{"id":"https://openalex.org/W4388937202","doi":"https://doi.org/10.1109/icccnt56998.2023.10307558","title":"Music Generation and Retrieval Using LSTM and VAE","display_name":"Music Generation and Retrieval Using LSTM and VAE","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4388937202","doi":"https://doi.org/10.1109/icccnt56998.2023.10307558"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt56998.2023.10307558","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icccnt56998.2023.10307558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5046207538","display_name":"Kunal Gupta","orcid":"https://orcid.org/0000-0001-8202-2120"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kunal Gupta","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India","Department of Electrical Engineering, Delhi Technological University, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]},{"raw_affiliation_string":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030803191","display_name":"Kshitij Srivastava","orcid":"https://orcid.org/0000-0002-3658-0815"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kshitij Srivastava","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India","Department of Electrical Engineering, Delhi Technological University, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]},{"raw_affiliation_string":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031819183","display_name":"Krishan P. Singh","orcid":"https://orcid.org/0000-0002-8815-9336"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishan Singh","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India","Department of Electrical Engineering, Delhi Technological University, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]},{"raw_affiliation_string":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019120869","display_name":"Rohan Pillai","orcid":null},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohan Pillai","raw_affiliation_strings":["Delhi Technological University,Department of Electrical Engineering,New Delhi,India","Department of Electrical Engineering, Delhi Technological University, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Department of Electrical Engineering,New Delhi,India","institution_ids":["https://openalex.org/I863896202"]},{"raw_affiliation_string":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India","institution_ids":["https://openalex.org/I863896202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046207538"],"corresponding_institution_ids":["https://openalex.org/I863896202"],"apc_list":null,"apc_paid":null,"fwci":0.2033,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47455718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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":0.9987000226974487,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362796306610107},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6995257139205933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6711424589157104},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.6457253694534302},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6154634952545166},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.48373985290527344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48369747400283813},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.4539588987827301},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4444211423397064},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42996153235435486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4047693610191345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3679489195346832},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.21548983454704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362796306610107},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6995257139205933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6711424589157104},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.6457253694534302},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6154634952545166},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.48373985290527344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48369747400283813},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.4539588987827301},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4444211423397064},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42996153235435486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4047693610191345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3679489195346832},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.21548983454704285},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt56998.2023.10307558","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icccnt56998.2023.10307558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/W1513372824","https://openalex.org/W1965555277","https://openalex.org/W2148730083","https://openalex.org/W2211228203","https://openalex.org/W2225156818","https://openalex.org/W2338312508","https://openalex.org/W2769418646","https://openalex.org/W2809456243","https://openalex.org/W2912259457","https://openalex.org/W2946149332","https://openalex.org/W2966727317","https://openalex.org/W3037000952","https://openalex.org/W3107761867","https://openalex.org/W4308936376","https://openalex.org/W6640963894","https://openalex.org/W6703879901","https://openalex.org/W6746589939","https://openalex.org/W6762849721"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2386555541","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2889651276","https://openalex.org/W599334349","https://openalex.org/W1978870958","https://openalex.org/W4390557242"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"explores":[4],"the":[5,54,61,69,91,100,118,127,133,148,181,188],"use":[6],"of":[7,93,102,117,135,150,164,183,190],"machine":[8],"learning":[9,46,185],"algorithms":[10,186],"for":[11,107],"music":[12,29,56,62,66,82,108,136,156,177,191],"generation":[13,137,178],"and":[14,21,47,59,64,98,105,123,141,152,157,167,179],"retrieval.":[15],"Specifically,":[16],"Long":[17],"Short-Term":[18],"Memory":[19],"(LSTM)":[20],"Variational":[22],"Autoencoders":[23],"(VAEs)":[24],"are":[25,74],"employed":[26],"to":[27,52],"generate":[28],"based":[30],"on":[31],"a":[32,39,81,85,114],"monodic":[33],"sound":[34],"composition":[35,96],"(MIDI":[36],"file).":[37],"LSTM,":[38,140],"neural":[40,143],"network":[41],"commonly":[42],"used":[43],"in":[44,132,154,162,175,187],"deep":[45,184],"artificial":[48],"intelligence,":[49],"is":[50],"utilized":[51],"train":[53],"initial":[55],"set,":[57],"evaluate":[58],"filter":[60],"collection,":[63],"compose":[65],"by":[67],"minimizing":[68],"loss":[70],"function.":[71],"VAEs,":[72],"which":[73],"nonlinear":[75],"unsupervised":[76],"dimensionality":[77],"reduction":[78],"techniques,":[79],"compress":[80],"dataset":[83,119],"into":[84],"low-dimensional":[86],"representation.":[87],"The":[88,110,145,169],"paper":[89,128],"discusses":[90],"limitations":[92],"conventional":[94],"algorithmic":[95],"techniques":[97],"presents":[99,129],"advantages":[101],"using":[103,138],"LSTM":[104,151],"VAEs":[106,153],"generation.":[109],"methodology":[111],"section":[112],"provides":[113],"detailed":[115],"explanation":[116],"loading,":[120],"exploration,":[121],"cleaning,":[122],"preprocessing":[124],"processes.":[125],"Furthermore,":[126],"related":[130],"works":[131],"field":[134,189],"CNN,":[139],"other":[142],"networks.":[144],"results":[146],"indicate":[147],"effectiveness":[149],"generating":[155],"melodies,":[158],"surpassing":[159],"traditional":[160],"methods":[161],"terms":[163],"melody":[165],"clarity":[166],"complexity.":[168],"proposed":[170],"models":[171],"offer":[172],"promising":[173],"outcomes":[174],"automatic":[176],"demonstrate":[180],"potential":[182],"composition.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}