{"id":"https://openalex.org/W7148256809","doi":"https://doi.org/10.1109/asru65441.2025.11434746","title":"Geolocation-Aware Robust Spoken Language Identification","display_name":"Geolocation-Aware Robust Spoken Language Identification","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148256809","doi":"https://doi.org/10.1109/asru65441.2025.11434746"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025190934","display_name":"Q Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qingzheng Wang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800744","display_name":"Hye-jin Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hye-Jin Shim","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132758474","display_name":"Jiancheng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiancheng Sun","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132789061","display_name":"Shinji Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025190934"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92934972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.335999995470047,"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":0.335999995470047,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.219200000166893,"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/T12031","display_name":"Speech and dialogue systems","score":0.14159999787807465,"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/spoken-language","display_name":"Spoken language","score":0.4733000099658966},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.39309999346733093},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.36419999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6480000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5540000200271606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5309000015258789},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.39309999346733093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3230000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2031367292","https://openalex.org/W2739967986","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2890128119","https://openalex.org/W2928165649","https://openalex.org/W2933138175","https://openalex.org/W2962739339","https://openalex.org/W2962780374","https://openalex.org/W2969985801","https://openalex.org/W3015960524","https://openalex.org/W3024869864","https://openalex.org/W3119308075","https://openalex.org/W3139878283","https://openalex.org/W3139939832","https://openalex.org/W3162249256","https://openalex.org/W3197140813","https://openalex.org/W3197580070","https://openalex.org/W3213029956","https://openalex.org/W4292968575","https://openalex.org/W4296069321","https://openalex.org/W4319862635","https://openalex.org/W4372259817","https://openalex.org/W4385245566","https://openalex.org/W4385822693","https://openalex.org/W4385823368","https://openalex.org/W4401042974","https://openalex.org/W4402111799","https://openalex.org/W4402112192","https://openalex.org/W4402112198","https://openalex.org/W4404782746","https://openalex.org/W4415432973","https://openalex.org/W4415433449","https://openalex.org/W4415433462","https://openalex.org/W7131780627"],"related_works":[],"abstract_inverted_index":{"While":[0],"Self-supervised":[1],"Learning":[2],"(SSL)":[3],"has":[4],"significantly":[5],"improved":[6],"Spoken":[7],"Language":[8],"Identification":[9],"(LID),":[10],"existing":[11],"models":[12],"often":[13],"struggle":[14],"to":[15,76,97],"consistently":[16],"classify":[17],"dialects":[18],"and":[19,59,83,100,110],"accents":[20],"of":[21],"the":[22,46,61,74],"same":[23],"language":[24],"as":[25,55,67],"a":[26,37],"unified":[27,79],"class.":[28],"To":[29],"address":[30],"this":[31],"challenge,":[32],"we":[33,51],"propose":[34],"geolocation-aware":[35],"LID,":[36],"novel":[38],"approach":[39,94],"that":[40,92],"incorporates":[41],"language-level":[42],"geolocation":[43,53],"information":[44],"into":[45,64],"SSL-based":[47],"LID":[48],"model.":[49],"Specifically,":[50],"introduce":[52],"prediction":[54],"an":[56],"auxiliary":[57],"task":[58],"inject":[60],"predicted":[62],"vectors":[63],"intermediate":[65],"representations":[66,80],"conditioning":[68,72],"signals.":[69],"This":[70],"explicit":[71],"encourages":[73],"model":[75],"learn":[77],"more":[78],"for":[81],"dialectal":[82],"accented":[84],"variations.":[85],"Experiments":[86],"across":[87],"six":[88],"multilingual":[89],"datasets":[90],"demonstrate":[91],"our":[93],"improves":[95],"robustness":[96],"intra-language":[98],"variations":[99],"unseen":[101],"domains,":[102],"achieving":[103],"new":[104],"state-of-the-art":[105],"accuracy":[106],"on":[107,114],"FLEURS":[108],"(97.7%)":[109],"9.7%":[111],"relative":[112],"improvement":[113],"ML-SUPERB":[115],"2.0":[116],"dialect":[117],"set.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}