{"id":"https://openalex.org/W1484258769","doi":"https://doi.org/10.1109/icassp.2015.7178887","title":"Deep neural networks for cochannel speaker identification","display_name":"Deep neural networks for cochannel speaker identification","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1484258769","doi":"https://doi.org/10.1109/icassp.2015.7178887","mag":"1484258769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102205042","display_name":"Xiaojia Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaojia Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039091156","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-9153-3512"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102205042"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.5886,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91030484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4824","last_page":"4828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.8309491872787476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412267923355103},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6480046510696411},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6164560914039612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5867596864700317},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5257191061973572},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46096014976501465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4571925699710846}],"concepts":[{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.8309491872787476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412267923355103},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6480046510696411},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6164560914039612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5867596864700317},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5257191061973572},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46096014976501465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4571925699710846},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1639266067","https://openalex.org/W1951870577","https://openalex.org/W2041823554","https://openalex.org/W2055611715","https://openalex.org/W2061140267","https://openalex.org/W2069883713","https://openalex.org/W2079362249","https://openalex.org/W2105092968","https://openalex.org/W2106934198","https://openalex.org/W2109761419","https://openalex.org/W2117678320","https://openalex.org/W2119901478","https://openalex.org/W2123879651","https://openalex.org/W2157906748","https://openalex.org/W2165237516","https://openalex.org/W2168793898","https://openalex.org/W2170825946","https://openalex.org/W2403389749","https://openalex.org/W4233392025","https://openalex.org/W4390926420","https://openalex.org/W6636614438","https://openalex.org/W6676617595","https://openalex.org/W6684458083","https://openalex.org/W6713186265"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W4234190324","https://openalex.org/W321304764","https://openalex.org/W3162054169","https://openalex.org/W2249138175","https://openalex.org/W1521049138","https://openalex.org/W2154141294","https://openalex.org/W3035928819"],"abstract_inverted_index":{"Speaker":[0],"identification":[1],"(SID)":[2],"in":[3,26,43,55,90],"cochannel":[4,41,53,68,87],"speech,":[5],"where":[6],"two":[7,85],"speakers":[8],"are":[9],"talking":[10],"simultaneously":[11],"over":[12],"a":[13,18,72],"single":[14],"recording":[15],"channel,":[16],"is":[17],"challenging":[19],"problem.":[20],"Previous":[21],"studies":[22,52],"address":[23],"this":[24],"problem":[25],"the":[27,31,38,79,84],"anechoic":[28,57,92],"environment":[29],"under":[30],"Gaussian":[32],"mixture":[33],"model":[34],"(GMM)":[35],"framework.":[36],"On":[37],"other":[39],"hand,":[40],"SID":[42,54,69,88],"reverberant":[44,59,94],"conditions":[45,95],"has":[46],"not":[47],"been":[48],"addressed.":[49],"This":[50],"paper":[51],"both":[56,91],"and":[58,70,93,96],"conditions.":[60],"We":[61],"explore":[62],"deep":[63],"neural":[64],"networks":[65],"(DNNs)":[66],"for":[67],"propose":[71],"DNN-based":[73,81],"recognition":[74],"system.":[75],"Evaluation":[76],"results":[77],"demonstrate":[78],"proposed":[80],"system":[82],"outperforms":[83],"state-of-the-art":[86],"systems":[89],"various":[97],"target-to-interferer":[98],"ratios.":[99]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}