{"id":"https://openalex.org/W4372266715","doi":"https://doi.org/10.1109/icassp49357.2023.10096465","title":"Active Learning of non-Semantic Speech Tasks with Pretrained models","display_name":"Active Learning of non-Semantic Speech Tasks with Pretrained models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266715","doi":"https://doi.org/10.1109/icassp49357.2023.10096465"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt0zd6s1k2/qt0zd6s1k2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055567952","display_name":"Harlin Lee","orcid":"https://orcid.org/0000-0001-6128-9942"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harlin Lee","raw_affiliation_strings":["University of California Los Angeles,Los Angeles,CA,USA","University of California Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Los Angeles,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011960578","display_name":"Aaqib Saeed","orcid":"https://orcid.org/0000-0003-1473-0322"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aaqib Saeed","raw_affiliation_strings":["Eindhoven University of Technology,Eindhoven,The Netherlands","Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Eindhoven,The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090707978","display_name":"Andrea L. Bertozzi","orcid":"https://orcid.org/0000-0003-0396-7391"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea L. Bertozzi","raw_affiliation_strings":["University of California Los Angeles,Los Angeles,CA,USA","University of California Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Los Angeles,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9872000217437744,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9815999865531921,"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/computer-science","display_name":"Computer science","score":0.8357693552970886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316502094268799},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6141501665115356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5451960563659668},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5381951928138733},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5214506983757019},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.519862174987793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4560111165046692},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4516080319881439},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.4498332440853119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357693552970886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316502094268799},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6141501665115356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5451960563659668},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5381951928138733},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5214506983757019},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.519862174987793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4560111165046692},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4516080319881439},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4498332440853119},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096465","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt0zd6s1k2","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/0zd6s1k2","pdf_url":"https://escholarship.org/content/qt0zd6s1k2/qt0zd6s1k2.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/a347f72b-6dcc-4b5d-99d0-0d9cfe4b8d0c","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/a347f72b-6dcc-4b5d-99d0-0d9cfe4b8d0c","pdf_url":"https://pure.tue.nl/ws/files/315919148/Active_Learning_of_non-Semantic_Speech_Tasks_with_Pretrained_models.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lee, H, Saeed, A & Bertozzi, A L 2023, Active Learning of non-Semantic Speech Tasks with Pretrained models. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 10096465, IEEE/LEOS, 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096465","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.tue.nl:openaire/a347f72b-6dcc-4b5d-99d0-0d9cfe4b8d0c","is_oa":true,"landing_page_url":"https://research.tue.nl/files/315919148/Active_Learning_of_non-Semantic_Speech_Tasks_with_Pretrained_models.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lee, H, Saeed, A & Bertozzi, A L 2023, Active Learning of non-Semantic Speech Tasks with Pretrained models. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 10096465, IEEE/LEOS, 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096465","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt0zd6s1k2","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/0zd6s1k2","pdf_url":"https://escholarship.org/content/qt0zd6s1k2/qt0zd6s1k2.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2850294695","display_name":null,"funder_award_id":"DMS-2152717","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4003705234","display_name":"Collaborative Research: Differential Equations Motivated Multi-Agent Sequential Deep Learning: Algorithms, Theory, and Validation","funder_award_id":"2152717","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8689655813","display_name":"FRG: Collaborative Research: Robust, Efficient, and Private Deep Learning Algorithms","funder_award_id":"1952339","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372266715.pdf","grobid_xml":"https://content.openalex.org/works/W4372266715.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1513874326","https://openalex.org/W2095629250","https://openalex.org/W2564784249","https://openalex.org/W2797583228","https://openalex.org/W2951911250","https://openalex.org/W2972551158","https://openalex.org/W2972584841","https://openalex.org/W3006926732","https://openalex.org/W3036601975","https://openalex.org/W3162391496","https://openalex.org/W3196876847","https://openalex.org/W3198059188","https://openalex.org/W4225299287","https://openalex.org/W4281842030","https://openalex.org/W4296068413","https://openalex.org/W4298132949","https://openalex.org/W6750665317","https://openalex.org/W6780218876","https://openalex.org/W6800638362"],"related_works":["https://openalex.org/W3204418343","https://openalex.org/W4292388283","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W1560624709","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W3214142563","https://openalex.org/W3166286441"],"abstract_inverted_index":{"Pretraining":[0],"neural":[1],"networks":[2],"with":[3,16,60,70,120],"massive":[4],"unlabeled":[5],"datasets":[6],"has":[7],"become":[8],"popular":[9],"as":[10],"it":[11],"equips":[12],"the":[13,30,52,85,94,133],"deep":[14],"models":[15,67],"a":[17,47,99,111,117],"better":[18],"prior":[19],"to":[20,35,73,87,124,128],"solve":[21],"downstream":[22,31,81],"tasks.":[23],"However,":[24],"this":[25,42],"approach":[26],"generally":[27],"assumes":[28],"that":[29,131],"tasks":[32,59],"have":[33],"access":[34],"annotated":[36],"data":[37,75,90],"of":[38,56,96,102,116],"sufficient":[39],"size.":[40],"In":[41],"work,":[43],"we":[44],"propose":[45],"ALOE,":[46],"novel":[48],"system":[49],"for":[50,80],"improving":[51],"data-":[53],"and":[54,77,107],"label-efficiency":[55],"non-semantic":[57],"speech":[58],"active":[61,71],"learning":[62,72],"(AL).":[63],"ALOE":[64,97,121],"uses":[65],"pretrained":[66],"in":[68],"conjunction":[69],"label":[74],"incrementally":[76],"learn":[78],"classifiers":[79],"tasks,":[82,103],"thereby":[83],"mitigating":[84],"need":[86],"acquire":[88],"labeled":[89,135],"beforehand.":[91],"We":[92],"demonstrate":[93],"effectiveness":[95],"on":[98,114],"wide":[100],"range":[101],"uncertainty-based":[104],"acquisition":[105],"functions,":[106],"model":[108],"architectures.":[109],"Training":[110],"linear":[112],"classifier":[113],"top":[115],"frozen":[118],"encoder":[119],"is":[122],"shown":[123],"achieve":[125],"performance":[126],"similar":[127],"several":[129],"baselines":[130],"utilize":[132],"entire":[134],"data.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}