{"id":"https://openalex.org/W3037057938","doi":"https://doi.org/10.21437/interspeech.2021-329","title":"Unsupervised Cross-Lingual Representation Learning for Speech Recognition","display_name":"Unsupervised Cross-Lingual Representation Learning for Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3037057938","doi":"https://doi.org/10.21437/interspeech.2021-329","mag":"3037057938"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-329","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.13979","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068394403","display_name":"Alexis Conneau","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Alexis Conneau","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068394403"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":11.4787,"has_fulltext":true,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98756697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2426","last_page":"2430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9980999827384949,"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":0.7913632392883301},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6888595819473267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5744616985321045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5571082234382629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356060862541199},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49983978271484375},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41626426577568054},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4116441011428833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913632392883301},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6888595819473267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5744616985321045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5571082234382629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356060862541199},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49983978271484375},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41626426577568054},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4116441011428833},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-329","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.13979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13979","pdf_url":"https://arxiv.org/pdf/2006.13979","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3037057938","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.13979.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.13979","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.13979","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.13979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.13979","pdf_url":"https://arxiv.org/pdf/2006.13979","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037057938.pdf","grobid_xml":"https://content.openalex.org/works/W3037057938.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1524956127","https://openalex.org/W1846073453","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2123798005","https://openalex.org/W2124509324","https://openalex.org/W2127141656","https://openalex.org/W2141440284","https://openalex.org/W2141820854","https://openalex.org/W2292087804","https://openalex.org/W2547875792","https://openalex.org/W2671812860","https://openalex.org/W2696253854","https://openalex.org/W2730658205","https://openalex.org/W2811079561","https://openalex.org/W2842511635","https://openalex.org/W2891616026","https://openalex.org/W2894835365","https://openalex.org/W2896457183","https://openalex.org/W2898630520","https://openalex.org/W2933138175","https://openalex.org/W2936295285","https://openalex.org/W2941814890","https://openalex.org/W2947591107","https://openalex.org/W2958953787","https://openalex.org/W2962739339","https://openalex.org/W2963027641","https://openalex.org/W2963403868","https://openalex.org/W2963425185","https://openalex.org/W2964121744","https://openalex.org/W2964309797","https://openalex.org/W2970049541","https://openalex.org/W2971840980","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2981991061","https://openalex.org/W2983040767","https://openalex.org/W2987283559","https://openalex.org/W2988736778","https://openalex.org/W2995680346","https://openalex.org/W2996383576","https://openalex.org/W3005511757","https://openalex.org/W3005680577","https://openalex.org/W3032816972","https://openalex.org/W3095410713","https://openalex.org/W3099782249"],"related_works":["https://openalex.org/W3099782249","https://openalex.org/W2963341956","https://openalex.org/W2842511635","https://openalex.org/W2127141656","https://openalex.org/W1494198834","https://openalex.org/W2973049979","https://openalex.org/W2933138175","https://openalex.org/W2963403868","https://openalex.org/W2996383576","https://openalex.org/W2936774411","https://openalex.org/W3016181583","https://openalex.org/W3093579165","https://openalex.org/W2964121744","https://openalex.org/W2327501763","https://openalex.org/W1828163288","https://openalex.org/W3025165719","https://openalex.org/W2995181338","https://openalex.org/W2982223350","https://openalex.org/W2547875792","https://openalex.org/W2972943112"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"XLSR":[3,74],"which":[4,28,115],"learns":[5,43],"cross-lingual":[6,64],"speech":[7,19,39,112,128,147],"representations":[8,40,129],"by":[9,31,98,149],"pretraining":[10,65],"a":[11,33,44,76,103,109,152],"single":[12,110],"model":[13,54,114,154],"from":[14],"the":[15,47,71,86,125],"raw":[16],"waveform":[17],"of":[18,46,82],"in":[20,145,156],"multiple":[21],"languages.":[22,51,139,158],"We":[23,140],"build":[24],"on":[25,57],"wav2vec":[26],"2.0":[27],"is":[29,55,116],"trained":[30],"solving":[32],"contrastive":[34],"task":[35],"over":[36],"masked":[37],"latent":[38,126],"and":[41,60],"jointly":[42],"quantization":[45],"latents":[48],"shared":[49,131],"across":[50,132],"The":[52],"resulting":[53],"fine-tuned":[56],"labeled":[58],"data":[59],"experiments":[61],"show":[62],"that":[63,124],"significantly":[66],"outperforms":[67],"monolingual":[68],"pretraining.":[69],"On":[70,90],"CommonVoice":[72],"benchmark,":[73],"shows":[75,123],"relative":[77,100],"phoneme":[78],"error":[79,96],"rate":[80,97],"reduction":[81],"72%":[83],"compared":[84,101],"to":[85,102,118,142],"best":[87],"known":[88],"results.":[89],"BABEL,":[91],"our":[92],"approach":[93,107],"improves":[94],"word":[95],"16%":[99],"comparable":[104],"system.":[105],"Our":[106],"enables":[108],"multilingual":[111],"recognition":[113],"competitive":[117],"strong":[119],"individual":[120],"models.":[121],"Analysis":[122],"discrete":[127],"are":[130],"languages":[133],"with":[134],"increased":[135],"sharing":[136],"for":[137],"related":[138],"hope":[141],"catalyze":[143],"research":[144],"low-resource":[146],"understanding":[148],"releasing":[150],"XLSR-53,":[151],"large":[153],"pretrained":[155],"53":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}