{"id":"https://openalex.org/W2405476549","doi":"https://doi.org/10.21437/interspeech.2014-172","title":"Application of convolutional neural networks to speaker recognition in noisy conditions","display_name":"Application of convolutional neural networks to speaker recognition in noisy conditions","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2405476549","doi":"https://doi.org/10.21437/interspeech.2014-172","mag":"2405476549"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-172","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Scheffer","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9987000226974487,"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":0.9941999912261963,"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":0.809370756149292},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7274330854415894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7147639393806458},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6558840274810791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5750681757926941},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5550011992454529},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.49668580293655396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44617539644241333},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4444385766983032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4322878420352936},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05957907438278198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809370756149292},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7274330854415894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7147639393806458},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6558840274810791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5750681757926941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5550011992454529},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.49668580293655396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44617539644241333},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4444385766983032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4322878420352936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05957907438278198},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-172","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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":16,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W2031585553","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2043994950","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2114719288","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2155273149","https://openalex.org/W2183984815","https://openalex.org/W2188183693","https://openalex.org/W2294730941","https://openalex.org/W2887979278","https://openalex.org/W2888441252"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"This":[0],"paper":[1],"applies":[2],"a":[3],"convolutional":[4],"neural":[5,116,119],"network":[6],"(CNN)":[7],"trained":[8],"for":[9],"automatic":[10],"speech":[11,51,125],"recognition":[12],"(ASR)":[13],"to":[14,40,60,72,80,108],"the":[15,22,26,33,36,41,53,61,83,90,97,102],"task":[16],"of":[17,35,66,75,85,96,101],"speaker":[18],"identification":[19],"(SID).":[20],"In":[21],"CNN/i-vector":[23,54,103],"front":[24,55],"end,":[25],"sufficient":[27],"statistics":[28],"are":[29],"collected":[30],"based":[31],"on":[32,48],"outputs":[34],"CNN":[37],"as":[38],"opposed":[39],"traditional":[42,91],"universal":[43],"background":[44],"model":[45],"(UBM).":[46],"Evaluated":[47],"heavily":[49],"degraded":[50],"data,":[52],"end":[56],"provides":[57],"performance":[58],"comparable":[59],"UBM/i-vector":[62],"baseline.":[63],"The":[64],"combination":[65],"these":[67],"approaches,":[68],"however,":[69],"is":[70,105],"shown":[71],"provide":[73],"improvements":[74],"26%":[76],"in":[77,89],"miss":[78],"rate":[79],"considerably":[81],"outperform":[82],"fusion":[84],"two":[86],"different":[87],"features":[88],"UBM/i-vectors":[92],"approach.":[93],"An":[94],"analysis":[95],"language-":[98],"and":[99],"channel-dependency":[100],"approach":[104],"also":[106],"provided":[107],"highlight":[109],"future":[110],"research":[111],"directions.":[112],"Index":[113],"Terms:":[114],"Deep":[115],"networks,":[117,120],"Convolutional":[118],"Speaker":[121],"recognition,":[122],"i-vectors,":[123],"noisy":[124]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
