{"id":"https://openalex.org/W4412376909","doi":"https://doi.org/10.1145/3726302.3730261","title":"Understanding Audio-Text Retrieval Through Singular Value Decomposition","display_name":"Understanding Audio-Text Retrieval Through Singular Value Decomposition","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376909","doi":"https://doi.org/10.1145/3726302.3730261"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730261","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730261","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020776717","display_name":"Yoori Oh","orcid":"https://orcid.org/0009-0002-2557-0934"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoori Oh","raw_affiliation_strings":["Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-2557-0934","affiliations":[{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027171928","display_name":"Yoseob Han","orcid":"https://orcid.org/0000-0002-0382-7826"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoseob Han","raw_affiliation_strings":["Department of Electronic Engineering, Soongsil University, Seoul, Republic of Korea and Department of Intelligent Semiconductors, Soongsil University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0382-7826","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Soongsil University, Seoul, Republic of Korea and Department of Intelligent Semiconductors, Soongsil University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joonhyeon Bae","orcid":"https://orcid.org/0009-0004-5417-7968"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonhyeon Bae","raw_affiliation_strings":["IPAI, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-5417-7968","affiliations":[{"raw_affiliation_string":"IPAI, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110024485","display_name":"Jae Sung Sim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeheon Sim","raw_affiliation_strings":["IPAI, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-3609-4259","affiliations":[{"raw_affiliation_string":"IPAI, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["IPAI, Seoul National University, Seoul, Republic of Korea, Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea, and AI Institute, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4210-0312","affiliations":[{"raw_affiliation_string":"IPAI, Seoul National University, Seoul, Republic of Korea, Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea, and AI Institute, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3085","last_page":"3089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9894000291824341,"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":0.983299970626831,"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/singular-value-decomposition","display_name":"Singular value decomposition","score":0.7689670324325562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6831005811691284},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5925735831260681},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5312597155570984},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49306556582450867},{"id":"https://openalex.org/keywords/singular-spectrum-analysis","display_name":"Singular spectrum analysis","score":0.418001651763916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3999089002609253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35534965991973877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3348398208618164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0660826563835144}],"concepts":[{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.7689670324325562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6831005811691284},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5925735831260681},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5312597155570984},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49306556582450867},{"id":"https://openalex.org/C136272165","wikidata":"https://www.wikidata.org/wiki/Q4048889","display_name":"Singular spectrum analysis","level":3,"score":0.418001651763916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3999089002609253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35534965991973877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3348398208618164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0660826563835144},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730261","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730261","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1451011034","display_name":null,"funder_award_id":"2021-II212068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3598079552","display_name":null,"funder_award_id":"RS-2021-II211343","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4709003234","display_name":null,"funder_award_id":"2022-0-00320","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6467365393","display_name":null,"funder_award_id":"2022-0-00320","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6789039607","display_name":null,"funder_award_id":"RS-2021-II211343","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7288789209","display_name":null,"funder_award_id":"RS-2021-II211343","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7575369263","display_name":null,"funder_award_id":"RS-2021-II212068","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7699972493","display_name":null,"funder_award_id":"RS-2021-II212068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7798134731","display_name":null,"funder_award_id":"RS-2021-II211343","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G8793268583","display_name":null,"funder_award_id":"RS-2022-II220320","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376909.pdf","grobid_xml":"https://content.openalex.org/works/W4412376909.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2069065514","https://openalex.org/W2750779823","https://openalex.org/W3015591594","https://openalex.org/W3035524453","https://openalex.org/W4210913346","https://openalex.org/W4224933373","https://openalex.org/W4372260310","https://openalex.org/W4372260330","https://openalex.org/W4384661029","https://openalex.org/W4396788598","https://openalex.org/W4400530533"],"related_works":["https://openalex.org/W2157839873","https://openalex.org/W1563281071","https://openalex.org/W4379468113","https://openalex.org/W1498350217","https://openalex.org/W3027946011","https://openalex.org/W2038393145","https://openalex.org/W1997246199","https://openalex.org/W2085555817","https://openalex.org/W2138650361","https://openalex.org/W239869582"],"abstract_inverted_index":{"Audio-language":[0],"retrieval":[1,54,165,193],"faces":[2],"a":[3,48,77,84,95,99],"fundamental":[4],"challenge":[5],"due":[6],"to":[7,15,25,33,73,143],"many-to-one":[8],"mappings,":[9],"where":[10],"multiple":[11],"audio":[12],"instances":[13],"correspond":[14],"the":[16,62,69,102,111,117,120,124,133,144,148],"same":[17],"or":[18],"similar":[19],"textual":[20],"descriptions.":[21],"This":[22],"ambiguity":[23,45],"leads":[24],"overlapping":[26],"representations,":[27],"making":[28],"it":[29],"difficult":[30],"for":[31,65],"models":[32],"learn":[34],"discriminative":[35],"features":[36],"between":[37],"samples.":[38],"Queue-based":[39],"contrastive":[40],"learning":[41],"helps":[42],"mitigate":[43],"this":[44,80],"by":[46],"maintaining":[47],"large":[49],"pool":[50],"of":[51,71,98,104,126],"negatives,":[52],"improving":[53],"performance.":[55,176],"However,":[56],"selecting":[57],"appropriate":[58],"hyperparameters,":[59],"such":[60],"as":[61,132],"queue":[63,100,118,169],"size":[64],"optimal":[66,138],"performance":[67,113,166,194],"and":[68,108,159],"number":[70],"epochs":[72],"prevent":[74],"overfitting,":[75],"remains":[76],"challenge.":[78],"In":[79],"study,":[81],"we":[82,92],"propose":[83],"LAtent":[85],"Space":[86],"Embedding":[87],"Rank":[88],"(LASER)":[89],"analysis.":[90],"Specifically,":[91],"analyze":[93],"that":[94,110,164,180],"low-rank":[96],"property":[97],"indicates":[101],"presence":[103],"informative":[105],"negative":[106],"samples,":[107],"demonstrate":[109],"best":[112],"is":[114],"achieved":[115],"when":[116],"has":[119],"lowest":[121],"rank.":[122],"Furthermore,":[123],"convergence":[125],"rank":[127],"variation":[128],"can":[129,151,184,191],"be":[130,152],"interpreted":[131],"model":[134,149],"parameters":[135],"reaching":[136],"an":[137],"state":[139],"during":[140],"training.":[141],"Thanks":[142],"proposed":[145],"rank-based":[146,189],"analysis,":[147],"hyperparameters":[150],"selected":[153],"analytically":[154],"rather":[155],"than":[156],"through":[157],"trial":[158],"error.":[160],"Experimental":[161],"results":[162],"confirm":[163],"depends":[167],"on":[168],"rank,":[170],"with":[171],"lower":[172],"ranks":[173],"yielding":[174],"better":[175],"These":[177],"findings":[178],"suggest":[179],"our":[181],"LASER":[182],"analysis":[183,190],"provide":[185],"insight":[186],"into":[187],"how":[188],"improve":[192],"in":[195],"audio-language":[196],"tasks.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
