{"id":"https://openalex.org/W4289821214","doi":"https://doi.org/10.1109/jstsp.2022.3195430","title":"Pretext Tasks Selection for Multitask Self-Supervised Audio Representation Learning","display_name":"Pretext Tasks Selection for Multitask Self-Supervised Audio Representation Learning","publication_year":2022,"publication_date":"2022-08-05","ids":{"openalex":"https://openalex.org/W4289821214","doi":"https://doi.org/10.1109/jstsp.2022.3195430"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3195430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3195430","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5058914746","display_name":"Salah Zaiem","orcid":"https://orcid.org/0000-0002-0788-3219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salah Zaiem","raw_affiliation_strings":["Télécom Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-0788-3219","affiliations":[{"raw_affiliation_string":"Télécom Paris, Palaiseau, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089505434","display_name":"Titouan Parcollet","orcid":"https://orcid.org/0000-0003-0672-1346"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Titouan Parcollet","raw_affiliation_strings":["LIA, Avignon Université, Avignon, France","LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA, Avignon Université, Avignon, France","institution_ids":["https://openalex.org/I4210119991"]},{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["Télécom Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-0028-327X","affiliations":[{"raw_affiliation_string":"Télécom Paris, Palaiseau, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048810248","display_name":"Abdelwahab Heba","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdelwahab Heba","raw_affiliation_strings":["Université Paul Sabatier, IRIT, CNRS, Toulouse, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paul Sabatier, IRIT, CNRS, Toulouse, France","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2297,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87869946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"16","issue":"6","first_page":"1439","last_page":"1453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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"}},{"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/pretext","display_name":"Pretext","score":0.9496414065361023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8048117756843567},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6840599775314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.600831925868988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.570188045501709},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5538609027862549},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5342981219291687},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5250584483146667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4771920442581177},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4487650394439697},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.42820796370506287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3374638557434082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33177992701530457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1107017993927002}],"concepts":[{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.9496414065361023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8048117756843567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6840599775314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.600831925868988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.570188045501709},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5538609027862549},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5342981219291687},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5250584483146667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4771920442581177},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4487650394439697},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.42820796370506287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3374638557434082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33177992701530457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1107017993927002},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3195430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3195430","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-03601330v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03601330","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing, 2022, 16 (6), pp.1439-1453. ⟨10.1109/JSTSP.2022.3195430⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":114,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W343636949","https://openalex.org/W1494198834","https://openalex.org/W1589137271","https://openalex.org/W1796128977","https://openalex.org/W2090042521","https://openalex.org/W2100643000","https://openalex.org/W2110709236","https://openalex.org/W2128790395","https://openalex.org/W2138019504","https://openalex.org/W2143426320","https://openalex.org/W2146334809","https://openalex.org/W2150772522","https://openalex.org/W2154053567","https://openalex.org/W2154462399","https://openalex.org/W2242632974","https://openalex.org/W2290689761","https://openalex.org/W2296643551","https://openalex.org/W2321533354","https://openalex.org/W2395899413","https://openalex.org/W2402146185","https://openalex.org/W2407151108","https://openalex.org/W2726515241","https://openalex.org/W2747874407","https://openalex.org/W2755891984","https://openalex.org/W2758739367","https://openalex.org/W2797510035","https://openalex.org/W2890964092","