{"id":"https://openalex.org/W4390693634","doi":"https://doi.org/10.1109/iccais59597.2023.10382318","title":"Dense-U-Net assisted Localization of Speech Sources in Motion under Reverberant conditions","display_name":"Dense-U-Net assisted Localization of Speech Sources in Motion under Reverberant conditions","publication_year":2023,"publication_date":"2023-11-27","ids":{"openalex":"https://openalex.org/W4390693634","doi":"https://doi.org/10.1109/iccais59597.2023.10382318"},"language":"en","primary_location":{"id":"doi:10.1109/iccais59597.2023.10382318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais59597.2023.10382318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)","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/A5032885990","display_name":"Jayanta Datta","orcid":"https://orcid.org/0000-0001-6348-3386"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Jayanta Datta","raw_affiliation_strings":["University of Chile,Department of Electrical Engineering,Santiago,Chile","Department of Electrical Engineering, University of Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"University of Chile,Department of Electrical Engineering,Santiago,Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030210127","display_name":"Martin Adams","orcid":"https://orcid.org/0000-0002-1085-0506"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Martin Adams","raw_affiliation_strings":["University of Chile,Department of Electrical Engineering,Santiago,Chile","Department of Electrical Engineering, University of Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"University of Chile,Department of Electrical Engineering,Santiago,Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101809187","display_name":"Carlos A. Perez","orcid":"https://orcid.org/0000-0002-5484-4159"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Claudio Perez","raw_affiliation_strings":["University of Chile,Department of Electrical Engineering,Santiago,Chile","Department of Electrical Engineering, University of Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"University of Chile,Department of Electrical Engineering,Santiago,Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032885990"],"corresponding_institution_ids":["https://openalex.org/I69737025"],"apc_list":null,"apc_paid":null,"fwci":0.6125,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68244131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"440","last_page":"447"},"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11698","display_name":"Underwater Acoustics Research","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7658514976501465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7151363492012024},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6456203460693359},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6170568466186523},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6015537977218628},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5889599919319153},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.503973662853241},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4736032485961914},{"id":"https://openalex.org/keywords/cross-correlation","display_name":"Cross-correlation","score":0.42098426818847656},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4133915901184082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3584236800670624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3543868064880371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3475111722946167},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34390079975128174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16708311438560486},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13595011830329895},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.119273841381073},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09321233630180359}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7658514976501465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151363492012024},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6456203460693359},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6170568466186523},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6015537977218628},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5889599919319153},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.503973662853241},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4736032485961914},{"id":"https://openalex.org/C163018871","wikidata":"https://www.wikidata.org/wiki/Q1302587","display_name":"Cross-correlation","level":2,"score":0.42098426818847656},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4133915901184082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3584236800670624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3543868064880371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3475111722946167},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34390079975128174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16708311438560486},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13595011830329895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.119273841381073},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09321233630180359},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais59597.2023.10382318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais59597.2023.10382318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 12th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331146","display_name":"Agencia Nacional de Investigaci\u00f3n y Desarrollo","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1648602279","https://openalex.org/W1901129140","https://openalex.org/W2102958376","https://openalex.org/W2107493093","https://openalex.org/W2130357996","https://openalex.org/W2611943505","https://openalex.org/W2701869962","https://openalex.org/W2810934215","https://openalex.org/W2884822476","https://openalex.org/W2898268964","https://openalex.org/W2964342924","https://openalex.org/W2987372735","https://openalex.org/W3011890046","https://openalex.org/W3015791598","https://openalex.org/W3016666924","https://openalex.org/W3030515889","https://openalex.org/W3034751264","https://openalex.org/W3104196160","https://openalex.org/W3104757150","https://openalex.org/W3108495681","https://openalex.org/W3117498573","https://openalex.org/W3167605560","https://openalex.org/W3169146199","https://openalex.org/W3197097128","https://openalex.org/W4225280365","https://openalex.org/W4230806803","https://openalex.org/W4312522883","https://openalex.org/W4323060438"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,35,47,179,188,210,228],"deep":[4],"learning":[5],"(DL)":[6],"approach,":[7],"based":[8,53],"on":[9,54,126],"dense":[10,180,213],"convolutional":[11],"neural":[12],"networks,":[13],"to":[14,90,109,150,193,216,224],"improve":[15],"the":[16,24,55,70,74,83,93,96,104,136,152,160,207,218,225],"localization":[17,39,240],"of":[18,57,73,95,106,113,121,178,209,227,241],"target":[19,75,242],"sources":[20,243],"in":[21,92,100,187,244,250],"motion":[22,245],"using":[23],"steered":[25],"response":[26],"power-phase":[27],"transform":[28,155],"(SRP-PHAT)":[29],"concept.":[30],"The":[31],"SRPPHAT":[32],"method":[33],"is":[34,52],"state-of-the-art":[36],"acoustic":[37,65],"source":[38],"(ASL)":[40],"technique":[41],"and":[42,62,81,130,199],"can":[43,174,191,222],"be":[44,175],"regarded":[45],"as":[46,143],"filter-and-sum":[48],"(F-S)":[49],"beam-former,":[50],"which":[51,162,221],"summation":[56],"generalized":[58,153],"cross-correlation":[59],"(GCC)":[60],"components":[61,85,157,220],"constructs":[63],"an":[64,183,238,251],"power":[66],"map":[67],"(APM)":[68],"depicting":[69],"position":[71],"estimates":[72],"sources.":[76],"However,":[77,119],"under":[78,115,167,196,246],"strong":[79],"reverberation":[80,198],"noise,":[82],"GCC":[84],"are":[86,124],"adversely":[87],"affected":[88],"leading":[89],"inaccuracies":[91],"computation":[94],"SRP-PHAT.":[97],"Recent":[98],"advances":[99],"DL":[101,107,140],"have":[102,146,163],"shown":[103],"capability":[105],"algorithms":[108],"outperform":[110],"traditional":[111],"methods":[112,123,141],"ASL,":[114],"noisy,":[116],"reverberant":[117,168],"conditions.":[118,169],"most":[120],"these":[122],"dependent":[125],"microphone":[127],"array":[128],"geometry":[129],"other":[131],"environmental":[132],"conditions":[133,249],"available":[134],"during":[135],"training":[137],"phase.":[138],"Alternative":[139],"such":[142],"encoder-decoder":[144,172,184],"structures":[145,173],"been":[147],"recently":[148],"applied":[149],"denoise":[151],"cross-correlation-phase":[154],"(GCC-PHAT)":[156],"before":[158],"constructing":[159],"SRP-PHAT,":[161],"demonstrated":[164],"good":[165],"performance":[166,195],"While":[170],"conventional":[171],"helpful,":[176],"incorporation":[177],"block":[181,214],"within":[182],"framework":[185],"arranged":[186],"U-Net":[189,211],"structure":[190],"lead":[192,223],"better":[194],"severe":[197],"background":[200],"noise.":[201],"In":[202],"this":[203,235],"work,":[204],"we":[205],"propose":[206],"application":[208],"with":[212],"(Dense-U-Net)":[215],"de-noise":[217],"GCC-PHAT":[219],"construction":[226],"refined":[229],"APM.":[230],"Computer":[231],"simulations":[232],"demonstrate":[233],"that":[234],"process":[236],"yields":[237],"improved":[239],"reverberant,":[247],"noisy":[248],"indoor":[252],"environment.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}