{"id":"https://openalex.org/W2939762919","doi":"https://doi.org/10.1109/icassp.2019.8683332","title":"Deep Speaker Representation Using Orthogonal Decomposition and Recombination for Speaker Verification","display_name":"Deep Speaker Representation Using Orthogonal Decomposition and Recombination for Speaker Verification","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939762919","doi":"https://doi.org/10.1109/icassp.2019.8683332","mag":"2939762919"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5022484330","display_name":"In-Soo Kim","orcid":"https://orcid.org/0000-0001-6539-1776"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Insoo Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology (SAIT), South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology (SAIT), South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032636394","display_name":"Kyu Hong Kim","orcid":"https://orcid.org/0000-0001-5738-2693"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuhong Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology (SAIT), South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology (SAIT), South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084518640","display_name":"Jiwhan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwhan Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology (SAIT), South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology (SAIT), South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045861786","display_name":"Changkyu Choi","orcid":"https://orcid.org/0000-0002-1470-8662"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changkyu Choi","raw_affiliation_strings":["Samsung Advanced Institute of Technology (SAIT), South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology (SAIT), South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7353,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88487308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6126","last_page":"6130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.9968000054359436,"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":0.7350224852561951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7185671329498291},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6249797344207764},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6232324242591858},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6148927211761475},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6064258217811584},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6049927473068237},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5173187255859375},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5140296220779419},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4841049909591675},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.4634086787700653},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4512386620044708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.392398476600647},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08145064115524292}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7350224852561951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185671329498291},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6249797344207764},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6232324242591858},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6148927211761475},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6064258217811584},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6049927473068237},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5173187255859375},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5140296220779419},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4841049909591675},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.4634086787700653},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4512386620044708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.392398476600647},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08145064115524292},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W17749540","https://openalex.org/W128628490","https://openalex.org/W1916834241","https://openalex.org/W1959608418","https://openalex.org/W2025768430","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2144760012","https://openalex.org/W2150769028","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2397634864","https://openalex.org/W2516547830","https://openalex.org/W2559823555","https://openalex.org/W2584329820","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2801581493","https://openalex.org/W2801608439","https://openalex.org/W2890493389","https://openalex.org/W2890654588","https://openalex.org/W2890704021","https://openalex.org/W2962959915","https://openalex.org/W2963911037","https://openalex.org/W6600721324","https://openalex.org/W6605273041","https://openalex.org/W6638444622","https://openalex.org/W6640010188","https://openalex.org/W6640963894","https://openalex.org/W6712325649","https://openalex.org/W6745983287","https://openalex.org/W6754615656"],"related_works":["https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W215245425","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504"],"abstract_inverted_index":{"Speech":[0],"signal":[1],"contains":[2],"intrinsic":[3],"and":[4,17,25,54,78],"extrinsic":[5],"variations":[6,22],"such":[7],"as":[8],"accent,":[9],"emotion,":[10],"dialect,":[11],"phoneme,":[12],"speaking":[13],"manner,":[14],"noise,":[15],"music,":[16],"reverberation.":[18],"Some":[19],"of":[20,29,48,117,123],"these":[21,79],"are":[23,26,81],"unnecessary":[24],"unspecified":[27,46],"factors":[28,32,47],"variation.":[30],"These":[31],"lead":[33],"to":[34,57,89,120],"increased":[35],"variability":[36,59],"in":[37,51,60],"speaker":[38,52,61,70,91,98],"representation.":[39,62],"In":[40],"this":[41],"paper,":[42],"we":[43,55],"assume":[44],"that":[45,67,105],"variation":[49],"exist":[50],"representations,":[53],"attempt":[56],"minimize":[58],"The":[63,101],"key":[64],"idea":[65],"is":[66],"a":[68,110],"primal":[69],"representation":[71,92],"can":[72],"be":[73],"decomposed":[74],"into":[75],"orthogonal":[76],"vectors":[77,80],"recombined":[82],"by":[83],"using":[84],"deep":[85],"neural":[86,127],"networks":[87],"(DNN)":[88],"reduce":[90],"variability,":[93],"yielding":[94],"performance":[95],"improvement":[96,141],"for":[97,142],"verification":[99],"(SV).":[100],"experimental":[102],"results":[103],"show":[104],"our":[106,136],"proposed":[107,137],"approach":[108],"produces":[109],"relative":[111],"equal":[112],"error":[113],"rate":[114],"(EER)":[115],"reduction":[116],"47.1%":[118],"compared":[119],"the":[121,124,132],"use":[122],"same":[125],"convolutional":[126],"network":[128],"(CNN)":[129],"architecture":[130],"on":[131],"Vox-Celeb":[133],"dataset.":[134],"Furthermore,":[135],"method":[138],"provides":[139],"significant":[140],"short":[143],"utterances.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}