{"id":"https://openalex.org/W2950414763","doi":"https://doi.org/10.21437/interspeech.2019-1337","title":"Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling","display_name":"Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2950414763","doi":"https://doi.org/10.21437/interspeech.2019-1337","mag":"2950414763"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.07234","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075223216","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0000-0002-9870-4422"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyuan Peng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":2.5374,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91767976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1093","last_page":"1097"},"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7775335311889648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72599858045578},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6571002006530762},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6040714383125305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5766951441764832},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.530471682548523},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45379674434661865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43578171730041504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3829260468482971},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1547439694404602}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7775335311889648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72599858045578},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6571002006530762},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6040714383125305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5766951441764832},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.530471682548523},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45379674434661865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43578171730041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3829260468482971},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1547439694404602},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.07234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07234","pdf_url":"https://arxiv.org/pdf/1906.07234","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:1906.07234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.07234","pdf_url":"https://arxiv.org/pdf/1906.07234","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":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1545920196","https://openalex.org/W1796128977","https://openalex.org/W1882958252","https://openalex.org/W2128032727","https://openalex.org/W2399576818","https://openalex.org/W2402144811","https://openalex.org/W2404799143","https://openalex.org/W2516890051","https://openalex.org/W2547039119","https://openalex.org/W2587088898","https://openalex.org/W2598638573","https://openalex.org/W2758785877","https://openalex.org/W2785860501","https://openalex.org/W2786608204","https://openalex.org/W2786902352","https://openalex.org/W2787426069","https://openalex.org/W2787447541","https://openalex.org/W2796339975","https://openalex.org/W2826003142","https://openalex.org/W2889228998","https://openalex.org/W2906459023","https://openalex.org/W2936120996","https://openalex.org/W2940544976","https://openalex.org/W2949510815","https://openalex.org/W2953384591","https://openalex.org/W2963618559","https://openalex.org/W2963620343","https://openalex.org/W2963826681","https://openalex.org/W2964121744","https://openalex.org/W3125709657","https://openalex.org/W4288107125","https://openalex.org/W4289564011","https://openalex.org/W4300047444"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,15,18,62,83,119,142,150,160],"problem":[4],"of":[5,17,21,40,82,175],"unsupervised":[6,53],"subword":[7],"unit":[8,33,46,165],"discovery":[9,34],"from":[10],"untranscribed":[11],"speech.":[12],"It":[13],"forms":[14],"basis":[16],"ultimate":[19],"goal":[20],"ZeroSpeech":[22,103,110,137],"2019,":[23],"building":[24],"text-to-speech":[25],"systems":[26],"without":[27],"text":[28],"labels.":[29],"In":[30],"this":[31],"work,":[32],"is":[35,56,67,91,121],"formulated":[36],"as":[37,86,88],"a":[38,94,173],"pipeline":[39],"phonetically":[41],"discriminative":[42],"feature":[43,54,96],"learning":[44,55],"and":[45,73,105,124,153],"inference.":[47],"One":[48],"major":[49],"difficulty":[50],"in":[51,93,132,141,178],"robust":[52],"dealing":[57],"with":[58],"speaker":[59,65],"variation.":[60],"Here":[61],"robustness":[63],"towards":[64],"variation":[66],"achieved":[68],"by":[69],"applying":[70],"adversarial":[71],"training":[72],"FHVAE":[74],"based":[75],"disentangled":[76],"speech":[77],"representation":[78],"learning.":[79],"A":[80],"comparison":[81],"two":[84],"approaches":[85,115,147],"well":[87],"their":[89,126],"combination":[90,127],"studied":[92],"DNN-bottleneck":[95],"(DNN-BNF)":[97],"architecture.":[98],"Experiments":[99],"are":[100,116,154],"conducted":[101],"on":[102,109,136],"2019":[104,138],"2017.":[106],"Experimental":[107],"results":[108],"2017":[111],"show":[112,139],"that":[113,125,140],"both":[114],"effective":[117],"while":[118],"latter":[120],"more":[122],"prominent,":[123],"brings":[128],"further":[129],"marginal":[130],"improvement":[131],"across-speaker":[133],"condition.":[134],"Results":[135],"ABX":[143,179],"discriminability":[144],"task,":[145],"our":[146],"significantly":[148],"outperform":[149,159],"official":[151,161],"baseline,":[152],"competitive":[155],"to":[156],"or":[157],"even":[158],"topline.":[162],"The":[163],"proposed":[164],"sequence":[166],"smoothing":[167],"algorithm":[168],"improves":[169],"synthesis":[170],"quality,":[171],"at":[172],"cost":[174],"slight":[176],"decrease":[177],"discriminability.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-06-27T00:00:00"}