{"id":"https://openalex.org/W3159642309","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533461","title":"MusCaps: Generating Captions for Music Audio","display_name":"MusCaps: Generating Captions for Music Audio","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3159642309","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533461","mag":"3159642309"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.11984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069645267","display_name":"Ilaria Manco","orcid":"https://orcid.org/0000-0001-8945-7557"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ilaria Manco","raw_affiliation_strings":["Music & Audio Machine Learning Lab, Universal Music Group, London, U.K","School of EECS, Queen Mary University of London, U.K","[School of EECS, Queen Mary University of London, U.K.]"],"affiliations":[{"raw_affiliation_string":"Music & Audio Machine Learning Lab, Universal Music Group, London, U.K","institution_ids":[]},{"raw_affiliation_string":"School of EECS, Queen Mary University of London, U.K","institution_ids":[]},{"raw_affiliation_string":"[School of EECS, Queen Mary University of London, U.K.]","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["School of EECS, Queen Mary University of London, U.K","[School of EECS, Queen Mary University of London, U.K.]"],"affiliations":[{"raw_affiliation_string":"School of EECS, Queen Mary University of London, U.K","institution_ids":[]},{"raw_affiliation_string":"[School of EECS, Queen Mary University of London, U.K.]","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051960947","display_name":"Elio Quinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elio Quinton","raw_affiliation_strings":["Music & Audio Machine Learning Lab, Universal Music Group, London, U.K","Universal Music Group,Music & Audio Machine Learning Lab,London,U.K"],"affiliations":[{"raw_affiliation_string":"Music & Audio Machine Learning Lab, Universal Music Group, London, U.K","institution_ids":[]},{"raw_affiliation_string":"Universal Music Group,Music & Audio Machine Learning Lab,London,U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gyorgy Fazekas","raw_affiliation_strings":["School of EECS, Queen Mary University of London, U.K","[School of EECS, Queen Mary University of London, U.K.]"],"affiliations":[{"raw_affiliation_string":"School of EECS, Queen Mary University of London, U.K","institution_ids":[]},{"raw_affiliation_string":"[School of EECS, Queen Mary University of London, U.K.]","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069645267"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.3086,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52260567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10860","display_name":"Speech and Audio Processing","score":0.991599977016449,"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":0.9887999892234802,"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/computer-science","display_name":"Computer science","score":0.8488032817840576},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8164229393005371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5373541116714478},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5211767554283142},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5073074698448181},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47194474935531616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41975319385528564},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41498082876205444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8488032817840576},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8164229393005371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5373541116714478},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5211767554283142},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5073074698448181},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47194474935531616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41975319385528564},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41498082876205444},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.11984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11984","pdf_url":"https://arxiv.org/pdf/2104.11984","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/72068","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/72068","pdf_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/72068","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"mag:3159642309","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.11984","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.11984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.11984","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.11984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11984","pdf_url":"https://arxiv.org/pdf/2104.11984","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8793594538","display_name":null,"funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2016589492","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2127870