{"id":"https://openalex.org/W2044063703","doi":"https://doi.org/10.1109/tasl.2012.2193391","title":"A Binaural Scene Analyzer for Joint Localization and Recognition of Speakers in the Presence of Interfering Noise Sources and Reverberation","display_name":"A Binaural Scene Analyzer for Joint Localization and Recognition of Speakers in the Presence of Interfering Noise Sources and Reverberation","publication_year":2012,"publication_date":"2012-04-12","ids":{"openalex":"https://openalex.org/W2044063703","doi":"https://doi.org/10.1109/tasl.2012.2193391","mag":"2044063703"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2193391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2193391","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5052043106","display_name":"Tobias May","orcid":"https://orcid.org/0000-0002-5463-5509"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias May","raw_affiliation_strings":["Institute of Physics, University of Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005034522","display_name":"Steven van de Par","orcid":"https://orcid.org/0000-0002-3360-2011"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steven van de Par","raw_affiliation_strings":["Institute of Physics, University of Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112244882","display_name":"Armin Kohlrausch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122849","display_name":"Philips (Netherlands)","ror":"https://ror.org/02p2bgp27","country_code":"NL","type":"company","lineage":["https://openalex.org/I4210122849"]},{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Armin Kohlrausch","raw_affiliation_strings":["Philips Research, Eindhoven, Netherlands","School of Innovation vation Science, Eindhovan University of Technology, Eindhoven, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Research, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I4210122849"]},{"raw_affiliation_string":"School of Innovation vation Science, Eindhovan University of Technology, Eindhoven, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8736,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.9681915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"20","issue":"7","first_page":"2016","last_page":"2030"},"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":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.8841257095336914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7688008546829224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7448981404304504},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7000039219856262},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5029579997062683},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4866264760494232},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.47537317872047424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39100050926208496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3764670789241791},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.31895357370376587},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09264013171195984},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08426940441131592}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8841257095336914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688008546829224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7448981404304504},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7000039219856262},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5029579997062683},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4866264760494232},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.47537317872047424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39100050926208496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3764670789241791},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.31895357370376587},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09264013171195984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08426940441131592},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tasl.2012.2193391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2193391","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:publications/551abe6e-388e-4d05-aa53-3d68ddbf7b72","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/551abe6e-388e-4d05-aa53-3d68ddbf7b72","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"May, T, Par, van de, S L J D E & Kohlrausch, A G 2012, 'A binaural scene analyzer for joint localization and recognition of speakers in the presence of interfering noise sources and reverberation', IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 7, pp. 2016-2030. https://doi.org/10.1109/TASL.2012.2193391","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:747749","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=747749","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN:1558-7916","raw_type":"Article / Letter to the