{"id":"https://openalex.org/W2920942922","doi":"https://doi.org/10.23919/apsipa.2018.8659612","title":"Deep Learning Models for Melody Perception: An Investigation on Symbolic Music Data","display_name":"Deep Learning Models for Melody Perception: An Investigation on Symbolic Music Data","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2920942922","doi":"https://doi.org/10.23919/apsipa.2018.8659612","mag":"2920942922"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659612","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5070642261","display_name":"Wei-Tsung Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wei-Tsung Lu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070642261"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.3319,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.60174855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1620","last_page":"1625"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9983000159263611,"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":0.9972000122070312,"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":0.7372701168060303},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6589133739471436},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48750731348991394},{"id":"https://openalex.org/keywords/music-perception","display_name":"Music perception","score":0.46514761447906494},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.46144312620162964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45756393671035767},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4394336938858032},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42627331614494324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3973904252052307},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17183497548103333},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.14987298846244812},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.14220520853996277},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.13564741611480713},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07085615396499634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372701168060303},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6589133739471436},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48750731348991394},{"id":"https://openalex.org/C2987788386","wikidata":"https://www.wikidata.org/wiki/Q476590","display_name":"Music perception","level":3,"score":0.46514761447906494},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.46144312620162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45756393671035767},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4394336938858032},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42627331614494324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3973904252052307},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17183497548103333},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.14987298846244812},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.14220520853996277},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.13564741611480713},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07085615396499634},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659612","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W24073418","https://openalex.org/W1492730469","https://openalex.org/W1500684166","https://openalex.org/W1901129140","https://openalex.org/W1967959344","https://openalex.org/W1976069042","https://openalex.org/W1985300849","https://openalex.org/W1989708334","https://openalex.org/W2023800933","https://openalex.org/W2027518030","https://openalex.org/W2028145264","https://openalex.org/W2115057260","https://openalex.org/W2121693708","https://openalex.org/W2132715541","https://openalex.org/W2294039222","https://openalex.org/W2302255633","https://openalex.org/W2340199271","https://openalex.org/W2396684454","https://openalex.org/W2400121907","https://openalex.org/W2407685581","https://openalex.org/W2516301810","https://openalex.org/W2571951934","https://openalex.org/W2573843158","https://openalex.org/W2577202280","https://openalex.org/W2578550227","https://openalex.org/W2579424295","https://openalex.org/W2586947700","https://openalex.org/W2630837129","https://openalex.org/W2635912764","https://openalex.org/W2773294482","https://openalex.org/W2902480954","https://openalex.org/W2963351448","https://openalex.org/W2963575853","https://openalex.org/W2964309882","https://openalex.org/W6601024654","https://openalex.org/W6629679824","https://openalex.org/W6629994368","https://openalex.org/W6639824700","https://openalex.org/W6679882067","https://openalex.org/W6698183232","https://openalex.org/W6712557957","https://openalex.org/W6714030504","https://openalex.org/W6730558285","https://openalex.org/W6731524272","https://openalex.org/W6732421929","https://openalex.org/W6732642355","https://openalex.org/W6732726272","https://openalex.org/W6756648248"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W2464878701","https://openalex.org/W4247380401","https://openalex.org/W3013946943","https://openalex.org/W3112683371","https://openalex.org/W3113198510","https://openalex.org/W2053039539","https://openalex.org/W2056029801","https://openalex.org/W1597258651"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,7,21,39,75,88,91,98],"deep":[3],"learning":[4],"approaches":[5],"on":[6,11],"melody":[8,31,64],"extraction":[9,32],"problem":[10],"symbolic":[12],"music":[13],"data.":[14],"Specifically,":[15],"we":[16],"compare":[17],"two":[18],"different":[19],"approaches:":[20],"first":[22],"one":[23,80],"employs":[24,41],"recurrent":[25],"neural":[26],"networks":[27,44],"(RNN)":[28],"by":[29,46,79],"considering":[30,47],"as":[33,49,67],"a":[34,50,60],"sequence":[35],"prediction":[36],"problem,":[37],"while":[38],"second":[40],"fully":[42],"convolutional":[43],"(FCN)":[45],"it":[48],"image":[51],"semantic":[52,92],"segmentation":[53,93],"problem.":[54],"Both":[55],"methods":[56],"are":[57,77],"tested":[58],"against":[59],"MIDI":[61],"dataset":[62],"with":[63],"tracks":[65],"acting":[66],"ground":[68],"truth.":[69],"A":[70],"more":[71],"challenging":[72],"case":[73],"that":[74],"melodies":[76],"shifted":[78],"octave":[81],"is":[82],"also":[83],"considered.":[84],"Evaluation":[85],"results":[86],"show":[87],"advantage":[89],"of":[90,97],"approach":[94],"in":[95],"terms":[96],"accuracy.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-23T06:02:50.125483","created_date":"2025-10-10T00:00:00"}