748","https://openalex.org/W2154652894","https://openalex.org/W2250539671","https://openalex.org/W2293255527","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2515340777","https://openalex.org/W2745461083","https://openalex.org/W2916103538","https://openalex.org/W2945761034","https://openalex.org/W2949376505","https://openalex.org/W2950178297","https://openalex.org/W2962813390","https://openalex.org/W2963341956","https://openalex.org/W2963369619","https://openalex.org/W2963550089","https://openalex.org/W2964213897","https://openalex.org/W2964218314","https://openalex.org/W2968124245","https://openalex.org/W2970608575","https://openalex.org/W2981851019","https://openalex.org/W2982669287","https://openalex.org/W2995460200","https://openalex.org/W2997591391","https://openalex.org/W3015289235","https://openalex.org/W3033182893","https://openalex.org/W3035119608","https://openalex.org/W3035312337","https://openalex.org/W3037468418","https://openalex.org/W3042165234","https://openalex.org/W3093937952","https://openalex.org/W3097791920","https://openalex.org/W3112467147","https://openalex.org/W6630875275","https://openalex.org/W6678969435","https://openalex.org/W6682631176","https://openalex.org/W6715395060","https://openalex.org/W6725318829","https://openalex.org/W6726072906","https://openalex.org/W6736327223","https://openalex.org/W6745878906","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6778572914","https://openalex.org/W6779136962","https://openalex.org/W6779191341","https://openalex.org/W6779786894","https://openalex.org/W6783957057","https://openalex.org/W6787564935"],"related_works":["https://openalex.org/W3201326582","https://openalex.org/W3205708381","https://openalex.org/W3207925746","https://openalex.org/W2905139236","https://openalex.org/W3163035491","https://openalex.org/W3040260790","https://openalex.org/W2999642076","https://openalex.org/W3201143670","https://openalex.org/W3162391496","https://openalex.org/W3102163718","https://openalex.org/W3000256674","https://openalex.org/W2105332826","https://openalex.org/W3134092202","https://openalex.org/W3139240716","https://openalex.org/W3093494400","https://openalex.org/W3009270862","https://openalex.org/W3123172502","https://openalex.org/W3014487864","https://openalex.org/W3143035657","https://openalex.org/W2110465268"],"abstract_inverted_index":{"Content-based":[0],"music":[1,18,42,58,72,187,204],"information":[2,205],"retrieval":[3,206],"has":[4],"seen":[5],"rapid":[6],"progress":[7],"with":[8,81],"the":[9,49,70,119,123,158,171,200],"adoption":[10],"of":[11,23,51,57,78,122,157,173],"deep":[12],"learning.":[13],"Current":[14],"approaches":[15],"to":[16,40,93,108,155,198],"high-level":[17],"description":[19,43,56,188],"typically":[20],"make":[21],"use":[22,172],"classification":[24],"models,":[25],"such":[26],"as":[27,48],"in":[28,61,118,203],"auto-tagging":[29],"or":[30],"genre":[31],"and":[32,88,102,114,170,189,195],"mood":[33],"classification.":[34],"In":[35],"this":[36,66,148],"work,":[37],"we":[38,68,145],"propose":[39],"address":[41],"via":[44],"audio":[45,59,73,106,139,159],"captioning,":[46],"defined":[47],"task":[50],"generating":[52],"a":[53,62,99,134,182],"natural":[54],"language":[55],"content":[60],"human-like":[63],"manner.":[64],"To":[65],"end,":[67],"present":[69],"first":[71],"captioning":[74],"model,":[75],"MusCaps,":[76],"consisting":[77],"an":[79,142],"encoder-decoder":[80],"temporal":[82],"attention.":[83],"Our":[84,179],"method":[85,132],"combines":[86,190],"convolutional":[87],"recurrent":[89],"neural":[90],"network":[91],"architectures":[92],"jointly":[94],"process":[95],"audio-text":[96],"inputs":[97],"through":[98,126],"multimodal":[100],"encoder":[101],"leverages":[103],"pretraining":[104],"on":[105],"data":[107],"obtain":[109],"representations":[110],"that":[111,130,147],"effectively":[112],"capture":[113],"summarise":[115],"musical":[116],"features":[117],"input.":[120],"Evaluation":[121],"generated":[124],"captions":[125],"automatic":[127],"metrics":[128],"shows":[129],"our":[131],"outperforms":[133],"baseline":[135],"designed":[136],"for":[137],"non-music":[138],"captioning.":[140],"Through":[141],"ablation":[143],"study,":[144],"unveil":[146],"performance":[149],"boost":[150],"can":[151],"be":[152],"mainly":[153],"attributed":[154],"pre-training":[156],"encoder,":[160],"while":[161],"other":[162],"design":[163],"choices":[164],"-":[165,175],"modality":[166],"fusion,":[167],"decoding":[168],"strategy":[169],"attention":[174],"contribute":[176],"only":[177],"marginally.":[178],"model":[180],"represents":[181],"shift":[183],"away":[184],"from":[185],"classification-based":[186],"tasks":[191],"requiring":[192],"both":[193],"auditory":[194],"linguistic":[196],"understanding":[197],"bridge":[199],"semantic":[201],"gap":[202],"<sup":[207,210],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[208,211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[209,212],"Code":[213],"available":[214],"at":[215],"https://github.com/ilaria-manco/muscaps.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}