{"id":"https://openalex.org/W3048217770","doi":"https://doi.org/10.21437/interspeech.2020-1821","title":"Phonological Features for 0-Shot Multilingual Speech Synthesis","display_name":"Phonological Features for 0-Shot Multilingual Speech Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3048217770","doi":"https://doi.org/10.21437/interspeech.2020-1821","mag":"3048217770"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.04107","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008306627","display_name":"Marlene Staib","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marlene Staib","raw_affiliation_strings":["Papercup Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038517086","display_name":"Tian Huey Teh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Huey Teh","raw_affiliation_strings":["Papercup Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083188961","display_name":"Alexandra Torresquintero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandra Torresquintero","raw_affiliation_strings":["Papercup Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024033876","display_name":"Devang S Ram Mohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devang S. Ram Mohan","raw_affiliation_strings":["Papercup Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068657700","display_name":"Lorenzo Foglianti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Foglianti","raw_affiliation_strings":["Papercup Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038524461","display_name":"Raphael Lenain","orcid":"https://orcid.org/0000-0001-5345-0628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raphael Lenain","raw_affiliation_strings":["Novoic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Novoic","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007377741","display_name":"Jiameng Gao","orcid":"https://orcid.org/0000-0003-4161-938X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiameng Gao","raw_affiliation_strings":["Papercup Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8436,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9252805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2942","last_page":"2946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9986000061035156,"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":0.7659599184989929},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.6800228357315063},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6676540374755859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5615320205688477},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5555393099784851},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5442413091659546},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.537786066532135},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5151437520980835},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5001590251922607},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47630321979522705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4563981890678406},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45468780398368835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4415728449821472},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26479166746139526},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0836951732635498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659599184989929},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.6800228357315063},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6676540374755859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5615320205688477},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5555393099784851},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5442413091659546},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.537786066532135},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5151437520980835},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5001590251922607},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47630321979522705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4563981890678406},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45468780398368835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415728449821472},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26479166746139526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0836951732635498},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/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.2020-1821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.04107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04107","pdf_url":"https://arxiv.org/pdf/2008.04107","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:2008.04107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04107","pdf_url":"https://arxiv.org/pdf/2008.04107","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1598851216","https://openalex.org/W1630569004","https://openalex.org/W1992153276","https://openalex.org/W2010800472","https://openalex.org/W2068772561","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2151311453","https://openalex.org/W2169203263","https://openalex.org/W2187089797","https://openalex.org/W2316803017","https://openalex.org/W2527729766","https://openalex.org/W2572670101","https://openalex.org/W2573877011","https://openalex.org/W2622010270","https://openalex.org/W2622265915","https://openalex.org/W2746132399","https://openalex.org/W2806482367","https://openalex.org/W2891730843","https://openalex.org/W2964002616","https://openalex.org/W2964170290","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2972489453","https://openalex.org/W2972708855","https://openalex.org/W3022351837"],"related_works":["https://openalex.org/W1964706935","https://openalex.org/W2020946215","https://openalex.org/W2801025542","https://openalex.org/W1966580183","https://openalex.org/W2002773879","https://openalex.org/W2083136263","https://openalex.org/W4213283234","https://openalex.org/W4252296115","https://openalex.org/W2373394249","https://openalex.org/W2906310393"],"abstract_inverted_index":{"Code-switching---the":[0],"intra-utterance":[1],"use":[2,45],"of":[3,49,114],"multiple":[4],"languages---is":[5],"prevalent":[6],"across":[7],"the":[8,23,54,71,91,112],"world.":[9],"Within":[10],"text-to-speech":[11],"(TTS),":[12],"multilingual":[13],"models":[14],"have":[15],"been":[16],"found":[17],"to":[18,26,74,87,99],"enable":[19],"code-switching.":[20],"By":[21],"modifying":[22],"linguistic":[24],"input":[25],"sequence-to-sequence":[27],"TTS,":[28],"we":[29],"show":[30,94],"that":[31,95],"code-switching":[32],"is":[33],"possible":[34],"for":[35,77],"languages":[36],"unseen":[37,84],"during":[38],"training,":[39],"even":[40],"within":[41],"monolingual":[42],"models.":[43],"We":[44,93],"a":[46,105],"small":[47],"set":[48],"phonological":[50],"features":[51],"derived":[52],"from":[53],"International":[55],"Phonetic":[56],"Alphabet":[57],"(IPA),":[58],"such":[59],"as":[60],"vowel":[61],"height":[62],"and":[63,67,80],"frontness,":[64],"consonant":[65],"place":[66],"manner.":[68],"This":[69],"allows":[70,97],"model":[72],"topology":[73],"stay":[75],"unchanged":[76],"different":[78],"languages,":[79],"enables":[81],"new,":[82],"previously":[83],"feature":[85],"combinations":[86],"be":[88],"interpreted":[89],"by":[90],"model.":[92],"this":[96],"us":[98],"generate":[100],"intelligible,":[101],"code-switched":[102],"speech":[103],"in":[104,118],"new":[106],"language":[107],"at":[108],"test":[109],"time,":[110],"including":[111],"approximation":[113],"sounds":[115],"never":[116],"seen":[117],"training.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}