{"id":"https://openalex.org/W49975404","doi":null,"title":"Speaker recognition by means of Deep Belief Networks","display_name":"Speaker recognition by means of Deep Belief Networks","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W49975404","mag":"49975404"},"language":"en","primary_location":{"id":"pmh:oai:iris.polito.it:11583/2518972","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11583/2518972","pdf_url":"https://iris.polito.it/bitstream/11583/2518972/1/btfs2013_submission_5.pdf","source":{"id":"https://openalex.org/S7407055329","display_name":"PORTO@Iris","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://iris.polito.it/bitstream/11583/2518972/1/btfs2013_submission_5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009419243","display_name":"Vasileios Vasilakakis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasileios Vasilakakis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015516603","display_name":"Sandro Cumani","orcid":"https://orcid.org/0000-0001-6036-0065","observed_orcids":["https://orcid.org/0000-0001-6036-0065"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandro Cumani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6036-0065","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023812879","display_name":"Pietro Laface","orcid":"https://orcid.org/0000-0003-2841-7695","observed_orcids":["https://orcid.org/0000-0003-2841-7695"]},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Laface","raw_affiliation_strings":["POLYTECHNIC UNIVERSITY OF TURIN"],"raw_orcid":"https://orcid.org/0000-0003-2841-7695","affiliations":[{"raw_affiliation_string":"POLYTECHNIC UNIVERSITY OF TURIN","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6653,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97134378,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/speaker-recognition","display_name":"speaker recognition","score":0.9980000257492065},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"deep belief network","score":0.9860000014305115},{"id":"https://openalex.org/keywords/factor-analysis","display_name":"factor analysis","score":0.5820000171661377},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.7039999961853027},{"id":"https://openalex.org/keywords/inter-session-variability","display_name":"inter-session variability","score":0.8019999861717224},{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.39899998903274536},{"id":"https://openalex.org/keywords/nist-speaker-recognition-evaluation","display_name":"NIST Speaker Recognition Evaluation","score":0.8349999785423279}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.762492299079895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063767910003662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6458625793457031},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5973514318466187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5946733355522156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869415998458862},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5662565231323242},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5569797158241272},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.5497314929962158},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5490992665290833},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5404772162437439},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4962506890296936},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48886317014694214},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.45681843161582947},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37640756368637085},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:iris.polito.it:11583/2518972","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11583/2518972","pdf_url":"https://iris.polito.it/bitstream/11583/2518972/1/btfs2013_submission_5.pdf","source":{"id":"https://openalex.org/S7407055329","display_name":"PORTO@Iris","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:porto.polito.it:2518972","doi":null,"is_oa":true,"landing_page_url":"http://porto.polito.it/2518972/","pdf_url":"http://porto.polito.it/2518972/","source":{"id":"https://openalex.org/S4306402038","display_name":"PORTO Publications Open Repository TOrino (Politecnico di Torino)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I177477856","host_organization_name":"Politecnico di Torino","host_organization_lineage":["https://openalex.org/I177477856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:49975404","doi":null,"is_oa":false,"landing_page_url":"https://cls.ru.nl/staff/dvleeuwen/btfs-2013/vasilakakis-btfs2013.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:iris.polito.it:11583/2518972","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11583/2518972","pdf_url":"https://iris.polito.it/bitstream/11583/2518972/1/btfs2013_submission_5.pdf","source":{"id":"https://openalex.org/S7407055329","display_name":"PORTO@Iris","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W49975404.pdf","grobid_xml":"https://content.openalex.org/works/W49975404.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W128628490","https://openalex.org/W204053250","https://openalex.org/W1481676178","https://openalex.org/W2000359198","https://openalex.org/W2069883713","https://openalex.org/W2091432990","https://openalex.org/W2116064496","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2159948109","https://openalex.org/W2165237516","https://openalex.org/W2167458787","https://openalex.org/W2184045248","https://openalex.org/W2294814385","https://openalex.org/W2397634864","https://openalex.org/W2399828378","https://openalex.org/W2405403457","https://openalex.org/W2406312423"],"related_works":["https://openalex.org/W2400388989","https://openalex.org/W2215795812","https://openalex.org/W2167136086","https://openalex.org/W2039057510","https://openalex.org/W2803697965","https://openalex.org/W2405950182","https://openalex.org/W2296295429","https://openalex.org/W2183016404","https://openalex.org/W2942915498","https://openalex.org/W2181350785"],"abstract_inverted_index":{"Most":[0],"state-of-the-art":[1],"speaker":[2,141],"recognition":[3],"systems":[4,151],"are":[5],"based":[6],"on":[7,144],"Gaussian":[8],"Mixture":[9],"Models":[10],"(GMMs),":[11],"where":[12],"a":[13,19,52,77,80,100,133],"speech":[14],"segment":[15],"is":[16,42,49,115],"represented":[17],"by":[18,31,132],"compact":[20],"representation,":[21],"referred":[22],"to":[23,51,74],"as":[24,76],"\"identity":[25],"vector\"":[26],"(ivector":[27],"for":[28,148,156],"short),":[29],"extracted":[30],"means":[32],"of":[33,39,46,65,90,103,125,136],"Factor":[34],"Analysis.":[35],"The":[36],"main":[37],"advantage":[38],"this":[40,70,95,163],"representation":[41],"that":[43,111,138,152],"the":[44,62,66,88,97,104,109,118,123,126,140,145,150,157],"problem":[45],"intersession":[47],"variability":[48],"deferred":[50],"second":[53],"stage,":[54],"dealing":[55],"with":[56,61,87],"low-dimensional":[57],"vectors":[58],"rather":[59],"than":[60],"high-dimensional":[63],"space":[64],"GMM":[67],"means.":[68],"In":[69,94],"paper,":[71],"we":[72],"propose":[73],"use":[75],"pseudo-ivector":[78],"extractor":[79],"Deep":[81],"Belief":[82],"Network":[83],"(DBN)":[84],"architecture,":[85],"trained":[86],"utterances":[89],"several":[91],"hundred":[92],"speakers.":[93],"approach,":[96],"DBN":[98],"performs":[99],"non-linear":[101],"transformation":[102],"input":[105,119],"features,":[106],"which":[107],"produces":[108],"probability":[110],"an":[112,130],"output":[113,127],"unit":[114],"on,":[116],"given":[117,129],"features.":[120],"We":[121],"model":[122],"distribution":[124],"units,":[128],"utterance,":[131],"reduced":[134],"set":[135],"parameters":[137],"embed":[139],"characteristics.":[142],"Tested":[143],"dataset":[146],"exploited":[147],"training":[149],"have":[153],"been":[154],"used":[155],"NIST":[158],"2012":[159],"Speaker":[160],"Recognition":[161],"Evaluation,":[162],"approach":[164],"shows":[165],"promising":[166],"results":[167]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}