{"id":"https://openalex.org/W4385822629","doi":"https://doi.org/10.21437/interspeech.2023-2148","title":"The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech","display_name":"The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822629","doi":"https://doi.org/10.21437/interspeech.2023-2148"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2148","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/d337688a-a441-495c-bb7a-abab8a06075c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065364398","display_name":"Phat Do","orcid":"https://orcid.org/0000-0002-3186-9679"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Phat Do","raw_affiliation_strings":["Campus Frysl\u00e2n, University of Groningen, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Campus Frysl\u00e2n, University of Groningen, the Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090819693","display_name":"Matt Coler","orcid":"https://orcid.org/0000-0002-7631-5063"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Matt Coler","raw_affiliation_strings":["Campus Frysl\u00e2n, University of Groningen, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Campus Frysl\u00e2n, University of Groningen, the Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049678985","display_name":"Jelske Dijkstra","orcid":null},"institutions":[{"id":"https://openalex.org/I196758499","display_name":"Fryske Akademy","ror":"https://ror.org/05fcmfe52","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196758499"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jelske D\u0133kstra","raw_affiliation_strings":["Fryske Akademy/Mercator Research Centre, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fryske Akademy/Mercator Research Centre, the Netherlands","institution_ids":["https://openalex.org/I196758499"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109914325","display_name":"Esther Klabbers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esther Klabbers","raw_affiliation_strings":["ReadSpeaker, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ReadSpeaker, the Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09453357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5461","last_page":"5465"},"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":0.9991999864578247,"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":0.9984999895095825,"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":0.8324893712997437},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.8154639005661011},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.808813214302063},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7014675140380859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6391401886940002},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5546624660491943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5416581630706787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48434197902679443},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.46536898612976074},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11851653456687927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324893712997437},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.8154639005661011},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.808813214302063},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7014675140380859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6391401886940002},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5546624660491943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5416581630706787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48434197902679443},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.46536898612976074},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11851653456687927},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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":5,"locations":[{"id":"doi:10.21437/interspeech.2023-2148","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/d337688a-a441-495c-bb7a-abab8a06075c","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/d337688a-a441-495c-bb7a-abab8a06075c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Do, P, Coler, M, D\u0133kstra, J & Klabbers, E 2023, The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech. in Proceedings of Interspeech 2023. ISCA, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/interspeech.2023-2148","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.knaw.nl:openaire_cris_publications/eadbfc01-ea09-4a79-8d26-54866ede6be5","is_oa":true,"landing_page_url":"https://pure.knaw.nl/portal/en/publications/eadbfc01-ea09-4a79-8d26-54866ede6be5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400439","display_name":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Do, P, Coler, M, Dijkstra, J & Klabbers, E 2023, 'The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech', Paper presented at Interspeech 2023, Dublin, Ireland, 20/08/2023 - 24/08/2023 pp. 5461-5465. https://doi.org/10.21437/interspeech.2023-2148","raw_type":"conferenceObject"},{"id":"pmh:oai:pure.knaw.nl:publications/eadbfc01-ea09-4a79-8d26-54866ede6be5","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11755/eadbfc01-ea09-4a79-8d26-54866ede6be5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400439","display_name":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Do, P, Coler, M, Dijkstra, J & Klabbers, E 2023, 'The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech', Paper presented at Interspeech 2023, Dublin, Ireland, 20/08/2023 - 24/08/2023 pp. 5461-5465. https://doi.org/10.21437/interspeech.2023-2148","raw_type":"conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/d337688a-a441-495c-bb7a-abab8a06075c","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/d337688a-a441-495c-bb7a-abab8a06075c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Do, P, Coler, M, D\u0133kstra, J & Klabbers, E 2023, The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech. in Proceedings of Interspeech 2023. ISCA, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/interspeech.2023-2148","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:publications/d337688a-a441-495c-bb7a-abab8a06075c","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/d337688a-a441-495c-bb7a-abab8a06075c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Do, P, Coler, M, D\u0133kstra, J & Klabbers, E 2023, The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech. in Proceedings of Interspeech 2023. ISCA, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/interspeech.2023-2148","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2512355221","https://openalex.org/W2747874407","https://openalex.org/W2963212250","https://openalex.org/W2964243274","https://openalex.org/W2973034126","https://openalex.org/W3015877095","https://openalex.org/W3030437843","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3048217770","https://openalex.org/W3092028330","https://openalex.org/W3161704465","https://openalex.org/W3174758275","https://openalex.org/W3185635705","https://openalex.org/W3194464626","https://openalex.org/W3202278141","https://openalex.org/W4285181910","https://openalex.org/W4285182272","https://openalex.org/W4285189120","https://openalex.org/W4297570641","https://openalex.org/W4379087097","https://openalex.org/W4394671563"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2023694213"],"abstract_inverted_index":{"We":[0],"compare":[1],"phone":[2,36,73,97,126],"labels":[3,37],"and":[4,24,41,66,68,95],"articulatory":[5,32,120],"features":[6,33,121],"as":[7,122],"input":[8,123],"for":[9,16,108,112],"cross-lingual":[10],"transfer":[11],"learning":[12],"in":[13,38,63],"text-to-speech":[14],"(TTS)":[15],"low-resource":[17],"languages":[18],"(LRLs).":[19],"Experiments":[20],"with":[21,90],"FastSpeech":[22],"2":[23],"the":[25,83,96,113],"LRL":[26],"West":[27],"Frisian":[28],"show":[29,81],"that":[30,82],"using":[31,35,54,70,91,119,125],"outperformed":[34],"both":[39,64],"intelligibility":[40],"naturalness.":[42],"For":[43],"LRLs":[44,109],"without":[45],"pronunciation":[46],"dictionaries,":[47],"we":[48],"propose":[49],"two":[50],"novel":[51],"approaches:":[52],"a)":[53],"a":[55,71,77,92,105],"massively":[56],"multilingual":[57],"model":[58],"to":[59,75],"convert":[60],"grapheme-to-phone":[61],"(G2P)":[62],"training":[65],"synthesizing,":[67],"b)":[69],"universal":[72],"recognizer":[74],"create":[76],"makeshift":[78],"dictionary.":[79],"Results":[80],"G2P":[84,114],"approach":[85],"performs":[86],"largely":[87],"on":[88],"par":[89],"ground-truth":[93],"dictionary":[94],"recognition":[98],"approach,":[99,118],"while":[100],"performing":[101],"generally":[102],"worse,":[103],"remains":[104],"viable":[106],"option":[107],"less":[110],"suitable":[111],"approach.":[115],"Within":[116],"each":[117],"outperforms":[124],"labels.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}