{"id":"https://openalex.org/W3016112863","doi":"https://doi.org/10.1109/icassp40776.2020.9054624","title":"Voiceai Systems to NIST Sre19 Evaluation: Robust Speaker Recognition on Conversational Telephone Speech","display_name":"Voiceai Systems to NIST Sre19 Evaluation: Robust Speaker Recognition on Conversational Telephone Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016112863","doi":"https://doi.org/10.1109/icassp40776.2020.9054624","mag":"3016112863"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5053549702","display_name":"Rongjin Li","orcid":"https://orcid.org/0000-0002-0178-5167"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rongjin Li","raw_affiliation_strings":["VoiceAI Technologies, Co. Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"VoiceAI Technologies, Co. Ltd, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004048913","display_name":"Dongpeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongpeng Chen","raw_affiliation_strings":["VoiceAI Technologies, Co. Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"VoiceAI Technologies, Co. Ltd, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448759","display_name":"Weibin Zhang","orcid":"https://orcid.org/0000-0002-0701-9690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weibin Zhang","raw_affiliation_strings":["VoiceAI Technologies, Co. Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"VoiceAI Technologies, Co. Ltd, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053549702"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75071343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6459","last_page":"6463"},"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":0.9984999895095825,"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":0.9934999942779541,"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":0.9449816942214966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617875933647156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7558614015579224},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6171126961708069}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9449816942214966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617875933647156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7558614015579224},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6171126961708069}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":36,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1600744878","https://openalex.org/W2107638917","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2293634267","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2807373279","https://openalex.org/W2888867175","https://openalex.org/W2888957211","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2939634425","https://openalex.org/W2941320063","https://openalex.org/W2960935792","https://openalex.org/W2972392008","https://openalex.org/W2972609576","https://openalex.org/W2972961496","https://openalex.org/W2972986505","https://openalex.org/W3024880099","https://openalex.org/W4288282821","https://openalex.org/W6605243796","https://openalex.org/W6631362777","https://openalex.org/W6635152626","https://openalex.org/W6688816777","https://openalex.org/W6696934422","https://openalex.org/W6712930963","https://openalex.org/W6751846975","https://openalex.org/W6765488738"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"In":[0,66,84],"this":[1,45],"study,":[2],"we":[3,69,86],"present":[4],"the":[5,15,58,61,93,126,132,148,175,182],"VoiceAI":[6],"(VAI)":[7],"submissions":[8],"to":[9,36,43,91,121,130],"NIST":[10,151],"SRE":[11],"2019":[12],"challenge":[13],"on":[14,30,71,150,174,181],"task":[16],"of":[17,60,95,125,161],"speaker":[18],"recognition":[19],"using":[20,75],"conversational":[21],"telephone":[22],"speech.":[23],"Domain":[24],"mismatching":[25,134],"remains":[26],"a":[27,140,159],"challenging":[28],"problem":[29],"SRE19.":[31],"However,":[32],"participants":[33],"are":[34,81],"unconstrained":[35],"use":[37,124],"any":[38],"public":[39],"or":[40],"proprietary":[41],"data":[42,54,128,177],"mitigate":[44],"problem.":[46,135],"Using":[47],"larger":[48],"scale":[49],"and":[50,111,129,170],"more":[51],"diverse":[52],"training":[53],"can":[55],"effectively":[56],"improve":[57],"performance":[59],"front-end":[62],"neural":[63,89,97,108],"networks":[64,98],"(NN).":[65],"our":[67],"experiments,":[68],"focus":[70],"constructing":[72],"robust":[73],"systems":[74],"x-vectors.":[76],"Different":[77],"input":[78],"acoustic":[79],"features":[80],"also":[82,116],"investigated.":[83],"addition,":[85],"propose":[87],"hybrid":[88],"architectures":[90],"utilizing":[92],"strength":[94],"different":[96],"such":[99],"as":[100],"long":[101],"short-term":[102],"memory":[103],"(LSTM),":[104],"extended":[105],"time":[106],"delay":[107],"network":[109,138],"(ETDNN)":[110],"factorized":[112],"TDNN":[113],"(FTDNN).":[114],"We":[115],"explore":[117],"many":[118],"back-end":[119],"strategies":[120],"make":[122],"full":[123],"development":[127],"relief":[131],"domain":[133],"Our":[136],"best":[137],"topology,":[139],"FTDNN":[141],"with":[142],"two":[143],"LSTMP":[144],"layers,":[145],"significantly":[146],"outperforms":[147],"baseline":[149],"SRE18":[152],"evaluation":[153],"set":[154],"(SRE18Eval).":[155],"The":[156],"final":[157],"system,":[158],"fusion":[160],"five":[162],"systems,":[163],"yields":[164],"EER":[165],"2.59%,":[166],"minimum":[167],"cost":[168,172],"0.153,":[169],"actual":[171],"0.155":[173],"progress":[176],"set,":[178],"ranking":[179],"second":[180],"leaderboard":[183],"among":[184],"all":[185],"participants.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
