{"id":"https://openalex.org/W7108616935","doi":"https://doi.org/10.5281/zenodo.17811389","title":"SLAP: Siamese Language-Audio Pretraining without negative samples for Music Understanding","display_name":"SLAP: Siamese Language-Audio Pretraining without negative samples for Music Understanding","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108616935","doi":"https://doi.org/10.5281/zenodo.17811389"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Julien Guinot","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Julien Guinot","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Alain Riou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alain Riou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Elio Quinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elio Quinton","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"George Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Fazekas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62471601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9811000227928162,"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":0.9811000227928162,"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":0.002300000051036477,"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/T10860","display_name":"Speech and Audio Processing","score":0.0015999999595806003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8070999979972839},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6448000073432922},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6215000152587891},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5683000087738037},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5504999756813049},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4034000039100647},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.3720000088214874},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8070999979972839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728000044822693},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6448000073432922},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5817000269889832},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3538999855518341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2831000089645386},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8001889586448669,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Joint":[0],"embedding":[1,42,60,103],"spaces":[2,43],"have":[3],"significantly":[4],"advanced":[5],"music":[6,117],"understanding":[7],"and":[8,13,118,134,154,171],"generation":[9],"by":[10],"linking":[11],"text":[12,119],"audio":[14],"through":[15,192],"multimodal":[16,40,74,95,102],"contrastive":[17],"learning.":[18],"However,":[19],"these":[20,64],"approaches":[21],"face":[22],"large":[23,31],"memory":[24],"requirement":[25],"limitations":[26],"due":[27],"to":[28,34,112,174],"relying":[29],"on":[30,128,143,178,188],"batch":[32,175],"sizes":[33],"effectively":[35],"utilize":[36],"negative":[37,83],"samples.":[38,84],"Further,":[39],"joint":[41],"suffer":[44],"from":[45,51],"a":[46,72,166,189],"modality":[47,169],"gap":[48,170],"wherein":[49],"embeddings":[50],"different":[52,56],"modalities":[53],"lie":[54],"in":[55,100],"manifolds":[57],"of":[58,109],"the":[59,87,107],"space.":[61],"To":[62],"address":[63],"challenges,":[65],"we":[66,122],"propose":[67],"Siamese":[68],"Language-Audio":[69],"Pretraining":[70],"(SLAP),":[71],"novel":[73,183],"pretraining":[75],"framework":[76],"that":[77,124],"allows":[78],"learning":[79],"powerful":[80],"representations":[81],"without":[82],"SLAP":[85,125],"adapts":[86],"Bootstrap":[88],"Your":[89],"Own":[90],"Latent":[91],"(BYOL)":[92],"paradigm":[93],"for":[94],"audio-text":[96],"training,":[97],"promoting":[98],"scalability":[99],"training":[101,187],"spaces.":[104],"We":[105,137],"illustrate":[106],"ability":[108],"our":[110,159],"model":[111],"learn":[113],"meaningful":[114],"relationships":[115],"between":[116],"---":[120],"specifically,":[121],"show":[123],"outperforms":[126],"CLAP":[127],"tasks":[129],"such":[130,164],"as":[131,165],"text-music":[132],"retrieval":[133,179],"zero-shot":[135],"classification.":[136],"also":[138],"observe":[139],"competitive":[140],"downstream":[141],"performance":[142],"several":[144],"MIR":[145],"tasks,":[146],"including":[147],"with":[148],"larger":[149],"or":[150],"supervised":[151],"models":[152],"(genre":[153],"instrument":[155],"classification,":[156],"auto-tagging).":[157],"Additionally,":[158],"approach":[160],"has":[161],"attractive":[162],"properties,":[163],"quantifiably":[167],"reduced":[168],"improved":[172],"robustness":[173],"size":[176],"variations":[177],"performance.":[180],"Finally,":[181],"its":[182],"formulation":[184],"unlocks":[185],"large-scale":[186],"single":[190],"GPU":[191],"gradient":[193],"accumulation.":[194]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}