https://openalex.org/W2899260162","https://openalex.org/W2940256401","https://openalex.org/W2944255943","https://openalex.org/W2948012107","https://openalex.org/W2962824366","https://openalex.org/W2963115079","https://openalex.org/W2963683295","https://openalex.org/W2963826423","https://openalex.org/W2964185501","https://openalex.org/W2972943112","https://openalex.org/W2973127116","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2982303846","https://openalex.org/W2994633389","https://openalex.org/W2996428491","https://openalex.org/W2996905456","https://openalex.org/W2998216295","https://openalex.org/W3006926732","https://openalex.org/W3015213852","https://openalex.org/W3023371261","https://openalex.org/W3030437843","https://openalex.org/W3033038061","https://openalex.org/W3034781633","https://openalex.org/W3042860357","https://openalex.org/W3044967013","https://openalex.org/W3048911294","https://openalex.org/W3093579165","https://openalex.org/W3096196861","https://openalex.org/W3096485810","https://openalex.org/W3096715616","https://openalex.org/W3103005696","https://openalex.org/W3127686677","https://openalex.org/W3160719641","https://openalex.org/W3160799772","https://openalex.org/W3162391496","https://openalex.org/W3168921237","https://openalex.org/W3189296823","https://openalex.org/W3196876847","https://openalex.org/W3197411683","https://openalex.org/W3197580070","https://openalex.org/W3197981364","https://openalex.org/W3198275944","https://openalex.org/W3198608154","https://openalex.org/W3198771897","https://openalex.org/W3202037040","https://openalex.org/W3206252155","https://openalex.org/W3206495532","https://openalex.org/W3208860981","https://openalex.org/W3209984917","https://openalex.org/W4225755266","https://openalex.org/W4287726044","https://openalex.org/W4297808394","https://openalex.org/W4394671563","https://openalex.org/W6639808567","https://openalex.org/W6676726796","https://openalex.org/W6683181193","https://openalex.org/W6691766336","https://openalex.org/W6696886941","https://openalex.org/W6747899497","https://openalex.org/W6760212410","https://openalex.org/W6766489549","https://openalex.org/W6768021236","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6771977725","https://openalex.org/W6774314701","https://openalex.org/W6777179611","https://openalex.org/W6779326418","https://openalex.org/W6779919476","https://openalex.org/W6779977557","https://openalex.org/W6780218876","https://openalex.org/W6780637495","https://openalex.org/W6781476637","https://openalex.org/W6781834539","https://openalex.org/W6783792957","https://openalex.org/W6784232266","https://openalex.org/W6784614252","https://openalex.org/W6788335241","https://openalex.org/W6789826613","https://openalex.org/W6790356757","https://openalex.org/W6796422976","https://openalex.org/W6801625237","https://openalex.org/W6844194202","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W161456234","https://openalex.org/W3123043866","https://openalex.org/W2765162471","https://openalex.org/W2367130511","https://openalex.org/W4235007455","https://openalex.org/W2538661024","https://openalex.org/W4287781552","https://openalex.org/W3023831224","https://openalex.org/W2148252020","https://openalex.org/W4386598220"],"abstract_inverted_index":{"Through":[0],"solving":[1],"pretext":[2,56,79,118,130,152],"tasks,":[3],"self-supervised":[4,61,156,201],"learning":[5,44],"leverages":[6],"unlabeled":[7],"data":[8],"to":[9,45,51,59,65,125,149],"extract":[10],"useful":[11,60],"latent":[12],"representations":[13,62],"replacing":[14],"traditional":[15],"input":[16],"features":[17,32,48],"in":[18],"the":[19,85,97,112,115,145,150,155,177,192],"downstream":[20,69,86],"task.":[21],"In":[22,95],"audio":[23],"and":[24,73,92,167,170,180,194],"speech":[25,164],"signal":[26],"processing,":[27],"a":[28,53,103,123,127,133],"wide":[29],"range":[30],"of":[31,37,114,117,129,135,196],"were":[33],"engineered":[34],"through":[35],"decades":[36],"research":[38],"efforts.":[39],"As":[40],"it":[41],"turns":[42],"out,":[43],"predict":[46],"such":[47,78],"has":[49],"proven":[50],"be":[52,66],"particularly":[54],"relevant":[55,197],"task,":[57],"leading":[58],"which":[63,108],"prove":[64],"effective":[67],"for":[68,76,81,144,200],"tasks.":[70,119],"However,":[71],"methods":[72],"common":[74],"practices":[75],"combining":[77],"tasks":[80,131,153],"better":[82,186],"performance":[83],"on":[84,102,162],"task":[87],"have":[88],"not":[89],"been":[90],"explored":[91],"understood":[93],"properly.":[94],"fact,":[96],"process":[98],"relies":[99],"almost":[100],"exclusively":[101],"computationally":[104],"heavy":[105],"experimental":[106],"procedure,":[107],"becomes":[109],"intractable":[110],"with":[111,182],"increase":[113],"number":[116],"This":[120],"paper":[121],"introduces":[122],"method":[124,138,184],"select":[126],"group":[128],"among":[132],"set":[134],"candidates.":[136],"The":[137,159],"we":[139],"propose":[140],"estimates":[141],"calibrated":[142],"weights":[143],"partial":[146],"losses":[147],"corresponding":[148],"considered":[151],"during":[154],"training":[157],"process.":[158],"experiments":[160],"conducted":[161],"automatic":[163],"recognition,":[165],"speaker":[166],"emotion":[168],"recognition":[169],"instrument":[171],"classification":[172],"validate":[173],"our":[174,183],"approach":[175],"as":[176],"groups":[178],"selected":[179],"weighted":[181],"perform":[185],"than":[187],"classic":[188],"baselines,":[189],"thus":[190],"facilitating":[191],"selection":[193],"combination":[195],"pretext-task":[198],"labels":[199],"representation":[202],"learning.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-08-05T00:00:00"}