{"id":"https://openalex.org/W2900109395","doi":"https://doi.org/10.1109/icassp.2019.8683445","title":"How to Improve Your Speaker Embeddings Extractor in Generic Toolkits","display_name":"How to Improve Your Speaker Embeddings Extractor in Generic Toolkits","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2900109395","doi":"https://doi.org/10.1109/icassp.2019.8683445","mag":"2900109395"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.02066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002474493","display_name":"Hossein Zeinali","orcid":"https://orcid.org/0000-0002-8921-1052"},"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":"Hossein Zeinali","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, 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":["Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239262","display_name":"Johan Rohdin","orcid":"https://orcid.org/0000-0003-0978-2064"},"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":"Johan Rohdin","raw_affiliation_strings":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Omilia - Conversational Intelligence, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Omilia - Conversational Intelligence, Athens, Greece","institution_ids":[]}]},{"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 Cernocky","raw_affiliation_strings":["Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2028,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84315834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":null,"first_page":"6141","last_page":"6145"},"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":0.9975000023841858,"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":0.9951000213623047,"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/overfitting","display_name":"Overfitting","score":0.8740738034248352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8034704923629761},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5067611336708069},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48413142561912537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4330154061317444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34497880935668945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3349118232727051}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8740738034248352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034704923629761},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5067611336708069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48413142561912537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4330154061317444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34497880935668945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3349118232727051}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.02066","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.02066","pdf_url":"https://arxiv.org/pdf/1811.02066","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2900109395","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1811.02066","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1811.02066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.02066","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.02066","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.02066","pdf_url":"https://arxiv.org/pdf/1811.02066","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W2039057510","https://openalex.org/W2121812409","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2150769028","https://openalex.org/W2183016404","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2399828378","https://openalex.org/W2485419308","https://openalex.org/W2491474862","https://openalex.org/W2516631658","https://openalex.org/W2587150483","https://openalex.org/W2606778926","https://openalex.org/W2612122134","https://openalex.org/W2766191375","https://openalex.org/W2794506738","https://openalex.org/W2805332618","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2897435617","https://openalex.org/W2949117887","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6687442591","https://openalex.org/W6688816777","https://openalex.org/W6712943345","https://openalex.org/W6740167877","https://openalex.org/W6745983287","https://openalex.org/W6752234738","https://openalex.org/W6756022612"],"related_works":["https://openalex.org/W2890964092","https://openalex.org/W3025075133","https://openalex.org/W3149926570","https://openalex.org/W2898924647","https://openalex.org/W2779266008","https://openalex.org/W2736569854","https://openalex.org/W2963565199","https://openalex.org/W3107798002","https://openalex.org/W3198987135","https://openalex.org/W2888546277","https://openalex.org/W3202667537","https://openalex.org/W3174154133","https://openalex.org/W2992548114","https://openalex.org/W2886422331","https://openalex.org/W2414994497","https://openalex.org/W3030267806","https://openalex.org/W2888839716","https://openalex.org/W2983165789","https://openalex.org/W2889266829","https://openalex.org/W3214220351"],"abstract_inverted_index":{"Recently,":[0],"speaker":[1,13],"embeddings":[2],"extracted":[3],"with":[4],"deep":[5],"neural":[6],"networks":[7],"became":[8],"the":[9,39,49,81,101,110,113],"state-of-the-art":[10],"method":[11],"for":[12,60],"verification.":[14],"In":[15,77],"this":[16],"paper":[17],"we":[18,32,79],"aim":[19],"to":[20,34],"facilitate":[21],"its":[22],"implementation":[23],"on":[24,38,98],"a":[25],"more":[26],"generic":[27],"toolkit":[28],"than":[29],"Kaldi,":[30],"which":[31],"anticipate":[33],"enable":[35],"further":[36],"improvements":[37],"method.":[40],"We":[41],"examine":[42],"several":[43],"tricks":[44],"in":[45,83,100],"training,":[46],"such":[47],"as":[48,63,65],"effects":[50],"of":[51,73,93,112],"normalizing":[52],"input":[53],"features":[54],"and":[55,87,89,105],"pooled":[56],"statistics,":[57],"different":[58],"methods":[59],"preventing":[61],"overfitting":[62],"well":[64],"alternative":[66],"non-linearities":[67],"that":[68],"can":[69],"be":[70],"used":[71],"instead":[72],"Rectifier":[74],"Linear":[75],"Units.":[76],"addition,":[78],"investigate":[80],"difference":[82],"performance":[84],"between":[85,90],"TDNN":[86],"CNN,":[88],"two":[91],"types":[92],"attention":[94],"mechanism.":[95],"Experimental":[96],"results":[97],"Speaker":[99],"Wild,":[102],"SRE":[103,106],"2016":[104],"2018":[107],"datasets":[108],"demonstrate":[109],"effectiveness":[111],"proposed":[114],"implementation.":[115]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}