editor"},{"id":"pmh:oai:library.tue.nl:747749","is_oa":false,"landing_page_url":"http://repository.tue.nl/747749","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN:1558-7916","raw_type":"Article / Letter to the editor"},{"id":"pmh:tue:oai:pure.tue.nl:publications/551abe6e-388e-4d05-aa53-3d68ddbf7b72","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/551abe6e-388e-4d05-aa53-3d68ddbf7b72","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing, 20(7), 2016 - 2030. Institute of Electrical and Electronics Engineers","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321651","display_name":"Technische Universiteit Eindhoven","ror":"https://ror.org/02c2kyt77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W3703470","https://openalex.org/W90966543","https://openalex.org/W160800111","https://openalex.org/W1558276682","https://openalex.org/W1631909651","https://openalex.org/W1677705107","https://openalex.org/W1865095259","https://openalex.org/W1963970749","https://openalex.org/W1964538581","https://openalex.org/W1968483846","https://openalex.org/W1991139021","https://openalex.org/W1996759108","https://openalex.org/W2026205542","https://openalex.org/W2027701650","https://openalex.org/W2034040413","https://openalex.org/W2039081291","https://openalex.org/W2041823554","https://openalex.org/W2044222806","https://openalex.org/W2049633694","https://openalex.org/W2050758723","https://openalex.org/W2057851139","https://openalex.org/W2057889776","https://openalex.org/W2059145199","https://openalex.org/W2060011767","https://openalex.org/W2074354966","https://openalex.org/W2075076415","https://openalex.org/W2086139506","https://openalex.org/W2088399049","https://openalex.org/W2096554907","https://openalex.org/W2098882755","https://openalex.org/W2106325442","https://openalex.org/W2107274532","https://openalex.org/W2109816922","https://openalex.org/W2117678320","https://openalex.org/W2121973264","https://openalex.org/W2122562222","https://openalex.org/W2129697784","https://openalex.org/W2130283666","https://openalex.org/W2130775302","https://openalex.org/W2134162816","https://openalex.org/W2139102950","https://openalex.org/W2142328794","https://openalex.org/W2146083413","https://openalex.org/W2150008717","https://openalex.org/W2150593711","https://openalex.org/W2152488273","https://openalex.org/W2158698691","https://openalex.org/W2166682639","https://openalex.org/W2166817508","https://openalex.org/W3124666641","https://openalex.org/W3129711340","https://openalex.org/W4256399001","https://openalex.org/W6637354246","https://openalex.org/W6679535723","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W1982169876","https://openalex.org/W2770624987","https://openalex.org/W4256175191","https://openalex.org/W2964951088","https://openalex.org/W2280467666","https://openalex.org/W2100854157","https://openalex.org/W4247725880","https://openalex.org/W2978471304","https://openalex.org/W2564915558","https://openalex.org/W2130168793"],"abstract_inverted_index":{"In":[0,34],"this":[1],"study,":[2],"we":[3],"present":[4],"a":[5,18,49,79,92,112,121,136],"binaural":[6,39,69,80,133],"scene":[7],"analyzer":[8],"that":[9,124],"is":[10,82,101,125,141,156],"able":[11],"to":[12,36,84,103,111,115,143,165],"simultaneously":[13],"localize,":[14],"detect":[15],"and":[16,32,74],"identify":[17],"known":[19],"number":[20],"of":[21,27,56,64,148],"target":[22,58],"speakers":[23],"in":[24,159],"the":[25,43,53,57,132,145,170],"presence":[26],"spatially":[28],"positioned":[29],"noise":[30,118],"sources":[31],"reverberation.":[33],"contrast":[35],"many":[37],"other":[38],"cocktail":[40],"party":[41],"processors,":[42],"proposed":[44,61,154,171],"system":[45,62,155],"does":[46],"not":[47],"require":[48],"priori":[50],"knowledge":[51],"about":[52],"azimuth":[54],"position":[55],"speakers.":[59],"The":[60,153],"consists":[63],"three":[65],"main":[66],"building":[67],"blocks:":[68],"localization,":[70],"speech":[71,93,151],"source":[72,89,108,119],"detection,":[73],"automatic":[75],"speaker":[76,113,146,175],"identification.":[77],"First,":[78],"front-end":[81],"used":[83,142],"robustly":[85],"localize":[86],"relevant":[87],"sound":[88,107],"activity.":[90],"Second,":[91],"detection":[94],"module":[95],"based":[96,126],"on":[97,127],"missing":[98,138],"data":[99,139],"classification":[100],"employed":[102],"determine":[104],"whether":[105],"detected":[106,150],"activity":[109],"corresponds":[110],"or":[114],"an":[116],"interfering":[117],"using":[120],"binary":[122],"mask":[123],"spatial":[128],"evidence":[129],"supplied":[130],"by":[131],"front-end.":[134],"Third,":[135],"second":[137],"classifier":[140],"recognize":[144],"identities":[147],"all":[149],"sources.":[152],"systematically":[157],"evaluated":[158],"simulated":[160],"adverse":[161],"acoustic":[162],"scenarios.":[163],"Compared":[164],"state-of-the":[166],"art":[167],"MFCC":[168],"recognizers,":[169],"model":[172],"achieves":[173],"significant":[174],"recognition":[176],"accuracy":[177],"improvements.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}