{"id":"https://openalex.org/W2591643707","doi":"https://doi.org/10.1109/icassp.2017.7952230","title":"Revisiting the problem of audio-based hit song prediction using convolutional neural networks","display_name":"Revisiting the problem of audio-based hit song prediction using convolutional neural networks","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2591643707","doi":"https://doi.org/10.1109/icassp.2017.7952230","mag":"2591643707"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5068970053","display_name":"Li-Chia Yang","orcid":"https://orcid.org/0000-0001-7342-6529"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Chia Yang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103126460","display_name":"Szu-Yu Chou","orcid":"https://orcid.org/0000-0002-5201-0580"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Szu-Yu Chou","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626873","display_name":"Yi\u2010An Chen","orcid":"https://orcid.org/0000-0002-6889-5213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-An Chen","raw_affiliation_strings":["Machine Learning Research Team, KKBOX Inc., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Research Team, KKBOX Inc., Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"625"},"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":0.9921000003814697,"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/T11113","display_name":"Music History and Culture","score":0.9847000241279602,"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/popularity","display_name":"Popularity","score":0.8217224478721619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7947991490364075},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7771193981170654},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6632912158966064},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6419082880020142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.592951774597168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4812321662902832},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.476496160030365},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4464060962200165},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4388354420661926},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.425011545419693}],"concepts":[{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.8217224478721619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947991490364075},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7771193981170654},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6632912158966064},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6419082880020142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.592951774597168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4812321662902832},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.476496160030365},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4464060962200165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4388354420661926},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.425011545419693},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":29,"referenced_works":["https://openalex.org/W47828995","https://openalex.org/W80219283","https://openalex.org/W1762479869","https://openalex.org/W1903029394","https://openalex.org/W1923230460","https://openalex.org/W1980092792","https://openalex.org/W1995562189","https://openalex.org/W2059652044","https://openalex.org/W2082891083","https://openalex.org/W2097117768","https://openalex.org/W2115387076","https://openalex.org/W2127870748","https://openalex.org/W2147453867","https://openalex.org/W2242773987","https://openalex.org/W2321416072","https://openalex.org/W2395611524","https://openalex.org/W2414894569","https://openalex.org/W2525577390","https://openalex.org/W2571568675","https://openalex.org/W2963369619","https://openalex.org/W2964300898","https://openalex.org/W4301891957","https://openalex.org/W6601976940","https://openalex.org/W6603339013","https://openalex.org/W6678969435","https://openalex.org/W6690394000","https://openalex.org/W6711868289","https://openalex.org/W6715395060","https://openalex.org/W6731439077"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W3048601286","https://openalex.org/W2965925734"],"abstract_inverted_index":{"Being":[0],"able":[1],"to":[2,41,79,148,189],"predict":[3,57],"whether":[4],"a":[5,9,26,103,119],"song":[6,27,58,85,128],"can":[7,28,56],"be":[8,29],"hit":[10,84],"has":[11],"important":[12],"applications":[13],"in":[14,152,168,179],"the":[15,23,70,90,110,114,136,145,170,184,193],"music":[16],"industry.":[17],"Although":[18],"it":[19],"is":[20,60],"true":[21],"that":[22,108,124,158],"popularity":[24,59,171],"of":[25,73,138,172,195],"greatly":[30],"affected":[31],"by":[32,69,87,187],"external":[33,127],"factors":[34],"such":[35],"as":[36,53,113],"social":[37],"and":[38,93,133,135],"commercial":[39],"influences,":[40],"which":[42],"degree":[43],"audio":[44,91,150],"features":[45,92],"computed":[46],"from":[47],"musical":[48],"signals":[49],"(whom":[50],"we":[51,77,100],"regard":[52],"internal":[54],"factors)":[55],"an":[61,126],"interesting":[62],"research":[63],"question":[64],"on":[65,83],"its":[66],"own.":[67],"Motivated":[68],"recent":[71],"success":[72],"deep":[74,97,159],"learning":[75,89],"techniques,":[76],"attempt":[78],"extend":[80],"previous":[81],"work":[82],"prediction":[86,94],"jointly":[88],"models":[95],"using":[96],"learning.":[98],"Specifically,":[99],"experiment":[101],"with":[102],"convolutional":[104],"neural":[105],"network":[106],"model":[107,123,147],"takes":[109],"primitive":[111],"mel-spectrogram":[112],"input":[115],"for":[116,130],"feature":[117],"learning,":[118],"more":[120,163],"advanced":[121],"JYnet":[122,188],"uses":[125],"dataset":[129],"supervised":[131],"pre-training":[132],"auto-tagging,":[134],"combination":[137],"these":[139],"two":[140],"models.":[141,197],"We":[142,181],"also":[143,182],"consider":[144],"inception":[146],"characterize":[149],"information":[151],"different":[153,196],"scales.":[154],"Our":[155],"experiments":[156],"suggest":[157],"structures":[160,167],"are":[161],"indeed":[162],"accurate":[164],"than":[165],"shallow":[166],"predicting":[169],"either":[173],"Chinese":[174],"or":[175],"Western":[176],"Pop":[177],"songs":[178],"Taiwan.":[180],"use":[183],"tags":[185],"predicted":[186],"gain":[190],"insights":[191],"into":[192],"result":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}