{"id":"https://openalex.org/W3148101939","doi":"https://doi.org/10.1109/slt48900.2021.9383461","title":"Towards Unsupervised Learning of Speech Features in the Wild","display_name":"Towards Unsupervised Learning of Speech Features in the Wild","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3148101939","doi":"https://doi.org/10.1109/slt48900.2021.9383461","mag":"3148101939"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/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 Riviere","raw_affiliation_strings":["Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","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/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"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"]},{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["FR","IL"],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":["EHESS, CNRS, INRIA, ENS-PSL University","Facebook AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EHESS, CNRS, INRIA, ENS-PSL University","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I90669466"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6375,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91870942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"163"},"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.8148503303527832},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7768270373344421},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6782247424125671},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5432658195495605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5299932360649109},{"id":"https://openalex.org/keywords/abx-test","display_name":"ABX test","score":0.5247419476509094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5104852914810181},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5071308612823486},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4809809923171997},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.433575302362442},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43343058228492737},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42562180757522583},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40652140974998474},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2739325761795044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148503303527832},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7768270373344421},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6782247424125671},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5432658195495605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5299932360649109},{"id":"https://openalex.org/C60962613","wikidata":"https://www.wikidata.org/wiki/Q287654","display_name":"ABX test","level":2,"score":0.5247419476509094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5104852914810181},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5071308612823486},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4809809923171997},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.433575302362442},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43343058228492737},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42562180757522583},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40652140974998474},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2739325761795044},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2658974192","display_name":"Paris Sciences et Lettres","funder_award_id":"ANR-10-IDEX-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4209519768","display_name":"Fronti\u00e8res en cognition","funder_award_id":"ANR-17-EURE-0017","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5838787665","display_name":"PaRis Artificial Intelligence Research InstitutE","funder_award_id":"ANR-19-P3IA-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2055408826","https://openalex.org/W2079623482","https://openalex.org/W2111702745","https://openalex.org/W2124558353","https://openalex.org/W2127141656","https://openalex.org/W2133223948","https://openalex.org/W2147590749","https://openalex.org/W2346964103","https://openalex.org/W2395899413","https://openalex.org/W2407151108","https://openalex.org/W2430252546","https://openalex.org/W2593779438","https://openalex.org/W2753008876","https://openalex.org/W2786608204","https://openalex.org/W2787447541","https://openalex.org/W2795282075","https://openalex.org/W2796339975","https://openalex.org/W2842511635","https://openalex.org/W2889374926","https://openalex.org/W2930682606","https://openalex.org/W2940544976","https://openalex.org/W2950414763","https://openalex.org/W2953190524","https://openalex.org/W2962850179","https://openalex.org/W2963371670","https://openalex.org/W2963381607","https://openalex.org/W2963403868","https://openalex.org/W2963620343","https://openalex.org/W2973026522","https://openalex.org/W2973049979","https://openalex.org/W2983785920","https://openalex.org/W2988736778","https://openalex.org/W2990583358","https://openalex.org/W2995181338","https://openalex.org/W3003875258","https://openalex.org/W3015213852","https://openalex.org/W3015501067","https://openalex.org/W3015783745","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3093096176","https://openalex.org/W3093427098","https://openalex.org/W3099782249","https://openalex.org/W3102342027","https://openalex.org/W3144810982","https://openalex.org/W4289564011","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6697293080","https://openalex.org/W6712444837","https://openalex.org/W6714100551","https://openalex.org/W6739901393","https://openalex.org/W6743986254","https://openalex.org/W6750523955","https://openalex.org/W6761553608","https://openalex.org/W6769455919","https://openalex.org/W6770514103","https://openalex.org/W6771812881","https://openalex.org/W6780218876","https://openalex.org/W6780483730","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,67],"unsupervised":[3],"contrastive":[4],"learning":[5,142],"of":[6,48,89,120,150],"speech":[7,23,56,116,161],"representation":[8],"has":[9,16],"shown":[10],"promising":[11],"results,":[12],"but":[13],"so":[14],"far":[15],"mostly":[17],"been":[18],"applied":[19],"to":[20,91,128,167],"clean,":[21],"curated":[22],"datasets.":[24],"Can":[25],"it":[26],"also":[27],"be":[28,106,139,165],"used":[29],"with":[30,111,124],"unprepared":[31],"audio":[32],"data":[33,109,126],"\"in":[34],"the":[35,68,95,101,135,147,151,172],"wild\"?":[36],"Here,":[37],"we":[38],"explore":[39],"three":[40],"potential":[41],"problems":[42,81,104],"in":[43,61,146,171],"this":[44],"setting:":[45],"(i)":[46],"presence":[47],"non-speech":[49],"data,":[50,57],"(ii)":[51],"noisy":[52],"or":[53],"low":[54,173],"quality":[55],"and":[58],"(iii)":[59],"imbalance":[60],"speaker":[62,144],"distribution.":[63],"We":[64,98,132,153],"show":[65,99,133,154],"that":[66,100,134,155,163],"Libri-light":[69],"train":[70],"set,":[71],"which":[72],"is":[73],"itself":[74],"a":[75,86,121,143],"relatively":[76],"clean":[77,125],"speech-only":[78],"dataset,":[79],"these":[80,156],"combined":[82],"can":[83,105,138,164],"already":[84],"have":[85],"performance":[87],"cost":[88],"up":[90],"30%":[92],"relative":[93],"for":[94],"ABX":[96],"score.":[97],"first":[102],"two":[103],"alleviated":[107,140],"by":[108,141],"filtering,":[110],"voice":[112],"activity":[113],"detection":[114],"selecting":[115],"segments,":[117],"while":[118],"perplexity":[119],"model":[122],"trained":[123],"helping":[127],"discard":[129],"entire":[130],"files.":[131],"third":[136],"problem":[137],"embedding":[145],"predictive":[148],"branch":[149],"model.":[152],"techniques":[157],"build":[158],"more":[159],"robust":[160],"features":[162],"transferred":[166],"an":[168],"ASR":[169],"task":[170],"resource":[174],"setting.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}