{"id":"https://openalex.org/W2937776600","doi":"https://doi.org/10.21437/interspeech.2019-2783","title":"STC Speaker Recognition Systems for the VOiCES from a Distance Challenge","display_name":"STC Speaker Recognition Systems for the VOiCES from a Distance Challenge","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2937776600","doi":"https://doi.org/10.21437/interspeech.2019-2783","mag":"2937776600"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2783","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.06093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109435545","display_name":"Sergey Novoselov","orcid":"https://orcid.org/0009-0009-9354-8967"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Novoselov","raw_affiliation_strings":["ITMO University, St Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University, St Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102708099","display_name":"Aleksei Gusev","orcid":"https://orcid.org/0009-0001-5200-747X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksei Gusev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275304","display_name":"Artem Ivanov","orcid":"https://orcid.org/0009-0001-6576-6547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artem Ivanov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029036362","display_name":"Timur Pekhovsky","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Timur Pekhovsky","raw_affiliation_strings":["ITMO University, St Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University, St Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072778309","display_name":"Andrey Shulipa","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Shulipa","raw_affiliation_strings":["ITMO University, St Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University, St Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047323209","display_name":"Galina Lavrentyeva","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Galina Lavrentyeva","raw_affiliation_strings":["ITMO University, St Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University, St Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084186518","display_name":"Vladimir Volokhov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Volokhov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108707228","display_name":"Alexandr Kozlov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandr Kozlov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.724,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77826341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2443","last_page":"2447"},"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":0.9998000264167786,"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":0.9983999729156494,"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":0.8090533018112183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.731448769569397},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6413023471832275},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5908086895942688},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5738525986671448},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5214621424674988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45490938425064087},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4528461694717407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41922807693481445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090533018112183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.731448769569397},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6413023471832275},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5908086895942688},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5738525986671448},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5214621424674988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45490938425064087},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4528461694717407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41922807693481445},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2783","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.06093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.06093","pdf_url":"https://arxiv.org/pdf/1904.06093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2937776600","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1904.06093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.1904.06093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.06093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:1904.06093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.06093","pdf_url":"https://arxiv.org/pdf/1904.06093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2937776600.pdf","grobid_xml":"https://content.openalex.org/works/W2937776600.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1481676178","https://openalex.org/W1524333225","https://openalex.org/W2164502538","https://openalex.org/W2170088868","https://openalex.org/W2404617565","https://openalex.org/W2516631658","https://openalex.org/W2609296554","https://openalex.org/W2796485741","https://openalex.org/W2796898542","https://openalex.org/W2798405286","https://openalex.org/W2807305309","https://openalex.org/W2888968865","https://openalex.org/W2889045432","https://openalex.org/W2890964092","https://openalex.org/W2916024349","https://openalex.org/W2963460857","https://openalex.org/W2972821391"],"related_works":["https://openalex.org/W2339276216","https://openalex.org/W3025515949","https://openalex.org/W3211614993","https://openalex.org/W3015231328","https://openalex.org/W2096594917","https://openalex.org/W2332932830","https://openalex.org/W2345067732","https://openalex.org/W2916058012","https://openalex.org/W2765233562","https://openalex.org/W3125394307","https://openalex.org/W3102370694","https://openalex.org/W3016048045","https://openalex.org/W3163929126","https://openalex.org/W2219249508","https://openalex.org/W2936847140","https://openalex.org/W3108184206","https://openalex.org/W3209376089","https://openalex.org/W1604738882","https://openalex.org/W2892204792","https://openalex.org/W1585307611"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,14,28,57,95,108,152,161,172],"Speech":[4],"Technology":[5],"Center":[6],"(STC)":[7],"speaker":[8,31,52],"recognition":[9,32,83],"(SR)":[10],"systems":[11,121,148,174],"submitted":[12,147],"to":[13,55],"VOiCES":[15,162],"From":[16],"a":[17],"Distance":[18],"challenge":[19],"2019.":[20],"The":[21,105,157],"challenge's":[22],"SR":[23],"task":[24],"is":[25],"focused":[26],"on":[27,151,160],"problem":[29,96],"of":[30,97,154,171],"in":[33,89],"single":[34],"channel":[35],"distant/far-field":[36,178],"audio":[37,179],"under":[38,180],"noisy":[39,181],"conditions.":[40,182],"In":[41,119],"this":[42,90],"work":[43],"we":[44,122,143],"investigate":[45],"different":[46,155],"deep":[47,62],"neural":[48],"networks":[49,63],"architectures":[50],"for":[51,100,107,139],"embedding":[53,102,132],"extraction":[54],"solve":[56],"task.":[58],"We":[59,92],"show":[60],"that":[61],"with":[64,177],"residual":[65],"frame":[66],"level":[67],"connections":[68],"outperform":[69],"more":[70],"shallow":[71],"architectures.":[72],"Simple":[73],"energy":[74],"based":[75,85,150],"speech":[76,82],"activity":[77],"detector":[78],"(SAD)":[79],"and":[80,164,169],"automatic":[81,114],"(ASR)":[84],"SAD":[86],"are":[87],"investigated":[88],"work.":[91],"also":[93],"address":[94],"data":[98,109],"preparation":[99],"robust":[101],"extractors":[103],"training.":[104],"reverberation":[106],"augmentation":[110],"was":[111,137],"performed":[112],"using":[113],"room":[115],"impulse":[116],"response":[117],"generator.":[118],"our":[120],"used":[123],"discriminatively":[124],"trained":[125],"cosine":[126],"similarity":[127],"metric":[128],"learning":[129],"model":[130],"as":[131],"backend.":[133],"Scores":[134],"normalization":[135],"procedure":[136],"applied":[138],"each":[140],"individual":[141],"subsystem":[142],"used.":[144],"Our":[145],"final":[146],"were":[149],"fusion":[153],"subsystems.":[156],"results":[158],"obtained":[159],"development":[163],"evaluation":[165],"sets":[166],"demonstrate":[167],"effectiveness":[168],"robustness":[170],"proposed":[173],"when":[175],"dealing":[176]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}