{"id":"https://openalex.org/W7161287605","doi":"https://doi.org/10.1145/3805712.3808600","title":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","display_name":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7161287605","doi":"https://doi.org/10.1145/3805712.3808600"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808600","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808600","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123315060","display_name":"Yuejie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuejie Li","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-4058-5123","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136224096","display_name":"Ke Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ke Yang","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0004-4527-9292","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113391956","display_name":"Yueying Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueying Hua","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-4456-6008","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136237095","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolin Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-7311-2918","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126157392","display_name":"Jianhao Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhao Nie","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0004-5561-6635","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126122663","display_name":"Yueping He","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueping He","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0775-9549","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048132729","display_name":"Caixin Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Caixin Kang","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0001-1924-9311","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3276","last_page":"3283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7960000038146973,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7960000038146973,"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/T11309","display_name":"Music and Audio Processing","score":0.03449999913573265,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.027000000700354576,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/robustness","display_name":"Robustness (evolution)","score":0.8474000096321106},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5960000157356262},{"id":"https://openalex.org/keywords/quiet","display_name":"QUIET","score":0.46939998865127563},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.45840001106262207},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4417000114917755},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8474000096321106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878000140190125},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090999960899353},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3822999894618988},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3808600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808600","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.12783","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.12783","pdf_url":"https://arxiv.org/pdf/2602.12783","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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808600","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spoken":[0],"query":[1,35,54,86,185],"retrieval":[2,36,55,79,133,139,153],"is":[3],"an":[4],"important":[5],"interaction":[6],"mode":[7],"in":[8,183],"modern":[9],"information":[10],"retrieval.":[11,188],"However,":[12],"existing":[13],"evaluation":[14,64,113],"datasets":[15],"are":[16],"often":[17],"limited":[18],"to":[19,116,186],"simple":[20],"queries":[21,70],"under":[22,38,106,156],"constrained":[23],"noise":[24,105,143],"conditions,":[25],"making":[26],"them":[27],"inadequate":[28],"for":[29,52,172],"assessing":[30],"the":[31,121],"robustness":[32,50,112,161,182],"of":[33,102],"spoken":[34,53,184],"systems":[37],"complex":[39],"acoustic":[40],"perturbations.":[41],"To":[42],"address":[43],"this":[44],"limitation,":[45],"we":[46,124],"present":[47],"SQuTR,":[48],"a":[49,58,62,163,169],"benchmark":[51],"that":[56,138,160],"includes":[57],"large-scale":[59,126,152],"dataset":[60],"and":[61,76,84,98,131,174,177],"unified":[63,122],"protocol.":[65],"SQuTR":[66,167],"aggregates":[67],"37,317":[68],"unique":[69],"from":[71,94,114],"six":[72],"commonly":[73],"used":[74],"English":[75],"Chinese":[77],"text":[78,187],"datasets,":[80],"spanning":[81],"multiple":[82],"domains":[83],"diverse":[85],"types.":[87],"We":[88],"synthesize":[89],"speech":[90],"using":[91],"voice":[92],"profiles":[93],"200":[95],"real":[96],"speakers":[97],"mix":[99],"17":[100],"categories":[101],"real-world":[103],"environmental":[104],"controlled":[107],"SNR":[108],"levels,":[109],"enabling":[110],"reproducible":[111,170],"quiet":[115],"highly":[117],"noisy":[118],"conditions.":[119],"Under":[120],"protocol,":[123],"conduct":[125],"evaluations":[127],"on":[128,181],"representative":[129],"cascaded":[130],"end-to-end":[132],"systems.":[134,150],"Experimental":[135],"results":[136],"show":[137],"performance":[140],"decreases":[141],"as":[142],"increases,":[144],"with":[145],"substantially":[146],"different":[147],"drops":[148],"across":[149],"Even":[151],"models":[154],"struggle":[155],"extreme":[157],"noise,":[158],"indicating":[159],"remains":[162],"critical":[164],"bottleneck.":[165],"Overall,":[166],"provides":[168],"testbed":[171],"benchmarking":[173],"diagnostic":[175],"analysis,":[176],"facilitates":[178],"future":[179],"research":[180]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-05-16T00:00:00"}