{"id":"https://openalex.org/W4224933321","doi":"https://doi.org/10.1109/icassp43922.2022.9746798","title":"Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation","display_name":"Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933321","doi":"https://doi.org/10.1109/icassp43922.2022.9746798"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746798","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5074471104","display_name":"Ibuki Kuroyanagi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ibuki Kuroyanagi","raw_affiliation_strings":["Line Corporation,Tokyo,Japan","Line Corporation, Tokyo, Japan","Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Line Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Line Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["Line Corporation,Tokyo,Japan","Line Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Line Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Line Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074471104"],"corresponding_institution_ids":["https://openalex.org/I4210096607","https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01390205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"119","issue":null,"first_page":"3263","last_page":"3267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9950000047683716,"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":0.8109219074249268},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6557061672210693},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6325464248657227},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6138628721237183},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6081603169441223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5782781839370728},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5600900650024414},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5236625075340271},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4280276894569397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40636956691741943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40061724185943604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1627649962902069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109219074249268},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6557061672210693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6325464248657227},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6138628721237183},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6081603169441223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5782781839370728},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5600900650024414},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5236625075340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4280276894569397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40636956691741943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40061724185943604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1627649962902069},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.1109/icassp43922.2022.9746798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746798","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2767754137","https://openalex.org/W2775794021","https://openalex.org/W2797583228","https://openalex.org/W2808631503","https://openalex.org/W2896457183","https://openalex.org/W2955425717","https://openalex.org/W2962677373","https://openalex.org/W2962866891","https://openalex.org/W2979476256","https://openalex.org/W3005680577","https://openalex.org/W3006926732","https://openalex.org/W3015437096","https://openalex.org/W3016181583","https://openalex.org/W3023351797","https://openalex.org/W3035524453","https://openalex.org/W3093579165","https://openalex.org/W3094550259","https://openalex.org/W3115293622","https://openalex.org/W3144810982","https://openalex.org/W3145385912","https://openalex.org/W3162391496","https://openalex.org/W3196496149","https://openalex.org/W4288348042","https://openalex.org/W4292779060","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6734260513","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6769196770","https://openalex.org/W6774314701","https://openalex.org/W6778883912","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"We":[0,89],"propose":[1],"a":[2,54,58,94,102],"self-supervised":[3],"learning":[4],"method":[5,23,92,110],"using":[6],"multiple":[7,63],"sampling":[8,16,47,87],"strategies":[9,17,64],"to":[10,24,42,101],"obtain":[11],"general-purpose":[12],"audio":[13],"representation.":[14],"Multiple":[15],"are":[18,78],"used":[19,45],"in":[20,40],"the":[21,43,66,80,83,91],"proposed":[22,62,109],"construct":[25],"contrastive":[26],"losses":[27],"from":[28],"different":[29],"perspectives":[30],"and":[31,57,71,98,117,126],"learn":[32],"representations":[33],"based":[34],"on":[35,93],"them.":[36],"In":[37],"this":[38],"study,":[39],"addition":[41],"widely":[44],"clip-level":[46,86],"strategy,":[48],"we":[49],"introduce":[50],"two":[51],"new":[52],"strategies,":[53],"frame-level":[55,69],"strategy":[56],"task-specific":[59],"strategy.":[60,88],"The":[61,108],"improve":[65],"performance":[67,120],"of":[68,82,96],"classification":[70],"other":[72],"tasks":[73],"like":[74],"pitch":[75,118],"detection,":[76,116],"which":[77],"not":[79],"focus":[81],"conventional":[84],"single":[85],"pre-trained":[90],"subset":[95],"Audioset":[97],"applied":[99],"it":[100],"downstream":[103],"task":[104],"with":[105],"frozen":[106],"weights.":[107],"improved":[111],"clip":[112],"classification,":[113],"sound":[114],"event":[115],"detection":[119],"by":[121],"25":[122],"%,":[123,125],"20":[124],"3.6":[127],"%.":[128]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}