{"id":"https://openalex.org/W3034751264","doi":"https://doi.org/10.1109/taslp.2020.3040031","title":"Robust Sound Source Tracking Using SRP-PHAT and 3D Convolutional Neural Networks","display_name":"Robust Sound Source Tracking Using SRP-PHAT and 3D Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W3034751264","doi":"https://doi.org/10.1109/taslp.2020.3040031","mag":"3034751264"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3040031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3040031","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.09006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"David Diaz-Guerra","orcid":"https://orcid.org/0000-0002-1041-0498"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Diaz-Guerra","raw_affiliation_strings":["Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1041-0498","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Antonio Miguel","orcid":null},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Miguel","raw_affiliation_strings":["Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jose R. Beltran","orcid":"https://orcid.org/0000-0002-7500-4650"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose R. Beltran","raw_affiliation_strings":["Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7500-4650","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I255234318"],"apc_list":null,"apc_paid":null,"fwci":6.2362,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.97454203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"300","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.970300018787384,"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":0.970300018787384,"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":0.005200000014156103,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.8287000060081482},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7746000289916992},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7576000094413757},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3887999951839447},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.3312999904155731},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.33009999990463257},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3147999942302704}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8287000060081482},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7746000289916992},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7576000094413757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41839998960494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.3040031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3040031","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:zaguan.unizar.es:165793","is_oa":false,"landing_page_url":"http://zaguan.unizar.es/record/165793","pdf_url":null,"source":{"id":"https://openalex.org/S4306401812","display_name":"Zaguan (University of Zaragoza Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I255234318","host_organization_name":"Universidad de Zaragoza","host_organization_lineage":["https://openalex.org/I255234318"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2006.09006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.09006","pdf_url":"https://arxiv.org/pdf/2006.09006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.09006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.09006","pdf_url":"https://arxiv.org/pdf/2006.09006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320326208","display_name":"Gobierno de Arag\u00f3n","ror":"https://ror.org/0425pg203"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1555217905","https://openalex.org/W1603075283","https://openalex.org/W1677182931","https://openalex.org/W1982728343","https://openalex.org/W1988904709","https://openalex.org/W1991032800","https://openalex.org/W1994301419","https://openalex.org/W2008750120","https://openalex.org/W2046317813","https://openalex.org/W2090629256","https://openalex.org/W2099085385","https://openalex.org/W2107493093","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2128970593","https://openalex.org/W2128977628","https://openalex.org/W2149900846","https://openalex.org/W2157331557","https://openalex.org/W2164602770","https://openalex.org/W2165927731","https://openalex.org/W2296073425","https://openalex.org/W2313370639","https://openalex.org/W2532891002","https://openalex.org/W2571623814","https://openalex.org/W2586642235","https://openalex.org/W2592109325","https://openalex.org/W2742299865","https://openalex.org/W2772736377","https://openalex.org/W2776323726","https://openalex.org/W2781903915","https://openalex.org/W2801659857","https://openalex.org/W2810934215","https://openalex.org/W2884822476","https://openalex.org/W2885091335","https://openalex.org/W2885219692","https://openalex.org/W2888793942","https://openalex.org/W2898268964","https://openalex.org/W2917254586","https://openalex.org/W2940285530","https://openalex.org/W2948091552","https://openalex.org/W2962708126","https://openalex.org/W2964342924","https://openalex.org/W2970971581","https://openalex.org/W2982429715","https://openalex.org/W2982477635","https://openalex.org/W2994724472","https://openalex.org/W3015605759","https://openalex.org/W6605165268","https://openalex.org/W6631190155","https://openalex.org/W6769516661","https://openalex.org/W6922472746"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,74,115],"present":[4],"a":[5,22,36,52,102,117,155],"new":[6,103,108,118],"single":[7],"sound":[8,53],"source":[9,54],"DOA":[10,104],"estimation":[11,105],"and":[12,21,81,99,161,176],"tracking":[13,50],"system":[14,93,175],"based":[15],"on":[16,154],"the":[17,49,63,66,89,113,129,146,162,166,171],"well-known":[18],"SRP-PHAT":[19,29,109,183],"algorithm":[20],"three-dimensional":[23],"Convolutional":[24],"Neural":[25],"Network.":[26],"It":[27],"uses":[28,42],"power":[30],"maps":[31],"as":[32,124,145],"input":[33],"features":[34],"of":[35,51,62,65,158,165,173],"fully":[37],"convolutional":[38,44,84],"causal":[39,87],"architecture":[40],"that":[41],"3D":[43],"layers":[45,80,85],"to":[46,120,132,139,169],"accurately":[47],"perform":[48],"even":[55,180],"in":[56,88],"highly":[57],"reverberant":[58],"scenarios":[59],"where":[60],"most":[61],"state":[64],"art":[67],"techniques":[68],"fail.":[69],"Unlike":[70],"previous":[71],"methods,":[72],"since":[73],"do":[75],"not":[76],"use":[77,150],"bidirectional":[78],"recurrent":[79],"all":[82],"our":[83,92,174],"are":[86,126],"time":[90],"dimension,":[91],"is":[94],"feasible":[95],"for":[96,106],"real-time":[97],"applications":[98],"it":[100],"provides":[101],"each":[107],"map.":[110],"To":[111],"train":[112],"model,":[114],"introduce":[116],"procedure":[119],"simulate":[121],"random":[122],"trajectories":[123],"they":[125],"needed":[127],"during":[128],"training,":[130],"equivalent":[131],"an":[133],"infinite-size":[134],"dataset":[135,168],"with":[136],"high":[137],"flexibility":[138],"modify":[140],"its":[141,177],"acoustical":[142,152],"conditions":[143],"such":[144],"reverberation":[147,159],"time.":[148],"We":[149],"both":[151],"simulations":[153],"large":[156],"range":[157],"times":[160],"actual":[163],"recordings":[164],"LOCATA":[167],"prove":[170],"robustness":[172],"good":[178],"performance":[179],"using":[181],"low-resolution":[182],"maps.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-06-19T00:00:00"}