{"id":"https://openalex.org/W6967342533","doi":"https://doi.org/10.5281/zenodo.10265247","title":"CLaMP: Contrastive Language-Music Pre-Training for Cross-Modal Symbolic Music Information Retrieval","display_name":"CLaMP: Contrastive Language-Music Pre-Training for Cross-Modal Symbolic Music Information Retrieval","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6967342533","doi":"https://doi.org/10.5281/zenodo.10265247"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265247","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265247","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.10265247","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shangda Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangda Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dingyao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dingyao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Maosong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":[],"raw_orcid":null,"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":0.32691593,"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":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9187999963760376,"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":0.9187999963760376,"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":0.03550000116229057,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5594000220298767},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46540001034736633},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4503999948501587},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42239999771118164},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.364300012588501},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.33570000529289246},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3352999985218048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5778999924659729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5644999742507935},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5594000220298767},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4230000078678131},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.33570000529289246},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265247","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265247","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.10265247","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265247","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":[{"score":0.8555700778961182,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"CLaMP:":[2],"Contrastive":[3],"Language-Music":[4],"Pre-training,":[5],"which":[6,60],"learns":[7],"cross-modal":[8],"representations":[9],"between":[10],"natural":[11],"language":[12],"and":[13,20,52,87,97,116,140,162],"symbolic":[14,101],"music":[15,18,58,74,81,117],"using":[16],"a":[17,21,27,35,48,72,124,136],"encoder":[19,23],"text":[22,45],"trained":[24],"jointly":[25],"with":[26],"contrastive":[28],"loss.":[29],"To":[30,109],"pre-train":[31],"CLaMP,":[32],"we":[33,70,119],"collected":[34],"large":[36],"dataset":[37,125],"of":[38,84,106,113,126],"1.4":[39],"million":[40],"music-text":[41],"pairs.":[42],"It":[43],"employed":[44],"dropout":[46],"as":[47],"data":[49,59],"augmentation":[50],"technique":[51],"bar":[53],"patching":[54],"to":[55,64,78,93,144],"efficiently":[56],"represent":[57],"reduces":[61],"sequence":[62],"length":[63],"less":[65],"than":[66],"10%.":[67],"In":[68,142],"addition,":[69],"developed":[71],"masked":[73],"model":[75],"pre-training":[76],"objective":[77],"enhance":[79],"the":[80,104,111],"encoder's":[82],"comprehension":[83],"musical":[85],"context":[86],"structure.":[88],"CLaMP":[89,151],"integrates":[90],"textual":[91],"information":[92],"enable":[94],"semantic":[95,114],"search":[96,115],"zero-shot":[98,150],"classification":[99],"for":[100],"music,":[102],"surpassing":[103],"capabilities":[105],"previous":[107],"models.":[108],"support":[110],"evaluation":[112],"classification,":[118],"publicly":[120],"release":[121],"WikiMusicText":[122],"(WikiMT),":[123],"1010":[127],"lead":[128],"sheets":[129],"in":[130],"ABC":[131],"notation,":[132],"each":[133],"accompanied":[134],"by":[135],"title,":[137],"artist,":[138],"genre,":[139],"description.":[141],"comparison":[143],"state-of-the-art":[145],"models":[146,161],"that":[147],"require":[148],"fine-tuning,":[149],"demonstrated":[152],"comparable":[153],"or":[154],"superior":[155],"performance":[156],"on":[157],"score-oriented":[158],"datasets.":[159],"Our":[160],"code":[163],"are":[164],"available":[165],"at":[166],"https://github.com/microsoft/muzic/tree/main/clamp.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}