{"id":"https://openalex.org/W3015985683","doi":"https://doi.org/10.1109/icassp40776.2020.9053198","title":"Orthogonal Training for Text-Independent Speaker Verification","display_name":"Orthogonal Training for Text-Independent Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015985683","doi":"https://doi.org/10.1109/icassp40776.2020.9053198","mag":"3015985683"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5064702198","display_name":"Yingke Zhu","orcid":"https://orcid.org/0000-0002-9370-6082"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yingke Zhu","raw_affiliation_strings":["Department of Computer Science & Engineering, The Hong Kong University of Science & Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Hong Kong University of Science & Technology","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":["Department of Computer Science & Engineering, The Hong Kong University of Science & Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, The Hong Kong University of Science & Technology","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064702198"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67339091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6584","last_page":"6588"},"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":0.9990000128746033,"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":0.996399998664856,"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/orthogonality","display_name":"Orthogonality","score":0.7649357318878174},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.7172565460205078},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.7139711380004883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5951138734817505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5576161742210388},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.5035490393638611},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.49766042828559875},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45387545228004456},{"id":"https://openalex.org/keywords/singular-value","display_name":"Singular value","score":0.4488426446914673},{"id":"https://openalex.org/keywords/orthogonal-matrix","display_name":"Orthogonal matrix","score":0.4335607886314392},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43274497985839844},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4164109528064728},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41377368569374084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4132537543773651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36171674728393555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35773754119873047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30874013900756836}],"concepts":[{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7649357318878174},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.7172565460205078},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.7139711380004883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5951138734817505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5576161742210388},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.5035490393638611},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.49766042828559875},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45387545228004456},{"id":"https://openalex.org/C109282560","wikidata":"https://www.wikidata.org/wiki/Q4166054","display_name":"Singular value","level":3,"score":0.4488426446914673},{"id":"https://openalex.org/C44292817","wikidata":"https://www.wikidata.org/wiki/Q333871","display_name":"Orthogonal matrix","level":3,"score":0.4335607886314392},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43274497985839844},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4164109528064728},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41377368569374084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4132537543773651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36171674728393555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35773754119873047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30874013900756836},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C187064257","wikidata":"https://www.wikidata.org/wiki/Q3306808","display_name":"Orthogonal basis","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-104398","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-104398","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-104398","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-104398","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2125930537","https://openalex.org/W2134192361","https://openalex.org/W2178237821","https://openalex.org/W2516631658","https://openalex.org/W2551557006","https://openalex.org/W2552391848","https://openalex.org/W2553902701","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2888867175","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2963103976","https://openalex.org/W2964130064","https://openalex.org/W2972961496","https://openalex.org/W3010925296","https://openalex.org/W4295126650","https://openalex.org/W4300537377","https://openalex.org/W6635152626","https://openalex.org/W6732884072"],"related_works":["https://openalex.org/W34220","https://openalex.org/W1614943","https://openalex.org/W7655147","https://openalex.org/W11060696","https://openalex.org/W7296353","https://openalex.org/W11080984","https://openalex.org/W8440297","https://openalex.org/W5871360","https://openalex.org/W404804","https://openalex.org/W1954738"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"orthogonal":[5,159,176],"training":[6,89,160,177],"schemes":[7],"to":[8,23,31,42,96],"improve":[9,181],"the":[10,24,63,71,74,97,101,117,122,126,131,136,140,147,168,182],"effectiveness":[11],"of":[12,49,73,100],"cosine":[13,27,50,64,187],"similarity":[14,28,51,65,188],"measurements":[15],"in":[16,84,106,139],"text-independent":[17],"speaker":[18,75,102],"verification":[19],"(SV)":[20],"tasks.":[21],"Compared":[22],"PLDA":[25],"backend,":[26],"is":[29,53,80,143,150],"simple":[30],"compute,":[32],"and":[33,115,130,146],"it":[34],"does":[35],"not":[36,82],"require":[37],"extra":[38],"data":[39],"or":[40],"time":[41,108],"build":[43],"a":[44,186],"separate":[45],"model.":[46],"The":[47,88],"use":[48],"measurement":[52],"also":[54],"highly":[55],"desirable":[56],"for":[57],"building":[58],"end-to-end":[59],"SV":[60,86,113],"systems.":[61,87],"However,":[62],"has":[66],"an":[67,153],"underlying":[68],"assumption":[69],"that":[70,174],"dimensions":[72],"embeddings":[76],"are":[77],"orthogonal,":[78],"which":[79],"usually":[81],"satisfied":[83],"current":[85],"scheme":[90],"applies":[91],"singular":[92,132],"vector":[93],"decomposition":[94],"(SVD)":[95],"weight":[98,119],"matrix":[99,120,123,129,138],"embedding":[103],"extraction":[104,141],"layer":[105,142],"our":[107,175],"delay":[109],"neural":[110],"network":[111,149,169],"(TDNN)-based":[112],"system,":[114],"replaces":[116],"original":[118],"by":[121],"constructed":[124],"from":[125,161],"left":[127],"unitary":[128],"value":[133],"matrix.":[134],"Then":[135],"reconstructed":[137],"held":[144],"constant":[145],"remaining":[148],"fine-tuned":[151],"with":[152,163,185],"orthogonality":[154,164],"regularizer.":[155],"We":[156],"further":[157],"investigate":[158],"scratch,":[162],"regularization":[165],"incorporated":[166],"throughout":[167],"training.":[170],"Experimental":[171],"results":[172],"show":[173],"methods":[178],"can":[179],"significantly":[180],"system":[183],"performance":[184],"backend.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}