{"id":"https://openalex.org/W2733963828","doi":"https://doi.org/10.1145/3125486.3125492","title":"A Deep Multimodal Approach for Cold-start Music Recommendation","display_name":"A Deep Multimodal Approach for Cold-start Music Recommendation","publication_year":2017,"publication_date":"2017-08-24","ids":{"openalex":"https://openalex.org/W2733963828","doi":"https://doi.org/10.1145/3125486.3125492","mag":"2733963828"},"language":"en","primary_location":{"id":"doi:10.1145/3125486.3125492","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3125486.3125492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1706.09739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sergio Oramas","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Sergio Oramas","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123445","display_name":"Pandora (United States)","ror":"https://ror.org/038m7b802","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Pandora Media, Inc., Oakland, CA"],"affiliations":[{"raw_affiliation_string":"Pandora Media, Inc., Oakland, CA","institution_ids":["https://openalex.org/I4210123445"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mohamed Sordo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123445","display_name":"Pandora (United States)","ror":"https://ror.org/038m7b802","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Sordo","raw_affiliation_strings":["Pandora Media, Inc., Oakland, CA"],"affiliations":[{"raw_affiliation_string":"Pandora Media, Inc., Oakland, CA","institution_ids":["https://openalex.org/I4210123445"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":2.8036,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.91702549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"37"},"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":0.9927999973297119,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9865999817848206,"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/metadata","display_name":"Metadata","score":0.8219000101089478},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6521000266075134},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5551999807357788},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5457000136375427},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.46860000491142273},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.40549999475479126},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8219000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831000089645386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6521000266075134},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5551999807357788},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5457000136375427},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.35850000381469727},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.2840000092983246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2766000032424927}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3125486.3125492","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3125486.3125492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/33519","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/33519","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:1706.09739","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.09739","pdf_url":"https://arxiv.org/pdf/1706.09739","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1706.09739","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.09739","pdf_url":"https://arxiv.org/pdf/1706.09739","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W281665770","https://openalex.org/W1814328102","https://openalex.org/W1832693441","https://openalex.org/W1965657003","https://openalex.org/W2020901563","https://openalex.org/W2031767620","https://openalex.org/W2054141820","https://openalex.org/W2082927600","https://openalex.org/W2101409192","https://openalex.org/W2102982709","https://openalex.org/W2113479237","https://openalex.org/W2120699290","https://openalex.org/W2127289991","https://openalex.org/W2140833774","https://openalex.org/W2415794803","https://openalex.org/W2510317721","https://openalex.org/W2532651260","https://openalex.org/W2619329613","https://openalex.org/W2997617958","https://openalex.org/W2998704965"],"related_works":[],"abstract_inverted_index":{"An":[0],"increasing":[1],"amount":[2],"of":[3,134],"digital":[4],"music":[5],"is":[6,32,61],"being":[7],"published":[8],"daily.":[9],"Music":[10],"streaming":[11],"services":[12],"often":[13],"ingest":[14],"all":[15],"available":[16,92],"music,":[17],"but":[18],"this":[19,35,41],"poses":[20],"a":[21,103,128],"challenge:":[22],"how":[23],"to":[24,39],"recommend":[25],"new":[26],"artists":[27],"for":[28],"which":[29],"prior":[30],"knowledge":[31],"scarce?":[33],"In":[34],"work":[36],"we":[37],"aim":[38],"address":[40],"so-called":[42],"cold-start":[43],"problem":[44,113],"by":[45,73],"combining":[46,74],"text":[47,76],"and":[48,78,91,97,120,123],"audio":[49,89,121],"information":[50],"with":[51],"user":[52],"feedback":[53,93],"data":[54],"using":[55],"deep":[56],"network":[57],"architectures.":[58],"Our":[59],"method":[60],"divided":[62],"into":[63],"three":[64],"steps.":[65],"First,":[66],"artist":[67,96,118],"embeddings":[68,84,99,126],"are":[69,85,100],"learned":[70,86],"from":[71,87],"biographies":[72],"semantics,":[75],"features,":[77],"aggregated":[79],"usage":[80],"data.":[81,94],"Second,":[82],"track":[83,98],"the":[88,111,132,135],"signal":[90],"Finally,":[95],"combined":[101],"in":[102,127],"multimodal":[104,129],"network.":[105],"Results":[106],"suggest":[107],"that":[108],"both":[109],"splitting":[110],"recommendation":[112],"between":[114],"feature":[115,125],"levels":[116],"(i.e.,":[117],"metadata":[119],"track),":[122],"merging":[124],"approach":[130],"improve":[131],"accuracy":[133],"recommendations.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2017-07-14T00:00:00"}