{"id":"https://openalex.org/W3198032048","doi":"https://doi.org/10.21437/interspeech.2021-327","title":"Cross-Lingual Low Resource Speaker Adaptation Using Phonological Features","display_name":"Cross-Lingual Low Resource Speaker Adaptation Using Phonological Features","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198032048","doi":"https://doi.org/10.21437/interspeech.2021-327","mag":"3198032048"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-327","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.09075","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037667852","display_name":"Georgia Maniati","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Georgia Maniati","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050072052","display_name":"\u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c2 \u039c\u03b1\u03c1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Markopoulos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310876","display_name":"Georgios Vamvoukakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Vamvoukakis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006509336","display_name":"Hyoung-Min Park","orcid":"https://orcid.org/0000-0001-7397-8286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyoungmin Park","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108894078","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5037667852"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5398,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86096268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1594","last_page":"1598"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9961000084877014,"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":0.8377159833908081},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8362298607826233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6055063605308533},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5124531388282776},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5029422640800476},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4789979159832001},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47379371523857117},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43452900648117065},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4293050765991211},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.42630526423454285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4065660536289215},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1321144700050354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377159833908081},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8362298607826233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6055063605308533},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5124531388282776},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5029422640800476},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4789979159832001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47379371523857117},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43452900648117065},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4293050765991211},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.42630526423454285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065660536289215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1321144700050354},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-327","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.09075","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09075","pdf_url":"https://arxiv.org/pdf/2111.09075","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:2111.09075","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09075","pdf_url":"https://arxiv.org/pdf/2111.09075","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":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1525954971","https://openalex.org/W1598851216","https://openalex.org/W1982490440","https://openalex.org/W2010800472","https://openalex.org/W2169203263","https://openalex.org/W2622010270","https://openalex.org/W2746132399","https://openalex.org/W2806482367","https://openalex.org/W2891730843","https://openalex.org/W2963091184","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2972489453","https://openalex.org/W3015484365","https://openalex.org/W3027127570","https://openalex.org/W3048217770","https://openalex.org/W3091928890","https://openalex.org/W3092496982","https://openalex.org/W3095012670","https://openalex.org/W3095389792","https://openalex.org/W3096514088","https://openalex.org/W3096656663","https://openalex.org/W3096894480","https://openalex.org/W3097297926","https://openalex.org/W3099992561","https://openalex.org/W3181257032"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"The":[0],"idea":[1],"of":[2,7,35,42,58,69,80,87,101,118,135,156],"using":[3],"phonological":[4,82],"features":[5,61],"instead":[6],"phonemes":[8],"as":[9,29,128,130,168,172],"input":[10],"to":[11,148],"sequence-to-sequence":[12],"TTS":[13,86],"has":[14],"been":[15],"recently":[16],"proposed":[17],"for":[18,27],"zero-shot":[19],"multilingual":[20],"speech":[21,117],"synthesis.":[22],"This":[23],"approach":[24],"is":[25,175],"useful":[26],"code-switching,":[28],"it":[30],"facilitates":[31],"the":[32,67,78,95,123,149,153,173,179],"seamless":[33],"uttering":[34],"foreign":[36],"text":[37],"embedded":[38],"in":[39,106,177],"a":[40,50,56,102,108,169],"stream":[41],"native":[43],"text.":[44],"In":[45,152],"our":[46,165],"work,":[47],"we":[48,93,139,162],"train":[49],"language-agnostic":[51],"multispeaker":[52],"model":[53,96,166],"conditioned":[54],"on":[55,84],"set":[57],"phonologically":[59],"derived":[60],"common":[62],"across":[63],"different":[64],"languages,":[65],"with":[66,77,97],"goal":[68],"achieving":[70],"cross-lingual":[71,85],"speaker":[72,137,142],"adaptation.":[73],"We":[74],"first":[75],"experiment":[76],"effect":[79],"language":[81,90,184],"similarity":[83,143],"several":[88],"source-target":[89],"combinations.":[91],"Subsequently,":[92],"fine-tune":[94],"very":[98],"limited":[99],"data":[100],"new":[103],"speaker's":[104,125],"voice":[105],"either":[107],"seen":[109,180],"or":[110],"an":[111],"unseen":[112,182],"language,":[113],"and":[114,132,145,181],"achieve":[115],"synthetic":[116],"equal":[119],"quality,":[120],"while":[121],"preserving":[122],"target":[124,136],"identity.":[126],"With":[127],"few":[129],"32":[131],"8":[133],"utterances":[134],"data,":[138],"obtain":[140],"high":[141],"scores":[144],"naturalness":[146],"comparable":[147],"corresponding":[150],"literature.":[151],"extreme":[154],"case":[155],"only":[157],"2":[158],"available":[159],"adaptation":[160,183],"utterances,":[161],"find":[163],"that":[164],"behaves":[167],"few-shot":[170],"learner,":[171],"performance":[174],"similar":[176],"both":[178],"scenarios.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-09-13T00:00:00"}