{"id":"https://openalex.org/W7166820955","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1297","title":"The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models","display_name":"The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166820955","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1297"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1297","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1297","pdf_url":"https://aclanthology.org/2026.findings-acl.1297.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1297.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079028025","display_name":"Ruixing Zhang","orcid":"https://orcid.org/0000-0001-9414-6198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruixing Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838329","display_name":"Zihan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081275566","display_name":"Leilei Sun","orcid":"https://orcid.org/0000-0002-0157-1716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leilei Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784934","display_name":"Tongyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongyu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139799121","display_name":"Weifeng Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weifeng Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85764668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26045","last_page":"26065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8902000188827515,"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":0.8902000188827515,"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":0.029200000688433647,"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":0.01899999938905239,"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/sonar","display_name":"Sonar","score":0.6104999780654907},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/synthetic-aperture-sonar","display_name":"Synthetic aperture sonar","score":0.3278000056743622},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3197000026702881},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30140000581741333}],"concepts":[{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5958999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C181255713","wikidata":"https://www.wikidata.org/wiki/Q7662740","display_name":"Synthetic aperture sonar","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1297","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1297","pdf_url":"https://aclanthology.org/2026.findings-acl.1297.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1297","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1297","pdf_url":"https://aclanthology.org/2026.findings-acl.1297.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166820955.pdf","grobid_xml":"https://content.openalex.org/works/W7166820955.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Geo-localization":[0],"aims":[1],"to":[2,26],"infer":[3],"the":[4,38,50,75,81,132,135],"geographic":[5],"origin":[6],"of":[7,40,83,134],"a":[8,17,70,118,140],"given":[9],"signal.In":[10],"computer":[11],"vision,":[12],"geo-localization":[13,33,101,144],"has":[14,34],"served":[15],"as":[16,117],"demanding":[18],"benchmark":[19,54,141],"for":[20,55,120,142],"compositional":[21],"reasoning":[22,125,152],"and":[23,63,111,131,145],"is":[24],"relevant":[25],"public":[27],"safety.In":[28],"contrast,":[29],"progress":[30],"on":[31,91],"audio":[32,52,56,89,100,143],"been":[35],"constrained":[36],"by":[37],"lack":[39],"high-quality":[41],"audio-location":[42],"pairs.To":[43],"address":[44],"this":[45],"gap,":[46],"we":[47,73],"introduce":[48],"AGL1K,":[49],"first":[51],"geolocalization":[53],"language":[57],"models":[58,106],"(ALMs),":[59],"spanning":[60],"72":[61],"countries":[62],"territories.To":[64],"extract":[65],"reliably":[66],"localizable":[67],"samples":[68],"from":[69],"crowd-sourced":[71],"platform,":[72],"propose":[74],"Audio":[76],"Localizability":[77],"metric":[78],"that":[79,95,104,112],"quantifies":[80],"informativeness":[82],"each":[84],"recording,":[85],"yielding":[86],"1,444":[87],"curated":[88],"clips.Evaluations":[90],"16":[92],"ALMs":[93,96,124,148],"show":[94],"have":[97],"emerged":[98],"with":[99,149],"capability.We":[102],"find":[103],"closed-source":[105],"substantially":[107],"outperform":[108],"open-source":[109],"models,":[110],"linguistic":[113],"clues":[114],"often":[115],"dominate":[116],"scaffold":[119],"prediction.We":[121],"further":[122],"analyze":[123],"traces,":[126],"regional":[127],"bias,":[128],"error":[129],"causes,":[130],"interpretability":[133],"localizability":[136],"metric.Overall,":[137],"AGL1K":[138],"establishes":[139],"may":[146],"advance":[147],"better":[150],"geospatial":[151],"capability.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
