{"id":"https://openalex.org/W4392909815","doi":"https://doi.org/10.1109/icassp48485.2024.10446424","title":"Multi-Modal Continual Pre-Training For Audio Encoders","display_name":"Multi-Modal Continual Pre-Training For Audio Encoders","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909815","doi":"https://doi.org/10.1109/icassp48485.2024.10446424"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5017100245","display_name":"Gyuhak Kim","orcid":"https://orcid.org/0000-0002-3110-4561"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gyuhak Kim","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035643647","display_name":"Ho-Hsiang Wu","orcid":"https://orcid.org/0000-0002-1102-074X"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ho-Hsiang Wu","raw_affiliation_strings":["USA - Bosch Center for Artificial Intelligence,Bosch Research","Bosch Research, USA - Bosch Center for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"USA - Bosch Center for Artificial Intelligence,Bosch Research","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Bosch Research, USA - Bosch Center for Artificial Intelligence","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061125165","display_name":"Luca Bondi","orcid":"https://orcid.org/0000-0003-3974-7542"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luca Bondi","raw_affiliation_strings":["USA - Bosch Center for Artificial Intelligence,Bosch Research","Bosch Research, USA - Bosch Center for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"USA - Bosch Center for Artificial Intelligence,Bosch Research","institution_ids":["https://openalex.org/I4210120115"]},{"raw_affiliation_string":"Bosch Research, USA - Bosch Center for Artificial Intelligence","institution_ids":["https://openalex.org/I4210120115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339927","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-4096-6980"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bing Liu","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017100245"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":0.31,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5640704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"691","last_page":"695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11283","display_name":"Experimental Learning in Engineering","score":0.9333999752998352,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11283","display_name":"Experimental Learning in Engineering","score":0.9333999752998352,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7563373446464539},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6942257285118103},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6712098121643066},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.615468442440033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6073152422904968},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3569202423095703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3461334705352783},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10015752911567688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563373446464539},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6942257285118103},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6712098121643066},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.615468442440033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6073152422904968},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3569202423095703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3461334705352783},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10015752911567688},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2324505288","display_name":null,"funder_award_id":"IIS-1838770","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3973128626","display_name":null,"funder_award_id":"2225427","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5390123671","display_name":null,"funder_award_id":"10424","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5603462533","display_name":null,"funder_award_id":"CNS-2225427","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6085028527","display_name":"SCH: INT: The Virtual Assistant Health Coach: Learning to Autonomously Improve Health Behaviors","funder_award_id":"1838770","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1682403713","https://openalex.org/W1821462560","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2473930607","https://openalex.org/W2593116425","https://openalex.org/W2945761034","https://openalex.org/W2964109005","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3030364939","https://openalex.org/W3094550259","https://openalex.org/W3162331882","https://openalex.org/W3176445421","https://openalex.org/W4205689591","https://openalex.org/W4225777901","https://openalex.org/W4283332761","https://openalex.org/W4284898017","https://openalex.org/W4372260340","https://openalex.org/W4372266552","https://openalex.org/W4400033239","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6791353385","https://openalex.org/W6809947431","https://openalex.org/W6838669176","https://openalex.org/W6849424676"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4390516098","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611"],"abstract_inverted_index":{"Several":[0],"approaches":[1,34,87],"have":[2],"been":[3],"proposed":[4],"to":[5,10,22,37,45,65,90,102,136,142],"pre-train":[6],"an":[7],"audio":[8,13,108,113,146],"encoder":[9,109],"learn":[11,67],"fundamental":[12],"knowledge.":[14],"These":[15],"training":[16,53],"frameworks":[17],"range":[18],"from":[19],"supervised":[20],"learning":[21,24,56,63,91,139],"self-supervised":[23],"with":[25,106],"a":[26,38,68,119],"contrastive":[27],"objective":[28],"under":[29],"multi-modal":[30,46,122],"supervision.":[31],"However,":[32],"these":[33],"are":[35,88,148],"constrained":[36],"single":[39],"pretext":[40],"task,":[41],"preventing":[42],"their":[43,137],"adaptability":[44],"interactions":[47],"beyond":[48],"the":[49,59,73,78],"modalities":[50],"provided":[51],"in":[52,58],"data.":[54],"Continual":[55],"(CL),":[57],"meantime,":[60],"allows":[61],"machine":[62],"systems":[64],"incrementally":[66],"new":[69],"task":[70],"while":[71],"preserving":[72],"previously":[74],"acquired":[75],"knowledge,":[76],"making":[77],"system":[79],"more":[80],"knowledgeable":[81],"over":[82,118],"time.":[83],"The":[84,112,145],"existing":[85],"CL":[86,104],"limited":[89],"downstream":[92,133],"tasks":[93,134,154],"such":[94],"as":[95],"classification.":[96],"In":[97],"this":[98],"work,":[99],"we":[100],"propose":[101],"combine":[103],"methods":[105],"several":[107],"pre-training":[110],"methods.":[111],"encoders,":[114],"when":[115],"pre-trained":[116],"continually":[117],"sequence":[120],"of":[121,151,155],"tasks,":[123],"namely":[124],"audiovisual":[125],"and":[126],"audio-text,":[127],"exhibit":[128],"improved":[129],"performance":[130],"across":[131],"various":[132],"compared":[135],"non-continual":[138],"counterparts,":[140],"due":[141],"knowledge":[143],"accumulation.":[144],"encoders":[147],"also":[149],"capable":[150],"performing":[152],"cross-modal":[153],"all":[156],"learned":[157],"modalities.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}