{"id":"https://openalex.org/W4386289668","doi":"https://doi.org/10.1186/s13636-023-00301-x","title":"Dual input neural networks for positional sound source localization","display_name":"Dual input neural networks for positional sound source localization","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4386289668","doi":"https://doi.org/10.1186/s13636-023-00301-x"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00301-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00301-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00301-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00301-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011673214","display_name":"Eric Grinstein","orcid":"https://orcid.org/0000-0003-4502-5407"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Eric Grinstein","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, UK"],"raw_orcid":"https://orcid.org/0000-0003-4502-5407","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016082280","display_name":"Vincent W. Neo","orcid":"https://orcid.org/0000-0003-0731-2157"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vincent W. Neo","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011673214"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.3336,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81613683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2023","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.813468337059021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6210272908210754},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5719139575958252},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.524291455745697},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5187585353851318},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5160545706748962},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5086253881454468},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5047281980514526},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4899848997592926},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47956913709640503},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4366391599178314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41732507944107056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36914584040641785},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3588687777519226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3541605770587921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813468337059021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6210272908210754},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5719139575958252},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.524291455745697},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5187585353851318},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5160545706748962},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5086253881454468},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5047281980514526},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4899848997592926},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47956913709640503},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4366391599178314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41732507944107056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36914584040641785},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3588687777519226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3541605770587921},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-023-00301-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00301-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00301-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:96d9082238954506a790c7d6f103280f","is_oa":true,"landing_page_url":"https://doaj.org/article/96d9082238954506a790c7d6f103280f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-12 (2023)","raw_type":"article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/106532","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/106532","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00301-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00301-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00301-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2556816831","display_name":"Service-Oriented Ubiquitous Network-Driven Sound","funder_award_id":"956369","funder_id":"https://openalex.org/F4320338337","funder_display_name":"H2020 Marie Sk\u0142odowska-Curie Actions"},{"id":"https://openalex.org/G5125349196","display_name":null,"funder_award_id":"EP/S035842/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5952785084","display_name":"Environment and Listener Optimised Speech Processing for Hearing Enhancement in Real Situations (ELO-SPHERES)","funder_award_id":"EP/S035842/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7537482475","display_name":null,"funder_award_id":"956369","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320338337","display_name":"H2020 Marie Sk\u0142odowska-Curie Actions","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386289668.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1981755271","https://openalex.org/W2020997493","https://openalex.org/W2027691292","https://openalex.org/W2037958743","https://openalex.org/W2046317813","https://openalex.org/W2053101950","https://openalex.org/W2071608040","https://openalex.org/W2081683365","https://openalex.org/W2092231504","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2114219351","https://openalex.org/W2117678320","https://openalex.org/W2137867936","https://openalex.org/W2149298302","https://openalex.org/W2164809687","https://openalex.org/W2257086086","https://openalex.org/W2460742184","https://openalex.org/W2539864613","https://openalex.org/W2561817999","https://openalex.org/W2592109325","https://openalex.org/W2611943505","https://openalex.org/W2616516232","https://openalex.org/W2619383789","https://openalex.org/W2763188033","https://openalex.org/W2765464705","https://openalex.org/W2772736377","https://openalex.org/W2807015669","https://openalex.org/W2884822476","https://openalex.org/W2900429685","https://openalex.org/W2905521202","https://openalex.org/W2917254586","https://openalex.org/W2942551338","https://openalex.org/W2948091552","https://openalex.org/W2963451564","https://openalex.org/W2964342924","https://openalex.org/W2998572311","https://openalex.org/W3011890046","https://openalex.org/W3096287167","https://openalex.org/W3098454764","https://openalex.org/W3103589224","https://openalex.org/W3104757150","https://openalex.org/W3105684258","https://openalex.org/W3117312351","https://openalex.org/W3197097128","https://openalex.org/W4206377423","https://openalex.org/W4225270933","https://openalex.org/W4249052411","https://openalex.org/W4297277729"],"related_works":["https://openalex.org/W2062427795","https://openalex.org/W1533329019","https://openalex.org/W4362508223","https://openalex.org/W2360553097","https://openalex.org/W2354642172","https://openalex.org/W2949455538","https://openalex.org/W4299576237","https://openalex.org/W2767651786","https://openalex.org/W2912288872","https://openalex.org/W564581980"],"abstract_inverted_index":{"Abstract":[0],"In":[1,23],"many":[2,43],"signal":[3,17],"processing":[4],"applications,":[5],"metadata":[6],"may":[7],"be":[8],"advantageously":[9],"used":[10],"in":[11,61,90,158],"conjunction":[12],"with":[13,48],"a":[14,20,35,68,79,91,115,123,141,159],"high":[15,36],"dimensional":[16],"to":[18,63,84],"produce":[19],"desired":[21],"output.":[22],"the":[24,54,58,65,134,138,148,156],"case":[25],"of":[26,53,67,103,162],"classical":[27,116,124],"Sound":[28],"Source":[29],"Localization":[30],"(SSL)":[31],"algorithms,":[32],"information":[33,49],"from":[34],"dimensional,":[37],"multichannel":[38],"audio":[39],"signals":[40],"received":[41],"by":[42],"distributed":[44],"microphones":[45],"is":[46],"combined":[47],"describing":[50],"acoustic":[51],"properties":[52],"scene,":[55],"such":[56],"as":[57,78,120,122],"microphones\u2019":[59],"coordinates":[60],"space,":[62],"estimate":[64],"position":[66],"sound":[69],"source.":[70],"We":[71,94],"introduce":[72],"Dual":[73],"Input":[74],"Neural":[75,127],"Networks":[76],"(DI-NNs)":[77],"simple":[80],"and":[81,96,106,108,151],"effective":[82],"way":[83],"model":[85],"these":[86],"two":[87,152],"data":[88],"types":[89],"neural":[92],"network.":[93],"train":[95],"evaluate":[97],"our":[98],"proposed":[99],"DI-NN":[100,135],"on":[101],"scenarios":[102],"varying":[104],"difficulty":[105],"realism":[107],"compare":[109],"it":[110],"against":[111],"an":[112],"alternative":[113],"architecture,":[114],"Least-Squares":[117],"(LS)":[118],"method":[119,150],"well":[121],"Convolutional":[125],"Recurrent":[126],"Network":[128],"(CRNN).":[129],"Our":[130],"results":[131],"show":[132],"that":[133],"significantly":[136],"outperforms":[137],"baselines,":[139],"achieving":[140],"five":[142],"times":[143,153],"lower":[144,154],"localization":[145],"error":[146],"than":[147,155],"LS":[149],"CRNN":[157],"test":[160],"dataset":[161],"real":[163],"recordings.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}