{"id":"https://openalex.org/W2772736377","doi":"https://doi.org/10.1109/icra.2018.8461267","title":"Deep Neural Networks for Multiple Speaker Detection and Localization","display_name":"Deep Neural Networks for Multiple Speaker Detection and Localization","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2772736377","doi":"https://doi.org/10.1109/icra.2018.8461267","mag":"2772736377"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.11565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103162780","display_name":"Weipeng He","orcid":"https://orcid.org/0000-0002-3874-3083"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Weipeng He","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jean-Marc Odobez","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103162780"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":16.4141,"has_fulltext":false,"cited_by_count":198,"citation_normalized_percentile":{"value":0.99408169,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"79"},"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":0.9976000189781189,"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":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7638514041900635},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.6798262596130371},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6747132539749146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6136474609375},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5116572976112366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4796450734138489},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4508518576622009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35318395495414734},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.21145561337471008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638514041900635},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.6798262596130371},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6747132539749146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136474609375},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5116572976112366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4796450734138489},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4508518576622009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35318395495414734},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.21145561337471008},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2018.8461267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1711.11565","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.11565","pdf_url":"https://arxiv.org/pdf/1711.11565","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:256279","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256279","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256279","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:256336","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256336","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256336","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.11565","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.11565","pdf_url":"https://arxiv.org/pdf/1711.11565","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1603075283","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2035083192","https://openalex.org/W2046317813","https://openalex.org/W2078528333","https://openalex.org/W2100818340","https://openalex.org/W2101856597","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2162654459","https://openalex.org/W2168772277","https://openalex.org/W2403149086","https://openalex.org/W2405404760","https://openalex.org/W2586642235","https://openalex.org/W2592109325","https://openalex.org/W2595770358","https://openalex.org/W2964304707","https://openalex.org/W6633847657","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6713369370"],"related_works":["https://openalex.org/W4235381733","https://openalex.org/W2355022049","https://openalex.org/W2060429446","https://openalex.org/W8302103","https://openalex.org/W2741782512","https://openalex.org/W3011302839","https://openalex.org/W2392958391","https://openalex.org/W3155227409","https://openalex.org/W2386709048","https://openalex.org/W2898682874"],"abstract_inverted_index":{"We":[0],"propose":[1,69],"to":[2,20,55],"use":[3,93],"neural":[4,25,39],"networks":[5],"for":[6,100],"simultaneous":[7],"detection":[8,61,81],"and":[9,62],"localization":[10,29,102],"of":[11,60,73,82,86,94],"multiple":[12,56],"sound":[13,27,49,104],"sources":[14,57],"in":[15,58,103],"human-robot":[16],"interaction.":[17],"In":[18,64,88],"contrast":[19],"conventional":[21],"signal":[22],"processing":[23],"techniques,":[24],"network-based":[26,40],"source":[28],"methods":[30,41,129],"require":[31],"fewer":[32],"strong":[33],"assumptions":[34],"about":[35],"the":[36,74,80,92,132],"environment.":[37],"Previous":[38],"have":[42],"been":[43],"focusing":[44],"on":[45,114,118],"localizing":[46],"a":[47,70,123],"single":[48],"source,":[50],"which":[51,77],"do":[52],"not":[53],"extend":[54],"terms":[59],"localization.":[63],"this":[65],"paper,":[66],"we":[67,90],"thus":[68],"likelihood-based":[71],"encoding":[72],"network":[75,111],"output,":[76],"naturally":[78],"allows":[79],"an":[83],"arbitrary":[84],"number":[85],"sources.":[87],"addition,":[89],"investigate":[91],"sub-band":[95],"cross-correlation":[96],"information":[97],"as":[98,106,108],"features":[99],"better":[101],"mixtures,":[105],"well":[107],"three":[109],"different":[110,115],"architectures":[112],"based":[113],"motivations.":[116],"Experiments":[117],"real":[119],"data":[120],"recorded":[121],"from":[122],"robot":[124],"show":[125],"that":[126],"our":[127],"proposed":[128],"significantly":[130],"outperform":[131],"popular":[133],"spatial":[134],"spectrum-based":[135],"approaches.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
