{"id":"https://openalex.org/W2777684944","doi":"https://doi.org/10.1109/asru.2017.8268994","title":"Leveraging native language speech for accent identification using deep Siamese networks","display_name":"Leveraging native language speech for accent identification using deep Siamese networks","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2777684944","doi":"https://doi.org/10.1109/asru.2017.8268994","mag":"2777684944"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268994","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.08992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021329708","display_name":"Aditya Siddhant","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aditya Siddhant","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, US"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, US","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021329708"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8314,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81571867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.991100013256073,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063646554946899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7348402142524719},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6550962328910828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129953861236572},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5046266317367554},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4753446578979492},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.46460431814193726},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46215301752090454},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.45311933755874634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44363996386528015},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43618714809417725},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43039119243621826},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4214320778846741},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2545817196369171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063646554946899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7348402142524719},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6550962328910828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129953861236572},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5046266317367554},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4753446578979492},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.46460431814193726},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46215301752090454},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.45311933755874634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44363996386528015},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43618714809417725},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43039119243621826},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4214320778846741},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2545817196369171},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2017.8268994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268994","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai::76328","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:arXiv.org:1712.08992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.08992","pdf_url":"https://arxiv.org/pdf/1712.08992","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.08992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.08992","pdf_url":"https://arxiv.org/pdf/1712.08992","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W252777880","https://openalex.org/W1515008200","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1971273973","https://openalex.org/W2069620976","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2121415728","https://openalex.org/W2127589108","https://openalex.org/W2150769028","https://openalex.org/W2157364932","https://openalex.org/W2166637769","https://openalex.org/W2172287020","https://openalex.org/W2183984815","https://openalex.org/W2281877999","https://openalex.org/W2295754094","https://openalex.org/W2405476549","https://openalex.org/W2408021097","https://openalex.org/W2505434962","https://openalex.org/W2963068250","https://openalex.org/W2964121744","https://openalex.org/W4252399209","https://openalex.org/W6608353291","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6674330103","https://openalex.org/W6675354045","https://openalex.org/W6686415532","https://openalex.org/W6713590052"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W2032826752","https://openalex.org/W2784059283","https://openalex.org/W2976274203","https://openalex.org/W2291624303","https://openalex.org/W2101694857"],"abstract_inverted_index":{"The":[0,24,91],"problem":[1],"of":[2,27,36,149,174],"automatic":[3],"accent":[4,53,123,154,177],"identification":[5,54,124,155,178],"is":[6],"important":[7],"for":[8,19],"several":[9,122],"applications":[10],"like":[11],"speaker":[12],"profiling":[13],"and":[14,85],"recognition":[15,22],"as":[16,18],"well":[17],"improving":[20],"speech":[21,28,44,59,83,89,102],"systems.":[23],"accented":[25,66,82],"nature":[26],"can":[29],"be":[30],"primarily":[31],"attributed":[32],"to":[33],"the":[34,37,42,65,79,86,101,127,175],"influence":[35],"speaker's":[38],"native":[39,61,87],"language":[40,88],"on":[41,151],"given":[43],"recording.":[45],"In":[46,134],"this":[47],"paper,":[48],"we":[49,69,168],"propose":[50],"a":[51,71,113,152,158,170],"novel":[52],"system":[55,162],"whose":[56],"training":[57],"exploits":[58],"in":[60],"languages":[62],"along":[63],"with":[64,96],"speech.":[67],"Specifically,":[68],"develop":[70],"deep":[72,115,141],"Siamese":[73,92,142],"network":[74,117],"based":[75],"model":[76,110],"which":[77],"learns":[78],"association":[80],"between":[81],"recordings":[84,103],"recordings.":[90],"networks":[93,143],"are":[94],"trained":[95],"i-vector":[97],"features":[98],"extracted":[99],"from":[100],"using":[104,126,140],"either":[105],"an":[106],"unsupervised":[107],"Gaussian":[108],"mixture":[109],"(GMM)":[111],"or":[112],"supervised":[114],"neural":[116],"(DNN)":[118],"model.":[119],"We":[120],"perform":[121],"experiments":[125],"CSLU":[128],"Foreign":[129],"Accented":[130],"English":[131],"(FAE)":[132],"corpus.":[133],"these":[135],"experiments,":[136],"our":[137],"proposed":[138,176],"approach":[139],"yield":[144],"significant":[145],"relative":[146],"performance":[147],"improvements":[148],"15.4%":[150],"10-class":[153],"task,":[156],"over":[157],"baseline":[159],"DNN-based":[160],"classification":[161],"that":[163],"uses":[164],"GMM":[165],"i-vectors.":[166],"Furthermore,":[167],"present":[169],"detailed":[171],"error":[172],"analysis":[173],"system.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}