparative":[137],"studies":[138],"suggest":[139],"future":[140],"research":[141],"directions":[142],"representation":[147],"learning.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}