{"id":"https://openalex.org/W3016912202","doi":"https://doi.org/10.1109/taslp.2020.2986896","title":"Robust Speaker Recognition Based on Single-Channel and Multi-Channel Speech Enhancement","display_name":"Robust Speaker Recognition Based on Single-Channel and Multi-Channel Speech Enhancement","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3016912202","doi":"https://doi.org/10.1109/taslp.2020.2986896","mag":"3016912202"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2986896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2986896","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/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"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":"Hassan Taherian","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0002-7548-3081","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0002-4204-9430","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029447474","display_name":"Jorge Chang","orcid":"https://orcid.org/0000-0002-9289-4480"},"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":"Jorge Chang","raw_affiliation_strings":["Department of Psychology, The Ohio State University, Columbus, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology, 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/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"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":["CN","US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi\u2019an, China","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA","Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3847,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97555226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"1293","last_page":"1302"},"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":0.9991999864578247,"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":0.9923999905586243,"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/speech-recognition","display_name":"Speech recognition","score":0.7382655143737793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6757497191429138},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6502647399902344},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5431129336357117},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5115388631820679},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4788125157356262},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.46686482429504395},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4153779447078705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3769758343696594},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.33336248993873596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3054308295249939},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14044004678726196},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08769506216049194}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7382655143737793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757497191429138},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6502647399902344},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5431129336357117},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5115388631820679},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4788125157356262},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.46686482429504395},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4153779447078705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3769758343696594},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.33336248993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3054308295249939},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14044004678726196},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08769506216049194},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2986896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2986896","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":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7513161494","display_name":null,"funder_award_id":"ECCS-1808932","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W46095808","https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1528954144","https://openalex.org/W1589137271","https://openalex.org/W1936725236","https://openalex.org/W1983812858","https://openalex.org/W2007645738","https://openalex.org/W2039057510","https://openalex.org/W2061140267","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2089586791","https://openalex.org/W2102346872","https://openalex.org/W2114925438","https://openalex.org/W2129066450","https://openalex.org/W2144244295","https://openalex.org/W2145846419","https://openalex.org/W2148024641","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2288645994","https://openalex.org/W2290689761","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2407127962","https://openalex.org/W2491474862","https://openalex.org/W2561557072","https://openalex.org/W2567070169","https://openalex.org/W2568308529","https://openalex.org/W2718052359","https://openalex.org/W2718701456","https://openalex.org/W2746457594","https://openalex.org/W2774389566","https://openalex.org/W2785523195","https://openalex.org/W2799831802","https://openalex.org/W2805332618","https://openalex.org/W2888954542","https://openalex.org/W2890964092","https://openalex.org/W2891219041","https://openalex.org/W2891803057","https://openalex.org/W2914926710","https://openalex.org/W2937813194","https://openalex.org/W2939497224","https://openalex.org/W2940275453","https://openalex.org/W2962866211","https://openalex.org/W2963127163","https://openalex.org/W2963488660","https://openalex.org/W2963970792","https://openalex.org/W2964351684","https://openalex.org/W2972425344","https://openalex.org/W2972992051","https://openalex.org/W4234330420","https://openalex.org/W6631362777","https://openalex.org/W6675700563","https://openalex.org/W6688816777","https://openalex.org/W6731370813","https://openalex.org/W6747620207"],"related_works":["https://openalex.org/W2100772705","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2135485548","https://openalex.org/W1975881626","https://openalex.org/W4252208810","https://openalex.org/W2020386191","https://openalex.org/W2373767407","https://openalex.org/W2187949121","https://openalex.org/W2376606440"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"embeddings":[4,45],"for":[5,48,58,105,166],"speaker":[6,49,60,134],"recognition":[7],"have":[8],"recently":[9],"attracted":[10],"much":[11],"attention.":[12],"Compared":[13],"to":[14,20,89],"i-vectors,":[15],"they":[16],"are":[17,40,46,73],"more":[18],"robust":[19,133],"noise":[21,70],"and":[22,54,71,86,101,138,151,159],"room":[23],"reverberation":[24,72],"as":[25,132],"DNNs":[26],"leverage":[27],"large-scale":[28],"training.":[29],"This":[30],"article":[31],"addresses":[32],"the":[33,119,141,167],"question":[34],"of":[35,114],"whether":[36],"speech":[37,56,78,107,153],"enhancement":[38,57,79,154],"approaches":[39],"still":[41],"useful":[42],"when":[43],"DNN":[44],"used":[47],"recognition.":[50],"We":[51,92,109],"investigate":[52,126],"single-":[53],"multi-channel":[55,106,152],"text-independent":[59],"verification":[61],"based":[62,81],"on":[63,82,140],"x-vectors":[64],"in":[65],"conditions":[66],"where":[67],"strong":[68],"diffuse":[69],"both":[74,149],"present.":[75],"Single-channel":[76],"(monaural)":[77],"is":[80,87,164],"complex":[83,121],"spectral":[84],"mapping":[85],"applied":[88],"individual":[90],"microphones.":[91],"use":[93],"masking-based":[94],"minimum":[95],"variance":[96],"distortion-less":[97],"response":[98],"(MVDR)":[99],"beamformer":[100],"its":[102],"rank-1":[103],"approximation":[104],"enhancement.":[108],"propose":[110],"a":[111],"novel":[112],"method":[113],"deriving":[115],"time-frequency":[116],"masks":[117],"from":[118],"estimated":[120],"spectrogram.":[122],"In":[123],"addition,":[124],"we":[125],"gammatone":[127],"frequency":[128],"cepstral":[129],"coefficients":[130],"(GFCCs)":[131],"features.":[135],"Systematic":[136],"evaluations":[137],"comparisons":[139],"NIST":[142],"SRE":[143],"2010":[144],"retransmitted":[145],"corpus":[146],"show":[147],"that":[148],"monaural":[150],"significantly":[155],"outperform":[156],"x-vector's":[157],"performance,":[158],"our":[160],"covariance":[161],"matrix":[162],"estimate":[163],"effective":[165],"MVDR":[168],"beamformer.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}