{"id":"https://openalex.org/W2134676611","doi":"https://doi.org/10.1109/icassp.2013.6639183","title":"Using binarual processing for automatic speech recognition in multi-talker scenes","display_name":"Using binarual processing for automatic speech recognition in multi-talker scenes","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2134676611","doi":"https://doi.org/10.1109/icassp.2013.6639183","mag":"2134676611"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036912609","display_name":"Constantin Spille","orcid":"https://orcid.org/0000-0002-4226-7470"},"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":"Constantin Spille","raw_affiliation_strings":["Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066524428","display_name":"Mathias Dietz","orcid":"https://orcid.org/0000-0002-1830-469X"},"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":"Mathias Dietz","raw_affiliation_strings":["Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002002386","display_name":"Volker Hohmann","orcid":"https://orcid.org/0000-0001-7056-1880"},"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":"Volker Hohmann","raw_affiliation_strings":["Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"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":"Bernd T. Meyer","raw_affiliation_strings":["Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Physics, Carl von Ossietzky Universit\u00e4t Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Med. Phys., Carl-von-Ossietzky Univ. Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129877168"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"7805","last_page":"7809"},"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":0.9995999932289124,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.998199999332428,"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":0.8733630180358887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8049759268760681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7721953392028809},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.5570938587188721},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.4891870319843292},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.48705342411994934},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45521682500839233},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4465633034706116},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.44538700580596924},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44508078694343567},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4364880919456482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42398011684417725},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2506638765335083},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1736573874950409},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07882639765739441}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8733630180358887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8049759268760681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721953392028809},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.5570938587188721},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.4891870319843292},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.48705342411994934},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45521682500839233},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4465633034706116},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.44538700580596924},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44508078694343567},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4364880919456482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42398011684417725},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2506638765335083},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1736573874950409},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07882639765739441},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W258638584","https://openalex.org/W1517146827","https://openalex.org/W1964538581","https://openalex.org/W1965159237","https://openalex.org/W1970563292","https://openalex.org/W1998303870","https://openalex.org/W2009649672","https://openalex.org/W2034040413","https://openalex.org/W2071988465","https://openalex.org/W2093225945","https://openalex.org/W2120688778","https://openalex.org/W2145647377","https://openalex.org/W2148154194","https://openalex.org/W2155636609","https://openalex.org/W2166817508","https://openalex.org/W3105118415","https://openalex.org/W3148168866","https://openalex.org/W4256399001","https://openalex.org/W4285719527","https://openalex.org/W6603616073","https://openalex.org/W6609694752","https://openalex.org/W6630906535"],"related_works":["https://openalex.org/W2113060204","https://openalex.org/W2786302331","https://openalex.org/W2110678343","https://openalex.org/W2782029243","https://openalex.org/W2539207221","https://openalex.org/W1921088284","https://openalex.org/W2935873029","https://openalex.org/W2295827011","https://openalex.org/W2772030003","https://openalex.org/W2033988353"],"abstract_inverted_index":{"The":[0,40,72],"segregation":[1],"of":[2,13,47,54,120,134,154],"concurrent":[3],"speakers":[4,56],"and":[5,37,70,81,137],"other":[6],"sound":[7],"sources":[8],"is":[9,19,75],"an":[10,98],"important":[11],"aspect":[12],"the":[14,52,92,106,118,121,143],"human":[15,36],"auditory":[16],"system":[17],"but":[18],"missing":[20],"in":[21,31,57,100],"most":[22],"current":[23],"systems":[24],"for":[25,132],"automatic":[26],"speech":[27],"recognition":[28,108],"(ASR),":[29],"resulting":[30],"a":[32,44,58,78,82,151],"large":[33],"gap":[34],"between":[35],"machine":[38],"performance.":[39],"present":[41],"study":[42],"uses":[43],"physiologically-motivated":[45],"model":[46,74],"binaural":[48,73],"hearing":[49],"to":[50,84,110,115,142],"estimate":[51],"position":[53],"moving":[55],"noisy":[59,126],"environment":[60],"by":[61,91],"combining":[62],"methods":[63],"from":[64,113],"Computational":[65],"Auditory":[66],"Scene":[67],"Analysis":[68],"(CASA)":[69],"ASR.":[71],"paired":[76],"with":[77],"particle":[79],"filter":[80],"beamformer":[83],"enhance":[85],"spoken":[86],"sentences":[87],"that":[88,147],"are":[89],"transcribed":[90],"ASR":[93],"system.":[94],"Results":[95],"based":[96],"on":[97],"evaluation":[99],"clean,":[101],"anechoic":[102],"two-speaker":[103],"condition":[104],"shows":[105],"word":[107],"rates":[109],"be":[111],"increased":[112],"30.8%":[114],"72.6%,":[116],"demonstrating":[117],"potential":[119],"CASA-based":[122],"approach.":[123],"In":[124],"different":[125],"environments,":[127],"improvements":[128],"were":[129,148],"also":[130],"observed":[131],"SNRs":[133],"5":[135],"dB":[136],"above,":[138],"which":[139],"was":[140],"attributed":[141],"average":[144],"tracking":[145],"errors":[146],"consistent":[149],"over":[150],"wide":[152],"range":[153],"SNRs.":[155]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}