{"id":"https://openalex.org/W2964161387","doi":"https://doi.org/10.1109/icassp.2019.8683343","title":"Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation","display_name":"Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2964161387","doi":"https://doi.org/10.1109/icassp.2019.8683343","mag":"2964161387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"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/A5076150774","display_name":"Melvin Johnson","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":"Melvin Johnson","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/A5018646392","display_name":"Wolfgang Macherey","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":"Wolfgang Macherey","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/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","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/A5101989491","display_name":"Yuan Cao","orcid":"https://orcid.org/0000-0002-2495-4701"},"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":"Yuan Cao","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/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"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":"Chung-Cheng Chiu","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/A5031588851","display_name":"Naveen Ari","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":"Naveen Ari","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/A5071613306","display_name":"Stella Laurenzo","orcid":"https://orcid.org/0000-0001-5806-4611"},"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":"Stella Laurenzo","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/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","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":9,"corresponding_author_ids":["https://openalex.org/A5102792436"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":16.1021,"has_fulltext":false,"cited_by_count":153,"citation_normalized_percentile":{"value":0.99258909,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7180","last_page":"7184"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.8175604939460754},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7082860469818115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6204230785369873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6098228096961975},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5859979391098022},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.544418215751648},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5166983604431152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.494521826505661},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4793282747268677},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4466601610183716},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4165901243686676},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.41567763686180115},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14276477694511414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175604939460754},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7082860469818115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6204230785369873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098228096961975},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5859979391098022},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.544418215751648},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5166983604431152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.494521826505661},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4793282747268677},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4466601610183716},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4165901243686676},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.41567763686180115},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14276477694511414},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1537859740","https://openalex.org/W1821462560","https://openalex.org/W2101105183","https://openalex.org/W2113106066","https://openalex.org/W2120847449","https://openalex.org/W2121879602","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2525778437","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2766812927","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2808706139","https://openalex.org/W2883586237","https://openalex.org/W2949328740","https://openalex.org/W2962680099","https://openalex.org/W2962824709","https://openalex.org/W2963216553","https://openalex.org/W2963272440","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963779652","https://openalex.org/W2963796886","https://openalex.org/W2963927338","https://openalex.org/W2964012862","https://openalex.org/W2964045208","https://openalex.org/W2964172053","https://openalex.org/W2964199361","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W3012492057","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6632017195","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6739901393","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6753186555","https://openalex.org/W6754400763","https://openalex.org/W6755300632","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W2338806053","https://openalex.org/W3037186962","https://openalex.org/W4385571610","https://openalex.org/W3177132412","https://openalex.org/W3198731777","https://openalex.org/W2293738010","https://openalex.org/W4391147652"],"abstract_inverted_index":{"End-to-end":[0],"Speech":[1,16],"Translation":[2,22],"(ST)":[3],"models":[4,105],"have":[5,67],"many":[6],"potential":[7],"advantages":[8],"when":[9],"compared":[10],"to":[11,54,79,106,156,166],"the":[12,30,36,69],"cascade":[13],"of":[14,32,38,47,59,71],"Automatic":[15],"Recognition":[17],"(ASR)":[18],"and":[19,29,61,74,142],"text":[20,150],"Machine":[21],"(MT)":[23],"models,":[24],"including":[25],"lowered":[26],"inference":[27],"latency":[28],"avoidance":[31],"error":[33],"compounding.":[34],"However,":[35],"quality":[37,130],"end-to-end":[39,131],"ST":[40,115,132],"is":[41,52],"often":[42],"limited":[43],"by":[44],"a":[45,128,170],"paucity":[46],"training":[48,84,116],"data,":[49,85],"since":[50],"it":[51],"difficult":[53],"collect":[55],"large":[56],"parallel":[57],"corpora":[58],"speech":[60,152,168],"translated":[62],"transcript":[63],"pairs.":[64,91],"Previous":[65],"studies":[66],"proposed":[68],"use":[70],"pre-trained":[72,99],"components":[73],"multi-task":[75,122],"learning":[76],"in":[77],"order":[78],"benefit":[80],"from":[81,147],"weakly":[82,108,139],"supervised":[83,109,140],"such":[86],"as":[87],"speech-to-transcript":[88],"or":[89,101,151],"text-to-foreign-text":[90],"In":[92],"this":[93],"paper,":[94],"we":[95,125,160],"demonstrate":[96,126],"that":[97,127,143],"using":[98,137],"MT":[100],"text-to-speech":[102],"(TTS)":[103],"synthesis":[104],"convert":[107],"data":[110,145],"into":[111],"speech-to-translation":[112],"pairs":[113],"for":[114,163],"can":[117,134,153],"be":[118,135,154],"more":[119],"effective":[120],"than":[121],"learning.":[123],"Furthermore,":[124],"high":[129],"model":[133],"trained":[136],"only":[138],"datasets,":[141],"synthetic":[144,167],"sourced":[146],"unlabeled":[148],"monolingual":[149],"used":[155],"improve":[157],"performance.":[158],"Finally,":[159],"discuss":[161],"methods":[162],"avoiding":[164],"overfitting":[165],"with":[169],"quantitative":[171],"ablation":[172],"study.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":13}],"updated_date":"2026-01-30T23:17:42.513302","created_date":"2025-10-10T00:00:00"}