{"id":"https://openalex.org/W2487408737","doi":"https://doi.org/10.21437/odyssey.2016-30","title":"LID-senone Extraction via Deep Neural Networks for End-to-End Language Identification","display_name":"LID-senone Extraction via Deep Neural Networks for End-to-End Language Identification","publication_year":2016,"publication_date":"2016-06-21","ids":{"openalex":"https://openalex.org/W2487408737","doi":"https://doi.org/10.21437/odyssey.2016-30","mag":"2487408737"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2016-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2016)","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/A5101444144","display_name":"Jin Ma","orcid":"https://orcid.org/0000-0001-8313-8301"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ma Jin","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054674018","display_name":"Yan Song","orcid":"https://orcid.org/0000-0001-7927-0908"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]},{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Mcloughlin","raw_affiliation_strings":["School of Computing, University of Kent, Medway, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, Medway, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China","National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101444144"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.2848,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94855326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9980999827384949,"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":0.7955712080001831},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7087132930755615},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.680090069770813},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6500365138053894},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6256619095802307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5647863745689392},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5447526574134827},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5336397886276245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5039884448051453},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.47280970215797424},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4606182277202606},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44053131341934204},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4352276921272278},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4306778311729431},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4293782114982605},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41179513931274414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41127273440361023},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.24326199293136597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955712080001831},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7087132930755615},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.680090069770813},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6500365138053894},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6256619095802307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5647863745689392},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5447526574134827},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5336397886276245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5039884448051453},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.47280970215797424},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4606182277202606},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44053131341934204},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4352276921272278},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4306778311729431},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4293782114982605},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41179513931274414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41127273440361023},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24326199293136597},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2016-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2016)","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:55055","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2016-30>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W614822286","https://openalex.org/W1522720415","https://openalex.org/W1995562189","https://openalex.org/W2056119007","https://openalex.org/W2098196171","https://openalex.org/W2106837051","https://openalex.org/W2146194791","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2165698076","https://openalex.org/W2175575774","https://openalex.org/W2179352600","https://openalex.org/W2183016404","https://openalex.org/W2296178052","https://openalex.org/W2396910632","https://openalex.org/W2406392101","https://openalex.org/W2408021097","https://openalex.org/W2408175559","https://openalex.org/W2962853205","https://openalex.org/W4234330420","https://openalex.org/W4299518610"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W1985349217","https://openalex.org/W2098508228","https://openalex.org/W2624072012","https://openalex.org/W1508853749","https://openalex.org/W2810399133"],"abstract_inverted_index":{"A":[0],"key":[1],"problem":[2],"in":[3,75,114,129],"spoken":[4],"language":[5,111,120],"identification":[6],"(LID)":[7],"is":[8,105],"how":[9],"to":[10,62,73,107,137],"effectively":[11],"model":[12],"features":[13,117],"from":[14],"a":[15,55,83,93,100],"given":[16],"speech":[17,76],"utterance.":[18],"Recent":[19],"techniques":[20],"such":[21,33],"as":[22,34,70],"end-to-end":[23,57,145],"schemes":[24],"and":[25,96,140],"deep":[26],"neural":[27,58],"networks":[28],"(DNNs)":[29],"utilising":[30],"transfer":[31],"learning":[32],"bottleneck":[35],"(BN)":[36],"features,":[37],"have":[38,44],"demonstrated":[39],"good":[40,134],"overall":[41],"performance,":[42],"but":[43,163],"not":[45,159],"addressed":[46],"the":[47,87,109,115,124],"extraction":[48],"of":[49,86,118],"LID-specific":[50],"features.":[51],"We":[52,78],"thus":[53],"propose":[54],"novel":[56,101],"network":[59],"which":[60,67,153],"aims":[61],"obtain":[63],"effective":[64],"LID-senone":[65],"representations,":[66],"we":[68],"define":[69],"being":[71],"analogous":[72],"senones":[74],"recognition.":[77],"show":[79,133],"that":[80],"LID-senones":[81],"combine":[82],"compact":[84],"representation":[85],"original":[88],"acoustic":[89,116],"feature":[90],"space":[91],"with":[92,148],"powerful":[94],"descriptive":[95],"discriminative":[97],"capability.":[98],"Furthermore,":[99],"incremental":[102,150],"training":[103,151],"method":[104,152],"proposed":[106,144],"extract":[108],"weak":[110],"information":[112],"buried":[113],"insufficient":[119],"resources.":[121],"Results":[122],"on":[123],"six":[125],"most":[126],"confused":[127],"languages":[128],"NIST":[130],"LRE":[131],"2009":[132],"performance":[135],"compared":[136],"state-of-the-art":[138],"BN-GMM/i-vector":[139],"BN-DNN/i-vector":[141],"systems.":[142],"The":[143],"network,":[146],"coupled":[147],"an":[149],"mitigates":[154],"against":[155],"over-fitting,":[156],"has":[157],"potential":[158],"just":[160],"for":[161,165],"LID,":[162],"also":[164],"other":[166],"resource":[167],"constrained":[168],"tasks.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}