{"id":"https://openalex.org/W2407857848","doi":"https://doi.org/10.1109/icassp.2016.7472649","title":"Analysis of DNN approaches to speaker identification","display_name":"Analysis of DNN approaches to speaker identification","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407857848","doi":"https://doi.org/10.1109/icassp.2016.7472649","mag":"2407857848"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472649","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/A5076315361","display_name":"Pavel Mat\u011bjka","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Pavel Matejka","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008717681","display_name":"Ond\u0159ej Glembek","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ondrej Glembek","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075269577","display_name":"Ond\u0159ej Novotn\u00fd","orcid":"https://orcid.org/0000-0001-6258-9971"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ondrej Novotny","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Oldrich Plchot","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112655592","display_name":"Franti\u0161ek Gr\u00e9zl","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Frantisek Grezl","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076315361"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":15.22135147,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99545068,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5100","last_page":"5104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9976999759674072,"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":0.8248995542526245},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8222103118896484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640072107315063},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7569675445556641},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6965571045875549},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5632348656654358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5420641899108887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5369642972946167},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5086889863014221},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5074285864830017},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5063546895980835},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.505795955657959},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4443351924419403},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4198979139328003},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15539765357971191},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10834425687789917}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8248995542526245},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8222103118896484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640072107315063},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7569675445556641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6965571045875549},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5632348656654358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5420641899108887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5369642972946167},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5086889863014221},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5074285864830017},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5063546895980835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.505795955657959},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4443351924419403},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4198979139328003},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15539765357971191},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10834425687789917},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472649","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W128628490","https://openalex.org/W153983408","https://openalex.org/W1006777433","https://openalex.org/W1528954144","https://openalex.org/W1909308924","https://openalex.org/W1969121061","https://openalex.org/W1970890968","https://openalex.org/W2004497042","https://openalex.org/W2039057510","https://openalex.org/W2056119007","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2185814970","https://openalex.org/W2397450537","https://openalex.org/W2398569491","https://openalex.org/W2399270979","https://openalex.org/W2402919203","https://openalex.org/W2405950182","https://openalex.org/W2406215990","https://openalex.org/W2962853205","https://openalex.org/W6605273041","https://openalex.org/W6606260724","https://openalex.org/W6631542512","https://openalex.org/W6682600690","https://openalex.org/W6714096116"],"related_works":["https://openalex.org/W2888091758","https://openalex.org/W2134209752","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2104528589","https://openalex.org/W4229940372","https://openalex.org/W2186375278","https://openalex.org/W2749720872","https://openalex.org/W2793748347","https://openalex.org/W4250904811"],"abstract_inverted_index":{"This":[0],"work":[1],"studies":[2],"the":[3,6,16,21,29,48,59,65,78,81,86,97,106],"usage":[4,49],"of":[5,23,50,67],"Deep":[7],"Neural":[8],"Network":[9],"(DNN)":[10],"Bottleneck":[11],"(BN)":[12],"features":[13,19,54],"together":[14],"with":[15],"traditional":[17,98],"MFCC":[18,53,99],"in":[20,58,111],"task":[22],"i-vector-based":[24],"speaker":[25],"recognition.":[26],"We":[27,62],"decouple":[28],"sufficient":[30],"statistics":[31,43],"extraction":[32],"by":[33],"using":[34,68],"separate":[35],"GMM":[36,70],"models":[37],"for":[38,42,101,105],"frame":[39],"alignment,":[40],"and":[41,45,52],"normalization":[44],"we":[46,76,91],"analyze":[47],"BN":[51],"(and":[55,103],"their":[56],"concatenation)":[57],"two":[60],"stages.":[61],"also":[63],"show":[64,92],"effect":[66],"full-covariance":[69],"models,":[71],"and,":[72],"as":[73],"a":[74],"contrast,":[75],"compare":[77],"result":[79],"to":[80],"recent":[82],"DNN-alignment":[83],"approach.":[84],"On":[85],"NIST":[87,107],"SRE2010,":[88],"telephone":[89],"condition,":[90],"60%":[93],"relative":[94],"gain":[95],"over":[96],"baseline":[100],"EER":[102],"similar":[104],"DCF":[108],"metrics),":[109],"resulting":[110],"0.94%":[112],"EER.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}