{"id":"https://openalex.org/W2962824004","doi":"https://doi.org/10.1109/ijcnn.2018.8489497","title":"Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification","display_name":"Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2962824004","doi":"https://doi.org/10.1109/ijcnn.2018.8489497","mag":"2962824004"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nottingham-repository.worktribe.com/output/945806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053061988","display_name":"Siyang Song","orcid":"https://orcid.org/0000-0003-2339-5685"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Siyang Song","raw_affiliation_strings":["School of Computer Science, University of Nottingham, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053562625","display_name":"Shuimei Zhang","orcid":"https://orcid.org/0000-0001-8477-5417"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuimei Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Temple University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Temple University, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["Group on Language, Audio and Music Imperial College London, UK Embedded Intelligence for Health Care and Wellbeing, Augsburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Group on Language, Audio and Music Imperial College London, UK Embedded Intelligence for Health Care and Wellbeing, Augsburg University, Germany","institution_ids":["https://openalex.org/I179225836","https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019313200","display_name":"Linlin Shen","orcid":"https://orcid.org/0000-0003-1420-0815"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089151131","display_name":"Michel Valstar","orcid":"https://orcid.org/0000-0003-2414-161X"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michel Valstar","raw_affiliation_strings":["School of Computer Science, University of Nottingham, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053061988"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":null,"apc_paid":null,"fwci":0.4887,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74837753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9990000128746033,"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":0.996399998664856,"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":0.7204856276512146},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6294252276420593},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6003789901733398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5543199181556702},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5295772552490234},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5047050714492798},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4712907373905182},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4616455137729645},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4389258623123169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2609805762767792},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.22215816378593445},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1815027892589569},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16841748356819153},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10964930057525635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204856276512146},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6294252276420593},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6003789901733398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5543199181556702},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5295772552490234},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5047050714492798},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4712907373905182},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4616455137729645},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4389258623123169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2609805762767792},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.22215816378593445},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1815027892589569},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16841748356819153},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10964930057525635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:nottingham-repository.worktribe.com:945806","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/945806","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71797","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-717972","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:nottingham-repository.worktribe.com:945806","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/945806","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1235596305","https://openalex.org/W1572981715","https://openalex.org/W1574747749","https://openalex.org/W1974387177","https://openalex.org/W2023840531","https://openalex.org/W2041823554","https://openalex.org/W2062164080","https://openalex.org/W2077651652","https://openalex.org/W2121095010","https://openalex.org/W2122699724","https://openalex.org/W2128202590","https://openalex.org/W2137336030","https://openalex.org/W2147147599","https://openalex.org/W2148154194","https://openalex.org/W2150373343","https://openalex.org/W2150660184","https://openalex.org/W2163786726","https://openalex.org/W2165880886","https://openalex.org/W2198724430","https://openalex.org/W2295188089","https://openalex.org/W2405476549","https://openalex.org/W2407857848","https://openalex.org/W2617260931","https://openalex.org/W2620528906","https://openalex.org/W2673722796","https://openalex.org/W2697254725","https://openalex.org/W2711861986","https://openalex.org/W2749173541","https://openalex.org/W6713590052"],"related_works":["https://openalex.org/W2376224659","https://openalex.org/W2169064893","https://openalex.org/W32484671","https://openalex.org/W4294437891","https://openalex.org/W1970491877","https://openalex.org/W2157090657","https://openalex.org/W2031740531","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727"],"abstract_inverted_index":{"The":[0],"performance":[1,72,110],"of":[2,16,23,73],"speaker-related":[3],"systems":[4,25,87,107],"usually":[5],"degrades":[6],"heavily":[7],"in":[8,26,88,96],"practical":[9],"applications":[10],"largely":[11],"due":[12],"to":[13,55,98,127,142],"the":[14,21,61,66,71,102,114],"presence":[15],"background":[17],"noise.":[18],"To":[19],"improve":[20,70],"robustness":[22],"such":[24],"unknown":[27,90],"noisy":[28,46,91],"environments,":[29],"this":[30],"paper":[31],"proposes":[32],"a":[33,134],"simple":[34],"pre-processing":[35],"method":[36],"called":[37],"Noise":[38],"Invariant":[39],"Frame":[40],"Selection":[41],"(NIFS).":[42],"Based":[43],"on":[44,60],"several":[45],"constraints,":[47],"it":[48,122,137],"selects":[49],"noise":[50],"invariant":[51],"frames":[52],"from":[53],"utterances":[54],"represent":[56],"speakers.":[57],"Experiments":[58],"conducted":[59],"TIMIT":[62],"database":[63],"showed":[64],"that":[65,121],"NIFS":[67,130],"can":[68],"significantly":[69],"Vector":[74],"Quantization":[75],"(VQ),":[76],"Gaussian":[77],"Mixture":[78],"Model-Universal":[79],"Background":[80],"Model":[81],"(GMM-UBM)":[82],"and":[83,125],"i-vector-based":[84],"speaker":[85,105],"verification":[86,106],"different":[89,94],"environments":[92],"with":[93],"SNRs,":[95],"comparison":[97],"their":[99],"baselines.":[100],"Meanwhile,":[101],"proposed":[103],"NIFS-based":[104],"achieves":[108],"similar":[109,144],"when":[111],"we":[112],"change":[113],"constraints":[115],"(hyper-parameters)":[116],"or":[117],"features,":[118],"which":[119],"indicates":[120],"is":[123,131],"robust":[124],"easy":[126],"reproduce.":[128],"Since":[129],"designed":[132],"as":[133],"general":[135],"algorithm,":[136],"could":[138],"be":[139],"further":[140],"applied":[141],"other":[143],"tasks.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}