{"id":"https://openalex.org/W7148583375","doi":"https://doi.org/10.1109/asru65441.2025.11434773","title":"A Momentum-Based Framework with Contrastive Data Generation for Robust Sound Source Localization","display_name":"A Momentum-Based Framework with Contrastive Data Generation for Robust Sound Source Localization","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148583375","doi":"https://doi.org/10.1109/asru65441.2025.11434773"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434773","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/A5100441147","display_name":"Hyunsoo Kim","orcid":"https://orcid.org/0000-0002-5194-0372"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyun-Soo Kim","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132799529","display_name":"Da-Hee Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Da-Hee Yang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132816791","display_name":"Joon-Hyuk Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100441147"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85908067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10860","display_name":"Speech and Audio Processing","score":0.7214999794960022,"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/T10860","display_name":"Speech and Audio Processing","score":0.7214999794960022,"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/T11008","display_name":"Aerodynamics and Acoustics in Jet Flows","score":0.12099999934434891,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.02850000001490116,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33959999680519104},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3328000009059906},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.275299996137619},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.27230000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.511900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5015000104904175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.24979999661445618}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434773","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/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1555217905","https://openalex.org/W2046317813","https://openalex.org/W2096733369","https://openalex.org/W2113638573","https://openalex.org/W2128977628","https://openalex.org/W2147665979","https://openalex.org/W2885219692","https://openalex.org/W2898268964","https://openalex.org/W2962869940","https://openalex.org/W2964342924","https://openalex.org/W2973133192","https://openalex.org/W3034751264","https://openalex.org/W3035524453","https://openalex.org/W3129910207","https://openalex.org/W3167256084","https://openalex.org/W4283642889","https://openalex.org/W4385822301","https://openalex.org/W4385823271","https://openalex.org/W4392904318","https://openalex.org/W4404577061","https://openalex.org/W4415432610","https://openalex.org/W7133218909"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"MoCo-SSL,":[2],"a":[3,67],"momentum-based":[4],"contrastive":[5,25],"learning":[6,26,44,113],"framework":[7],"for":[8],"multi-channel":[9],"sound":[10],"source":[11],"localization":[12],"(SSL)":[13],"that":[14,70,100],"enhances":[15],"azimuth-aware":[16],"representation":[17,112],"learning.":[18],"While":[19],"prior":[20],"SSL":[21,116],"studies":[22],"have":[23],"used":[24],"to":[27,58,85],"handle":[28],"varied":[29],"acoustic":[30],"conditions,":[31],"we":[32],"emphasize":[33],"hard":[34],"negatives-pairs":[35],"with":[36,80],"distinct":[37],"azimuths":[38],"recorded":[39],"in":[40,114],"the":[41,53,92,106],"same":[42],"room-for":[43],"fine-grained":[45],"spatial":[46],"cues.":[47],"A":[48],"curriculum-based":[49],"strategy":[50],"gradually":[51],"increases":[52],"proportion":[54],"of":[55,108],"such":[56],"samples":[57],"raise":[59],"task":[60],"difficulty.":[61],"The":[62],"momentum":[63],"contrast":[64],"design":[65],"employs":[66],"key":[68],"encoder":[69,94],"maintains":[71],"stable":[72],"embeddings":[73],"during":[74],"curriculum":[75],"transitions":[76],"and":[77,83,110],"receives":[78],"audio":[79],"less":[81],"noise":[82],"reverberation":[84],"produce":[86],"clearer":[87],"azimuth":[88],"cues,":[89],"thereby":[90],"guiding":[91],"query":[93],"toward":[95],"robust":[96],"representations.":[97],"Experiments":[98],"show":[99],"MoCo-SSL":[101],"consistently":[102],"surpasses":[103],"baselines,":[104],"demonstrating":[105],"value":[107],"structured":[109],"noise-resilient":[111],"challenging":[115],"scenarios.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}