{"id":"https://openalex.org/W4372266890","doi":"https://doi.org/10.1109/icassp49357.2023.10096211","title":"Simple Pooling Front-Ends for Efficient Audio Classification","display_name":"Simple Pooling Front-Ends for Efficient Audio Classification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266890","doi":"https://doi.org/10.1109/icassp49357.2023.10096211"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096211","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106407730","display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"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":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"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":"Haohe Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I1323199999","display_name":"Central Intelligence Agency","ror":"https://ror.org/0135c5n64","country_code":"US","type":"government","lineage":["https://openalex.org/I1323199999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance,China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance,China","institution_ids":["https://openalex.org/I1323199999"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070892237","display_name":"Xinhao Mei","orcid":"https://orcid.org/0000-0001-6079-5130"},"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":"Xinhao Mei","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"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":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"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":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"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":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9990000128746033,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spectrogram","display_name":"Spectrogram","score":0.8316679000854492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952110767364502},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7486944198608398},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5690319538116455},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5486224889755249},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5212819576263428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.501723051071167},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4865516722202301},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4424344003200531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002229571342468},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34257543087005615},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2645305395126343}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8316679000854492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952110767364502},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7486944198608398},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5690319538116455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5486224889755249},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5212819576263428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.501723051071167},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4865516722202301},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4424344003200531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002229571342468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34257543087005615},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2645305395126343},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096211","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:alma.44SUR_INST:11201080520002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320025","display_name":"British Council","ror":"https://ror.org/00t3pr326"},{"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":39,"referenced_works":["https://openalex.org/W1839118408","https://openalex.org/W2006546815","https://openalex.org/W2037595167","https://openalex.org/W2052666245","https://openalex.org/W2117647820","https://openalex.org/W2135342008","https://openalex.org/W2160860215","https://openalex.org/W2593116425","https://openalex.org/W2797583228","https://openalex.org/W2887814324","https://openalex.org/W2963723765","https://openalex.org/W2963864497","https://openalex.org/W3005225358","https://openalex.org/W3015995734","https://openalex.org/W3038667391","https://openalex.org/W3094550259","https://openalex.org/W3096297644","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W3205743929","https://openalex.org/W3210574093","https://openalex.org/W4287372095","https://openalex.org/W4289785182","https://openalex.org/W4295723153","https://openalex.org/W4296070204","https://openalex.org/W4297775537","https://openalex.org/W4312892465","https://openalex.org/W4320350718","https://openalex.org/W4393792386","https://openalex.org/W6638946568","https://openalex.org/W6683682394","https://openalex.org/W6737664043","https://openalex.org/W6750665317","https://openalex.org/W6752516136","https://openalex.org/W6753968785","https://openalex.org/W6789403026","https://openalex.org/W6802938626","https://openalex.org/W6840679096","https://openalex.org/W6849910596"],"related_works":["https://openalex.org/W4360764600","https://openalex.org/W2289868279","https://openalex.org/W2793814466","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"increasing":[4],"interest":[5],"in":[6,52,118,142],"building":[7],"efficient":[8,65],"audio":[9,25,55,66,100,132,143],"neural":[10,26,133],"networks":[11,27],"for":[12,64,130],"on-device":[13],"scenarios.":[14],"Most":[15],"existing":[16],"approaches":[17],"are":[18],"designed":[19],"to":[20,86,103],"reduce":[21,87],"the":[22,49,53,88,92,105,123],"size":[23,44],"of":[24,41,75,107,122,125],"using":[28,45],"methods":[29],"such":[30],"as":[31],"model":[32,43],"pruning.":[33],"In":[34],"this":[35],"work,":[36],"we":[37,71],"show":[38,111],"that":[39,112],"instead":[40],"reducing":[42],"complex":[46],"methods,":[47],"eliminating":[48],"temporal":[50],"redundancy":[51],"input":[54],"features":[56],"(e.g.,":[57],"mel-spectrogram)":[58],"could":[59],"be":[60],"an":[61],"effective":[62],"approach":[63],"classification.":[67],"To":[68],"do":[69],"so,":[70],"proposed":[72],"a":[73,116],"family":[74],"simple":[76,82],"pooling":[77,84],"front-ends":[78],"(SimPFs)":[79],"which":[80],"use":[81],"non-parametric":[83],"operations":[85,128],"redundant":[89],"information":[90],"within":[91],"mel-spectrogram.":[93],"We":[94],"perform":[95],"extensive":[96],"experiments":[97],"on":[98],"four":[99],"classification":[101,144],"tasks":[102],"evaluate":[104],"performance":[106],"SimPFs.":[108],"Experimental":[109],"results":[110],"SimPFs":[113],"can":[114],"achieve":[115],"reduction":[117],"more":[119],"than":[120],"half":[121],"number":[124],"floating":[126],"point":[127],"(FLOPs)":[129],"off-the-shelf":[131],"networks,":[134],"with":[135],"negligible":[136],"degradation":[137],"or":[138],"even":[139],"some":[140],"improvements":[141],"performance.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}