{"id":"https://openalex.org/W3194172310","doi":"https://doi.org/10.21437/ssw.2021-22","title":"Exploring Disentanglement with Multilingual and Monolingual VQ-VAE","display_name":"Exploring Disentanglement with Multilingual and Monolingual VQ-VAE","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3194172310","doi":"https://doi.org/10.21437/ssw.2021-22","mag":"3194172310"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/A5040626187","display_name":"Jennifer Williams","orcid":"https://orcid.org/0000-0003-1410-0427"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jennifer Williams","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043162691","display_name":"Jason Fong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Fong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040626187"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84559803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9965999722480774,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9965999722480774,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9934999942779541,"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":0.9139999747276306,"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":0.7671950459480286},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7214494943618774},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.701472282409668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5166218876838684},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.49912190437316895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4900888204574585},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.45602792501449585},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31176459789276123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671950459480286},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7214494943618774},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.701472282409668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5166218876838684},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.49912190437316895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4900888204574585},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.45602792501449585},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31176459789276123},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2021-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2061937230"],"abstract_inverted_index":{"This":[0],"work":[1],"examines":[2],"the":[3,32,77,102,131],"content":[4,103],"and":[5,10,24,34,47,60,119],"usefulness":[6],"of":[7,104,121,133],"disentangled":[8,58,134],"phone":[9,59,112],"speaker":[11,61,91,117],"representations":[12,62,79,92],"from":[13],"two":[14],"separately":[15],"trained":[16,20,26],"VQ-VAE":[17],"systems:":[18],"one":[19],"on":[21,27,56],"multilingual":[22],"data":[23],"another":[25],"monolingual":[28,35],"data.":[29],"We":[30,94],"explore":[31],"multi-":[33],"models":[36],"using":[37],"four":[38],"small":[39],"proof-of-concept":[40],"tasks:":[41],"copy-synthesis,":[42],"voice":[43],"transformation,":[44],"linguistic":[45],"code-switching,":[46],"content-based":[48],"privacy":[49],"masking.":[50],"From":[51],"these":[52,83],"tasks,":[53,84],"we":[54,125],"reflect":[55],"how":[57],"can":[63],"be":[64],"used":[65],"to":[66,100],"manipulate":[67],"speech":[68],"in":[69],"a":[70],"meaningful":[71],"way.":[72],"Our":[73],"experiments":[74],"demonstrate":[75],"that":[76],"VQ":[78,113],"are":[80],"suitable":[81],"for":[82,128],"including":[85],"creating":[86],"new":[87],"voices":[88],"by":[89,110],"mixing":[90],"together.":[93],"also":[95],"present":[96],"our":[97],"novel":[98],"technique":[99],"conceal":[101],"targeted":[105],"words":[106],"within":[107],"an":[108],"utterance":[109],"manipulating":[111],"codes,":[114],"while":[115],"retaining":[116],"identity":[118],"intelligibility":[120],"surrounding":[122],"words.":[123],"Finally,":[124],"discuss":[126],"recommendations":[127],"further":[129],"increasing":[130],"viability":[132],"representations.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
