{"id":"https://openalex.org/W3096710170","doi":"https://doi.org/10.21437/interspeech.2020-2955","title":"Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation","display_name":"Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096710170","doi":"https://doi.org/10.21437/interspeech.2020-2955","mag":"3096710170"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2955","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Changhan Wang","raw_affiliation_strings":["Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112542984","display_name":"Jiatao Gu","orcid":"https://orcid.org/0000-0003-3578-2711"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatao Gu","raw_affiliation_strings":["Facebook AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087491225"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4731","last_page":"4735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.994700014591217,"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":0.7549294233322144},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7334844470024109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7127826809883118},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.61372971534729},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43142253160476685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37588924169540405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3517952263355255},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2784704267978668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549294233322144},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7334844470024109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7127826809883118},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.61372971534729},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43142253160476685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37588924169540405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3517952263355255},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2784704267978668}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2955","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2466918907","https://openalex.org/W2605131327","https://openalex.org/W2697044473","https://openalex.org/W2808640845","https://openalex.org/W2883586237","https://openalex.org/W2885706078","https://openalex.org/W2901607128","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2949328740","https://openalex.org/W2952711665","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963292011","https://openalex.org/W2963378435","https://openalex.org/W2963532001","https://openalex.org/W2963736842","https://openalex.org/W2963779652","https://openalex.org/W2964172053","https://openalex.org/W2972448360","https://openalex.org/W2973132140","https://openalex.org/W2991213871","https://openalex.org/W2995732811","https://openalex.org/W3008125272","https://openalex.org/W3015585292","https://openalex.org/W3015810689","https://openalex.org/W3030437843","https://openalex.org/W3032433061","https://openalex.org/W3103029570","https://openalex.org/W4300558631","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W123774389","https://openalex.org/W4399356803","https://openalex.org/W3177132412","https://openalex.org/W3198731777"],"abstract_inverted_index":{"Transfer":[0],"learning":[1],"from":[2,68,127,169],"high-resource":[3,75,128],"languages":[4],"is":[5,40,88,137],"known":[6],"to":[7,12,42,57,115,122,158,178,182],"be":[8,43],"an":[9,54],"efficient":[10],"way":[11],"improve":[13],"end-to-end":[14],"automatic":[15],"speech":[16],"recognition":[17],"(ASR)":[18],"for":[19,35,45,110],"low-resource":[20,170],"languages.Pre-trained":[21],"or":[22],"jointly":[23],"trained":[24,140],"encoder-decoder":[25],"models,":[26],"however,":[27],"do":[28],"not":[29,138],"share":[30,94],"the":[31,36,62,95,111,123],"language":[32,64],"modeling":[33],"(decoder)":[34],"same":[37,96],"language,":[38,82],"which":[39,84],"likely":[41],"inefficient":[44],"distant":[46],"target":[47,63,70,80,92,159],"languages.We":[48],"introduce":[49],"speech-to-text":[50],"translation":[51,143],"(ST)":[52],"as":[53],"auxiliary":[55],"task":[56,103],"incorporate":[58],"additional":[59],"knowledge":[60],"of":[61],"and":[65,91,100],"enable":[66],"transferring":[67],"that":[69,131],"language.Specifically,":[71],"we":[72],"first":[73],"translate":[74],"ASR":[76,93,160],"transcripts":[77],"into":[78],"a":[79,85,106],"lowresource":[81],"with":[83,134,141,167],"ST":[86,90,133],"model":[87,109],"trained.Both":[89],"attention-based":[97],"encoderdecoder":[98],"architecture":[99],"vocabulary.The":[101],"former":[102],"then":[104],"provides":[105],"fully":[107],"pre-trained":[108],"latter,":[112],"bringing":[113],"up":[114,177],"24.6%":[116],"word":[117],"error":[118],"rate":[119],"(WER)":[120],"reduction":[121,181],"baseline":[124],"(direct":[125],"transfer":[126,175],"ASR).We":[129],"show":[130],"training":[132],"human":[135,154],"translations":[136],"necessary.ST":[139],"machine":[142],"(MT)":[144],"pseudo-labels":[145,168],"brings":[146,176],"consistent":[147],"gains.It":[148],"can":[149],"even":[150],"outperform":[151],"those":[152],"using":[153],"labels":[155],"when":[156],"transferred":[157],"by":[161],"leveraging":[162],"only":[163],"500K":[164],"MT":[165,171],"examples.Even":[166],"(200K":[172],"examples),":[173],"ST-enhanced":[174],"8.9%":[179],"WER":[180],"direct":[183],"transfer.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
