{"id":"https://openalex.org/W3126699312","doi":"https://doi.org/10.1109/icassp39728.2021.9414310","title":"On Scaling Contrastive Representations for Low-Resource Speech Recognition","display_name":"On Scaling Contrastive Representations for Low-Resource Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3126699312","doi":"https://doi.org/10.1109/icassp39728.2021.9414310","mag":"3126699312"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.00850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018340002","display_name":"Lasse Borgholt","orcid":"https://orcid.org/0000-0002-3562-8442"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lasse Borgholt","raw_affiliation_strings":["University of Copenhagen,Department of Computer Science,Denmark","University of Copenhagen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen,Department of Computer Science,Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"University of Copenhagen","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012024522","display_name":"Tycho Max Sylvester Tax","orcid":"https://orcid.org/0000-0002-1450-3077"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tycho M. S. Tax","raw_affiliation_strings":["University of Copenhagen,Department of Computer Science,Denmark","University of Copenhagen, Department of Computer Science, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen,Department of Computer Science,Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"University of Copenhagen, Department of Computer Science, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040069285","display_name":"Jakob D. Havtorn","orcid":"https://orcid.org/0000-0002-4849-0817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakob D. Havtorn","raw_affiliation_strings":["Corti,Copenhagen,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corti,Copenhagen,Denmark","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007556794","display_name":"Lars Maal\u00f8e","orcid":"https://orcid.org/0000-0003-2030-520X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lars Maaloe","raw_affiliation_strings":["Corti,Copenhagen,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corti,Copenhagen,Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042628612","display_name":"Christian Igel","orcid":"https://orcid.org/0000-0003-2868-0856"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christian Igel","raw_affiliation_strings":["University of Copenhagen,Department of Computer Science,Denmark","University of Copenhagen, Department of Computer Science, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Copenhagen,Department of Computer Science,Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"University of Copenhagen, Department of Computer Science, Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01890944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3885","last_page":"3889"},"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":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7966985702514648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7722986936569214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5998035669326782},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5628868937492371},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.45980846881866455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45434778928756714},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4276931583881378},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4119894504547119},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3266512155532837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09345999360084534}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7966985702514648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722986936569214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5998035669326782},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5628868937492371},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.45980846881866455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45434778928756714},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4276931583881378},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4119894504547119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3266512155532837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09345999360084534},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414310","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414310","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.00850","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00850","pdf_url":"https://arxiv.org/pdf/2102.00850","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3126699312","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.00850.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":"pmh:oai:pure.atira.dk:openaire_cris_publications/6724498f-1289-4bfe-9886-64cddf789a03","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/6724498f-1289-4bfe-9886-64cddf789a03","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Borgholt , L , Tax , T M S , Havtorn , J D , Maal\u00f8e , L & Igel , C 2021 , On scaling contrastive representations for low-resource speech recognition . in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . vol. 2021-June , IEEE , pp. 3885-3889 , 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 , Virtual, Toronto , Canada , 06/06/2021 . https://doi.org/10.1109/ICASSP39728.2021.9414310","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/58508304-688d-46b6-9d7e-278b91d3c780","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/58508304-688d-46b6-9d7e-278b91d3c780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Borgholt , L , Tax , T M S , Havtorn , J D , Maal\u00f8e , L &amp; Igel , C 2021 , On scaling contrastive representations for low-resource speech recognition . in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing . vol. 2021- , IEEE , ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , pp. 3885-3889 , 2021 IEEE International Conference on Acoustics, Speech and Signal Processing , Toronto , Ontario , Canada , 06/06/2021 . https://doi.org/10.1109/ICASSP39728.2021.9414310","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2102.00850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.00850","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/2c9b-2928","is_oa":true,"landing_page_url":"https://doi.org/10.17023/2c9b-2928","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.00850","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00850","pdf_url":"https://arxiv.org/pdf/2102.00850","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3126699312.pdf","grobid_xml":"https://content.openalex.org/works/W3126699312.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2181741066","https://openalex.org/W2842511635","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W3003875258","https://openalex.org/W3033038061","https://openalex.org/W3096664139","https://openalex.org/W3097286738","https://openalex.org/W3099782249","https://openalex.org/W4250482878","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6769196770","https://openalex.org/W6769455919","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3160303932","https://openalex.org/W3205533980","https://openalex.org/W3210188917","https://openalex.org/W3041561163","https://openalex.org/W3014973941","https://openalex.org/W3093911486","https://openalex.org/W2964182350","https://openalex.org/W1922655562","https://openalex.org/W2737108017","https://openalex.org/W3039910566","https://openalex.org/W2963679184","https://openalex.org/W2903799412","https://openalex.org/W2926827382","https://openalex.org/W2337627957","https://openalex.org/W1494243555","https://openalex.org/W1516698649","https://openalex.org/W2963057973","https://openalex.org/W2916058012","https://openalex.org/W3034384463","https://openalex.org/W3205715971"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,43,82,103],"self-supervised":[3],"learning":[4],"through":[5],"contrastive":[6],"training":[7,58,118],"have":[8],"shown":[9],"that":[10,98,109,135],"it":[11],"is":[12,89],"possible":[13],"to":[14,77,91,130],"learn":[15],"a":[16,44,59,104,127],"competitive":[17],"speech":[18,61,122],"recognition":[19],"system":[20],"with":[21],"as":[22,24],"little":[23],"10":[25],"minutes":[26],"of":[27,52,113,119],"labeled":[28],"data.":[29],"However,":[30],"these":[31],"systems":[32,54],"are":[33],"computationally":[34,69],"expensive":[35],"since":[36],"they":[37],"require":[38],"pre-training":[39],"followed":[40],"by":[41,57],"fine-tuning":[42,56,80],"large":[45],"parameter":[46],"space.":[47],"We":[48,74],"explore":[49],"the":[50,64,68,83,111,114,120,131],"performance":[51,76],"such":[53],"without":[55,79],"state-of-the-art":[60],"recognizer":[62],"on":[63],"fixed":[65],"representations":[66,101,115],"from":[67],"demanding":[70],"wav2vec":[71,87,99,133],"2.0":[72,88,100],"framework.":[73],"find":[75,97],"decrease":[78],"and,":[81],"extreme":[84],"low-resource":[85],"setting,":[86],"inferior":[90],"its":[92],"predecessor.":[93],"In":[94],"addition,":[95],"we":[96,125],"live":[102],"low":[105],"dimensional":[106],"subspace":[107],"and":[108],"decorrelating":[110],"features":[112],"can":[116],"stabilize":[117],"automatic":[121],"recognizer.":[123],"Finally,":[124],"propose":[126],"bidirectional":[128],"extension":[129],"original":[132],"framework":[134],"consistently":[136],"improves":[137],"performance.":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-07-25T00:00:00"}
