{"id":"https://openalex.org/W2584408992","doi":"https://doi.org/10.1109/taslp.2017.2661712","title":"Combining Binaural and Cortical Features for Robust Speech Recognition","display_name":"Combining Binaural and Cortical Features for Robust Speech Recognition","publication_year":2017,"publication_date":"2017-01-31","ids":{"openalex":"https://openalex.org/W2584408992","doi":"https://doi.org/10.1109/taslp.2017.2661712","mag":"2584408992"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2661712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2661712","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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/A5036912609","display_name":"Constantin Spille","orcid":"https://orcid.org/0000-0002-4226-7470"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]},{"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":true,"raw_author_name":"Constantin Spille","raw_affiliation_strings":["Cluster of Excellence Hearing4all and Medizinische Physik, University of Oldenburg, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence Hearing4all and Medizinische Physik, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076869895","display_name":"Birger Kollmeier","orcid":"https://orcid.org/0000-0001-8584-4779"},"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"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Birger Kollmeier","raw_affiliation_strings":["Cluster of Excellence Hearing4all and Medizinische Physik, University of Oldenburg, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence Hearing4all and Medizinische Physik, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375","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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036912609"],"corresponding_institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":1.2945,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80549231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"25","issue":"4","first_page":"756","last_page":"767"},"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":0.9991999864578247,"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":0.9983999729156494,"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":0.8615077137947083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7613801956176758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6787571310997009},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.661422610282898},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5080282688140869},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4981231689453125},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48629483580589294},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4807307720184326},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.44555261731147766},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.4138548970222473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3854031562805176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3212518095970154},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2769068479537964},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.1719282567501068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13636049628257751},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10428336262702942}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8615077137947083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7613801956176758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787571310997009},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.661422610282898},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5080282688140869},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4981231689453125},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48629483580589294},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4807307720184326},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.44555261731147766},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.4138548970222473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3854031562805176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3212518095970154},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2769068479537964},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.1719282567501068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13636049628257751},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10428336262702942},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2661712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2661712","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W9692546","https://openalex.org/W104844710","https://openalex.org/W258638584","https://openalex.org/W1517146827","https://openalex.org/W1524333225","https://openalex.org/W1631909651","https://openalex.org/W1953873617","https://openalex.org/W1964538581","https://openalex.org/W1965159237","https://openalex.org/W1967590528","https://openalex.org/W1990934990","https://openalex.org/W1998303870","https://openalex.org/W2009649672","https://openalex.org/W2015293542","https://openalex.org/W2018384136","https://openalex.org/W2034040413","https://openalex.org/W2041638389","https://openalex.org/W2042687225","https://openalex.org/W2044063703","https://openalex.org/W2046099677","https://openalex.org/W2047919706","https://openalex.org/W2067841448","https://openalex.org/W2071988465","https://openalex.org/W2093225945","https://openalex.org/W2106405099","https://openalex.org/W2113107769","https://openalex.org/W2121973264","https://openalex.org/W2122001716","https://openalex.org/W2126151764","https://openalex.org/W2134676611","https://openalex.org/W2139916917","https://openalex.org/W2145647377","https://openalex.org/W2148154194","https://openalex.org/W2149283764","https://openalex.org/W2152131029","https://openalex.org/W2155636609","https://openalex.org/W2158010000","https://openalex.org/W2160779631","https://openalex.org/W2166067691","https://openalex.org/W2166817508","https://openalex.org/W2334904945","https://openalex.org/W2395809762","https://openalex.org/W2397260994","https://openalex.org/W2404548287","https://openalex.org/W2407835985","https://openalex.org/W3105118415","https://openalex.org/W4256399001","https://openalex.org/W4285719527","https://openalex.org/W6600365384","https://openalex.org/W6609694752","https://openalex.org/W6630906535","https://openalex.org/W6631362777","https://openalex.org/W6702735670","https://openalex.org/W6712407916","https://openalex.org/W6712652604","https://openalex.org/W6713630192","https://openalex.org/W6714050893"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W1970883244","https://openalex.org/W4367280804","https://openalex.org/W2333494157","https://openalex.org/W2076135780","https://openalex.org/W1987603461","https://openalex.org/W2080716336","https://openalex.org/W155806678","https://openalex.org/W1972459890","https://openalex.org/W4251652875"],"abstract_inverted_index":{"The":[0],"segregation":[1],"of":[2,13,50,62,137,144,154,159],"concurrent":[3,126],"speakers":[4,64],"and":[5,37,47,84,157,165],"other":[6],"sound":[7,155],"sources":[8,156],"is":[9,19],"an":[10],"important":[11],"ability":[12],"the":[14,51,60,67,135,160,173],"human":[15,36],"auditory":[16,52],"system,":[17],"but":[18],"missing":[20],"in":[21,31,92,101,115,121,134,176],"most":[22],"current":[23],"systems":[24],"for":[25],"automatic":[26],"speech":[27,69,82],"recognition":[28,99,174],"(ASR),":[29],"resulting":[30],"a":[32,125,138],"large":[33],"gap":[34],"between":[35],"machine":[38],"performance.":[39],"This":[40],"study":[41],"combines":[42],"processing":[43,113,130,146,149,170],"related":[44],"to":[45,65,75,89],"peripheral":[46],"cortical":[48,81],"stages":[49],"pathway:":[53],"A":[54],"physiologically":[55],"motivated":[56],"binaural":[57,145],"model":[58],"estimates":[59],"positions":[61],"moving":[63],"enhance":[66],"desired":[68],"signal.":[70],"Second,":[71],"signals":[72],"are":[73],"converted":[74],"spectro-temporal":[76],"Gabor":[77,96],"features":[78,97],"that":[79],"resemble":[80],"representations":[83],"which":[85],"have":[86],"been":[87],"shown":[88],"improve":[90,98],"ASR":[91],"noisy":[93],"conditions.":[94],"Spectro-temporal":[95],"results":[100,114],"all":[102],"acoustic":[103,122,177],"conditions":[104,178],"under":[105],"consideration":[106],"compared":[107],"with":[108,124,179],"Mel-frequency":[109],"cepstral":[110],"coefficients.":[111],"Binaural":[112],"lower":[116],"word":[117],"error":[118],"rates":[119],"(WERs)":[120],"scenes":[123],"speaker,":[127],"whereas":[128],"monaural":[129],"should":[131],"be":[132],"preferred":[133],"presence":[136],"stationary":[139],"masking":[140],"noise.":[141],"In-depth":[142],"analysis":[143],"identifies":[147],"crucial":[148],"steps":[150],"such":[151],"as":[152],"localization":[153],"estimation":[158],"beamformer's":[161],"noise":[162],"coherence":[163],"matrix,":[164],"shows":[166],"how":[167],"much":[168],"each":[169],"step":[171],"affects":[172],"performance":[175],"different":[180],"complexity.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}