{"id":"https://openalex.org/W4388115392","doi":"https://doi.org/10.23919/eusipco58844.2023.10289815","title":"Low-Complexity Audio Embedding Extractors","display_name":"Low-Complexity Audio Embedding Extractors","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388115392","doi":"https://doi.org/10.23919/eusipco58844.2023.10289815"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289815","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5103009549","display_name":"Florian Schmid","orcid":"https://orcid.org/0009-0007-4988-6067"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Florian Schmid","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University,Linz,Austria","Institute of Computational Perception, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026220503","display_name":"Khaled Koutini","orcid":"https://orcid.org/0000-0002-9193-732X"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Khaled Koutini","raw_affiliation_strings":["Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University,Linz,Austria","Institute of Computational Perception, Johannes Kepler University, Linz, Austria","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103009549"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":0.6203,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66771603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"451","last_page":"455"},"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":0.9993000030517578,"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":0.9951000213623047,"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":0.8643881678581238},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6645991802215576},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48644471168518066},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46544942259788513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43285852670669556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38064295053482056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8643881678581238},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6645991802215576},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48644471168518066},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46544942259788513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43285852670669556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38064295053482056},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289815","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W2085662862","https://openalex.org/W2108598243","https://openalex.org/W2519091744","https://openalex.org/W2526050071","https://openalex.org/W2584032004","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2842511635","https://openalex.org/W2939574508","https://openalex.org/W2955425717","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W3036601975","https://openalex.org/W3093563057","https://openalex.org/W3094550259","https://openalex.org/W3145444543","https://openalex.org/W3161026535","https://openalex.org/W3196974791","https://openalex.org/W3201143670","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W3206996142","https://openalex.org/W4221150524","https://openalex.org/W4224980507","https://openalex.org/W4225713393","https://openalex.org/W4226165006","https://openalex.org/W4283652729","https://openalex.org/W4285483774","https://openalex.org/W4288348042","https://openalex.org/W4297775537","https://openalex.org/W4297808394","https://openalex.org/W4297841853","https://openalex.org/W4310283062","https://openalex.org/W4313156423","https://openalex.org/W4313162486","https://openalex.org/W4372260403","https://openalex.org/W4375869340","https://openalex.org/W6600593648","https://openalex.org/W6727253422","https://openalex.org/W6732429163","https://openalex.org/W6734260513","https://openalex.org/W6737664043","https://openalex.org/W6749781174","https://openalex.org/W6761629969","https://openalex.org/W6762718338","https://openalex.org/W6780218876","https://openalex.org/W6784077883","https://openalex.org/W6792861227","https://openalex.org/W6793164127","https://openalex.org/W6804302685","https://openalex.org/W6809596386","https://openalex.org/W6809947431","https://openalex.org/W6810510949","https://openalex.org/W6810841414","https://openalex.org/W6838724896","https://openalex.org/W6840200333","https://openalex.org/W6840487619","https://openalex.org/W6846461521","https://openalex.org/W6846797836"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Solving":[0],"tasks":[1,83,97],"such":[2],"as":[3,133],"speaker":[4],"recognition,":[5],"music":[6],"classification,":[7],"or":[8],"semantic":[9],"audio":[10,23,31,41,86,172,179],"event":[11],"tagging":[12],"with":[13],"deep":[14],"learning":[15],"models":[16,162],"typically":[17],"requires":[18],"computationally":[19],"demanding":[20],"networks.":[21],"General-purpose":[22],"embed":[24],"dings":[25],"(GPAEs)":[26],"are":[27,68],"dense":[28,54,66],"representations":[29,67],"of":[30,82,109,155],"signals":[32],"that":[33,46,160],"allow":[34,72],"lightweight,":[35],"shallow":[36,57],"classifiers":[37,76],"to":[38,71,77,79,94,105,112,140,152],"tackle":[39],"various":[40],"tasks.":[42,183],"The":[43],"idea":[44],"is":[45],"a":[47,80,88,130],"single":[48,89],"complex":[49],"feature":[50],"extractor":[51],"would":[52],"extract":[53],"GPAEs,":[55,157,166],"while":[56],"MLPs":[58],"can":[59,163],"produce":[60],"task-specific":[61],"predictions.":[62],"If":[63],"the":[64,73,85,107,145,153,168],"extracted":[65,156],"general":[69],"enough":[70],"simple":[74],"downstream":[75],"generalize":[78],"variety":[81],"in":[84,98],"domain,":[87],"costly":[90],"forward":[91],"pass":[92],"suffices":[93],"solve":[95],"multiple":[96,178],"parallel.":[99],"In":[100],"this":[101],"work,":[102],"we":[103],"try":[104],"reduce":[106],"cost":[108],"GPAE":[110,135],"extractors":[111],"make":[113],"them":[114],"suitable":[115],"for":[116,170],"resource-constrained":[117],"devices.":[118],"We":[119,137],"use":[120],"efficient":[121,134],"MobileNets":[122],"trained":[123],"on":[124,174],"AudioSet":[125],"using":[126],"Knowledge":[127],"Distillation":[128],"from":[129,144],"Transformer":[131],"ensemble":[132],"extractors.":[136],"explore":[138],"how":[139,148],"obtain":[141],"high-quality":[142],"GPAEs":[143],"model,":[146],"study":[147],"model":[149],"complexity":[150],"relates":[151],"quality":[154],"and":[158,181],"conclude":[159],"low-complexity":[161],"generate":[164],"competitive":[165],"paving":[167],"way":[169],"analyzing":[171],"streams":[173],"edge":[175],"devices":[176],"w.r.t.":[177],"classification":[180],"recognition":[182]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}