{"id":"https://openalex.org/W2612339271","doi":"https://doi.org/10.1109/iscslp.2016.7918436","title":"Neural networks based channel compensation for i-vector speaker verification","display_name":"Neural networks based channel compensation for i-vector speaker verification","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2612339271","doi":"https://doi.org/10.1109/iscslp.2016.7918436","mag":"2612339271"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045487306","display_name":"KongAik Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"KongAik Lee","raw_affiliation_strings":["Human Language Technology Department, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Human Language Technology Department, A*STAR, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Human Language Technology Department, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4416,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81792505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9959999918937683,"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":0.979200005531311,"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/computer-science","display_name":"Computer science","score":0.7742013335227966},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7013412714004517},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6285490393638611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6010210514068604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5920828580856323},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5888754725456238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5867915749549866},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5645835995674133},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.536151647567749},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4660671055316925},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4642428159713745},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43995437026023865},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43750476837158203},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4124802350997925},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.380038321018219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742013335227966},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7013412714004517},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6285490393638611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010210514068604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5920828580856323},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5888754725456238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5867915749549866},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5645835995674133},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.536151647567749},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4660671055316925},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4642428159713745},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43995437026023865},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43750476837158203},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4124802350997925},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.380038321018219},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W128628490","https://openalex.org/W1524333225","https://openalex.org/W1985043720","https://openalex.org/W2009086942","https://openalex.org/W2039057510","https://openalex.org/W2050693797","https://openalex.org/W2076434944","https://openalex.org/W2078169166","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2148091317","https://openalex.org/W2150769028","https://openalex.org/W2156913409","https://openalex.org/W2160815625","https://openalex.org/W2180339972","https://openalex.org/W2395750323","https://openalex.org/W2402626018","https://openalex.org/W2405774341","https://openalex.org/W2406312423","https://openalex.org/W2485419308","https://openalex.org/W2488005896","https://openalex.org/W2951630015","https://openalex.org/W6601785968","https://openalex.org/W6605273041","https://openalex.org/W6631362777","https://openalex.org/W6677390740","https://openalex.org/W6713658392","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Linear":[0],"discriminant":[1],"analysis":[2],"(LDA)":[3],"and":[4,16,44,50,81,101,105,111,131,162],"Gaussian":[5,55],"probabilistic":[6],"LDA":[7,110,130],"(PLDA)":[8],"have":[9],"been":[10],"shown":[11],"to":[12,37,70,129],"effectively":[13],"suppress":[14],"channel-":[15],"session-variability":[17],"of":[18,42,79,135,142,146],"i-vectors.":[19],"But":[20],"they":[21,58],"suffer":[22],"the":[23,39,48,72,76,133,157],"following":[24],"limitations:":[25],"1)":[26],"In":[27],"LDA,":[28,160],"a":[29,54,68],"single":[30],"linear":[31],"transformation":[32],"may":[33],"not":[34,83],"be":[35],"adequate":[36],"describe":[38],"nonlinear":[40,77],"relationship":[41,78],"features":[43,80],"2)":[45],"Gaussian-PLDA":[46],"assumes":[47],"speaker":[49,118],"channel":[51,93,124],"factors":[52],"follow":[53],"distribution,":[56],"but":[57],"are":[59,127],"actually":[60],"non-Gaussians.":[61],"We":[62],"consider":[63],"neural":[64],"networks":[65],"(NN)":[66],"as":[67],"way":[69],"overcome":[71],"limitations,":[73],"that":[74,122,132,141],"captures":[75],"does":[82],"require":[84],"prior":[85],"assumptions.":[86],"This":[87],"paper":[88,152],"investigates":[89],"three":[90],"NN":[91,99,136,163],"based":[92,164],"compensation":[94,125],"methods:":[95],"deep":[96,102],"metric":[97],"learning,":[98],"classifier,":[100],"denoising":[103],"autoencoder":[104],"compares":[106],"their":[107],"performance":[108,134],"with":[109],"PLDA.":[112],"Experiments":[113],"conducted":[114],"on":[115],"NIST":[116],"2010":[117],"recognition":[119],"evaluation":[120,148],"suggest":[121],"NN-based":[123],"methods":[126],"superior":[128],"classifier":[137],"is":[138],"better":[139],"than":[140],"PLDA":[143],"under":[144],"most":[145],"common":[147],"conditions.":[149],"Additionally,":[150],"this":[151],"also":[153],"helps":[154],"us":[155],"understand":[156],"relationships":[158],"among":[159],"PLDA,":[161],"methods.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}