{"id":"https://openalex.org/W4407129263","doi":"https://doi.org/10.1109/cbmi62980.2024.10859250","title":"Evaluation of Deep Audio Representations for Semantic Sound Similarity","display_name":"Evaluation of Deep Audio Representations for Semantic Sound Similarity","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4407129263","doi":"https://doi.org/10.1109/cbmi62980.2024.10859250"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi62980.2024.10859250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/34c3e905-c1ac-462f-b4ed-80b5663502c2/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081395357","display_name":"R. Oguz Araz","orcid":"https://orcid.org/0000-0002-8456-0990"},"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":"Recep Oguz Araz","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004451369","display_name":"Dmitry Bogdanov","orcid":"https://orcid.org/0000-0002-9469-0633"},"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":"Dmitry Bogdanov","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085164793","display_name":"Pablo Alonso-Jim\u00e9nez","orcid":"https://orcid.org/0000-0002-4121-5089"},"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":"Pablo Alonso-Jim\u00e9nez","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072565954","display_name":"Frederic Font","orcid":"https://orcid.org/0000-0002-4360-3210"},"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":"Frederic Font","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.8349,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75281129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9886999726295471,"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":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.7141771912574768},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6100320219993591},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5788448452949524},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5716068744659424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4531266689300537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40834659337997437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3912135362625122},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13626128435134888},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06716233491897583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141771912574768},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6100320219993591},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5788448452949524},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5716068744659424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4531266689300537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40834659337997437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912135362625122},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13626128435134888},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06716233491897583},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cbmi62980.2024.10859250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/69722","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/69722","pdf_url":"https://repositori.upf.edu/bitstreams/34c3e905-c1ac-462f-b4ed-80b5663502c2/download","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositori-api.upf.edu:10230/69722","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/69722","pdf_url":"https://repositori.upf.edu/bitstreams/34c3e905-c1ac-462f-b4ed-80b5663502c2/download","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407129263.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1990014053","https://openalex.org/W2010486494","https://openalex.org/W2023934785","https://openalex.org/W2046345433","https://openalex.org/W2074188409","https://openalex.org/W2112861900","https://openalex.org/W2137637927","https://openalex.org/W2138666690","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2939574508","https://openalex.org/W2964287480","https://openalex.org/W2999442255","https://openalex.org/W3015371781","https://openalex.org/W3015419319","https://openalex.org/W3094550259","https://openalex.org/W3176445421","https://openalex.org/W3196974791","https://openalex.org/W3201065055","https://openalex.org/W4205689591","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4372260310","https://openalex.org/W4372260340","https://openalex.org/W4372266552","https://openalex.org/W4386071707","https://openalex.org/W4392903801","https://openalex.org/W6779191341","https://openalex.org/W6791353385","https://openalex.org/W6845577938","https://openalex.org/W6848208918","https://openalex.org/W6852818750"],"related_works":["https://openalex.org/W4376653378","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W4385239468","https://openalex.org/W4200476258","https://openalex.org/W2022470916","https://openalex.org/W3201962287","https://openalex.org/W3002840018"],"abstract_inverted_index":{"Navigating":[0],"large":[1],"audio":[2,38,56,61,132,147],"collections":[3],"presents":[4],"a":[5,29,71,140],"significant":[6,141],"challenge":[7],"due":[8],"to":[9,40,188],"the":[10,17,42,49,64,79,90,128,152,156,163,167],"intricate":[11],"nature":[12],"of":[13,20,37,44,52,74,81],"sound":[14,30,66,101,115,118,157,169],"properties":[15],"and":[16,58,86,117,133,148,180],"varied":[18],"needs":[19],"users.":[21],"To":[22],"enhance":[23],"user":[24],"experience,":[25],"audio-sharing":[26],"platforms":[27],"offer":[28],"similarity":[31,67,102,170,181],"function,":[32],"which":[33,143],"leverages":[34],"vector-based":[35],"representations":[36],"clips":[39],"facilitate":[41],"retrieval":[43,50,190],"sounds.":[45],"This":[46],"study":[47],"evaluates":[48],"performances":[51],"one":[53],"manually":[54],"engineered":[55],"representation":[57],"thirteen":[59],"deep":[60],"embeddings":[62,99],"in":[63,144,176],"semantic":[65,168],"task.":[68,171],"By":[69],"employing":[70],"diverse":[72],"range":[73],"models,":[75],"our":[76,174],"research":[77],"investigates":[78],"effects":[80],"utilizing":[82],"different":[83,193],"input":[84],"modalities":[85,135],"training":[87],"objectives.":[88],"In":[89,172],"process,":[91],"we":[92],"explore":[93],"various":[94],"design":[95],"choices":[96],"for":[97],"integrating":[98],"into":[100],"systems.":[103],"Our":[104],"evaluation":[105],"is":[106],"based":[107],"on":[108,155,166],"objective":[109],"ranked":[110],"performance":[111],"metrics":[112],"that":[113,127],"incorporate":[114],"classes":[116],"families,":[119],"complemented":[120],"by":[121,139],"preliminary":[122],"subjective":[123],"assessments.":[124],"We":[125],"observe":[126],"multimodal":[129],"models":[130,138,154,165],"using":[131],"language":[134],"outperform":[136,146],"audio-only":[137],"margin,":[142],"turn":[145],"image":[149],"models.":[150],"Notably,":[151],"state-of-the-art":[153],"event":[158],"classification":[159],"task":[160],"are":[161],"not":[162],"topperforming":[164],"addition,":[173],"findings":[175],"embedding":[177],"processing":[178],"methods":[179],"search":[182],"functions":[183],"provide":[184],"insights":[185],"broadly":[186],"applicable":[187],"information":[189],"systems":[191],"across":[192],"modalities.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}