{"id":"https://openalex.org/W4283770480","doi":"https://doi.org/10.21437/interspeech.2022-994","title":"Few Shot Cross-Lingual TTS Using Transferable Phoneme Embedding","display_name":"Few Shot Cross-Lingual TTS Using Transferable Phoneme Embedding","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283770480","doi":"https://doi.org/10.21437/interspeech.2022-994"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-994","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-994","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100533305","display_name":"Weiping Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Ping Huang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764069","display_name":"Po-Chun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Chun Chen","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sung-Feng Huang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040508737"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.25253178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4566","last_page":"4570"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.6460749506950378},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6003004908561707},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5054142475128174},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4629647731781006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32374852895736694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2505766451358795},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.15104222297668457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460749506950378},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6003004908561707},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5054142475128174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4629647731781006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32374852895736694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2505766451358795},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.15104222297668457},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-994","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-994","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316499","display_name":"National Applied Research Laboratories","ror":"https://ror.org/05wcstg80"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W1522301498","https://openalex.org/W2316803017","https://openalex.org/W2622010270","https://openalex.org/W2746132399","https://openalex.org/W2747874407","https://openalex.org/W2765486990","https://openalex.org/W2891730843","https://openalex.org/W2901997113","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2972802841","https://openalex.org/W2973034126","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3047866127","https://openalex.org/W3094002217","https://openalex.org/W3097297926","https://openalex.org/W3169320628","https://openalex.org/W3181257032","https://openalex.org/W3198032048","https://openalex.org/W3198429080","https://openalex.org/W4225528179","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"a":[3,24,78,83,88,98],"transferable":[4],"phoneme":[5],"embedding":[6],"framework":[7,79],"that":[8,47,80,118],"aims":[9],"to":[10,30,43,54,56,91,131,137],"deal":[11,72],"with":[12,73],"the":[13,19,48,74,112],"cross-lingual":[14],"text-to-speech":[15],"(TTS)":[16],"problem":[17,75],"under":[18,59],"few-shot":[20,31,38],"setting.Transfer":[21],"learning":[22,32,51],"is":[23,41,70,123,129],"common":[25],"approach":[26,52],"when":[27,135],"it":[28],"comes":[29],"since":[33],"training":[34,39],"from":[35,94],"scratch":[36],"on":[37],"data":[40,69],"bound":[42],"overfit.Still,":[44],"we":[45,109],"find":[46],"naive":[49],"transfer":[50],"fails":[53],"adapt":[55],"unseen":[57,139],"languages":[58,96],"extremely":[60],"fewshot":[61],"settings,":[62],"where":[63],"less":[64],"than":[65],"8":[66],"minutes":[67],"of":[68,82,114,127],"provided.We":[71],"by":[76,102],"proposing":[77],"consists":[81],"phoneme-based":[84],"TTS":[85],"model":[86],"and":[87],"codebook":[89],"module":[90],"project":[92],"phonemes":[93],"different":[95],"into":[97],"learned":[99,107],"latent":[100],"space.Furthermore,":[101],"utilizing":[103],"phoneme-level":[104],"averaged":[105],"selfsupervised":[106],"features,":[108],"effectively":[110],"improve":[111],"quality":[113],"synthesized":[115],"speeches.Experiments":[116],"show":[117],"using":[119,141],"4":[120],"utterances,":[121],"which":[122],"about":[124],"30":[125],"seconds":[126],"data,":[128],"enough":[130],"synthesize":[132],"intelligible":[133],"speech":[134],"adapting":[136],"an":[138],"language":[140],"our":[142],"framework.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}