{"id":"https://openalex.org/W4372259983","doi":"https://doi.org/10.1109/icassp49357.2023.10094617","title":"Data Leakage in Cross-Modal Retrieval Training: A Case Study","display_name":"Data Leakage in Cross-Modal Retrieval Training: A Case Study","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259983","doi":"https://doi.org/10.1109/icassp49357.2023.10094617"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094617","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/c3b54931-6e48-441b-b80b-9af3d8c6031d/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038446032","display_name":"Benno Weck","orcid":"https://orcid.org/0000-0002-5760-6922"},"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"]},{"id":"https://openalex.org/I4210129353","display_name":"Huawei Technologies (Germany)","ror":"https://ror.org/038cdme44","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353"]}],"countries":["DE","ES"],"is_corresponding":false,"raw_author_name":"Benno Weck","raw_affiliation_strings":["Huawei Technologies, Munich Research Center,Germany","Huawei Technologies, Munich Research Center, Germany","Universitat Pompeu Fabra, Music Technology Group, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies, Munich Research Center,Germany","institution_ids":["https://openalex.org/I4210129353"]},{"raw_affiliation_string":"Huawei Technologies, Munich Research Center, Germany","institution_ids":["https://openalex.org/I4210129353"]},{"raw_affiliation_string":"Universitat Pompeu Fabra, Music Technology Group, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"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":["Universitat Pompeu Fabra, Music Technology Group,Spain","Universitat Pompeu Fabra, Music Technology Group, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra, Music Technology Group,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":1.2083,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80060918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9958999752998352,"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":0.9926999807357788,"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":0.855652928352356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7465065717697144},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5253880620002747},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5167497992515564},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4764542877674103},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.4583129584789276},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.44598543643951416},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4365631639957428},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4304877519607544},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4277113676071167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36181145906448364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2996863126754761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855652928352356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7465065717697144},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5253880620002747},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5167497992515564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4764542877674103},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.4583129584789276},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.44598543643951416},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4365631639957428},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4304877519607544},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4277113676071167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36181145906448364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2996863126754761},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094617","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/70563","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/70563","pdf_url":"https://repositori.upf.edu/bitstreams/c3b54931-6e48-441b-b80b-9af3d8c6031d/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:10230/70563","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/70563","pdf_url":"https://repositori.upf.edu/bitstreams/c3b54931-6e48-441b-b80b-9af3d8c6031d/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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372259983.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2033875152","https://openalex.org/W2144346840","https://openalex.org/W2159540918","https://openalex.org/W2736287575","https://openalex.org/W2768580362","https://openalex.org/W2965373594","https://openalex.org/W2965458216","https://openalex.org/W2978017171","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W4205689591","https://openalex.org/W4210913346","https://openalex.org/W4221157007","https://openalex.org/W4304192851","https://openalex.org/W4308947931","https://openalex.org/W6766582784","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6850088200"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W2392693164","https://openalex.org/W2037239642","https://openalex.org/W1509924131","https://openalex.org/W4287241967","https://openalex.org/W3144173820","https://openalex.org/W209733029"],"abstract_inverted_index":{"The":[0],"recent":[1],"progress":[2],"in":[3,91],"text-based":[4],"audio":[5,120],"retrieval":[6,88],"was":[7,50],"largely":[8],"propelled":[9],"by":[10],"the":[11,17,43,54,77,103,115,133],"release":[12],"of":[13,20,73,114],"suitable":[14],"datasets.":[15,40],"Since":[16],"manual":[18],"creation":[19],"such":[21],"datasets":[22],"is":[23],"a":[24,34,138],"laborious":[25],"task,":[26],"obtaining":[27],"data":[28,75,81],"from":[29,53],"online":[30],"resources":[31],"can":[32],"be":[33],"cheap":[35],"solution":[36],"to":[37,76,85],"create":[38],"large-scale":[39],"We":[41,94],"study":[42],"recently":[44],"proposed":[45],"SoundDesc":[46,66],"benchmark":[47],"dataset,":[48],"which":[49],"automatically":[51],"sourced":[52],"BBC":[55],"Sound":[56],"Effects":[57],"web":[58],"page.":[59],"In":[60,127],"our":[61,128],"analysis,":[62],"we":[63,106,118,130],"find":[64,131],"that":[65,70,105,122,132],"contains":[67],"several":[68],"duplicates":[69],"cause":[71],"leakage":[72,82],"training":[74],"evaluation":[78],"data.":[79],"This":[80],"ultimately":[83],"leads":[84],"overly":[86],"optimistic":[87],"performance":[89],"estimates":[90],"previous":[92],"benchmarks.":[93],"propose":[95],"new":[96,134],"training,":[97],"validation,":[98],"and":[99],"testing":[100],"splits":[101,135],"for":[102],"dataset":[104],"make":[107],"available":[108],"online.":[109],"To":[110],"avoid":[111],"weak":[112],"contamination":[113],"test":[116],"data,":[117],"pool":[119],"files":[121],"share":[123],"similar":[124],"recording":[125],"setups.":[126],"experiments,":[129],"serve":[136],"as":[137],"more":[139],"challenging":[140],"benchmark.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}