{"id":"https://openalex.org/W2015121520","doi":"https://doi.org/10.1109/iscslp.2014.6936722","title":"An iVector extractor using pre-trained neural networks for speaker verification","display_name":"An iVector extractor using pre-trained neural networks for speaker verification","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2015121520","doi":"https://doi.org/10.1109/iscslp.2014.6936722","mag":"2015121520"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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/A5100412142","display_name":"Shanshan Zhang","orcid":"https://orcid.org/0000-0003-4013-6300"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Zhang","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing","[Interactive Digital Media Technology Research Center Institute of Automation, Chinese Academy of Sciences, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Interactive Digital Media Technology Research Center Institute of Automation, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090419456","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0002-0991-4939"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing","[Interactive Digital Media Technology Research Center Institute of Automation, Chinese Academy of Sciences, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Interactive Digital Media Technology Research Center Institute of Automation, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062895972","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-5453-978X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing","[Interactive Digital Media Technology Research Center Institute of Automation, Chinese Academy of Sciences, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"[Interactive Digital Media Technology Research Center Institute of Automation, Chinese Academy of Sciences, Beijing, China]","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"73","last_page":"77"},"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":0.9945999979972839,"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":0.9922000169754028,"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/nist","display_name":"NIST","score":0.8801373243331909},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8129086494445801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7897522449493408},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6990875005722046},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6828055381774902},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6346479058265686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6189295649528503},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5953404903411865},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5641242861747742},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5444543957710266},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5356058478355408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4420342743396759},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4149585962295532},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4119688868522644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4000672996044159},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07613098621368408}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8801373243331909},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8129086494445801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897522449493408},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6990875005722046},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6828055381774902},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6346479058265686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6189295649528503},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5953404903411865},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5641242861747742},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5444543957710266},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5356058478355408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4420342743396759},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4149585962295532},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4119688868522644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4000672996044159},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07613098621368408},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1663973292","https://openalex.org/W2012897754","https://openalex.org/W2046056978","https://openalex.org/W2116064496","https://openalex.org/W2123237149","https://openalex.org/W2141083997","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2397474108","https://openalex.org/W2404874347","https://openalex.org/W6601785968","https://openalex.org/W6713414053"],"related_works":["https://openalex.org/W1521299571","https://openalex.org/W2767892728","https://openalex.org/W4235705411","https://openalex.org/W2395619480","https://openalex.org/W1998549096","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506"],"abstract_inverted_index":{"The":[0],"iVector":[1,20,77,91],"representation":[2],"of":[3,66,110],"speech":[4],"utterances":[5],"is":[6,26,54],"currently":[7],"widely":[8],"used":[9],"in":[10,104],"speaker":[11,29,57],"and":[12,115],"language":[13],"recognition":[14],"tasks.":[15],"In":[16,44],"this":[17],"paper,":[18],"an":[19,36],"extractor":[21],"using":[22],"pre-trained":[23],"neural":[24,49],"networks":[25],"proposed":[27,46,112],"for":[28],"verification.":[30],"It":[31],"can":[32],"be":[33],"viewed":[34],"as":[35],"alternative":[37],"to":[38,69],"the":[39,45,63,67,71,84,111,116],"classical":[40],"total":[41],"variability":[42],"approach.":[43],"system,":[47],"a":[48,75,101],"network":[50,68],"with":[51,56,83,108],"bottleneck":[52,64],"layer":[53],"trained":[55],"labeled":[58],"utterances,":[59],"then":[60],"we":[61],"utilize":[62],"features":[65],"represent":[70],"input":[72],"utterance.":[73],"As":[74],"new":[76],"representation,":[78],"it":[79],"shows":[80],"comparable":[81],"performance":[82],"state-of-the-art":[85],"Total":[86],"Variability":[87],"Model":[88],"(TVM)":[89],"based":[90],"extraction":[92,113],"system":[93,114],"on":[94],"NIST":[95],"2008":[96],"SRE.":[97],"We":[98],"further":[99],"achieve":[100],"10%":[102],"reduction":[103],"equal":[105],"error":[106],"rates":[107],"combination":[109],"TVM":[117],"system.":[118]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}