{"id":"https://openalex.org/W2935542736","doi":"https://doi.org/10.21437/interspeech.2019-2605","title":"Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks","display_name":"Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2935542736","doi":"https://doi.org/10.21437/interspeech.2019-2605","mag":"2935542736"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2605","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103092198","display_name":"Joan Serr\u00e0","orcid":"https://orcid.org/0000-0003-1303-6558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.7991287708282471},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6713201403617859},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6349561214447021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5562044382095337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4979970455169678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4715205430984497},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4638836979866028},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4502064287662506},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4328407347202301},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4240739941596985},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4221658706665039},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32912951707839966},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2513658404350281},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06953853368759155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991287708282471},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6713201403617859},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6349561214447021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562044382095337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4979970455169678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4715205430984497},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4638836979866028},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4502064287662506},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4328407347202301},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4240739941596985},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4221658706665039},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32912951707839966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2513658404350281},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06953853368759155},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2605","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03416","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03416","pdf_url":"https://arxiv.org/pdf/1904.03416","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2935542736","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.03416.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.1904.03416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03416","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03416","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03416","pdf_url":"https://arxiv.org/pdf/1904.03416","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2935542736.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W2328055","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2110798204","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2148154194","https://openalex.org/W2183341477","https://openalex.org/W2295582178","https://openalex.org/W2401942008","https://openalex.org/W2487442924","https://openalex.org/W2527729766","https://openalex.org/W2767754137","https://openalex.org/W2794209590","https://openalex.org/W2842511635","https://openalex.org/W2887997457","https://openalex.org/W2901616798","https://openalex.org/W2902368158","https://openalex.org/W2962736520","https://openalex.org/W2962742544","https://openalex.org/W2962824366","https://openalex.org/W2962835968","https://openalex.org/W2962969419","https://openalex.org/W2963115079","https://openalex.org/W2963127222","https://openalex.org/W2963241221","https://openalex.org/W2963341071","https://openalex.org/W2963661130","https://openalex.org/W2963714041","https://openalex.org/W2963799213","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2964147121","https://openalex.org/W2964227577","https://openalex.org/W3035219538","https://openalex.org/W3125709657","https://openalex.org/W3127686677","https://openalex.org/W3209382000"],"related_works":["https://openalex.org/W2973157397","https://openalex.org/W2842511635","https://openalex.org/W2963341956","https://openalex.org/W2973049979","https://openalex.org/W3099782249","https://openalex.org/W2982223350","https://openalex.org/W2926827382","https://openalex.org/W1494198834","https://openalex.org/W3016181583","https://openalex.org/W3005680577","https://openalex.org/W3008321871","https://openalex.org/W2143583071","https://openalex.org/W2977431735","https://openalex.org/W2970502342","https://openalex.org/W2899998199","https://openalex.org/W2617663343","https://openalex.org/W3173378776","https://openalex.org/W3014232838","https://openalex.org/W3147335029","https://openalex.org/W2990413070"],"abstract_inverted_index":{"Learning":[0],"good":[1],"representations":[2,46,93],"without":[3],"supervision":[4],"is":[5,14,40,65],"still":[6],"an":[7,56],"open":[8],"issue":[9],"in":[10],"machine":[11],"learning,":[12],"and":[13,94,113,130],"particularly":[15],"challenging":[16],"for":[17],"speech":[18,45,123],"signals,":[19],"which":[20],"are":[21],"often":[22],"characterized":[23],"by":[24,47,67],"long":[25],"sequences":[26],"with":[27],"a":[28,49,61,140],"complex":[29],"hierarchical":[30],"structure.":[31],"Some":[32],"recent":[33],"works,":[34],"however,":[35],"have":[36],"shown":[37],"that":[38,70,105,116],"it":[39],"possible":[41],"to":[42,86,90,95,156],"derive":[43],"useful":[44],"employing":[48],"self-supervised":[50,58,74],"encoder-discriminator":[51],"approach.":[52],"This":[53],"paper":[54],"proposes":[55],"improved":[57],"method,":[59],"where":[60],"single":[62],"neural":[63],"encoder":[64,147],"followed":[66],"multiple":[68],"workers":[69],"jointly":[71],"solve":[72],"different":[73,80,157],"tasks.":[75],"The":[76],"needed":[77],"consensus":[78],"across":[79],"tasks":[81],"naturally":[82],"imposes":[83],"meaningful":[84],"constraints":[85],"the":[87,97,106,122,146],"encoder,":[88],"contributing":[89],"discover":[91],"general":[92],"minimize":[96],"risk":[98],"of":[99,142],"learning":[100],"superficial":[101],"ones.":[102],"Experiments":[103],"show":[104],"proposed":[107],"approach":[108],"can":[109],"learn":[110],"transferable,":[111],"robust,":[112],"problem-agnostic":[114],"features":[115,133],"carry":[117],"on":[118],"relevant":[119],"information":[120],"from":[121],"signal,":[124],"such":[125,134],"as":[126,135],"speaker":[127],"identity,":[128],"phonemes,":[129],"even":[131],"higher-level":[132],"emotional":[136],"cues.":[137],"In":[138],"addition,":[139],"number":[141],"design":[143],"choices":[144],"make":[145],"easily":[148],"exportable,":[149],"facilitating":[150],"its":[151],"direct":[152],"usage":[153],"or":[154],"adaptation":[155],"problems.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}