{"id":"https://openalex.org/W2055611715","doi":"https://doi.org/10.1109/taslp.2014.2308398","title":"Robust Speaker Identification in Noisy and Reverberant Conditions","display_name":"Robust Speaker Identification in Noisy and Reverberant Conditions","publication_year":2014,"publication_date":"2014-02-25","ids":{"openalex":"https://openalex.org/W2055611715","doi":"https://doi.org/10.1109/taslp.2014.2308398","mag":"2055611715"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2308398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2308398","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/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","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"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":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"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","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"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":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, 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":["Department of Computer Science and Engineering & Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering and Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & 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 and Engineering and Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#","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":12.6731,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.9916048,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"22","issue":"4","first_page":"836","last_page":"845"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/reverberation","display_name":"Reverberation","score":0.9206721782684326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.736409068107605},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.7167675495147705},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7107504606246948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6631819009780884},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49805688858032227},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.490681529045105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43848133087158203},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42831116914749146},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42354488372802734},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.41748809814453125},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41522645950317383},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38639122247695923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3647773265838623},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3303648829460144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16985076665878296}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9206721782684326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.736409068107605},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7167675495147705},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7107504606246948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6631819009780884},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49805688858032227},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.490681529045105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43848133087158203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42831116914749146},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42354488372802734},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.41748809814453125},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41522645950317383},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38639122247695923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3647773265838623},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3303648829460144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16985076665878296},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2308398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2308398","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":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W204053250","https://openalex.org/W1888813847","https://openalex.org/W1963970749","https://openalex.org/W1967590528","https://openalex.org/W1974387177","https://openalex.org/W1989364685","https://openalex.org/W1991646723","https://openalex.org/W2006384862","https://openalex.org/W2027804983","https://openalex.org/W2031834500","https://openalex.org/W2041823554","https://openalex.org/W2044063703","https://openalex.org/W2047919706","https://openalex.org/W2061140267","https://openalex.org/W2066755975","https://openalex.org/W2069883713","https://openalex.org/W2070432038","https://openalex.org/W2074354966","https://openalex.org/W2085191029","https://openalex.org/W2096496615","https://openalex.org/W2103825654","https://openalex.org/W2117678320","https://openalex.org/W2118479009","https://openalex.org/W2121061347","https://openalex.org/W2122982914","https://openalex.org/W2129379984","https://openalex.org/W2131753991","https://openalex.org/W2133095132","https://openalex.org/W2136922672","https://openalex.org/W2139959413","https://openalex.org/W2147455188","https://openalex.org/W2150769028","https://openalex.org/W2153485077","https://openalex.org/W2156855092","https://openalex.org/W2164432048","https://openalex.org/W2166817508","https://openalex.org/W2168379380","https://openalex.org/W2339276216","https://openalex.org/W2561557072","https://openalex.org/W2970850616","https://openalex.org/W4233392025","https://openalex.org/W4301749645"],"related_works":["https://openalex.org/W2126085626","https://openalex.org/W2544039643","https://openalex.org/W2545131480","https://openalex.org/W208363076","https://openalex.org/W2087341511","https://openalex.org/W4230495983","https://openalex.org/W1946464671","https://openalex.org/W2141917278","https://openalex.org/W1843883989","https://openalex.org/W2162533796"],"abstract_inverted_index":{"Robustness":[0],"of":[1,23,75,99],"speaker":[2,34,65],"recognition":[3],"systems":[4,94],"is":[5],"crucial":[6],"for":[7],"real-world":[8],"applications,":[9],"which":[10],"typically":[11],"contain":[12],"both":[13],"additive":[14,24],"noise":[15,25,49],"and":[16,26,78,102],"room":[17],"reverberation.":[18],"However,":[19],"the":[20,73,85],"combined":[21],"effects":[22],"convolutive":[27],"reverberation":[28,100],"have":[29],"been":[30],"rarely":[31],"studied":[32],"in":[33,42,68,95],"identification":[35],"(SID).":[36],"This":[37],"paper":[38],"addresses":[39],"this":[40],"issue":[41],"two":[43],"phases.":[44],"We":[45],"first":[46],"remove":[47],"background":[48],"through":[50],"binary":[51],"masking":[52],"using":[53],"a":[54,96],"deep":[55],"neural":[56],"network":[57],"classifier.":[58],"Then":[59],"we":[60],"perform":[61],"robust":[62],"SID":[63,90],"with":[64],"models":[66],"trained":[67],"selected":[69],"reverberant":[70],"conditions,":[71],"on":[72],"basis":[74],"bounded":[76],"marginalization":[77],"direct":[79],"masking.":[80],"Evaluation":[81],"results":[82],"show":[83],"that":[84],"proposed":[86],"system":[87],"substantially":[88],"improves":[89],"performance":[91],"over":[92],"related":[93],"wide":[97],"range":[98],"time":[101],"signal-to-noise":[103],"ratios.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}