{"id":"https://openalex.org/W3187244867","doi":"https://doi.org/10.21437/interspeech.2021-1755","title":"The Zero Resource Speech Challenge 2021: Spoken Language Modelling","display_name":"The Zero Resource Speech Challenge 2021: Spoken Language Modelling","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3187244867","doi":"https://doi.org/10.21437/interspeech.2021-1755","mag":"3187244867"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1755","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1755","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":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.14700.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069239428","display_name":"Ewan Dunbar","orcid":"https://orcid.org/0000-0001-9603-953X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ewan Dunbar","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016931966","display_name":"Mathieu Bernard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Bernard","raw_affiliation_strings":["French Institute for Research in Computer Science and Automation"],"affiliations":[{"raw_affiliation_string":"French Institute for Research in Computer Science and Automation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024211274","display_name":"Nicolas Hamilakis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151031","display_name":"Laboratoire de Sciences Cognitives et Psycholinguistique","ror":"https://ror.org/05fvhm231","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210096427","https://openalex.org/I4210151031","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Hamilakis","raw_affiliation_strings":["Laboratoire de sciences cognitives et psycholinguistique"],"affiliations":[{"raw_affiliation_string":"Laboratoire de sciences cognitives et psycholinguistique","institution_ids":["https://openalex.org/I4210151031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091817823","display_name":"Tu Anh Nguyen","orcid":"https://orcid.org/0000-0002-9623-042X"},"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":"Tu Anh Nguyen","raw_affiliation_strings":["Facebook AI Research [Paris]"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research [Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031334559","display_name":"Maureen de Seyssel","orcid":"https://orcid.org/0000-0003-2345-5676"},"institutions":[{"id":"https://openalex.org/I4210151031","display_name":"Laboratoire de Sciences Cognitives et Psycholinguistique","ror":"https://ror.org/05fvhm231","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210096427","https://openalex.org/I4210151031","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maureen de Seyssel","raw_affiliation_strings":["Laboratoire de sciences cognitives et psycholinguistique"],"affiliations":[{"raw_affiliation_string":"Laboratoire de sciences cognitives et psycholinguistique","institution_ids":["https://openalex.org/I4210151031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067466958","display_name":"Patricia Roz\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI"],"is_corresponding":false,"raw_author_name":"Patricia Roz\u00e9","raw_affiliation_strings":["\u00c9cole Normale Superieure"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Normale Superieure","institution_ids":["https://openalex.org/I4210103330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112149946","display_name":"Morgane Rivi\u00e8re","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":"Morgane Rivi\u00e8re","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924622","display_name":"Eugene Kharitonov","orcid":"https://orcid.org/0009-0000-8653-721X"},"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":"Eugene Kharitonov","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[{"id":"https://openalex.org/I4210151031","display_name":"Laboratoire de Sciences Cognitives et Psycholinguistique","ror":"https://ror.org/05fvhm231","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2746051580","https://openalex.org/I29607241","https://openalex.org/I4210096427","https://openalex.org/I4210151031","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":["Laboratoire de sciences cognitives et psycholinguistique"],"affiliations":[{"raw_affiliation_string":"Laboratoire de sciences cognitives et psycholinguistique","institution_ids":["https://openalex.org/I4210151031"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5069239428"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.4199,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69315774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1574","last_page":"1578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758510112762451},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6891336441040039},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.658476710319519},{"id":"https://openalex.org/keywords/abx-test","display_name":"ABX test","score":0.587647557258606},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5628622770309448},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5598539113998413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5440541505813599},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5376445055007935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5152878761291504},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48281797766685486},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47899314761161804},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4765922725200653},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38008731603622437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07202807068824768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758510112762451},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6891336441040039},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.658476710319519},{"id":"https://openalex.org/C60962613","wikidata":"https://www.wikidata.org/wiki/Q287654","display_name":"ABX test","level":2,"score":0.587647557258606},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5628622770309448},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5598539113998413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5440541505813599},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5376445055007935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5152878761291504},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48281797766685486},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47899314761161804},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4765922725200653},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38008731603622437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07202807068824768},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-1755","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1755","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":"mag:3187244867","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.14700.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.2104.14700","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.14700","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"mag:3187244867","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.14700.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},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1854884267","https://openalex.org/W2014307400","https://openalex.org/W2026487812","https://openalex.org/W2080100102","https://openalex.org/W2103318667","https://openalex.org/W2132631284","https://openalex.org/W2137735870","https://openalex.org/W2142625445","https://openalex.org/W2170682101","https://openalex.org/W2176085882","https://openalex.org/W2251012068","https://openalex.org/W2510413766","https://openalex.org/W2593779438","https://openalex.org/W2794753807","https://openalex.org/W2842511635","https://openalex.org/W2933138175","https://openalex.org/W2940544976","https://openalex.org/W2963341956","https://openalex.org/W2963583956","https://openalex.org/W2965373594","https://openalex.org/W2982223350","https://openalex.org/W2990241049","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W3005511757","https://openalex.org/W3036601975","https://openalex.org/W3093096176","https://openalex.org/W3099782249","https://openalex.org/W3110458199","https://openalex.org/W3129009457","https://openalex.org/W3129289122"],"related_works":["https://openalex.org/W3197259906","https://openalex.org/W3032892481","https://openalex.org/W2963288440","https://openalex.org/W3206694069","https://openalex.org/W3174321708","https://openalex.org/W2950133079","https://openalex.org/W2967058205","https://openalex.org/W94318243","https://openalex.org/W2963525826","https://openalex.org/W3096589040","https://openalex.org/W2949079242","https://openalex.org/W2980689696","https://openalex.org/W265135404","https://openalex.org/W2964099072","https://openalex.org/W2122196922","https://openalex.org/W2057674233","https://openalex.org/W1591130683","https://openalex.org/W2522661147","https://openalex.org/W2126618487","https://openalex.org/W2050069490"],"abstract_inverted_index":{"We":[0,48,96],"present":[1,97],"the":[2,29,78,82,101,110],"Zero":[3],"Resource":[4],"Speech":[5],"Challenge":[6],"2021,":[7],"which":[8,32],"asks":[9],"participants":[10],"to":[11,35],"learn":[12],"a":[13,50,64,68],"language":[14,70],"model":[15,71],"directly":[16],"from":[17,40,105],"audio,":[18],"without":[19,44],"any":[20,45],"text":[21],"or":[22,73],"labels.":[23],"The":[24,75],"challenge":[25],"is":[26],"based":[27,58],"on":[28,55,59],"Libri-light":[30],"dataset,":[31],"provides":[33],"up":[34],"60k":[36],"hours":[37],"of":[38,100],"audio":[39,42],"English":[41],"books":[43],"associated":[46],"text.":[47],"provide":[49],"pipeline":[51],"baseline":[52],"system":[53],"consisting":[54],"an":[56,98],"encoder":[57],"contrastive":[60],"predictive":[61],"coding":[62],"(CPC),":[63],"quantizer":[65],"($k$-means)":[66],"and":[67,91,108],"standard":[69],"(BERT":[72],"LSTM).":[74],"metrics":[76],"evaluate":[77],"learned":[79],"representations":[80],"at":[81],"acoustic":[83],"(ABX":[84],"discrimination),":[85],"lexical":[86],"(spot-the-word),":[87],"syntactic":[88],"(acceptability":[89],"judgment)":[90],"semantic":[92],"levels":[93],"(similarity":[94],"judgment).":[95],"overview":[99],"eight":[102],"submitted":[103],"systems":[104],"four":[106],"groups":[107],"discuss":[109],"main":[111],"results.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}