{"id":"https://openalex.org/W4385822828","doi":"https://doi.org/10.21437/interspeech.2023-2158","title":"Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages","display_name":"Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822828","doi":"https://doi.org/10.21437/interspeech.2023-2158"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2158","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2158","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/82f4ee64-f15f-4643-94a5-c04a3561557a","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":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7077693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5466","last_page":"5470"},"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.7113925218582153},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5555600523948669},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5193780064582825},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.44534626603126526},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4237954318523407},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4237714409828186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3921838402748108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37309008836746216},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.334844708442688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33287733793258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113925218582153},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5555600523948669},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5193780064582825},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.44534626603126526},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4237954318523407},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4237714409828186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921838402748108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37309008836746216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.334844708442688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33287733793258667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2023-2158","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2158","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:openaire_cris_publications/82f4ee64-f15f-4643-94a5-c04a3561557a","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/82f4ee64-f15f-4643-94a5-c04a3561557a","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, Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages. in Proceedings of Interspeech 2023. ISCA, pp. 5466-5470, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/interspeech.2023-2158","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.knaw.nl:publications/4abefb36-2588-4547-b831-092c38e1d989","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11755/4abefb36-2588-4547-b831-092c38e1d989","pdf_url":null,"source":{"id":"https://openalex.org/S4306401286","display_name":"KNAW research portal (Royal Academy of Art and Sciences (KNAW))","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, 'Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages', Interspeech 2023, Dublin, Ireland, 20/08/2023 - 24/08/2023 pp. 5466-5470. https://doi.org/10.21437/interspeech.2023-2158","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.knaw.nl:publications/4abefb36-2588-4547-b831-092c38e1d989","is_oa":true,"landing_page_url":"https://pure.knaw.nl/portal/en/publications/4abefb36-2588-4547-b831-092c38e1d989","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 , ' Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages ' , Interspeech 2023 , Dublin , Ireland , 20/08/2023 - 24/08/2023 pp. 5466-5470 . https://doi.org/10.21437/interspeech.2023-2158","raw_type":"conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire/82f4ee64-f15f-4643-94a5-c04a3561557a","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/82f4ee64-f15f-4643-94a5-c04a3561557a","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, Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages. in Proceedings of Interspeech 2023. ISCA, pp. 5466-5470, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/interspeech.2023-2158","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/82f4ee64-f15f-4643-94a5-c04a3561557a","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/82f4ee64-f15f-4643-94a5-c04a3561557a","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, Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages. in Proceedings of Interspeech 2023. ISCA, pp. 5466-5470, Interspeech 2023, Dublin, Ireland, 20/08/2023. https://doi.org/10.21437/interspeech.2023-2158","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2933138175","https://openalex.org/W2963609956","https://openalex.org/W2972394484","https://openalex.org/W3011535310","https://openalex.org/W3024752295","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3083776549","https://openalex.org/W3092028330","https://openalex.org/W3161558238","https://openalex.org/W3174758275","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W4285182272","https://openalex.org/W4296068832","https://openalex.org/W4297570641","https://openalex.org/W4297841766","https://openalex.org/W4300816538","https://openalex.org/W4312096575"],"related_works":["https://openalex.org/W3023285645","https://openalex.org/W3037551068","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W4287644835","https://openalex.org/W4380558612","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W4387829178","https://openalex.org/W4226410230"],"abstract_inverted_index":{"We":[0],"train":[1],"a":[2,77],"MOS":[3,108],"prediction":[4,109],"model":[5],"based":[6],"on":[7,34,38],"wav2vec":[8],"2.0":[9],"using":[10,56],"the":[11,25,42,62,85,96,112],"open-access":[12],"data":[13,23,64,75],"sets":[14],"BVCC":[15,35],"and":[16,48,110],"SOMOS.":[17],"Our":[18],"test":[19],"with":[20,74],"neural":[21],"TTS":[22,100],"in":[24,118],"low-resource":[26],"language":[27],"(LRL)":[28],"West":[29],"Frisian":[30],"shows":[31,80],"that":[32,55],"pre-training":[33],"before":[36],"fine-tuning":[37,52,73],"SOMOS":[39],"leads":[40],"to":[41,68],"best":[43],"accuracy":[44],"for":[45,101],"both":[46],"fine-tuned":[47],"zero-shot":[49,107],"prediction.":[50],"Further":[51],"experiments":[53],"show":[54],"more":[57],"than":[58],"30":[59],"percent":[60],"of":[61,87,99,114],"total":[63],"does":[65],"not":[66],"lead":[67],"significant":[69],"improvements.":[70],"In":[71],"addition,":[72],"from":[76],"single":[78],"listener":[79],"promising":[81],"system-level":[82],"accuracy,":[83],"supporting":[84],"viability":[86],"one-participant":[88],"pilot":[89],"tests.":[90],"These":[91],"findings":[92],"can":[93],"all":[94],"assist":[95],"resource-conscious":[97],"development":[98],"LRLs":[102],"by":[103],"progressing":[104],"towards":[105],"better":[106],"informing":[111],"design":[113],"listening":[115],"tests,":[116],"especially":[117],"early-stage":[119],"evaluation.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}