{"id":"https://openalex.org/W2405339854","doi":"https://doi.org/10.21437/interspeech.2014-150","title":"Identifying the human-machine differences in complex binaural scenes: what can be learned from our auditory system","display_name":"Identifying the human-machine differences in complex binaural scenes: what can be learned from our auditory system","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2405339854","doi":"https://doi.org/10.21437/interspeech.2014-150","mag":"2405339854"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-150","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-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/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":["Univ. of Oldenburg"],"affiliations":[{"raw_affiliation_string":"Univ. of Oldenburg","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":["Univ. of Oldenburg"],"affiliations":[{"raw_affiliation_string":"Univ. of Oldenburg","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036912609"],"corresponding_institution_ids":["https://openalex.org/I129877168"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28024999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11698","display_name":"Underwater Acoustics Research","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8965442180633545},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.78890061378479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7424725890159607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6787396669387817},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5973494052886963},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45909082889556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39449113607406616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3610283136367798},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3425726294517517},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0713067352771759}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8965442180633545},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.78890061378479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7424725890159607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787396669387817},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5973494052886963},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45909082889556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39449113607406616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610283136367798},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3425726294517517},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0713067352771759},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-150","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W6681681","https://openalex.org/W88081813","https://openalex.org/W102404664","https://openalex.org/W1964538581","https://openalex.org/W1965159237","https://openalex.org/W1990934990","https://openalex.org/W1991112797","https://openalex.org/W1993882792","https://openalex.org/W1994514225","https://openalex.org/W2009049512","https://openalex.org/W2009649672","https://openalex.org/W2027890689","https://openalex.org/W2057662515","https://openalex.org/W2068984931","https://openalex.org/W2093225945","https://openalex.org/W2120688778","https://openalex.org/W2124882279","https://openalex.org/W2134676611","https://openalex.org/W2145647377","https://openalex.org/W2151484683","https://openalex.org/W2152131029","https://openalex.org/W2163680580","https://openalex.org/W2334904945","https://openalex.org/W2395143415","https://openalex.org/W3105118415"],"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":{"Previous":[0],"comparisons":[1,146],"of":[2,32,39,68,76,136],"human":[3],"speech":[4,9,103],"recognition":[5,10,104,116],"(HSR)":[6],"and":[7,19,29,64,88],"automatic":[8],"(ASR)":[11],"focused":[12],"on":[13,144],"monaural":[14,141],"signals":[15],"in":[16,51,57,99,140],"additive":[17],"noise,":[18],"showed":[20],"that":[21,80,123,147,185],"HSR":[22],"is":[23,42,97,118],"far":[24],"more":[25,52],"robust":[26],"against":[27],"intrinsic":[28],"extrinsic":[30],"sources":[31],"variation":[33],"than":[34],"conventional":[35],"ASR.":[36],"The":[37,93,120,178],"aim":[38],"this":[40],"study":[41],"to":[43,74,127,160,169],"analyze":[44],"the":[45,102,108,124,134,152],"man-machine":[46,95],"gap":[47,96,125],"(and":[48],"its":[49],"causes)":[50],"complex":[53],"acoustic":[54],"scenarios,":[55],"particularly":[56],"scenes":[58],"with":[59,173],"two":[60],"moving":[61],"speakers,":[62],"reverberation":[63],"diffuse":[65],"noise.":[66],"Responses":[67],"nine":[69],"normal-hearing":[70],"listeners":[71],"are":[72,158],"compared":[73],"errors":[75,162],"an":[77],"ASR":[78,183],"system":[79],"employs":[81],"a":[82,113],"binaural":[83,191],"model":[84],"for":[85,90,101],"direction-of-arrival":[86],"estimation":[87],"beamforming":[89],"signal":[91,193],"enhancement.":[92],"overall":[94],"measured":[98],"terms":[100],"threshold":[105],"(SRT),":[106],"i.e.,":[107],"signal-to-noise":[109],"ratio":[110],"at":[111],"which":[112,132],"50":[114],"%":[115],"rate":[117],"obtained.":[119],"comparison":[121,179],"shows":[122],"amounts":[126],"16.7":[128],"dB":[129,138],"SRT":[130],"difference":[131,135],"exceeds":[133],"10":[137],"found":[139],"situations.":[142],"Based":[143],"cross":[145],"use":[148],"oracle":[149],"knowledge":[150],"(e.g.,":[151],"speakers\u2019":[153],"true":[154],"position),":[155],"incorrect":[156],"responses":[157],"attributed":[159],"localization":[161],"(7":[163],"dB)":[164],"or":[165],"missing":[166],"spectral":[167],"information":[168],"distinguish":[170],"between":[171],"speakers":[172],"different":[174],"gender":[175],"(3":[176],"dB).":[177],"hence":[180],"identifies":[181],"specific":[182],"components":[184],"can":[186],"profit":[187],"from":[188,190],"learning":[189],"auditory":[192],"processing.":[194]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}