{"id":"https://openalex.org/W2405404760","doi":"https://doi.org/10.21437/interspeech.2015-665","title":"Exploiting deep neural networks and head movements for binaural localisation of multiple speakers in reverberant conditions","display_name":"Exploiting deep neural networks and head movements for binaural localisation of multiple speakers in reverberant conditions","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2405404760","doi":"https://doi.org/10.21437/interspeech.2015-665","mag":"2405404760"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-665","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbit.dtu.dk/en/publications/bfa80199-272c-424b-834e-8e89e6a05eea","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","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":["Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052043106","display_name":"Tobias May","orcid":"https://orcid.org/0000-0002-5463-5509"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tobias May","raw_affiliation_strings":["Hearing Systems Group, Technical University of Denmark, DK -2800 Kgs. Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hearing Systems Group, Technical University of Denmark, DK -2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1163,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96152491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9933000206947327,"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/binaural-recording","display_name":"Binaural recording","score":0.7745816707611084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6080893874168396},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5951635241508484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5730167627334595},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.551277220249176},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.550317108631134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059707224369049},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10844001173973083}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7745816707611084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6080893874168396},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5951635241508484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5730167627334595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.551277220249176},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.550317108631134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059707224369049},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10844001173973083},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-665","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:102628","is_oa":false,"landing_page_url":"https://orcid.org/0000-0002-4112-3109>,","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":null,"raw_type":"Proceedings Paper"},{"id":"pmh:oai:pure.atira.dk:publications/bfa80199-272c-424b-834e-8e89e6a05eea","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/bfa80199-272c-424b-834e-8e89e6a05eea","pdf_url":"https://orbit.dtu.dk/en/publications/bfa80199-272c-424b-834e-8e89e6a05eea","source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"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":"Ma , N , Brown , G J & May , T 2015 , Exploiting deep neural networks and head movements for binaural localisation of multiple speakers in reverberant conditions . in Proceedings of Interspeech 2015 . ISCA , pp. 3302-3306 , INTERSPEECH 2015 , Dresden , Germany , 06/09/2015 .","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/bfa80199-272c-424b-834e-8e89e6a05eea","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/bfa80199-272c-424b-834e-8e89e6a05eea","pdf_url":"https://orbit.dtu.dk/en/publications/bfa80199-272c-424b-834e-8e89e6a05eea","source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"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":"Ma , N , Brown , G J & May , T 2015 , Exploiting deep neural networks and head movements for binaural localisation of multiple speakers in reverberant conditions . in Proceedings of Interspeech 2015 . ISCA , pp. 3302-3306 , INTERSPEECH 2015 , Dresden , Germany , 06/09/2015 .","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G5218062402","display_name":"TWO!EARS","funder_award_id":"618075","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2405404760.pdf","grobid_xml":"https://content.openalex.org/works/W2405404760.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W93202645","https://openalex.org/W1515109179","https://openalex.org/W1518870451","https://openalex.org/W1581848821","https://openalex.org/W1591446137","https://openalex.org/W1963487351","https://openalex.org/W1966081805","https://openalex.org/W1992879732","https://openalex.org/W1997110426","https://openalex.org/W2015143272","https://openalex.org/W2028184103","https://openalex.org/W2034040413","https://openalex.org/W2068325601","https://openalex.org/W2096439661","https://openalex.org/W2106925337","https://openalex.org/W2113067468","https://openalex.org/W2114218864","https://openalex.org/W2154392779","https://openalex.org/W2155323221","https://openalex.org/W2165507463","https://openalex.org/W2166682639","https://openalex.org/W2561557072","https://openalex.org/W4231109964"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2026165661","https://openalex.org/W2099651033","https://openalex.org/W2783525307","https://openalex.org/W2593008828","https://openalex.org/W2155323221"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,51,60,65,86,107,111],"novel":[4],"machine-hearing":[5],"system":[6,108,120],"that":[7],"exploits":[8],"deep":[9],"neural":[10],"networks":[11],"(DNNs)":[12],"and":[13,38,81,133],"head":[14,87],"movements":[15],"for":[16],"binaural":[17,29,76],"localisation":[18,52,123],"of":[19,32,75],"multiple":[20,131],"speakers":[21,132],"in":[22,54,59,78,92,129],"reverberant":[23],"conditions.DNNs":[24],"are":[25,136],"used":[26],"to":[27,43,72,96,106],"map":[28],"features,":[30],"consisting":[31],"the":[33,44,73,79,93,99,117],"complete":[34],"crosscorrelation":[35],"function":[36],"(CCF)":[37],"interaural":[39],"level":[40],"differences":[41],"(ILDs),":[42],"source":[45],"azimuth.Our":[46],"approach":[47],"was":[48,90],"evaluated":[49],"using":[50],"task":[53],"which":[55,130],"sources":[56],"were":[57],"located":[58],"full":[61],"360-degree":[62],"azimuth":[63],"range.As":[64],"result,":[66],"front-back":[67,100],"confusions":[68],"often":[69],"occurred":[70],"due":[71],"similarity":[74],"features":[77],"front":[80],"rear":[82],"hemifields.To":[83],"address":[84],"this,":[85],"movement":[88],"strategy":[89],"incorporated":[91],"DNN-based":[94],"model":[95,114],"help":[97],"reduce":[98],"errors.Our":[101],"experiments":[102],"show":[103],"that,":[104],"compared":[105],"based":[109],"on":[110],"Gaussian":[112],"mixture":[113],"(GMM)":[115],"classifier,":[116],"proposed":[118],"DNN":[119],"substantially":[121],"reduces":[122],"errors":[124],"under":[125],"challenging":[126],"acoustic":[127],"scenarios":[128],"room":[134],"reverberation":[135],"present.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}