{"id":"https://openalex.org/W4387954140","doi":"https://doi.org/10.1145/3607827.3616842","title":"Generating Multimodal Augmentations with LLMs from Song Metadata for Music Information Retrieval","display_name":"Generating Multimodal Augmentations with LLMs from Song Metadata for Music Information Retrieval","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387954140","doi":"https://doi.org/10.1145/3607827.3616842"},"language":"en","primary_location":{"id":"doi:10.1145/3607827.3616842","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607827.3616842","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616842?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616842?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085689170","display_name":"Federico Rossetto","orcid":"https://orcid.org/0000-0003-3806-9575"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Federico Rossetto","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3806-9575","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071842569","display_name":"Jeff Dalton","orcid":"https://orcid.org/0000-0003-2422-8651"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeffrey Dalton","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2422-8651","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070918132","display_name":"Roderick Murray\u2010Smith","orcid":"https://orcid.org/0000-0003-4228-7962"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roderick Murray-Smith","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4228-7962","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9937000274658203,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9915000200271606,"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/metadata","display_name":"Metadata","score":0.8871272206306458},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8511804342269897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039944171905518},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5281643271446228},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5271695852279663},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4811321794986725},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46282893419265747},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44210436940193176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35181763768196106},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3324437141418457}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8871272206306458},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8511804342269897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039944171905518},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5281643271446228},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5271695852279663},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4811321794986725},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46282893419265747},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44210436940193176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35181763768196106},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3324437141418457},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3607827.3616842","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607827.3616842","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616842?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:305760","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/305760/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"doi:10.1145/3607827.3616842","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607827.3616842","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607827.3616842?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st Workshop on Large Generative Models Meet Multimodal Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3203412108","display_name":"Turing AI Fellowship:Neural Conversational Information Seeking Assistant","funder_award_id":"EP/V025708/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7302224536","display_name":null,"funder_award_id":"EP/V025708/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387954140.pdf","grobid_xml":"https://content.openalex.org/works/W4387954140.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2127870748","https://openalex.org/W2133824856","https://openalex.org/W2136129419","https://openalex.org/W2149628368","https://openalex.org/W2178339699","https://openalex.org/W2592168896","https://openalex.org/W2733963828","https://openalex.org/W2890267272","https://openalex.org/W3098942062","https://openalex.org/W3105202226","https://openalex.org/W4221161255","https://openalex.org/W4225314222","https://openalex.org/W4293518855","https://openalex.org/W4308860702"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3],"propose":[4],"a":[5,63],"set":[6],"of":[7,69,92],"new":[8],"automatic":[9],"text":[10,101],"augmentations":[11],"that":[12,104],"leverage":[13,34],"Large":[14],"Language":[15],"Models":[16],"from":[17,41],"song":[18],"metadata":[19],"to":[20,28,46],"improve":[21],"on":[22,67,72,107],"music":[23,78],"information":[24],"retrieval":[25],"tasks.":[26],"Compared":[27],"recent":[29],"works,":[30],"our":[31],"proposed":[32],"methods":[33,103],"large":[35],"language":[36],"models":[37],"and":[38,77,86],"copyright-free":[39],"corpora":[40],"web":[42],"sources,":[43],"enabling":[44],"us":[45],"release":[47],"the":[48,59,90,108],"knowledge":[49,95],"sources":[50,96],"collected.":[51],"We":[52,88],"show":[53],"how":[54],"combining":[55],"these":[56],"representations":[57],"with":[58],"audio":[60],"signal":[61],"provides":[62],"21%":[64],"relative":[65],"improvement":[66],"five":[68],"six":[70],"datasets":[71],"genre":[73],"classification,":[74],"emotion":[75],"recognition":[76],"tagging,":[79],"achieving":[80],"state-of-the-art":[81],"in":[82],"three":[83],"(GTZAN,":[84],"FMA-Small":[85],"Deezer).":[87],"demonstrate":[89],"benefit":[91],"injecting":[93],"external":[94],"by":[97],"comparing":[98],"them":[99],"withintrinsic":[100],"representation":[102],"rely":[105],"only":[106],"sample's":[109],"information.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}