{"id":"https://openalex.org/W3015523207","doi":"https://doi.org/10.1109/icassp40776.2020.9053240","title":"Large-Scale Weakly-Supervised Content Embeddings for Music Recommendation and Tagging","display_name":"Large-Scale Weakly-Supervised Content Embeddings for Music Recommendation and Tagging","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015523207","doi":"https://doi.org/10.1109/icassp40776.2020.9053240","mag":"3015523207"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5019169850","display_name":"Qingqing Huang","orcid":"https://orcid.org/0000-0002-8298-5418"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qingqing Huang","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418950","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-6674-692X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel P. W. Ellis","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026650852","display_name":"Rif A. Saurous","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rif A. Saurous","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108509252","display_name":"John R. Anderson","orcid":"https://orcid.org/0000-0002-4977-6630"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Anderson","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019169850"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.5217,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.82807818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8364","last_page":"8368"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8271890878677368},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7920751571655273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5584622025489807},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.529179036617279},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5207217335700989},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5170744061470032},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5050745606422424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4812754988670349},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4592435657978058},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.45566266775131226},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4210607409477234},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4168650507926941},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1728537678718567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271890878677368},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7920751571655273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5584622025489807},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.529179036617279},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5207217335700989},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5170744061470032},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5050745606422424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4812754988670349},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4592435657978058},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.45566266775131226},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4210607409477234},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4168650507926941},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1728537678718567},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1556219185","https://openalex.org/W1566941822","https://openalex.org/W2059652044","https://openalex.org/W2067329295","https://openalex.org/W2096733369","https://openalex.org/W2101409192","https://openalex.org/W2137028279","https://openalex.org/W2165320163","https://openalex.org/W2194775991","https://openalex.org/W2240580723","https://openalex.org/W2293255527","https://openalex.org/W2296751288","https://openalex.org/W2516282932","https://openalex.org/W2526050071","https://openalex.org/W2580221632","https://openalex.org/W2593116425","https://openalex.org/W2604959036","https://openalex.org/W2612445135","https://openalex.org/W2713263280","https://openalex.org/W2765325162","https://openalex.org/W2795791968","https://openalex.org/W2963358591","https://openalex.org/W2963451564","https://openalex.org/W2963550089","https://openalex.org/W2963707325","https://openalex.org/W2964217740","https://openalex.org/W2964218314","https://openalex.org/W3027908062","https://openalex.org/W3099206234","https://openalex.org/W4297775537","https://openalex.org/W4323347044","https://openalex.org/W6633822702","https://openalex.org/W6689262250","https://openalex.org/W6690079499","https://openalex.org/W6697263322","https://openalex.org/W6726231179","https://openalex.org/W6732646663","https://openalex.org/W6736327223","https://openalex.org/W6737664043","https://openalex.org/W6745586488","https://openalex.org/W6749909211"],"related_works":["https://openalex.org/W2156869915","https://openalex.org/W3046577844","https://openalex.org/W3041186544","https://openalex.org/W2790173704","https://openalex.org/W2578143283","https://openalex.org/W2398825887","https://openalex.org/W4291123978","https://openalex.org/W2949185961","https://openalex.org/W4287497346","https://openalex.org/W2949267551"],"abstract_inverted_index":{"We":[0],"explore":[1],"content-based":[2],"representation":[3,97],"learning":[4,38],"strategies":[5],"tailored":[6],"for":[7],"large-scale,":[8],"uncurated":[9],"music":[10,103],"collections":[11],"that":[12,33],"afford":[13],"only":[14],"weak":[15],"supervision":[16],"through":[17],"unstructured":[18],"natural":[19],"language":[20],"metadata":[21],"and":[22,36,46,60,68],"co-listen":[23,48],"statistics.":[24],"At":[25],"the":[26],"core":[27],"is":[28],"a":[29,52,65,76,85],"hybrid":[30],"training":[31],"scheme":[32],"uses":[34],"classification":[35],"metric":[37,67],"losses":[39],"to":[40,92],"incorporate":[41],"both":[42],"metadata-derived":[43],"text":[44,59,73],"labels":[45,74],"aggregate":[47],"supervisory":[49],"signals":[50],"into":[51],"single":[53],"convolutional":[54],"model.":[55],"The":[56],"resulting":[57],"joint":[58],"audio":[61],"content":[62],"embedding":[63],"defines":[64],"similarity":[66],"supports":[69],"prediction":[70],"of":[71,78],"semantic":[72],"using":[75,84],"vocabulary":[77],"unprecedented":[79],"granularity,":[80],"which":[81],"we":[82],"refine":[83],"novel":[86],"word-sense":[87],"disambiguation":[88],"procedure.":[89],"As":[90],"input":[91],"simple":[93],"classifier":[94],"architectures,":[95],"our":[96],"achieves":[98],"state-of-the-art":[99],"performance":[100],"on":[101],"two":[102],"tagging":[104],"benchmarks.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-11T06:13:24.991567","created_date":"2025-10-10T00:00:00"}