{"id":"https://openalex.org/W2662639535","doi":"https://doi.org/10.1109/icassp.2017.7953095","title":"Variational manifold learning for speaker recognition","display_name":"Variational manifold learning for speaker recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2662639535","doi":"https://doi.org/10.1109/icassp.2017.7953095","mag":"2662639535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111323345","display_name":"Cheng-Wei Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Wei Hsu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4935","last_page":"4939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6210579872131348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6003288626670837},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5884249806404114},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.5698715448379517},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.549220621585846},{"id":"https://openalex.org/keywords/manifold-alignment","display_name":"Manifold alignment","score":0.5394580960273743},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.526134729385376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5153304934501648},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.48978400230407715},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4472603499889374},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43915486335754395},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.43379640579223633},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4244970381259918},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39479121565818787},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.19202110171318054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6210579872131348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003288626670837},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5884249806404114},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.5698715448379517},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.549220621585846},{"id":"https://openalex.org/C153120616","wikidata":"https://www.wikidata.org/wiki/Q17068315","display_name":"Manifold alignment","level":4,"score":0.5394580960273743},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.526134729385376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5153304934501648},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48978400230407715},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4472603499889374},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43915486335754395},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.43379640579223633},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4244970381259918},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39479121565818787},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.19202110171318054},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1539175566","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2049633694","https://openalex.org/W2121812409","https://openalex.org/W2143797877","https://openalex.org/W2150769028","https://openalex.org/W2157444450","https://openalex.org/W2162055300","https://openalex.org/W2180339972","https://openalex.org/W2187089797","https://openalex.org/W2396848693","https://openalex.org/W2405331948","https://openalex.org/W2408468826","https://openalex.org/W2941689885","https://openalex.org/W2962897886","https://openalex.org/W2964121744","https://openalex.org/W4212863985","https://openalex.org/W6631190155","https://openalex.org/W6632384406","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6681474766","https://openalex.org/W6683161245"],"related_works":["https://openalex.org/W3109610583","https://openalex.org/W2387045723","https://openalex.org/W2375518579","https://openalex.org/W117517268","https://openalex.org/W2944373987","https://openalex.org/W2112684860","https://openalex.org/W2391701611","https://openalex.org/W2149544245","https://openalex.org/W3000568127","https://openalex.org/W2923551166"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,55,60,66,98],"variational":[4,45,58,75,83,108],"manifold":[5,67,109,133],"learning":[6,46,68,134],"for":[7,57,69],"speaker":[8,125],"recognition":[9,126],"based":[10,62],"on":[11,63,122],"the":[12,28,31,37,82,90,93,102,106,118,128],"probabilistic":[13],"linear":[14],"discriminant":[15],"analysis":[16],"(PLDA)":[17],"using":[18,41],"i-vectors.":[19,42,119],"A":[20,43,72],"latent":[21,103],"variable":[22],"model":[23],"is":[24,47,78,95],"introduced":[25],"to":[26,49,80],"compensate":[27],"constraints":[29],"of":[30,86,114,130],"linearity":[32],"in":[33,40,92,105,132],"PLDA":[34,64,110],"scoring":[35],"and":[36,65,124,135],"high":[38],"dimensionality":[39],"deep":[44],"formulated":[48],"jointly":[50],"optimize":[51,81],"three":[52],"objectives":[53,94],"including":[54],"regularization":[56],"distributions,":[59],"reconstruction":[61],"neighbor":[70],"embedding.":[71],"stochastic":[73],"gradient":[74],"Bayesian":[76],"algorithm":[77],"developed":[79],"lower":[84],"bound":[85],"log":[87],"likelihood":[88],"where":[89],"expectation":[91],"estimated":[96],"via":[97],"sampling":[99],"method.":[100],"Interestingly,":[101],"variables":[104],"proposed":[107],"(vm-PLDA)":[111],"are":[112],"capable":[113],"decoding":[115],"or":[116],"reconstructing":[117],"The":[120],"experiments":[121],"visualization":[123],"show":[127],"merits":[129],"vm-PLDA":[131],"classification.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}