{"id":"https://openalex.org/W2403228223","doi":"https://doi.org/10.21437/interspeech.2014-521","title":"Binaural deep neural network classification for reverberant speech segregation","display_name":"Binaural deep neural network classification for reverberant speech segregation","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2403228223","doi":"https://doi.org/10.21437/interspeech.2014-521","mag":"2403228223"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-521","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-521","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":"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/A5101528596","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0003-0453-3130"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034981144","display_name":"Runsheng Liu","orcid":"https://orcid.org/0009-0005-0591-4770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"RunSheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2400","last_page":"2404"},"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":0.9991000294685364,"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":0.9987000226974487,"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":0.8782767057418823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459061145782471},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7332698106765747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7281315922737122},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6415817737579346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6343097686767578},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5315952897071838},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5032128691673279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4421391785144806},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.4182666540145874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33394238352775574},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.12859168648719788},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09366762638092041},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08331435918807983},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07536929845809937}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8782767057418823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459061145782471},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7332698106765747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7281315922737122},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6415817737579346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6343097686767578},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5315952897071838},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5032128691673279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4421391785144806},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.4182666540145874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33394238352775574},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.12859168648719788},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09366762638092041},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08331435918807983},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07536929845809937},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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:10.21437/interspeech.2014-521","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-521","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":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1575829986","https://openalex.org/W1581848821","https://openalex.org/W1963970749","https://openalex.org/W1966849888","https://openalex.org/W1974387177","https://openalex.org/W1979099822","https://openalex.org/W2034040413","https://openalex.org/W2044063703","https://openalex.org/W2044222806","https://openalex.org/W2057662515","https://openalex.org/W2111890897","https://openalex.org/W2114218864","https://openalex.org/W2136922672","https://openalex.org/W2166682639","https://openalex.org/W2561557072"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W4377018054","https://openalex.org/W2337758134","https://openalex.org/W2022765019","https://openalex.org/W4244700398","https://openalex.org/W1991739683","https://openalex.org/W2051221393","https://openalex.org/W2048646427","https://openalex.org/W4249720907"],"abstract_inverted_index":{"While":[0],"human":[1],"listening":[2],"is":[3],"robust":[4],"in":[5,17,27,62],"complex":[6],"auditory":[7],"scenes,":[8],"current":[9],"speech":[10,29],"segregation":[11,30,60],"algorithms":[12],"do":[13],"not":[14],"perform":[15],"well":[16],"noisy":[18],"and":[19,50,67],"reverberant":[20,68],"environments.":[21],"This":[22],"paper":[23],"addresses":[24],"the":[25],"robustness":[26],"binaural":[28,56],"by":[31],"employing":[32],"binary":[33],"classification":[34,57],"based":[35,55],"on":[36],"deep":[37],"neural":[38],"networks":[39],"(DNNs).":[40],"We":[41],"systematically":[42],"examine":[43],"DNN":[44,54],"generalization":[45],"to":[46],"untrained":[47],"configurations.":[48],"Evaluations":[49],"comparisons":[51],"show":[52],"that":[53],"produces":[58],"superior":[59],"performance":[61],"a":[63],"variety":[64],"of":[65],"multisource":[66],"conditions.":[69]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
