{"id":"https://openalex.org/W2063913958","doi":"https://doi.org/10.1109/iscslp.2014.6936580","title":"Performance evaluation of deep bottleneck features for spoken language identification","display_name":"Performance evaluation of deep bottleneck features for spoken language identification","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2063913958","doi":"https://doi.org/10.1109/iscslp.2014.6936580","mag":"2063913958"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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/A5103002960","display_name":"Bing Jiang","orcid":null},"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":"Bing Jiang","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","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","institution_ids":["https://openalex.org/I126520041"]},{"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/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","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","institution_ids":["https://openalex.org/I126520041"]},{"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/A5050660824","display_name":"Si Wei","orcid":"https://orcid.org/0009-0009-5748-699X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si Wei","raw_affiliation_strings":["iFlytek Research, Anhui USTC iFlytek Co., Ltd","iFlytek Research, Anhui USTC iFlytek Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, Anhui USTC iFlytek Co., Ltd","institution_ids":[]},{"raw_affiliation_string":"iFlytek Research, Anhui USTC iFlytek Co., Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037857879","display_name":"Mengge Wang","orcid":"https://orcid.org/0000-0002-3673-1855"},"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":"Meng-Ge Wang","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","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","institution_ids":["https://openalex.org/I126520041"]},{"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/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":"Ian McLoughlin","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","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","institution_ids":["https://openalex.org/I126520041"]},{"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/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","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","institution_ids":["https://openalex.org/I126520041"]},{"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":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103002960"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.2686,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85254018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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":0.7979439496994019},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7963568568229675},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.624843418598175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5828850269317627},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5814899206161499},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5798233151435852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5571317076683044},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5265184640884399},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5104824304580688},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4845975637435913},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.415643572807312},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41226324439048767},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08750852942466736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979439496994019},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7963568568229675},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.624843418598175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5828850269317627},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5814899206161499},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5798233151435852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5571317076683044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5265184640884399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5104824304580688},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4845975637435913},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.415643572807312},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41226324439048767},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08750852942466736},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp.2014.6936580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.714.4208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.714.4208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://home.ustc.edu.cn/%7Ebing2010/myfile/ISCSLP2014.pdf","raw_type":"text"},{"id":"pmh:oai:kar.kent.ac.uk:48804","is_oa":false,"landing_page_url":"https://kar.kent.ac.uk/48804/","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book section"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W1490504384","https://openalex.org/W1558802035","https://openalex.org/W2045801524","https://openalex.org/W2046899276","https://openalex.org/W2098196171","https://openalex.org/W2100495367","https://openalex.org/W2105099419","https://openalex.org/W2121415728","https://openalex.org/W2123237149","https://openalex.org/W2130633305","https://openalex.org/W2146194791","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2160815625","https://openalex.org/W2162042658","https://openalex.org/W2172287020","https://openalex.org/W2296178052","https://openalex.org/W2398046886","https://openalex.org/W2408021097","https://openalex.org/W4361745846","https://openalex.org/W6606123296","https://openalex.org/W6608710415","https://openalex.org/W6633523743","https://openalex.org/W6661873022"],"related_works":["https://openalex.org/W2106922437","https://openalex.org/W2807901368","https://openalex.org/W2158491338","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W1657880117","https://openalex.org/W4385956668","https://openalex.org/W1585144779","https://openalex.org/W1941834444"],"abstract_inverted_index":{"Our":[0],"previous":[1,70],"work":[2,71],"has":[3],"shown":[4],"that":[5,77,93,166],"Deep":[6,14],"Bottleneck":[7],"Features":[8],"(DBF),":[9],"generated":[10],"from":[11,74,91],"a":[12,33,49,75,81],"well-trained":[13],"Neural":[15],"Network":[16],"(DNN),":[17],"can":[18,171],"provide":[19],"high":[20],"performance":[21],"Language":[22],"Identification":[23],"(LID)":[24],"when":[25],"Total":[26],"Variability":[27],"(TV)":[28],"modelling":[29],"is":[30,53,125],"used":[31,126],"for":[32,47,99],"back-end.":[34],"This":[35],"may":[36,89],"largely":[37],"be":[38,97],"attributed":[39],"to":[40,55,96,127,150],"the":[41,45,66,69,129,134,143,152,174],"powerful":[42],"capability":[43],"of":[44],"DNN":[46,76],"finding":[48],"frame-level":[50],"representation":[51],"which":[52],"robust":[54],"variances":[56],"caused":[57],"by":[58],"different":[59,107,158],"speakers,":[60],"channels":[61],"and":[62,114,116],"background":[63],"noise.":[64],"However":[65],"DBF":[67,87,108,159,170],"in":[68],"were":[72],"extracted":[73],"was":[78],"trained":[79],"using":[80],"large":[82],"ASR":[83],"dataset.":[84],"Optimal":[85],"LID":[86,167],"parameters":[88],"differ":[90],"those":[92],"are":[94,148],"known":[95],"optimal":[98],"ASR.":[100],"Thus":[101],"this":[102],"paper":[103],"focuses":[104],"on":[105,133,142,169],"investigating":[106],"extractors,":[109],"input":[110],"layer":[111,118],"window":[112],"sizes":[113],"dimensionality,":[115],"bottleneck":[117],"location.":[119],"Additionally,":[120],"principal":[121],"component":[122],"analysis":[123],"(PCA)":[124],"decorrelate":[128],"DBF.":[130],"Experiments,":[131],"based":[132,168],"Gaussian":[135],"Mixture":[136],"Model-Universal":[137],"Background":[138],"Model":[139],"(GMM-UBM)":[140],"operating":[141],"NIST":[144],"LRE":[145],"2009":[146],"database,":[147],"conducted":[149],"evaluate":[151],"system.":[153],"Results":[154],"allow":[155],"comparison":[156],"between":[157],"extractor":[160],"parameters,":[161],"as":[162,164],"well":[163],"demonstrating":[165],"significantly":[172],"outperform":[173],"conventional":[175],"shift":[176],"delta":[177],"cepstral":[178],"(SDC)":[179],"features.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}