{"id":"https://openalex.org/W2399100775","doi":"https://doi.org/10.1109/icassp.2016.7472640","title":"Towards PLDA-RBM based speaker recognition in mobile environment: Designing stacked/deep PLDA-RBM systems","display_name":"Towards PLDA-RBM based speaker recognition in mobile environment: Designing stacked/deep PLDA-RBM systems","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2399100775","doi":"https://doi.org/10.1109/icassp.2016.7472640","mag":"2399100775"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5019383045","display_name":"Andreas Nautsch","orcid":null},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]},{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andreas Nautsch","raw_affiliation_strings":["Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany","institution_ids":["https://openalex.org/I107257983","https://openalex.org/I4210099379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101983101","display_name":"Hong Hao","orcid":"https://orcid.org/0000-0001-7509-8653"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]},{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]},{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]}],"countries":["DE","DK"],"is_corresponding":false,"raw_author_name":"Hong Hao","raw_affiliation_strings":["Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany","Department of Applied Mathematics and Computer Science, Technical University of Denmark"],"affiliations":[{"raw_affiliation_string":"Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany","institution_ids":["https://openalex.org/I107257983","https://openalex.org/I4210099379"]},{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Centre de Recherche Informatique de Montr\u00e9al (CRIM), Canada"],"affiliations":[{"raw_affiliation_string":"Centre de Recherche Informatique de Montr\u00e9al (CRIM), Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087866084","display_name":"Christian Rathgeb","orcid":"https://orcid.org/0000-0003-1901-9468"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]},{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Rathgeb","raw_affiliation_strings":["Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany","institution_ids":["https://openalex.org/I107257983","https://openalex.org/I4210099379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017716310","display_name":"Christoph Busch","orcid":"https://orcid.org/0000-0002-9159-2923"},"institutions":[{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]},{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Busch","raw_affiliation_strings":["Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Da/sec - Biometrics and Internet Security Research Group, Hochschule Darmstadt, Germany","institution_ids":["https://openalex.org/I107257983","https://openalex.org/I4210099379"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019383045"],"corresponding_institution_ids":["https://openalex.org/I107257983","https://openalex.org/I4210099379"],"apc_list":null,"apc_paid":null,"fwci":0.4434,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78449457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5055","last_page":"5059"},"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":0.9986000061035156,"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":0.998199999332428,"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":0.821265697479248},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6939509510993958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6598228812217712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723525881767273},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5359687805175781},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.5272295475006104},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5215137600898743},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48086100816726685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45816877484321594},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.44401875138282776},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43829280138015747},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4280620217323303},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4143812954425812},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07430285215377808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821265697479248},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6939509510993958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6598228812217712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723525881767273},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5359687805175781},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.5272295475006104},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5215137600898743},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48086100816726685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45816877484321594},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.44401875138282776},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43829280138015747},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4280620217323303},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4143812954425812},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07430285215377808},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/f84ec9b5-ea83-4419-9b34-702e1cce464c","is_oa":false,"landing_page_url":"https://orbit.dtu.dk/en/publications/f84ec9b5-ea83-4419-9b34-702e1cce464c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nautsch , A , Hao , H , Stafylakis , T , Rathgeb , C &amp; Busch , C 2016 , Towards PLDA-RBM based speaker recognition in mobile environment: Designing stacked/deep PLDA-RBM systems . in Proceedings of 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . IEEE , I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings , 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing , Shanghai , China , 20/03/2016 . https://doi.org/10.1109/ICASSP.2016.7472640","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"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/W34085441","https://openalex.org/W1836183712","https://openalex.org/W2023238506","https://openalex.org/W2042492924","https://openalex.org/W2072128103","https://openalex.org/W2107091340","https://openalex.org/W2122702209","https://openalex.org/W2127411213","https://openalex.org/W2150769028","https://openalex.org/W2188092098","https://openalex.org/W2203070340","https://openalex.org/W2395750323","https://openalex.org/W2397634864","https://openalex.org/W2402626018","https://openalex.org/W2942177450","https://openalex.org/W3145164839","https://openalex.org/W4231109964","https://openalex.org/W4246070010","https://openalex.org/W6601341518","https://openalex.org/W6638844259","https://openalex.org/W6686818234","https://openalex.org/W6688261204","https://openalex.org/W6712325649","https://openalex.org/W6712908891","https://openalex.org/W7034203491"],"related_works":["https://openalex.org/W2952018105","https://openalex.org/W2916681395","https://openalex.org/W4283272532","https://openalex.org/W2119341610","https://openalex.org/W2556473569","https://openalex.org/W2193475944","https://openalex.org/W4302433642","https://openalex.org/W2529583158","https://openalex.org/W2551541394","https://openalex.org/W2601133591"],"abstract_inverted_index":{"The":[0,88],"vast":[1],"majority":[2],"of":[3,85,103,114],"text-independent":[4],"speaker":[5,35,80],"recognition":[6,81],"systems":[7],"rely":[8],"on":[9,54,57,65,105,109],"intermediate-sized":[10],"vectors":[11],"(i-vectors),":[12],"which":[13,44,70],"are":[14,40,62],"compared":[15],"by":[16,100],"probabilistic":[17],"linear":[18],"discriminant":[19],"analysis":[20],"(PLDA).":[21],"This":[22],"paper":[23],"proposes":[24],"a":[25,58,72],"PLDA-alike":[26],"approach":[27,99],"with":[28,82],"restricted":[29],"Boltzmann":[30],"machines":[31],"for":[32,78],"i-vector":[33],"based":[34],"recognition:":[36],"two":[37],"deep":[38],"architectures":[39],"presented":[41],"and":[42,50,74,107],"examined,":[43],"aim":[45],"at":[46],"suppressing":[47],"channel":[48],"effects":[49],"recovering":[51],"speaker-discriminative":[52],"information":[53],"back-ends":[55],"trained":[56],"small":[59],"dataset.":[60],"Experiments":[61],"carried":[63],"out":[64],"the":[66,92,96],"MOBIO":[67],"SRE'13":[68],"database,":[69],"is":[71],"challenging":[73],"publicly":[75],"available":[76],"dataset":[77],"mobile":[79],"limited":[83],"amounts":[84],"training":[86],"data.":[87],"experiments":[89],"show":[90],"that":[91],"proposed":[93],"system":[94],"outperforms":[95],"baseline":[97],"i-vector/PLDA":[98],"relative":[101],"gains":[102],"31%":[104],"female":[106],"9%":[108],"male":[110],"speakers":[111],"in":[112],"terms":[113],"half":[115],"total":[116],"error":[117],"rate.":[118]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
