{"id":"https://openalex.org/W4245933688","doi":"https://doi.org/10.1109/mmsp53017.2021.9733502","title":"Evaluating Deep Music Generation Methods Using Data Augmentation","display_name":"Evaluating Deep Music Generation Methods Using Data Augmentation","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W4245933688","doi":"https://doi.org/10.1109/mmsp53017.2021.9733502"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp53017.2021.9733502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp53017.2021.9733502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)","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/A5059644945","display_name":"Toby Godwin","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Toby Godwin","raw_affiliation_strings":["Imperial College London,GLAM,London,UK","GLAM, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054300849","display_name":"Georgios Rizos","orcid":"https://orcid.org/0000-0003-2483-5574"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Rizos","raw_affiliation_strings":["Imperial College London,GLAM,London,UK","GLAM, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030891676","display_name":"Alice Baird","orcid":"https://orcid.org/0000-0002-7003-5650"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alice Baird","raw_affiliation_strings":["University of Augsburg,EIHW,Augsburg,Germany","EIHW, University of Augsburg, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Augsburg,EIHW,Augsburg,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"EIHW, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552789","display_name":"Najla D. Al Futaisi","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Najla D. Al Futaisi","raw_affiliation_strings":["Imperial College London,GLAM,London,UK","GLAM, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001348903","display_name":"Vincent Brisse","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vincent Brisse","raw_affiliation_strings":["Imperial College London,GLAM,London,UK","GLAM, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["Imperial College London,GLAM,London,UK","GLAM, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1544,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49608355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.7359490394592285},{"id":"https://openalex.org/keywords/mood","display_name":"Mood","score":0.6329805254936218},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6319079995155334},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6000494360923767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5947482585906982},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.5542657375335693},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5509483218193054},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5092216730117798},{"id":"https://openalex.org/keywords/musicality","display_name":"Musicality","score":0.5074118971824646},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43960896134376526},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43024927377700806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34129002690315247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3257942795753479},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14730367064476013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10706400871276855},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10178685188293457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7359490394592285},{"id":"https://openalex.org/C2780733359","wikidata":"https://www.wikidata.org/wiki/Q331769","display_name":"Mood","level":2,"score":0.6329805254936218},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6319079995155334},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6000494360923767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947482585906982},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.5542657375335693},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5509483218193054},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5092216730117798},{"id":"https://openalex.org/C113194728","wikidata":"https://www.wikidata.org/wiki/Q4130159","display_name":"Musicality","level":3,"score":0.5074118971824646},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43960896134376526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43024927377700806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34129002690315247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3257942795753479},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14730367064476013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10706400871276855},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10178685188293457},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp53017.2021.9733502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp53017.2021.9733502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2014842839","https://openalex.org/W2088432713","https://openalex.org/W2165857685","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2765340009","https://openalex.org/W2766543209","https://openalex.org/W2811079561","https://openalex.org/W2898827701","https://openalex.org/W2937977583","https://openalex.org/W2950060770","https://openalex.org/W2950547518","https://openalex.org/W2953318193","https://openalex.org/W2963163009","https://openalex.org/W2963447013","https://openalex.org/W2964159205","https://openalex.org/W2971074500","https://openalex.org/W2972724712","https://openalex.org/W2982862350","https://openalex.org/W2984972638","https://openalex.org/W2985693847","https://openalex.org/W3000389243","https://openalex.org/W3015241559","https://openalex.org/W3090634605","https://openalex.org/W4287802874","https://openalex.org/W4289287927","https://openalex.org/W4323654151","https://openalex.org/W6637618735","https://openalex.org/W6732429163","https://openalex.org/W6745907911","https://openalex.org/W6753018729","https://openalex.org/W6755182157","https://openalex.org/W6755406732","https://openalex.org/W6756584662","https://openalex.org/W6761628794","https://openalex.org/W6762931180","https://openalex.org/W6763945542","https://openalex.org/W6769198072","https://openalex.org/W6771763809","https://openalex.org/W6776218486","https://openalex.org/W6784028902"],"related_works":["https://openalex.org/W2362143758","https://openalex.org/W3204559186","https://openalex.org/W4205374791","https://openalex.org/W2244560300","https://openalex.org/W2393643091","https://openalex.org/W2789677103","https://openalex.org/W2272312111","https://openalex.org/W4246054334","https://openalex.org/W635700799","https://openalex.org/W2085671451"],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,95],"deep":[3,161],"algorithmic":[4],"music":[5,42,56,100,113,146,162,173],"generation,":[6],"evaluation":[7],"of":[8,32,55,71,98,167,180,197],"generated":[9,34,41,72,78,109,115,152,199],"samples":[10,31,79,114],"often":[11],"relies":[12],"on":[13,23,189],"human":[14],"evaluation,":[15],"which":[16],"is":[17,139],"subjective":[18],"and":[19,122,125,164],"costly.":[20],"We":[21,62,88,111,154],"focus":[22],"designing":[24],"a":[25,99,127,145,186],"homogeneous,":[26],"objective":[27,136],"framework":[28,129],"for":[29,135],"evaluating":[30],"algorithmically":[33],"music.":[35,153],"Any":[36],"engineered":[37],"measures":[38],"to":[39,45,66,84,133,170,192],"evaluate":[40,193],"typically":[43],"attempt":[44,142],"define":[46],"the":[47,68,93,140,156,165,168,181,194],"samples\u2019":[48],"musicality,":[49],"but":[50,74],"do":[51,63],"not":[52,64],"capture":[53],"qualities":[54],"such":[57],"as":[58],"theme":[59],"or":[60,86],"mood.":[61],"seek":[65],"assess":[67],"musical":[69],"merit":[70],"music,":[73],"instead":[75],"explore":[76],"whether":[77],"contain":[80],"meaningful":[81],"information":[82],"pertaining":[83],"emotion":[85,178],"mood/theme.":[87],"achieve":[89],"this":[90],"by":[91,116,174],"measuring":[92],"change":[94],"predictive":[96],"performance":[97,158],"mood/theme":[101],"classifier":[102,187],"after":[103],"augmenting":[104,144],"its":[105],"training":[106],"data":[107,191],"with":[108,150],"samples.":[110,200],"analyse":[112],"three":[117],"models":[118],"\u2013":[119,124],"SampleRNN,":[120],"Jukebox,":[121],"DDSP":[123],"employ":[126],"homogeneous":[128],"across":[130],"all":[131],"methods":[132],"allow":[134],"comparison.":[137],"This":[138],"first":[141],"at":[143],"genre":[147],"classification":[148,157],"dataset":[149],"conditionally":[151],"investigate":[155],"improvement":[159],"using":[160,175],"generation":[163],"ability":[166],"generators":[169],"make":[171],"emotional":[172],"an":[176],"additional,":[177],"annotation":[179],"dataset.":[182],"Finally,":[183],"we":[184],"use":[185],"trained":[188],"real":[190],"label":[195],"validity":[196],"class-conditionally":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}