{"id":"https://openalex.org/W4375868867","doi":"https://doi.org/10.1109/icassp49357.2023.10096640","title":"Robust Binaural Sound Localisation with Temporal Attention","display_name":"Robust Binaural Sound Localisation with Temporal Attention","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868867","doi":"https://doi.org/10.1109/icassp49357.2023.10096640"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101921929","display_name":"Qi Hu","orcid":"https://orcid.org/0000-0001-8832-4728"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Hu","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics,Beijing,China","Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067036469","display_name":"Ning Ma","orcid":"https://orcid.org/0000-0002-4112-3109"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["University of Sheffield,Department of Computer Science,Sheffield,UK","Department of Computer Science, University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"University of Sheffield,Department of Computer Science,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080527909","display_name":"Guy J. Brown","orcid":"https://orcid.org/0000-0001-8565-5476"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy J. Brown","raw_affiliation_strings":["University of Sheffield,Department of Computer Science,Sheffield,UK","Department of Computer Science, University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"University of Sheffield,Department of Computer Science,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101921929"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.9854,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74502041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9983000159263611,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.8523330092430115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7834435701370239},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.7391393184661865},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.622344970703125},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5181726217269897},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.504313588142395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5035025477409363},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4720379114151001},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4502505660057068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41303640604019165},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2977049946784973},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.22530922293663025},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08280456066131592}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8523330092430115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834435701370239},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.7391393184661865},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.622344970703125},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5181726217269897},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.504313588142395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5035025477409363},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4720379114151001},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4502505660057068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41303640604019165},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2977049946784973},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.22530922293663025},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08280456066131592},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:196758","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1494198834","https://openalex.org/W1515109179","https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2129188305","https://openalex.org/W2155323221","https://openalex.org/W2166682639","https://openalex.org/W2701869962","https://openalex.org/W2765962757","https://openalex.org/W2773475413","https://openalex.org/W2810934215","https://openalex.org/W2884424734","https://openalex.org/W2885219692","https://openalex.org/W2897977894","https://openalex.org/W2918296821","https://openalex.org/W2947942791","https://openalex.org/W2954695182","https://openalex.org/W2963339453","https://openalex.org/W2972725301","https://openalex.org/W3015279216","https://openalex.org/W3016037102","https://openalex.org/W3016252974","https://openalex.org/W3081729342","https://openalex.org/W3092796334","https://openalex.org/W3111598519","https://openalex.org/W3127686677","https://openalex.org/W3163739652","https://openalex.org/W3167533889","https://openalex.org/W3197097128","https://openalex.org/W4285550691","https://openalex.org/W6630456326","https://openalex.org/W6735168207","https://openalex.org/W6768365444","https://openalex.org/W6784139575","https://openalex.org/W6789826613","https://openalex.org/W6795872614"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W2171322294","https://openalex.org/W3004570917","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W2041661331","https://openalex.org/W2539207221","https://openalex.org/W2045803470","https://openalex.org/W2242743481","https://openalex.org/W2015890751"],"abstract_inverted_index":{"Despite":[0],"there":[1],"being":[2],"clear":[3],"evidence":[4],"for":[5,39,78],"attentional":[6],"effects":[7],"in":[8,19,45,140,163],"biological":[9],"spatial":[10],"hearing,":[11],"relatively":[12],"few":[13],"machine":[14,33],"hearing":[15,34],"systems":[16],"exploit":[17],"attention":[18,38,83],"binaural":[20,32],"sound":[21,43,134,161],"localisation.":[22],"This":[23],"paper":[24],"addresses":[25],"this":[26],"issue":[27],"by":[28,92,114],"proposing":[29],"a":[30,96,141,160],"novel":[31],"system":[35,151],"with":[36],"temporal":[37,82,97,128],"robust":[40],"localisation":[41,59,135],"of":[42,72,88,95,159],"sources":[44],"noisy":[46,167],"and":[47,75,132,166],"reverberant":[48,165],"conditions.":[49,168],"A":[50,81],"convolutional":[51],"neural":[52],"network":[53],"is":[54,152],"employed":[55],"to":[56,64,121,154],"extract":[57],"noise-robust":[58],"features,":[60],"which":[61,118],"are":[62,111,137],"similar":[63],"interaural":[65],"phase":[66,70],"difference,":[67],"directly":[68],"from":[69],"spectra":[71],"the":[73,122,127,133,149,157],"left":[74],"right":[76],"ears":[77],"each":[79,106],"frame.":[80,107],"layer":[84],"operates":[85],"on":[86],"top":[87],"these":[89],"frame-level":[90],"features":[91,110],"incorporating":[93],"outputs":[94],"mask":[98,129],"estimation":[99,130],"module":[100,131,136],"that":[101,148],"indicate":[102],"target":[103],"dominance":[104],"within":[105],"The":[108],"combined":[109],"then":[112],"exploited":[113],"fully":[115],"connected":[116],"layers,":[117],"map":[119],"them":[120],"corresponding":[123],"source":[124,162],"azimuth.":[125],"Both":[126],"trained":[138],"jointly":[139],"multi-task":[142],"learning":[143],"manner.":[144],"Our":[145],"evaluation":[146],"shows":[147],"proposed":[150],"able":[153],"accurately":[155],"estimate":[156],"azimuth":[158],"various":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}