{"id":"https://openalex.org/W7148289230","doi":"https://doi.org/10.48550/arxiv.2604.01155","title":"FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining","display_name":"FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7148289230","doi":"https://doi.org/10.48550/arxiv.2604.01155"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01155","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.01155","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104326367","display_name":"Xiquan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Xiquan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132802871","display_name":"Xuenan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xuenan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132795184","display_name":"Ziyang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132829875","display_name":"Wenxi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wenxi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033885681","display_name":"Haolin He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Haolin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132791128","display_name":"Qiuqiang Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Qiuqiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132821488","display_name":"Xie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5104326367"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.7168999910354614,"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":0.7168999910354614,"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":0.14800000190734863,"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":0.08309999853372574,"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/exploit","display_name":"Exploit","score":0.710099995136261},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6384999752044678},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6258000135421753},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5746999979019165},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4555000066757202},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.37130001187324524},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3463999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910000085830688},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.710099995136261},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6384999752044678},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5062000155448914},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01155","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.01155","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6957477331161499}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contrastively":[0],"pretrained":[1],"audio-language":[2,160],"models":[3,161],"(e.g.,":[4],"CLAP)":[5],"excel":[6],"at":[7],"clip-level":[8,29],"understanding":[9,132],"but":[10],"struggle":[11],"with":[12,33,57,66],"frame-level":[13,35,53,77],"tasks.":[14],"Existing":[15],"extensions":[16],"fail":[17],"to":[18,71],"exploit":[19],"the":[20,101],"varying":[21],"granularity":[22],"of":[23,95,103],"real-world":[24],"audio-text":[25],"data,":[26,106],"where":[27],"massive":[28],"textual":[30],"descriptions":[31],"coexist":[32],"limited":[34],"annotations.":[36],"This":[37],"paper":[38],"proposes":[39],"Fine-grained":[40],"Language-Audio":[41],"Pretraining":[42],"(FineLAP),":[43],"a":[44,62,67,89,96,110,117],"novel":[45],"training":[46],"paradigm":[47],"that":[48,124,147],"advances":[49],"both":[50,81],"clip-":[51,75],"and":[52,76,84,140,149],"alignment":[54,151],"in":[55],"CLAP":[56],"heterogeneous":[58],"data.":[59],"FineLAP":[60,87,125],"introduces":[61],"dual-stream":[63],"sigmoid":[64],"loss":[65],"cluster-based":[68],"sampling":[69],"strategy":[70],"jointly":[72],"learn":[73],"from":[74],"supervision.":[78],"To":[79,99],"capture":[80],"global":[82],"semantics":[83],"local":[85],"details,":[86],"uses":[88],"decoupled":[90],"audio":[91,131],"projector":[92],"on":[93],"top":[94],"self-supervised":[97],"encoder.":[98],"alleviate":[100],"scarcity":[102],"temporally":[104],"annotated":[105],"we":[107],"present":[108],"FineLAP-100k,":[109],"large-scale":[111],"synthetic":[112],"SED":[113],"dataset":[114],"constructed":[115],"through":[116],"scalable":[118],"curation":[119],"pipeline.":[120],"Extensive":[121],"experiments":[122],"demonstrate":[123],"achieves":[126],"SOTA":[127],"performance":[128],"across":[129],"multiple":[130],"tasks,":[133],"including":[134],"retrieval,":[135],"classification,":[136],"sound":[137],"event":[138],"detection,":[139],"text-to-audio":[141],"grounding.":[142],"Ablation":[143],"studies":[144],"further":[145],"show":[146],"coarse-":[148],"fine-grained":[150],"are":[152],"mutually":[153],"beneficial,":[154],"providing":[155],"insights":[156],"for":[157],"building":[158],"better":[159],"(ALMs).":[162]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}