{"id":"https://openalex.org/W2891566965","doi":"https://doi.org/10.1109/slt.2018.8639650","title":"Unsupervised Representation Learning of Speech for Dialect Identification","display_name":"Unsupervised Representation Learning of Speech for Dialect Identification","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2891566965","doi":"https://doi.org/10.1109/slt.2018.8639650","mag":"2891566965"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.04458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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":0.9958999752998352,"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/latent-variable","display_name":"Latent variable","score":0.7836894989013672},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7381628751754761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6822432279586792},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.6012069582939148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5600273013114929},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5004169940948486},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.500410795211792},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49251827597618103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4857528805732727},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.46460646390914917},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45684564113616943},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45334526896476746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3832595944404602},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3352968692779541},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2693496346473694}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7836894989013672},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7381628751754761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822432279586792},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.6012069582939148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600273013114929},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5004169940948486},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.500410795211792},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49251827597618103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4857528805732727},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.46460646390914917},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45684564113616943},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45334526896476746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3832595944404602},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3352968692779541},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2693496346473694},{"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/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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt.2018.8639650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.04458","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04458","pdf_url":"https://arxiv.org/pdf/1809.04458","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"},{"id":"mag:2891566965","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.04458.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1809.04458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.04458","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.04458","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04458","pdf_url":"https://arxiv.org/pdf/1809.04458","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891566965.pdf","grobid_xml":"https://content.openalex.org/works/W2891566965.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2067301010","https://openalex.org/W2090958120","https://openalex.org/W2181594395","https://openalex.org/W2185814970","https://openalex.org/W2296483664","https://openalex.org/W2360384684","https://openalex.org/W2408021097","https://openalex.org/W2500162720","https://openalex.org/W2726515241","https://openalex.org/W2730530908","https://openalex.org/W2747743419","https://openalex.org/W2748528945","https://openalex.org/W2758785877","https://openalex.org/W2793012778","https://openalex.org/W2793646841","https://openalex.org/W2807627734","https://openalex.org/W2890004347","https://openalex.org/W2890704021","https://openalex.org/W2949870027","https://openalex.org/W2951004968","https://openalex.org/W2962679215","https://openalex.org/W2962850167","https://openalex.org/W2962922562","https://openalex.org/W2962944781","https://openalex.org/W2963466763","https://openalex.org/W2963486098","https://openalex.org/W2963499843","https://openalex.org/W2963599776","https://openalex.org/W2964245029","https://openalex.org/W6631190155","https://openalex.org/W6639916541","https://openalex.org/W6640963894","https://openalex.org/W6697003656","https://openalex.org/W6713134421","https://openalex.org/W6742911084","https://openalex.org/W6745117592","https://openalex.org/W6752688541","https://openalex.org/W6756465896","https://openalex.org/W6765774462"],"related_works":["https://openalex.org/W2161462756","https://openalex.org/W2957959342","https://openalex.org/W2181672650","https://openalex.org/W2901123912","https://openalex.org/W2045879682","https://openalex.org/W2964548769","https://openalex.org/W2398584126","https://openalex.org/W3205920203","https://openalex.org/W2588127192","https://openalex.org/W2574767818","https://openalex.org/W2962912551","https://openalex.org/W2738734060","https://openalex.org/W2901751252","https://openalex.org/W3098361150","https://openalex.org/W2899420204","https://openalex.org/W2903988268","https://openalex.org/W2110799598","https://openalex.org/W3209059054","https://openalex.org/W2742098066","https://openalex.org/W2987099509"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,161],"explore":[4],"the":[5,34,42,103,134,138,142,147,165,188,195,198],"use":[6],"of":[7,53,173],"a":[8,29,70,82,86,89,95,170,191],"factorized":[9],"hierarchical":[10],"variational":[11],"autoencoder":[12],"(FHVAE)":[13],"model":[14,131,140,149],"to":[15,109,146,179],"learn":[16,28,180],"an":[17,39,129,156],"unsupervised":[18],"latent":[19,30,54,72,97,105],"representation":[20],"for":[21,58,176,183,197],"dialect":[22,59],"identification":[23],"(DID).":[24],"An":[25],"FHVAE":[26,139,177],"can":[27,168],"space":[31],"that":[32,77,124,164],"separates":[33],"more":[35,43],"static":[36],"attributes":[37,45],"within":[38,81],"utterance":[40],"from":[41,118,137],"dynamic":[44],"by":[46,69,94],"encoding":[47],"them":[48],"into":[49],"two":[50],"different":[51],"sets":[52],"variables.":[55],"Useful":[56],"factors":[57,76],"identification,":[60],"such":[61,84],"as":[62,85],"phonetic":[63],"or":[64,88],"linguistic":[65],"content,":[66],"are":[67,78,92,201],"encoded":[68,93],"segmental":[71,104],"variable,":[73],"while":[74],"irrelevant":[75],"relatively":[79],"constant":[80],"sequence,":[83],"channel":[87,110,119],"speaker":[90,112],"information,":[91],"sequential":[96],"variable.":[98],"The":[99],"disentanglement":[100],"property":[101],"makes":[102],"variable":[106],"less":[107],"susceptible":[108],"and":[111,114,155,185],"variation,":[113],"thus":[115],"reduces":[116],"degradation":[117],"domain":[120],"mismatch.":[121],"We":[122],"demonstrate":[123],"on":[125,133,151],"fully-supervised":[126],"DID":[127],"tasks,":[128],"end-to-end":[130],"trained":[132,150],"features":[135,154,182],"extracted":[136],"achieves":[141],"best":[143],"performance,":[144],"compared":[145],"same":[148],"conventional":[152],"acoustic":[153],"i-vector":[157],"based":[158],"system.":[159],"Moreover,":[160],"also":[162],"show":[163],"proposed":[166],"approach":[167],"leverage":[169],"large":[171],"amount":[172],"unlabeled":[174],"data":[175,200],"training":[178],"domain-invariant":[181],"DID,":[184],"significantly":[186],"improve":[187],"performance":[189],"in":[190],"low-resource":[192],"condition,":[193],"where":[194],"labels":[196],"in-domain":[199],"not":[202],"available.":[203]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-08-03T00:00:00"}