{"id":"https://openalex.org/W4407900319","doi":"https://doi.org/10.1109/access.2025.3545065","title":"Hybrid Convolutional Neural Network-Transformer Model for End-to-End Binaural Sound Source Localization in Reverberant Environments","display_name":"Hybrid Convolutional Neural Network-Transformer Model for End-to-End Binaural Sound Source Localization in Reverberant Environments","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407900319","doi":"https://doi.org/10.1109/access.2025.3545065"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3545065","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3545065","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3545065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110529546","display_name":"Xinyi Chen","orcid":"https://orcid.org/0000-0003-3990-0383"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Chen","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lijia Zhao","orcid":"https://orcid.org/0009-0004-8188-7519"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijia Zhao","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8188-7519","affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025490169","display_name":"Jie Cui","orcid":"https://orcid.org/0000-0001-9391-6744"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Cui","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9391-6744","affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062981218","display_name":"Hua Li","orcid":"https://orcid.org/0000-0002-7470-2924"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Li","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7470-2924","affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091707964","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0001-6525-2362"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6525-2362","affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.9318,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83694316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"36701","last_page":"36713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.961899995803833,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7598633766174316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6849523782730103},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5986456274986267},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5227378010749817},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5008485317230225},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.4812014698982239},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4500831961631775},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4369620084762573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17133033275604248},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15708822011947632},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12066853046417236},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08833348751068115},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07654678821563721},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.07583078742027283}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7598633766174316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6849523782730103},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5986456274986267},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5227378010749817},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5008485317230225},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.4812014698982239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4500831961631775},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4369620084762573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17133033275604248},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15708822011947632},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12066853046417236},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08833348751068115},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07654678821563721},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.07583078742027283},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3545065","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3545065","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a43eea0e8b704e269934997b11925921","is_oa":true,"landing_page_url":"https://doaj.org/article/a43eea0e8b704e269934997b11925921","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 36701-36713 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3545065","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3545065","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6249807887","display_name":null,"funder_award_id":"2020YFC2004003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2012858128","https://openalex.org/W2089586791","https://openalex.org/W2152669807","https://openalex.org/W2155323221","https://openalex.org/W2765962757","https://openalex.org/W2884424734","https://openalex.org/W2921741089","https://openalex.org/W2963339453","https://openalex.org/W3029436999","https://openalex.org/W3046394092","https://openalex.org/W3117559649","https://openalex.org/W3133550200","https://openalex.org/W3134840222","https://openalex.org/W3160159330","https://openalex.org/W3196974791","https://openalex.org/W4285550691","https://openalex.org/W4312920378","https://openalex.org/W4366967194","https://openalex.org/W4385823179","https://openalex.org/W4391334585"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W4377018054","https://openalex.org/W3004570917","https://openalex.org/W2337758134","https://openalex.org/W2022765019","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W4244700398","https://openalex.org/W2041661331","https://openalex.org/W1991739683"],"abstract_inverted_index":{"The":[0,65,191],"end-to-end":[1,32,185],"binaural":[2,33,86,149,186],"sound":[3,34,187],"source":[4,35,188],"localization":[5,36,87,189],"model":[6,37,67,173,202],"can":[7],"implicitly":[8],"extract":[9],"features":[10,88],"from":[11,91],"the":[12,48,52,57,97,112,116,139,144,159,177,194,199,205,208,221,253],"original":[13],"signal":[14,94,211],"waveforms":[15,95],"and":[16,55,81,127,134,154,165,175,215,232,246,264,278],"take":[17],"full":[18],"advantage":[19],"of":[20,51,124,181,193,207,230,234,262,266],"neural":[21,78],"networks.":[22],"In":[23,115,138,252],"this":[24],"study,":[25],"we":[26,101,119,142],"propose":[27],"a":[28,42,69,76,103],"new":[29],"deep":[30],"learning-based":[31],"called":[38],"WavLocT,":[39],"which":[40,85],"employs":[41],"gammatone":[43],"filter":[44],"bank":[45],"to":[46,147,171],"simulate":[47],"frequency":[49,109],"properties":[50],"human":[53],"ear":[54],"decomposes":[56],"signals":[58],"received":[59],"by":[60],"microphones":[61],"into":[62],"subband":[63,93],"signals.":[64],"WavLocT":[66,201,225,257],"has":[68],"unique":[70],"feature":[71],"extraction":[72],"block":[73],"that":[74,198],"incorporates":[75],"convolutional":[77],"network":[79],"(CNN)":[80],"transformer":[82,113],"structure,":[83],"in":[84,212,220],"are":[89],"extracted":[90],"different":[92,108,125],"via":[96,111],"CNN":[98],"structure.":[99],"Additionally,":[100],"use":[102],"selective":[104],"attention":[105],"mechanism":[106],"for":[107,132],"subbands":[110],"encoder.":[114],"training":[117],"phase,":[118,141],"simulated":[120],"three":[121],"reverberant":[122],"rooms":[123],"sizes":[126],"trained":[128,145],"two":[129,182],"models":[130,146],"separately":[131],"diffuse":[133,214,222],"directional":[135,216,254],"noise":[136,217,223,255],"environments.":[137,156,218],"testing":[140],"applied":[143],"both":[148,213],"room":[150],"impulse":[151],"response":[152],"(BRIR)-matched":[153],"BRIR-mismatched":[155],"We":[157],"selected":[158],"root":[160],"mean":[161],"square":[162],"error":[163],"(RMSE)":[164],"accuracy":[166],"(Acc)":[167],"as":[168],"evaluation":[169],"metrics":[170],"evaluate":[172],"performance":[174],"compared":[176],"results":[178,192],"with":[179],"those":[180],"recent":[183],"CNN-based":[184],"models.":[190],"simulation":[195],"experiments":[196],"demonstrated":[197],"proposed":[200],"effectively":[203],"estimated":[204],"azimuth":[206],"desired":[209],"speech":[210],"Specifically,":[219],"environment,":[224,256],"achieved":[226,258],"an":[227,259],"average":[228,260],"RMSE":[229,261],"6.45\u00b0":[231],"Acc":[233,265],"70.02%":[235],"across":[236,268],"all":[237,269],"mismatched":[238,270],"rooms,":[239,271],"outperforming":[240,272],"WavLoc":[241,273],"(6.72\u00b0":[242],"RMSE,":[243,249,275,281],"56.10%":[244],"Acc)":[245,277],"WavLocEC":[247,279],"(7.46\u00b0":[248],"65.86%":[250],"Acc).":[251,283],"7.61\u00b0":[263],"63.38%":[267],"(8.34\u00b0":[274],"52.38%":[276],"(8.19\u00b0":[280],"58.05%":[282]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}