{"id":"https://openalex.org/W3210808295","doi":"https://doi.org/10.1109/waspaa52581.2021.9632773","title":"Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers","display_name":"Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3210808295","doi":"https://doi.org/10.1109/waspaa52581.2021.9632773","mag":"3210808295"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5054490307","display_name":"Sharath Adavanne","orcid":"https://orcid.org/0000-0002-5001-6911"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Sharath Adavanne","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054490307"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":2.1603,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88493682,"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":"211","last_page":"215"},"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":0.9993000030517578,"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":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.7851061820983887},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.582999587059021},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5630621910095215},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5599920749664307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5368417501449585},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5304567217826843},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4800468683242798},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4767640233039856},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4492458701133728},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4352874755859375},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4114535450935364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4090186357498169},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.382180392742157},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.366775780916214},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.23382335901260376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10661879181861877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851061820983887},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.582999587059021},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5630621910095215},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5599920749664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5368417501449585},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5304567217826843},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4800468683242798},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4767640233039856},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4492458701133728},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4352874755859375},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4114535450935364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4090186357498169},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382180392742157},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.366775780916214},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.23382335901260376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10661879181861877},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/220447","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/220447","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1515932869","https://openalex.org/W1555217905","https://openalex.org/W1557595030","https://openalex.org/W1603075283","https://openalex.org/W2124781496","https://openalex.org/W2126885789","https://openalex.org/W2135131618","https://openalex.org/W2222512263","https://openalex.org/W2551990143","https://openalex.org/W2761044439","https://openalex.org/W2810934215","https://openalex.org/W2885219692","https://openalex.org/W2897977894","https://openalex.org/W2917254586","https://openalex.org/W2948091552","https://openalex.org/W2963403868","https://openalex.org/W2964342924","https://openalex.org/W2982341288","https://openalex.org/W3006047556","https://openalex.org/W3033731578","https://openalex.org/W3034679090","https://openalex.org/W3034751264","https://openalex.org/W3081461453","https://openalex.org/W3083274258","https://openalex.org/W3091667472","https://openalex.org/W3108495681","https://openalex.org/W3108883555","https://openalex.org/W3117312351","https://openalex.org/W3119066640","https://openalex.org/W4249052411","https://openalex.org/W4287766186","https://openalex.org/W4288090873","https://openalex.org/W4385245566","https://openalex.org/W6633511732","https://openalex.org/W6739901393","https://openalex.org/W6779923105","https://openalex.org/W6782346483","https://openalex.org/W6784117923"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1604739066","https://openalex.org/W2115878407","https://openalex.org/W1980454230"],"abstract_inverted_index":{"Data-based":[0],"and":[1,14,39,109,135],"learning-based":[2],"sound":[3,64],"source":[4],"localization":[5,131],"(SSL)":[6],"has":[7],"shown":[8],"promising":[9],"results":[10],"in":[11,128],"challenging":[12],"conditions,":[13],"is":[15,90],"commonly":[16],"set":[17],"as":[18,33,62],"a":[19,22,49,74],"classification":[20],"or":[21],"regression":[23],"problem.":[24],"Regression-based":[25],"approaches":[26],"have":[27],"certain":[28],"advantages":[29],"over":[30,122],"classification-based,":[31],"such":[32,61,71],"continuous":[34],"direction-of-arrival":[35],"estimation":[36],"of":[37,70,99,130],"static":[38],"moving":[40],"sources.":[41],"However,":[42],"multi-source":[43],"scenarios":[44],"require":[45],"multiple":[46],"regressors":[47],"without":[48],"clear":[50],"training":[51,69],"strategy":[52],"up-to-date,":[53],"that":[54,92],"does":[55],"not":[56],"rely":[57],"on":[58],"auxiliary":[59],"information":[60],"simultaneous":[63],"classification.":[65],"We":[66],"investigate":[67],"end-to-end":[68],"methods":[72],"with":[73],"technique":[75],"recently":[76],"proposed":[77],"for":[78],"video":[79],"object":[80],"detectors,":[81],"adapted":[82],"to":[83,96,102],"the":[84,97,100,104,113],"SSL":[85],"setting.":[86],"A":[87],"differentiable":[88],"network":[89],"constructed":[91],"can":[93],"be":[94],"plugged":[95],"output":[98],"localizer":[101],"solve":[103],"optimal":[105],"assignment":[106],"between":[107],"predictions":[108],"references,":[110],"optimizing":[111,124],"directly":[112,123],"popular":[114],"CLEAR-MOT":[115],"tracking":[116,136],"metrics.":[117],"Results":[118],"indicate":[119],"large":[120],"improvements":[121],"mean":[125],"squared":[126],"errors,":[127],"terms":[129],"error,":[132],"detection":[133],"metrics,":[134],"capabilities.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}