{"id":"https://openalex.org/W4386764032","doi":"https://doi.org/10.1109/waspaa58266.2023.10248194","title":"Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions","display_name":"Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764032","doi":"https://doi.org/10.1109/waspaa58266.2023.10248194"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5114082621","display_name":"Saksham Singh Kushwaha","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saksham Singh Kushwaha","raw_affiliation_strings":["New York University,Courant Institute of Mathematical Sciences,NY,USA","Music and Audio Research Lab, New York University, NY, USA","Courant Institute of Mathematical Sciences, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Courant Institute of Mathematical Sciences,NY,USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Lab, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Courant Institute of Mathematical Sciences, New York University, NY, USA","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027526258","display_name":"Iran R. Roman","orcid":"https://orcid.org/0000-0003-3781-7244"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iran R. Roman","raw_affiliation_strings":["New York University,Music and Audio Research Lab,NY,USA","Music and Audio Research Lab, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Lab,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Lab, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["New York University,Music and Audio Research Lab,NY,USA","Integrated Design and Media, New York University, NY, USA","Music and Audio Research Lab, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Lab,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Integrated Design and Media, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Lab, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["New York University,Music and Audio Research Lab,NY,USA","Music and Audio Research Lab, New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Lab,NY,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Lab, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114082621"],"corresponding_institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":3.0498,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92614383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9969000220298767,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reverberation","display_name":"Reverberation","score":0.7282001376152039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7152160406112671},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.6786321401596069},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5972470641136169},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.575440526008606},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5477662086486816},{"id":"https://openalex.org/keywords/critical-distance","display_name":"Critical distance","score":0.4891379177570343},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.43270260095596313},{"id":"https://openalex.org/keywords/inverse-method","display_name":"Inverse method","score":0.4159155488014221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39216747879981995},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.22550207376480103},{"id":"https://openalex.org/keywords/sound-power","display_name":"Sound power","score":0.16078096628189087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13970845937728882},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1371336281299591},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07887879014015198}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7282001376152039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152160406112671},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.6786321401596069},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5972470641136169},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.575440526008606},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5477662086486816},{"id":"https://openalex.org/C24723263","wikidata":"https://www.wikidata.org/wiki/Q1571884","display_name":"Critical distance","level":4,"score":0.4891379177570343},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.43270260095596313},{"id":"https://openalex.org/C2983319462","wikidata":"https://www.wikidata.org/wiki/Q15948129","display_name":"Inverse method","level":2,"score":0.4159155488014221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39216747879981995},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.22550207376480103},{"id":"https://openalex.org/C67514181","wikidata":"https://www.wikidata.org/wiki/Q1588477","display_name":"Sound power","level":3,"score":0.16078096628189087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13970845937728882},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1371336281299591},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07887879014015198},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/102555","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/102555","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1967178846","https://openalex.org/W1997836753","https://openalex.org/W2091570515","https://openalex.org/W2113744809","https://openalex.org/W2133923349","https://openalex.org/W2135131618","https://openalex.org/W2403149086","https://openalex.org/W2509978695","https://openalex.org/W2810934215","https://openalex.org/W2972079735","https://openalex.org/W2995166308","https://openalex.org/W3021261768","https://openalex.org/W3092796334","https://openalex.org/W3102937397","https://openalex.org/W3108332675","https://openalex.org/W3142940959","https://openalex.org/W3162883221","https://openalex.org/W3197097128","https://openalex.org/W3203177955","https://openalex.org/W3206162458","https://openalex.org/W3206329344","https://openalex.org/W3210404408","https://openalex.org/W4313166297","https://openalex.org/W4324116353","https://openalex.org/W4393895215","https://openalex.org/W6771647114","https://openalex.org/W6784139575","https://openalex.org/W6802857102","https://openalex.org/W6803085933","https://openalex.org/W6863185053","https://openalex.org/W6924973070"],"related_works":["https://openalex.org/W1526330681","https://openalex.org/W2436875717","https://openalex.org/W1010438288","https://openalex.org/W1974198704","https://openalex.org/W4318566916","https://openalex.org/W4295835854","https://openalex.org/W4389061197","https://openalex.org/W2080359834","https://openalex.org/W4389110137","https://openalex.org/W3121690864"],"abstract_inverted_index":{"Localizing":[0],"a":[1,18,45,71,89,99,115],"moving":[2,79],"sound":[3,46,80,102,127,139],"source":[4,103,128,140],"in":[5,21,39,66],"the":[6,76,126,134],"real":[7],"world":[8],"involves":[9],"determining":[10],"its":[11],"direction-of-arrival":[12],"(DOA)":[13],"and":[14,105],"distance":[15,48,77,104,141],"relative":[16],"to":[17,58,64,74,136],"microphone.":[19],"Advancements":[20],"DOA":[22],"estimation":[23,142],"have":[24],"been":[25],"facilitated":[26],"by":[27,55],"data-driven":[28],"methods":[29,60],"optimized":[30],"with":[31,35],"large":[32],"open-source":[33],"datasets":[34,84],"microphone":[36],"array":[37],"recordings":[38,54],"diverse":[40,86,147],"environments.":[41],"In":[42],"contrast,":[43],"estimating":[44],"source\u2019s":[47],"remains":[49],"understudied.":[50],"Existing":[51],"approaches":[52],"assume":[53],"non-coincident":[56],"microphones":[57],"use":[59],"that":[61,117,138],"are":[62],"susceptible":[63],"differences":[65],"room":[67],"reverberation.":[68],"We":[69,92],"present":[70],"CRNN":[72],"able":[73],"estimate":[75],"of":[78,101,125],"sources":[81],"across":[82,146],"multiple":[83],"featuring":[85],"rooms,":[87],"outperforming":[88],"recently-published":[90],"approach.":[91],"also":[93],"characterize":[94],"our":[95],"model\u2019s":[96],"performance":[97],"as":[98,121],"function":[100,124],"different":[106],"training":[107,113],"losses.":[108],"This":[109],"analysis":[110],"reveals":[111],"optimal":[112],"using":[114,150],"loss":[116],"weighs":[118],"model":[119],"errors":[120],"an":[122],"inverse":[123],"true":[129],"distance.":[130],"Our":[131],"study":[132],"is":[133],"first":[135],"demonstrate":[137],"can":[143],"be":[144],"performed":[145],"acoustic":[148],"conditions":[149],"deep":[151],"learning.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}