{"id":"https://openalex.org/W4386597201","doi":"https://doi.org/10.1109/icip49359.2023.10222551","title":"Group Masked Model Learning for General Audio Representation","display_name":"Group Masked Model Learning for General Audio Representation","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597201","doi":"https://doi.org/10.1109/icip49359.2023.10222551"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222551","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5111136893","display_name":"Sara Atito","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Sara Atito","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","Surrey Institute for People-Centred AI, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Surrey Institute for People-Centred AI, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019103381","display_name":"Muhammed Awais","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Muhammed Awais","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","Surrey Institute for People-Centred AI, University of Surrey, Guildford, UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Surrey Institute for People-Centred AI, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108635068","display_name":"Tony Alex","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tony Alex","raw_affiliation_strings":["University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Surrey Institute for People-Centred AI,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028209738","display_name":"Josef Kittler","orcid":"https://orcid.org/0000-0002-8110-9205"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111136893"],"corresponding_institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11159196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"2600","last_page":"2604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.7897830009460449},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7307909727096558},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6736178398132324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5051191449165344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46691182255744934},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4579616189002991},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.44248688220977783},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4181218445301056},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.406259149312973},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3833964467048645},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.37641626596450806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10570234060287476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897830009460449},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7307909727096558},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6736178398132324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5051191449165344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46691182255744934},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4579616189002991},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.44248688220977783},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4181218445301056},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.406259149312973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3833964467048645},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.37641626596450806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10570234060287476},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222551","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1595280774","display_name":"JADE: Joint Academic Data science Endeavour - 2","funder_award_id":"EP/T022205/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6487001647","display_name":null,"funder_award_id":"T022205/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6868706350","display_name":"Multimodal Video Search by Examples (MVSE)","funder_award_id":"EP/V002856/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7111890331","display_name":null,"funder_award_id":"EP/V002856/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320332972","display_name":"Defence Science and Technology Laboratory","ror":"https://ror.org/04jswqb94"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1604034532","https://openalex.org/W2052666245","https://openalex.org/W2163605009","https://openalex.org/W2593116425","https://openalex.org/W2768282280","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2963263347","https://openalex.org/W2981087920","https://openalex.org/W3005680577","https://openalex.org/W3015949486","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3162391496","https://openalex.org/W3170863103","https://openalex.org/W3196974791","https://openalex.org/W3197580070","https://openalex.org/W3201143670","https://openalex.org/W3206996142","https://openalex.org/W4206121183","https://openalex.org/W4225911888","https://openalex.org/W4287236261","https://openalex.org/W4296960042","https://openalex.org/W4297841518","https://openalex.org/W4297841853","https://openalex.org/W4301914798","https://openalex.org/W4312804044","https://openalex.org/W4375869340","https://openalex.org/W4386598334","https://openalex.org/W6684191040","https://openalex.org/W6726497184","https://openalex.org/W6746052068","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6774314701","https://openalex.org/W6784333009","https://openalex.org/W6796761347","https://openalex.org/W6804262790","https://openalex.org/W6840952533","https://openalex.org/W6845452229"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W1611900921","https://openalex.org/W3110605476","https://openalex.org/W1803351015"],"abstract_inverted_index":{"Vision":[0],"transformers":[1,23],"have":[2],"recently":[3],"generated":[4],"significant":[5],"interest":[6],"in":[7,18,45],"the":[8,43,53,68,100,110,145],"computer":[9],"vision":[10],"and":[11,61,93,105,130,136],"audio":[12,49,69,82,129],"communities":[13],"due":[14],"to":[15,26,38,98],"their":[16],"flexibility":[17],"learning":[19],"long-range":[20],"relationships.":[21],"However,":[22],"are":[24],"known":[25],"be":[27,140],"data":[28,36,60],"hungry":[29],"which":[30,51],"require":[31],"orders":[32],"of":[33,48,58,67,102,109],"magnitude":[34],"more":[35],"[1]":[37],"train.":[39],"This":[40],"has":[41],"motivated":[42],"research":[44],"self-supervised":[46,78],"pretraining":[47],"transformers,":[50],"reduces":[52],"dependency":[54],"on":[55,63,87,118,127],"large":[56],"amounts":[57],"labeled":[59],"focuses":[62],"extracting":[64],"concise":[65],"representation":[66],"spectrograms.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"Audio-GMML,":[76],"a":[77,94,123],"transformer":[79],"for":[80,144],"general":[81],"representations":[83,104],"that":[84],"is":[85],"based":[86],"Group":[88],"Masked":[89],"Model":[90],"Learning":[91],"(GMML)":[92],"patch":[95],"aggregation":[96],"strategy":[97],"improve":[99],"performance":[101,126],"learned":[103],"enforce":[106],"global":[107],"structure":[108],"given":[111],"audio.":[112],"We":[113],"evaluate":[114],"our":[115],"pretrained":[116,137],"models":[117],"several":[119],"downstream":[120],"tasks,":[121],"setting":[122],"new":[124],"state-of-the-art":[125],"five":[128],"speech":[131],"classification":[132],"tasks.":[133],"The":[134],"code":[135],"weights":[138],"will":[139],"made":[141],"publicly":[142],"available":[143],"scientific":[146],"community.":[147]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
