{"id":"https://openalex.org/W4224919399","doi":"https://doi.org/10.1109/icassp43922.2022.9747604","title":"Locate This, Not that: Class-Conditioned Sound Event DOA Estimation","display_name":"Locate This, Not that: Class-Conditioned Sound Event DOA Estimation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919399","doi":"https://doi.org/10.1109/icassp43922.2022.9747604"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747604","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5061474153","display_name":"Olga Slizovskaia","orcid":"https://orcid.org/0000-0003-3118-5143"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Olga Slizovskaia","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061474153"],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":0.9819,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75987362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"711","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.6947882175445557},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6446643471717834},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5553476214408875},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4861873984336853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4819790720939636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4556882083415985},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44433894753456116},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4382932782173157},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.41687291860580444},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06799697875976562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947882175445557},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6446643471717834},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5553476214408875},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4861873984336853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4819790720939636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4556882083415985},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44433894753456116},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4382932782173157},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.41687291860580444},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06799697875976562},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747604","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2001571181","https://openalex.org/W2810934215","https://openalex.org/W2879390606","https://openalex.org/W2891833136","https://openalex.org/W2954304925","https://openalex.org/W2962753171","https://openalex.org/W2969034647","https://openalex.org/W2973062255","https://openalex.org/W2991107219","https://openalex.org/W2998139081","https://openalex.org/W3011429851","https://openalex.org/W3015201698","https://openalex.org/W3015205011","https://openalex.org/W3016037102","https://openalex.org/W3021261768","https://openalex.org/W3083274258","https://openalex.org/W3095263845","https://openalex.org/W3102937397","https://openalex.org/W3117314925","https://openalex.org/W3120252178","https://openalex.org/W3163193264","https://openalex.org/W3176079376","https://openalex.org/W3197097128","https://openalex.org/W4287120192","https://openalex.org/W4393783540","https://openalex.org/W6766938422","https://openalex.org/W6775715781","https://openalex.org/W6788349323","https://openalex.org/W6796679619","https://openalex.org/W6800971888","https://openalex.org/W6802746035"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2056769785","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Existing":[0],"systems":[1],"for":[2,16,33],"sound":[3,63],"event":[4],"localization":[5],"and":[6,58,65,130,171],"detection":[7],"(SELD)":[8],"typically":[9],"operate":[10],"by":[11],"estimating":[12],"a":[13,67,141],"source":[14],"location":[15],"all":[17,43,45,127],"classes":[18,44,128,164],"at":[19,84],"every":[20],"time":[21],"instant.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,36,73,105,165],"propose":[27],"an":[28],"alternative":[29],"class-conditioned":[30,50,110,178],"SELD":[31,51,111,119],"model":[32,52,89,112,124],"situations":[34],"where":[35],"may":[37],"not":[38,167],"be":[39],"interested":[40,76,168],"in":[41,77,87,115,169],"localizing":[42],"of":[46,117,144],"the":[47,56,62,71,81,99,108,122,151,177],"time.":[48],"This":[49],"takes":[53],"as":[54],"input":[55],"spatial":[57],"spectral":[59],"features":[60],"from":[61,163,176],"file,":[64],"also":[66,131,147],"one-hot":[68],"vector":[69],"indicating":[70],"class":[72,143],"are":[74,136,166],"currently":[75],"localizing.":[78],"We":[79,146],"inject":[80],"conditioning":[82],"information":[83],"several":[85],"points":[86],"our":[88],"using":[90],"feature-wise":[91],"linear":[92],"modulation":[93],"(FiLM)":[94],"layers.":[95],"Through":[96],"experiments":[97],"on":[98,150],"DCASE":[100,152],"2020":[101],"Task":[102,154],"3":[103,155],"dataset,":[104,156],"show":[106],"that":[107,125,135],"proposed":[109],"performs":[113],"better":[114],"terms":[116],"common":[118],"metrics":[120],"than":[121],"baseline":[123],"locates":[126],"simultaneously,":[129],"outperforms":[132],"specialist":[133],"models":[134],"trained":[137],"to":[138],"locate":[139],"only":[140],"single":[142],"interest.":[145],"evaluate":[148],"performance":[149],"2021":[153],"which":[157],"includes":[158],"directional":[159],"interference":[160],"(sound":[161],"events":[162],"localizing)":[170],"notice":[172],"especially":[173],"strong":[174],"improvement":[175],"model.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}