{"id":"https://openalex.org/W4408354300","doi":"https://doi.org/10.1109/icassp49660.2025.10888141","title":"Sound Source Distance Estimation Utilizing Physics-informed Prior for Sound Event Localization and Detection","display_name":"Sound Source Distance Estimation Utilizing Physics-informed Prior for Sound Event Localization and Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354300","doi":"https://doi.org/10.1109/icassp49660.2025.10888141"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111367164","display_name":"Nao Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nao Sato","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":6.0313,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96251701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/sound","display_name":"Sound (geography)","score":0.7544742822647095},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.6299406886100769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5930272936820984},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5780532360076904},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5509926676750183},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4629076421260834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36172711849212646},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3387773036956787},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.172740638256073}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7544742822647095},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.6299406886100769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5930272936820984},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5780532360076904},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5509926676750183},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4629076421260834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36172711849212646},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3387773036956787},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.172740638256073},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W1967178846","https://openalex.org/W2099973374","https://openalex.org/W2109689830","https://openalex.org/W2133923349","https://openalex.org/W2135131618","https://openalex.org/W2162607306","https://openalex.org/W2410879554","https://openalex.org/W2810934215","https://openalex.org/W2902440533","https://openalex.org/W2917254586","https://openalex.org/W3016037102","https://openalex.org/W3202438156","https://openalex.org/W3202467894","https://openalex.org/W3206329344","https://openalex.org/W4386764032","https://openalex.org/W4387146007","https://openalex.org/W4392904420","https://openalex.org/W4396753614","https://openalex.org/W4404577061","https://openalex.org/W6687054275","https://openalex.org/W6853532597","https://openalex.org/W6869931805","https://openalex.org/W6948136411"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Sound":[0,22],"Event":[1],"Localization":[2],"and":[3,14],"Detection":[4],"(SELD)":[5],"is":[6,106],"the":[7,72,79,85,108,119,146,149,156,161,165,181,199,215],"combined":[8],"task":[9],"of":[10,39,74,81,87,104,148,155,201],"detecting":[11],"sound":[12,48,112,151,157,182],"events":[13],"estimating":[15],"their":[16],"spatial":[17],"locations.":[18],"We":[19],"propose":[20,129],"a":[21,32,130,136,140,172,186,203],"source":[23],"Distance":[24],"Estimation":[25],"(SDE)":[26],"method":[27,133],"for":[28,41,71,168,189,208],"SELD":[29,42,61,83,142,209],"that":[30,107,114,134],"utilizes":[31,135],"physics-informed":[33,137,187,204],"prior.":[34,173],"The":[35],"conventional":[36],"data-driven":[37,141],"approach":[38],"SDE":[40,132,207],"can":[43],"handle":[44],"complex":[45],"situations":[46],"where":[47],"sources":[49,158],"move":[50],"or":[51],"overlap,":[52],"thanks":[53],"to":[54,69,210,214],"multitask":[55],"learning.":[56],"Deep":[57],"Neural":[58],"Network":[59],"(DNN)-based":[60],"systems":[62],"are":[63,91,123],"generally":[64],"pre-trained":[65,92],"with":[66,93],"synthesized":[67],"data":[68],"compensate":[70],"lack":[73],"real":[75,99,120,216],"data.":[76,100],"However,":[77],"in":[78,118,139,194,206],"context":[80],"recent":[82],"tasks,":[84],"performance":[86],"DNN":[88,109],"models,":[89],"which":[90],"synthetic":[94],"data,":[95,121],"significantly":[96],"degrades":[97],"on":[98,145,160],"One":[101],"possible":[102],"cause":[103],"this":[105],"models":[110],"overfit":[111],"characteristics":[113],"do":[115],"not":[116,124],"exist":[117],"i.e.,":[122],"physically":[125],"reasonable.":[126],"Therefore,":[127],"we":[128,163,178],"hybrid":[131],"prior":[138,188,205],"system.":[143],"Focusing":[144],"specificity":[147],"expected":[150],"PoWer":[152],"Level":[153],"(PWL)":[154],"depending":[159],"class,":[162],"set":[164],"typical":[166],"PWL":[167],"each":[169],"class":[170],"as":[171,185],"To":[174],"improve":[175,211],"real-world":[176],"applicability,":[177],"also":[179],"adopt":[180],"attenuation":[183],"model":[184],"explicitly":[190],"utilizing":[191,202],"physical":[192],"laws":[193],"SDE.":[195],"Experimental":[196],"results":[197],"suggested":[198],"effectiveness":[200],"its":[212],"applicability":[213],"world.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}