{"id":"https://openalex.org/W4415433147","doi":"https://doi.org/10.21437/interspeech.2025-1726","title":"Voice Reconstruction through Large-Scale TTS Models: Comparing Zero-Shot and Fine-tuning Approaches to Personalise TTS in Assistive Communication","display_name":"Voice Reconstruction through Large-Scale TTS Models: Comparing Zero-Shot and Fine-tuning Approaches to Personalise TTS in Assistive Communication","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433147","doi":"https://doi.org/10.21437/interspeech.2025-1726"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1726","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":["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/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"\u00c9va Sz\u00e9kely","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P\u00e9ter Mihajlik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113034319","display_name":"M\u00e1t\u00e9 Soma K\u00e1d\u00e1r","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00e1t\u00e9 Soma K\u00e1d\u00e1r","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020608163","display_name":"L\u00e1szl\u00f3 T\u00f3th","orcid":"https://orcid.org/0000-0003-0161-1375"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L\u00e1szl\u00f3 T\u00f3th","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063795282"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6611,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87776203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2735","last_page":"2739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9882000088691711,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9882000088691711,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9761000275611877,"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/closed-captioning","display_name":"Closed captioning","score":0.3772999942302704},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.29670000076293945},{"id":"https://openalex.org/keywords/voice-communication","display_name":"Voice communication","score":0.27639999985694885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27219998836517334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5234000086784363},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2983306500","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Voice communication","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2780493683","wikidata":"https://www.wikidata.org/wiki/Q16035842","display_name":"Hearing loss","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-1726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1726","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}