{"id":"https://openalex.org/W4415432651","doi":"https://doi.org/10.21437/interspeech.2025-2679","title":"Can We Reconstruct a Dysarthric Voice with the Large Speech Model Parler TTS?","display_name":"Can We Reconstruct a Dysarthric Voice with the Large Speech Model Parler TTS?","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432651","doi":"https://doi.org/10.21437/interspeech.2025-2679"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2679","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.04397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107424977","display_name":"Ariadna S\u00e1nchez","orcid":"https://orcid.org/0000-0003-0409-1328"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ariadna Sanchez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107424977"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35973808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4138","last_page":"4142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9914000034332275,"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/T11358","display_name":"Dysphagia Assessment and Management","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7857999801635742},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5180000066757202},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39169999957084656},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3822000026702881},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.35830000042915344},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7857999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285000085830688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6940000057220459},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C2983306500","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Voice communication","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2025-2679","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.04397","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04397","pdf_url":"https://arxiv.org/pdf/2506.04397","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b0a5fa5d-4c44-4095-b521-98d89539723d","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/b0a5fa5d-4c44-4095-b521-98d89539723d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Sanchez Cervera, A & King, S 2025, Can we reconstruct a dysarthric voice with the large speech model Parler TTS? in Interspeech 2025. Proceedings of the International Conference on Spoken Language Processing, pp. 4138-4142, 26th Edition of the Interspeech Conference, Rotterdam, Netherlands, 17/08/25. https://doi.org/10.21437/Interspeech.2025-2679","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b0a5fa5d-4c44-4095-b521-98d89539723d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b0a5fa5d-4c44-4095-b521-98d89539723d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Sanchez Cervera, A & King, S 2025, Can we reconstruct a dysarthric voice with the large speech model Parler TTS? in Interspeech 2025. Proceedings of the International Conference on Spoken Language Processing, pp. 4138-4142, 26th Edition of the Interspeech Conference, Rotterdam, Netherlands, 17/08/25. https://doi.org/10.21437/Interspeech.2025-2679","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.04397","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04397","pdf_url":"https://arxiv.org/pdf/2506.04397","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"disorders":[1],"can":[2,63,97],"make":[3],"communication":[4,22],"hard":[5],"or":[6],"even":[7],"impossible":[8],"for":[9,132],"those":[10],"who":[11],"develop":[12],"them.":[13],"Personalised":[14],"Text-to-Speech":[15],"is":[16],"an":[17,37],"attractive":[18],"option":[19],"as":[20],"a":[21,29,40,56,73],"aid.":[23],"We":[24,71,120],"attempt":[25],"voice":[26,43,134],"reconstruction":[27,135],"using":[28],"large":[30,58],"speech":[31,59,66],"model,":[32,60,131],"with":[33,78],"which":[34],"we":[35,53],"generate":[36,64,101],"approximation":[38],"of":[39,48,105,127,130],"dysarthric":[41],"speaker's":[42],"prior":[44],"to":[45,87,100,111,115,124],"the":[46,89,95,103,133],"onset":[47],"their":[49],"condition.":[50],"In":[51],"particular,":[52],"investigate":[54],"whether":[55],"state-of-the-art":[57],"Parler":[61],"TTS,":[62],"intelligible":[65],"while":[67],"maintaining":[68],"speaker":[69,80,118],"identity.":[70,119],"curate":[72],"dataset":[74],"and":[75,81,84,114],"annotate":[76],"it":[77],"relevant":[79],"intelligibility":[82,113],"information,":[83],"use":[85],"this":[86,106,128],"fine-tune":[88],"model.":[90],"Our":[91],"results":[92],"show":[93],"that":[94],"model":[96],"indeed":[98],"learn":[99],"from":[102],"distribution":[104],"challenging":[107],"data,":[108],"but":[109],"struggles":[110],"control":[112],"maintain":[116],"consistent":[117],"propose":[121],"future":[122],"directions":[123],"improve":[125],"controllability":[126],"class":[129],"task.":[136]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-23T00:00:00"}