{"id":"https://openalex.org/W2963103750","doi":"https://doi.org/10.1109/iscslp.2018.8706687","title":"End-to-end Language Identification using NetFV and NetVLAD","display_name":"End-to-end Language Identification using NetFV and NetVLAD","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2963103750","doi":"https://doi.org/10.1109/iscslp.2018.8706687","mag":"2963103750"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"preprint","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/A5103181178","display_name":"Jinkun Chen","orcid":"https://orcid.org/0000-0003-4657-1012"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinkun Chen","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103888187","display_name":"Weicheng Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weicheng Cai","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090055875","display_name":"Danwei Cai","orcid":"https://orcid.org/0000-0002-5122-0623"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danwei Cai","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076833848","display_name":"Zexin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexin Cai","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043431793","display_name":"Haibin Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibin Zhong","raw_affiliation_strings":["Jiangsu Jinling Science and Technology Group Limited, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Jinling Science and Technology Group Limited, Nanjing, China","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1827,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85137329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9904000163078308,"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":0.7169539928436279},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6444501876831055},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6232165098190308},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6048320531845093},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5153467059135437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4956599473953247},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.486145943403244},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.46807751059532166},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4670725464820862},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46523159742355347},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45452892780303955},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4513959288597107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39791351556777954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3715035319328308},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3433671295642853},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3303292393684387},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08674618601799011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169539928436279},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6444501876831055},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6232165098190308},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6048320531845093},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5153467059135437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4956599473953247},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.486145943403244},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.46807751059532166},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4670725464820862},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46523159742355347},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45452892780303955},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4513959288597107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39791351556777954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3715035319328308},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3433671295642853},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3303292393684387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08674618601799011},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1606858007","https://openalex.org/W1638980978","https://openalex.org/W1966385142","https://openalex.org/W2012592962","https://openalex.org/W2029776772","https://openalex.org/W2039057510","https://openalex.org/W2056119007","https://openalex.org/W2064675550","https://openalex.org/W2071027807","https://openalex.org/W2078169166","https://openalex.org/W2118202946","https://openalex.org/W2147147599","https://openalex.org/W2147238549","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2166473218","https://openalex.org/W2172287020","https://openalex.org/W2194775991","https://openalex.org/W2290689761","https://openalex.org/W2293442930","https://openalex.org/W2406392101","https://openalex.org/W2408021097","https://openalex.org/W2500786414","https://openalex.org/W2509913395","https://openalex.org/W2512537248","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2620629206","https://openalex.org/W2706729717","https://openalex.org/W2795913659","https://openalex.org/W2951019013","https://openalex.org/W2963077989","https://openalex.org/W6636412649","https://openalex.org/W6677835696","https://openalex.org/W6684116732","https://openalex.org/W6687442591","https://openalex.org/W6696950483","https://openalex.org/W6724098307","https://openalex.org/W6737575990","https://openalex.org/W6739520758","https://openalex.org/W6750417846"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2810399133"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,79],"apply":[4],"the":[5,11,21,25,65,70,74,100,107,115,123,128],"NetFV":[6,16],"and":[7,17,29,67,73,92,127],"NetVLAD":[8,18],"layers":[9,19],"for":[10,99],"end-to-end":[12,83],"language":[13,101],"identification":[14,102],"task.":[15,103],"are":[20],"differentiable":[22],"implementations":[23],"of":[24,31,39,45],"standard":[26],"Fisher":[27],"Vector":[28,30],"Locally":[32],"Aggregated":[33],"Descriptors":[34],"(VLAD)":[35],"methods,":[36],"respectively.":[37,134],"Both":[38],"them":[40],"can":[41],"encode":[42],"a":[43,49,81,86],"sequence":[44],"feature":[46],"vectors":[47],"into":[48],"fixed":[50],"dimensional":[51],"vector":[52],"which":[53],"is":[54],"very":[55],"important":[56],"to":[57],"process":[58],"those":[59],"variable-length":[60],"utterances.":[61],"We":[62],"first":[63],"present":[64],"relevances":[66],"differences":[68],"between":[69],"classical":[71],"i-vector":[72,125],"aforementioned":[75],"encoding":[76,94],"schemes.":[77],"Then,":[78],"construct":[80],"flexible":[82],"framework":[84],"including":[85],"convolutional":[87],"neural":[88],"network":[89],"(CNN)":[90],"architecture":[91],"an":[93],"layer":[95],"(NetFV":[96],"or":[97],"NetVLAD)":[98],"Experimental":[104],"results":[105],"on":[106],"NIST":[108],"LRE":[109],"2007":[110],"close-set":[111],"task":[112],"show":[113],"that":[114],"proposed":[116],"system":[117],"achieves":[118],"significant":[119],"EER":[120],"reductions":[121],"against":[122],"conventional":[124],"baseline":[126],"CNN":[129],"temporal":[130],"average":[131],"pooling":[132],"system,":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}