{"id":"https://openalex.org/W4206348758","doi":"https://doi.org/10.23919/eusipco54536.2021.9616254","title":"Word-Level Embeddings for Cross-Task Transfer Learning in Speech Processing","display_name":"Word-Level Embeddings for Cross-Task Transfer Learning in Speech Processing","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4206348758","doi":"https://doi.org/10.23919/eusipco54536.2021.9616254"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616254","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616254","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09909","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012253790","display_name":"Pierre Beckmann","orcid":"https://orcid.org/0000-0001-9247-4841"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Pierre Beckmann","raw_affiliation_strings":["Swiss Federal Institute of Technology Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Swiss Federal Institute of Technology Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029632932","display_name":"Mikolaj Kegler","orcid":"https://orcid.org/0000-0003-3408-2588"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mikolaj Kegler","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491"},"institutions":[{"id":"https://openalex.org/I4210148785","display_name":"Logitech (Switzerland)","ror":"https://ror.org/05pkpss54","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210148785"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Milos Cernak","raw_affiliation_strings":["Logitech Europe S.A., Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Logitech Europe S.A., Lausanne, Switzerland","institution_ids":["https://openalex.org/I4210148785"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012253790"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.6347,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71943443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"450"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293564319610596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6708873510360718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6643510460853577},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6578876972198486},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5971883535385132},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.581423282623291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5804356336593628},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5199583768844604},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5078826546669006},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44724929332733154},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.442336767911911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293564319610596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6708873510360718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6643510460853577},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6578876972198486},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5971883535385132},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.581423282623291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5804356336593628},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5199583768844604},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5078826546669006},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44724929332733154},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.442336767911911},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616254","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616254","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.09909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09909","pdf_url":"https://arxiv.org/pdf/1910.09909","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":"pmh:oai:infoscience.epfl.ch:293606","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/293606","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/94143","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/94143","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.09909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09909","pdf_url":"https://arxiv.org/pdf/1910.09909","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":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W1981976602","https://openalex.org/W2056486423","https://openalex.org/W2067295501","https://openalex.org/W2121061347","https://openalex.org/W2163922914","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2526050071","https://openalex.org/W2587024248","https://openalex.org/W2726367589","https://openalex.org/W2741913599","https://openalex.org/W2786459654","https://openalex.org/W2887280559","https://openalex.org/W2936774411","https://openalex.org/W2963425185","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981087920","https://openalex.org/W2981283774","https://openalex.org/W2982039329","https://openalex.org/W3015949486","https://openalex.org/W3036601975","https://openalex.org/W3100270690","https://openalex.org/W3102342027","https://openalex.org/W3125709657","https://openalex.org/W3127686677","https://openalex.org/W4288348042","https://openalex.org/W4297800839","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6687011383","https://openalex.org/W6692550842","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6789826613","https://openalex.org/W6840487619"],"related_works":["https://openalex.org/W2821676139","https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W3135975972","https://openalex.org/W3016888008"],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"in":[2,93],"deep":[3],"learning":[4,9,21,45,57,67,128],"often":[5],"rely":[6],"on":[7,171],"representation":[8,23,59,139],"and":[10,17,40,62,97,110,113,154],"knowledge":[11],"transfer.":[12],"In":[13,55,117],"recent":[14],"years,":[15],"unsupervised":[16],"self-supervised":[18],"techniques":[19],"for":[20,42,81],"speech":[22,29,61,80,96,102,138,151],"were":[24,168],"developed":[25],"to":[26,32,130],"foster":[27],"automatic":[28],"recognition.":[30],"Up":[31],"date,":[33],"most":[34],"of":[35,51,60,65,79,89,124,160],"these":[36],"approaches":[37],"are":[38],"task-specific":[39,131,165],"designed":[41],"within-task":[43],"transfer":[44,66,83,127],"between":[46],"different":[47],"datasets":[48],"or":[49,167],"setups":[50],"a":[52],"particular":[53],"task.":[54,173],"turn,":[56],"task-independent":[58],"cross-task":[63,82,126],"applications":[64,159],"remain":[68],"less":[69],"common.":[70],"Here,":[71],"we":[72,120],"introduce":[73],"an":[74],"encoder":[75,92,143,163],"capturing":[76],"word-level":[77],"representations":[78],"learning.":[84],"We":[85],"demonstrate":[86],"the":[87,90,122,137,142,145,172],"application":[88],"pre-trained":[91,162],"four":[94],"distinct":[95,150],"audio":[98],"processing":[99,152],"tasks:":[100],"(i)":[101],"enhancement,":[103],"(ii)":[104],"language":[105],"identification,":[106],"(iii)":[107],"speech,":[108],"noise,":[109],"music":[111],"classification,":[112],"(iv)":[114],"speaker":[115],"identification.":[116],"each":[118],"task,":[119],"compare":[121],"performance":[123],"our":[125,161],"approach":[129],"baselines.":[132],"Our":[133],"results":[134],"show":[135],"that":[136],"captured":[140],"by":[141],"through":[144],"pre-training":[146],"is":[147],"transferable":[148],"across":[149],"tasks":[153],"datasets.":[155],"Notably,":[156],"even":[157],"simple":[158],"outperformed":[164],"methods,":[166],"comparable,":[169],"depending":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}