{"id":"https://openalex.org/W4416798399","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249411","title":"Data-Efficient Music Captioning Via Contrastive and Semantic Alignment","display_name":"Data-Efficient Music Captioning Via Contrastive and Semantic Alignment","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798399","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249411"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5013331634","display_name":"Leekyung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Leekyung Kim","raw_affiliation_strings":["Seoul National University,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083504852","display_name":"Jonghun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonghun Park","raw_affiliation_strings":["Seoul National University,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.39210832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6139000058174133,"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":0.6139000058174133,"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":0.24719999730587006,"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":0.024900000542402267,"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/closed-captioning","display_name":"Closed captioning","score":0.939300000667572},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6485999822616577},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5613999962806702},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.539900004863739},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.39160001277923584},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3075999915599823}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.939300000667572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303999900817871},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5963000059127808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5766000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5683000087738037},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45989999175071716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":18,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2593116425","https://openalex.org/W2803054945","https://openalex.org/W3138516171","https://openalex.org/W3201326582","https://openalex.org/W4225328971","https://openalex.org/W4226442948","https://openalex.org/W4235505822","https://openalex.org/W4247726808","https://openalex.org/W4253028564","https://openalex.org/W4372259760","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385245566","https://openalex.org/W4392903033","https://openalex.org/W4392909390","https://openalex.org/W4416251578"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1,56],"a":[2,38,57,111,116],"music":[3,136],"captioning":[4,137],"framework":[5],"designed":[6],"for":[7],"low-resource":[8],"scenarios":[9],"by":[10],"leveraging":[11],"an":[12],"encoder-decoder":[13],"architecture":[14],"that":[15,61,68,89],"incorporates":[16],"the":[17,21,50,63,73,78,85,90,102,128],"audio":[18,23,45],"encoder":[19,24],"of":[20,25,130],"pretrained":[22],"Contrastive":[26],"Language-Audio":[27],"Pretraining":[28],"(CLAP)":[29],"and":[30,46,93,100],"two":[31],"auxiliary":[32],"training":[33,94,123],"objectives.":[34],"First,":[35],"we":[36,55],"introduce":[37],"contrastive":[39],"modality":[40],"alignment":[41,59,133],"loss":[42,60],"to":[43,65,72,105,110],"align":[44],"text":[47,80],"embeddings":[48],"in":[49,77,134],"CLAP":[51,79],"latent":[52],"space.":[53,82],"Second,":[54],"semantic":[58],"encourages":[62],"decoder":[64],"generate":[66],"captions":[67],"are":[69],"semantically":[70],"close":[71],"ground-truth":[74],"captions,":[75],"measured":[76],"embedding":[81],"Experiments":[83],"on":[84,115],"MusicCaps":[86],"dataset":[87],"demonstrate":[88],"proposed":[91,103],"model":[92,104,113],"objectives":[95],"improve":[96],"caption":[97],"generation":[98],"performance":[99],"enable":[101],"achieve":[106],"competitive":[107],"results":[108,126],"compared":[109],"baseline":[112],"trained":[114],"large-scale":[117],"dataset,":[118],"despite":[119],"using":[120],"significantly":[121],"less":[122],"data.":[124],"These":[125],"highlight":[127],"effectiveness":[129],"cross-modal":[131],"representation":[132],"improving":[135],"under":[138],"data":[139],"scarcity.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}