{"id":"https://openalex.org/W2730530908","doi":"https://doi.org/10.21437/interspeech.2017-44","title":"End-to-End Language Identification Using High-Order Utterance Representation with Bilinear Pooling","display_name":"End-to-End Language Identification Using High-Order Utterance Representation with Bilinear Pooling","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2730530908","doi":"https://doi.org/10.21437/interspeech.2017-44","mag":"2730530908"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-44","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-44","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/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":false,"raw_author_name":"Ma Jin","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"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, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, 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"],"raw_orcid":null,"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/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"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":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2571","last_page":"2575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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":0.9767000079154968,"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/pooling","display_name":"Pooling","score":0.7727075815200806},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7548689246177673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6676062345504761},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.653287410736084},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5263306498527527},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5098873376846313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4578169882297516},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.438772976398468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43736255168914795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39654916524887085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06437569856643677}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7727075815200806},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7548689246177673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676062345504761},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.653287410736084},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5263306498527527},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5098873376846313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4578169882297516},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.438772976398468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43736255168914795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39654916524887085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06437569856643677},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-44","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-44","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:61814","is_oa":false,"landing_page_url":"https://doi.org/10.21437/Interspeech.2017-44>)","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":"Conference proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W78159342","https://openalex.org/W1606858007","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2056119007","https://openalex.org/W2098196171","https://openalex.org/W2102113734","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2163605009","https://openalex.org/W2175575774","https://openalex.org/W2179352600","https://openalex.org/W2183016404","https://openalex.org/W2194775991","https://openalex.org/W2396910632","https://openalex.org/W2406392101","https://openalex.org/W2408021097","https://openalex.org/W2487408737","https://openalex.org/W2509913395","https://openalex.org/W2512537248","https://openalex.org/W2515090196","https://openalex.org/W2962853205","https://openalex.org/W4234330420","https://openalex.org/W4308909683"],"related_works":["https://openalex.org/W2950524887","https://openalex.org/W2883502031","https://openalex.org/W2261271299","https://openalex.org/W4280638452","https://openalex.org/W4285020665","https://openalex.org/W2963066927","https://openalex.org/W3160506688","https://openalex.org/W3111811104","https://openalex.org/W4380083739","https://openalex.org/W2964944724"],"abstract_inverted_index":{"A":[0],"key":[1],"problem":[2],"in":[3,22,31,67],"spoken":[4],"language":[5,18],"identification":[6],"(LID)":[7],"is":[8,77],"how":[9],"to":[10,17,28,47,79,94],"design":[11],"effective":[12,50],"representations":[13],"which":[14,45],"are":[15],"specific":[16],"information.":[19],"Recent":[20],"advances":[21],"deep":[23,34],"neural":[24],"networks":[25],"have":[26],"led":[27],"significant":[29],"improvements":[30],"results,":[32],"with":[33,86],"end-to-end":[35],"methods":[36],"proving":[37],"effective.":[38],"This":[39],"paper":[40],"proposes":[41],"a":[42],"novel":[43],"network":[44],"aims":[46],"model":[48],"an":[49],"representation":[51],"for":[52,110,121],"high":[53],"(first":[54],"and":[55,82,102,112,115],"second)-order":[56],"statistics":[57],"of":[58,65],"LID-senones,":[59],"defined":[60],"as":[61],"being":[62],"LID":[63],"analogues":[64],"senones":[66],"speech":[68],"recognition.":[69],"The":[70],"high-order":[71],"information":[72],"extracted":[73],"through":[74],"bilinear":[75],"pooling":[76],"robust":[78],"speakers,":[80],"channels":[81],"background":[83],"noise.":[84],"Evaluation":[85],"NIST":[87],"LRE":[88],"2009":[89],"shows":[90],"improved":[91],"performance":[92],"compared":[93],"current":[95],"state-of-the-art":[96],"DBF/i-vector":[97],"systems,":[98],"achieving":[99],"over":[100,116],"33%":[101],"20%":[103],"relative":[104,118],"equal":[105],"error":[106],"rate":[107],"(EER)":[108],"improvement":[109,120],"3s":[111],"10s":[113],"utterances":[114],"40%":[117],"Cavg":[119],"all":[122],"durations.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}