{"id":"https://openalex.org/W4414270579","doi":"https://doi.org/10.1109/access.2025.3611348","title":"M2D-CLAP: Exploring General-Purpose Audio-Language Representations Beyond CLAP","display_name":"M2D-CLAP: Exploring General-Purpose Audio-Language Representations Beyond CLAP","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414270579","doi":"https://doi.org/10.1109/access.2025.3611348"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3611348","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3611348","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3611348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091219538","display_name":"Daisuke Niizumi","orcid":"https://orcid.org/0000-0002-5063-0508"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Niizumi","raw_affiliation_strings":["Communication Science Laboratories, NTT, Inc., Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5063-0508","affiliations":[{"raw_affiliation_string":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103978078","display_name":"Daiki Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Takeuchi","raw_affiliation_strings":["Communication Science Laboratories, NTT, Inc., Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094340629","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0003-2776-9701"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["Communication Science Laboratories, NTT, Inc., Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2776-9701","affiliations":[{"raw_affiliation_string":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068261641","display_name":"Binh Thien Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Binh Thien Nguyen","raw_affiliation_strings":["Communication Science Laboratories, NTT, Inc., Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3883-1315","affiliations":[{"raw_affiliation_string":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062509967","display_name":"Yasunori Ohishi","orcid":"https://orcid.org/0000-0002-7856-248X"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasunori Ohishi","raw_affiliation_strings":["Communication Science Laboratories, NTT, Inc., Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7856-248X","affiliations":[{"raw_affiliation_string":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["Communication Science Laboratories, NTT, Inc., Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1759-4533","affiliations":[{"raw_affiliation_string":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210105847"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.5637,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95602837,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"13","issue":null,"first_page":"163313","last_page":"163330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9891999959945679,"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":0.9891999959945679,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9869999885559082,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9776999950408936,"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/audio-analyzer","display_name":"Audio analyzer","score":0.5730000138282776},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5648999810218811},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4848000109195709},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429999947547913},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5730000138282776},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360999703407288},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5224999785423279},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.29840001463890076},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.2759999930858612},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3611348","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3611348","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:95759f0380654e959cf24394137f0cbd","is_oa":true,"landing_page_url":"https://doaj.org/article/95759f0380654e959cf24394137f0cbd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 163313-163330 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3611348","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3611348","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"language-audio":[1],"pre-training":[2],"(CLAP),":[3],"which":[4,72],"learns":[5,61,171],"audio-language":[6,77,193],"representations":[7],"by":[8,106],"aligning":[9],"audio":[10,23,27,44,53,64,94,126,165,174],"and":[11,55,65,95,109,136,158,186],"text":[12],"in":[13,183],"a":[14,50,58,75,131,191],"common":[15],"feature":[16],"space,":[17],"has":[18],"become":[19],"popular":[20],"for":[21],"solving":[22],"tasks.":[24,45],"However,":[25],"CLAP\u2019s":[26],"features":[28,38,67,127,155,175],"lack":[29],"generalizability,":[30],"whereas":[31],"self-supervised":[32],"learning":[33],"(SSL)":[34],"models":[35],"offer":[36],"general-purpose":[37,76,192],"that":[39,57,60,169],"perform":[40],"well":[41],"across":[42],"diverse":[43],"We":[46],"aim":[47],"to":[48,89,144],"develop":[49],"broadly":[51],"applicable":[52],"representation":[54],"hypothesize":[56],"model":[59],"both":[62],"general":[63,93,173],"CLAP":[66,96,108,139,154,187],"should":[68],"achieve":[69],"our":[70,81],"goal,":[71],"we":[73,83],"call":[74],"representation.":[78,194],"To":[79],"implement":[80],"hypothesis,":[82],"propose":[84],"M2D-CLAP,":[85],"the":[86,122,151,163],"first":[87,123],"approach":[88],"jointly":[90],"learn":[91],"effective":[92],"features.":[97,166],"It":[98],"extends":[99],"an":[100],"SSL":[101],"masked":[102],"modeling":[103],"duo":[104],"(M2D)":[105],"incorporating":[107],"utilizes":[110],"LLM-based":[111,141],"sentence":[112],"embeddings.":[113],"The":[114],"training":[115],"process":[116],"consists":[117],"of":[118,179],"multiple":[119],"stages.":[120],"In":[121,150],"stage,":[124],"generalizable":[125],"are":[128,156],"pre-trained":[129,157],"via":[130],"multitask":[132],"objective":[133],"combining":[134],"M2D":[135],"CLAP,":[137],"with":[138,160],"leveraging":[140],"semantic":[142,146],"embeddings":[143],"distill":[145],"knowledge":[147],"into":[148],"them.":[149],"following":[152],"stages,":[153],"refined":[159],"guidance":[161],"from":[162],"learned":[164],"Experiments":[167],"demonstrated":[168],"M2D-CLAP":[170],"high-performing":[172],"(e.g.,":[176],"AudioSet":[177],"mAP":[178],"49.0,":[180],"SOTA":[181],"results":[182],"music":[184],"tasks)":[185],"features,":[188],"thereby":[189],"enabling":[190]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}