{"id":"https://openalex.org/W3095513901","doi":"https://doi.org/10.1109/icassp39728.2021.9414638","title":"Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags","display_name":"Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095513901","doi":"https://doi.org/10.1109/icassp39728.2021.9414638","mag":"3095513901"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066100176","display_name":"Xavier Favory","orcid":"https://orcid.org/0000-0001-6148-0018"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Favory","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Spain","Universitat Pompeu Fabra,Music Technology Group,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Audio Research Group, Tampere University, Finland","Tampere University,Audio Research Group,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University,Audio Research Group,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Audio Research Group, Tampere University, Finland","Tampere University,Audio Research Group,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University,Audio Research Group,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","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, Spain","Universitat Pompeu Fabra,Music Technology Group,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.361,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45996687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"596","last_page":"600"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8054802417755127},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7719894051551819},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6832116842269897},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6743966937065125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5585181713104248},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5308277010917664},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5146399736404419},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45557349920272827},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4325270354747772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.420526385307312},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.41493383049964905},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35056596994400024},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10824787616729736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8054802417755127},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7719894051551819},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6832116842269897},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6743966937065125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5585181713104248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5308277010917664},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5146399736404419},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45557349920272827},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4325270354747772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.420526385307312},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.41493383049964905},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35056596994400024},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10824787616729736},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/56042","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/56042","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2010.14171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14171","pdf_url":"https://arxiv.org/pdf/2010.14171","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"mag:3095513901","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.14171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.14171","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.14171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/5d2j-wd82","is_oa":true,"landing_page_url":"https://doi.org/10.17023/5d2j-wd82","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.14171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14171","pdf_url":"https://arxiv.org/pdf/2010.14171","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2133824856","https://openalex.org/W2304648132","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2767754137","https://openalex.org/W2794150026","https://openalex.org/W2842511635","https://openalex.org/W2917294828","https://openalex.org/W2939574508","https://openalex.org/W2950577311","https://openalex.org/W2962904371","https://openalex.org/W2963191020","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963684088","https://openalex.org/W2964005873","https://openalex.org/W2981586349","https://openalex.org/W2981991061","https://openalex.org/W2990408345","https://openalex.org/W3000400453","https://openalex.org/W3005680577","https://openalex.org/W3035312337","https://openalex.org/W3037932933","https://openalex.org/W3096655658","https://openalex.org/W6636510571","https://openalex.org/W6685352114","https://openalex.org/W6697974390","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6768465061","https://openalex.org/W6769238691","https://openalex.org/W6770805772","https://openalex.org/W6774314701","https://openalex.org/W6779191341","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W3163035491","https://openalex.org/W3139240716","https://openalex.org/W3093494400","https://openalex.org/W3040260790","https://openalex.org/W3201143670","https://openalex.org/W3123226376","https://openalex.org/W3159642309","https://openalex.org/W3162391496","https://openalex.org/W3159929162","https://openalex.org/W3099638501","https://openalex.org/W3198549210","https://openalex.org/W3094123278","https://openalex.org/W3015734344","https://openalex.org/W3205708381","https://openalex.org/W2991487804","https://openalex.org/W2930959424","https://openalex.org/W3180663620","https://openalex.org/W2963583362","https://openalex.org/W2963902314","https://openalex.org/W3123172502"],"abstract_inverted_index":{"Self-supervised":[0],"audio":[1,11,26,31,57,61,124,168],"representation":[2,87],"learning":[3,56],"offers":[4],"an":[5,60],"attractive":[6],"alternative":[7],"for":[8,55],"obtaining":[9],"generic":[10],"embeddings,":[12],"capable":[13,40],"to":[14,41,43],"be":[15],"employed":[16],"into":[17],"various":[18],"downstream":[19,140],"tasks.":[20],"Published":[21],"approaches":[22],"that":[23,38,153],"consider":[24],"both":[25],"and":[27,70,95,118,120,146],"words/tags":[28],"associated":[29,91],"with":[30,92,102,157],"do":[32],"not":[33],"employ":[34],"text":[35],"processing":[36],"models":[37],"are":[39],"generalize":[42],"tags":[44,90],"unknown":[45],"during":[46],"training.":[47],"In":[48],"this":[49],"work":[50],"we":[51,96,121],"propose":[52],"a":[53,64,71,85,111],"method":[54],"representations":[58,125],"using":[59,110],"autoencoder":[62],"(AAE),":[63],"general":[65],"word":[66],"embed-dings":[67],"model":[68],"(WEM),":[69],"multi-head":[72,155],"self-attention":[73,156],"(MHA)":[74],"mechanism.":[75],"MHA":[76,101,119],"attends":[77],"on":[78],"the":[79,82,89,93,98,103,106,123,127,130,161],"output":[80,99,128],"of":[81,88,100,105,108,129,132],"WEM,":[83],"pro-viding":[84],"contextualized":[86],"audio,":[94],"align":[97],"out-put":[104],"encoder":[107,131],"AAE":[109,117],"contrastive":[112],"loss.":[113],"We":[114],"jointly":[115],"optimize":[116],"evaluate":[122],"(i.e.":[126],"AAE)":[133],"by":[134],"utilizing":[135],"them":[136],"in":[137,160],"three":[138],"different":[139],"tasks,":[141],"namely":[142],"sound,":[143],"music":[144,147],"genre,":[145],"instrument":[148],"classification.":[149],"Our":[150],"results":[151],"show":[152],"employing":[154],"multiple":[158],"heads":[159],"tag-based":[162],"network":[163],"can":[164],"induce":[165],"better":[166],"learned":[167],"representations.":[169]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}