{"id":"https://openalex.org/W3015061299","doi":"https://doi.org/10.1145/3341105.3374114","title":"Unsupervised cross-modal audio representation learning from unstructured multilingual text","display_name":"Unsupervised cross-modal audio representation learning from unstructured multilingual text","publication_year":2020,"publication_date":"2020-03-29","ids":{"openalex":"https://openalex.org/W3015061299","doi":"https://doi.org/10.1145/3341105.3374114","mag":"3015061299"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341105.3374114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.12265","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102746568","display_name":"Alexander Schindler","orcid":"https://orcid.org/0000-0001-6058-7753"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alexander Schindler","raw_affiliation_strings":["Austrian Institute of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055282943","display_name":"Sergiu Gordea","orcid":"https://orcid.org/0000-0003-4385-7533"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sergiu Gordea","raw_affiliation_strings":["Austrian Institute of Technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362815","display_name":"Peter Knees","orcid":"https://orcid.org/0000-0003-3906-1292"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Peter Knees","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.393,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.214341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":73,"max":77},"biblio":{"volume":"2","issue":null,"first_page":"706","last_page":"713"},"is_retracted":false,"is_paratext":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":0.9996,"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":0.997,"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/feature-learning","display_name":"Feature Learning","score":0.59605384},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.48161596},{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.42584655},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4183699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346064},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.62475085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6120314},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.59605384},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5060198},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.48161596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47526544},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4305986},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42584655},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4183699},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.41280708},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40063006},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3511861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27021572},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1379002},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341105.3374114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2003.12265","pdf_url":"https://arxiv.org/pdf/2003.12265","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2003.12265","pdf_url":"https://arxiv.org/pdf/2003.12265","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.82,"display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":19,"referenced_works":["https://openalex.org/W1973397896","https://openalex.org/W1975929202","https://openalex.org/W1983507146","https://openalex.org/W2045135321","https://openalex.org/W2071103260","https://openalex.org/W2096733369","https://openalex.org/W2126410803","https://openalex.org/W2147152072","https://openalex.org/W2148748626","https://openalex.org/W2165320163","https://openalex.org/W2402588270","https://openalex.org/W2475016890","https://openalex.org/W2912973966","https://openalex.org/W2963451564","https://openalex.org/W2963775347","https://openalex.org/W2971670255","https://openalex.org/W2981571772","https://openalex.org/W3099206234","https://openalex.org/W785481131"],"related_works":["https://openalex.org/W4389358162","https://openalex.org/W3131501806","https://openalex.org/W2807745940","https://openalex.org/W2799683370","https://openalex.org/W2786094008","https://openalex.org/W2619127353","https://openalex.org/W2377594161","https://openalex.org/W2354947096","https://openalex.org/W2111020819","https://openalex.org/W1837533151"],"abstract_inverted_index":{"We":[0,107,137],"present":[1],"an":[2],"approach":[3,110,141],"to":[4,22,65,119,144,153,165],"unsupervised":[5],"audio":[6,24,68,97,124],"representation":[7,69,93],"learning.":[8],"Based":[9],"on":[10,111],"a":[11,38,71],"Triplet":[12],"Neural":[13,74],"Network":[14,75],"architecture,":[15],"we":[16,32,44,79],"harnesses":[17],"semantically":[18],"related":[19],"cross-modal":[20],"information":[21,36],"estimate":[23],"track-relatedness.":[25],"By":[26,77],"applying":[27],"Latent":[28],"Semantic":[29],"Indexing":[30],"(LSI)":[31],"embed":[33],"corresponding":[34],"textual":[35],"into":[37],"latent":[39],"vector":[40,189],"space":[41,94],"from":[42,105],"which":[43],"derive":[45],"track":[46],"relatedness":[47],"for":[48],"online":[49],"triplet":[50],"selection.":[51],"This":[52],"LSI":[53],"topic":[54],"modeling":[55],"facilitates":[56],"fine-grained":[57],"selection":[58],"of":[59,85,95,147,157,168,185],"similar":[60],"and":[61,116],"dissimilar":[62],"audio-track":[63],"pairs":[64],"learn":[66],"the":[67,82,86,91,96,112,128,145,154,166,186],"using":[70],"Convolution":[72],"Recurrent":[73],"(CRNN).":[76],"this":[78,158,173],"directly":[80],"project":[81],"semantic":[83],"context":[84],"unstructured":[87],"text":[88],"modality":[89,98],"onto":[90],"learned":[92,161],"without":[99],"deriving":[100],"structured":[101],"ground":[102],"truth":[103],"annotations":[104],"it.":[106],"evaluate":[108],"our":[109,140],"Europeana":[113],"Sounds":[114],"collection":[115],"show":[117,138],"how":[118],"improve":[120],"search":[121],"in":[122,175],"digital":[123,135],"libraries":[125],"by":[126,132],"harnessing":[127],"multilingual":[129],"metadata":[130],"provided":[131],"numerous":[133],"European":[134],"libraries.":[136],"that":[139],"is":[142],"invariant":[143],"variety":[146],"annotation":[148],"styles":[149],"as":[150,152],"well":[151],"different":[155],"languages":[156],"collection.":[159],"The":[160],"representations":[162],"perform":[163],"comparable":[164],"baseline":[167,174],"handcrafted":[169],"features,":[170],"respectively":[171],"exceeding":[172],"similarity":[176],"retrieval":[177],"precision":[178],"at":[179],"higher":[180],"cut-offs":[181],"with":[182],"only":[183],"15%":[184],"baseline's":[187],"feature":[188],"length.":[190]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3015061299","counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2025-01-02T06:57:22.267047","created_date":"2020-04-10"}