{"id":"https://openalex.org/W7160051071","doi":"https://doi.org/10.63317/57peripccxqx","title":"TTSVowelViz: A Tool for Visualising Text-to-Speech Model Training via Vowel Spaces","display_name":"TTSVowelViz: A Tool for Visualising Text-to-Speech Model Training via Vowel Spaces","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160051071","doi":"https://doi.org/10.63317/57peripccxqx"},"language":null,"primary_location":{"id":"doi:10.63317/57peripccxqx","is_oa":false,"landing_page_url":"https://doi.org/10.63317/57peripccxqx","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2292/75967","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095689666","display_name":"Pasindu Udawatta","orcid":"https://orcid.org/0009-0005-5332-9461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasindu Udawatta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082577862","display_name":"Jesin James","orcid":"https://orcid.org/0000-0003-0024-9597"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesin James","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074019528","display_name":"B T Balamurali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balamurali B T","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043249487","display_name":"Catherine Watson","orcid":"https://orcid.org/0000-0001-9010-5188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Catherine Inez Watson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128963793","display_name":"Ake Nicholas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ake Nicholas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135178673","display_name":"Binu Nisal Abeysinghe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binu Nisal Abeysinghe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.41640111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4778","last_page":"4786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.20010000467300415,"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":0.20010000467300415,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.1868000030517578,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.1662999987602234,"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/training","display_name":"Training (meteorology)","score":0.6531999707221985},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.39989998936653137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3424000144004822},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2870999872684479}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6531999707221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5612000226974487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/57peripccxqx","is_oa":false,"landing_page_url":"https://doi.org/10.63317/57peripccxqx","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/75967","is_oa":true,"landing_page_url":"https://hdl.handle.net/2292/75967","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference item"}],"best_oa_location":{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/75967","is_oa":true,"landing_page_url":"https://hdl.handle.net/2292/75967","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference item"},"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":{"In":[0],"text-to-speech":[1],"(TTS)":[2],"model":[3,15,46,62,69,96],"training,":[4,63],"the":[5,8,17,20,28,33,39,82,114,120,132],"saturation":[6],"of":[7,19,116],"loss":[9],"curve":[10],"indicates":[11],"how":[12,81],"well":[13],"a":[14,51,94,107,143],"learns":[16],"characteristics":[18],"training":[21],"dataset.":[22],"But":[23],"it":[24],"does":[25],"not":[26],"reveal":[27],"linguistic":[29,43,65],"properties":[30],"learned":[31,79],"by":[32,124],"model.":[34],"Existing":[35],"TTS":[36,68,95,148],"approaches":[37],"miss":[38],"potential":[40],"to":[41,101],"incorporate":[42],"insights":[44],"into":[45],"training.":[47,88,149],"We":[48],"introduce":[49],"TTSVowelViz,":[50,91],"novel":[52],"tool":[53,146],"that":[54,113],"visualises":[55],"static":[56],"and":[57,67,80,105],"dynamic":[58],"vowel":[59,75,83,121,139],"spaces":[60,84,122],"during":[61,87],"bridging":[64],"knowledge":[66],"development.":[70],"It":[71],"helps":[72],"identify":[73],"which":[74],"sounds":[76],"are":[77,85],"accurately":[78],"evolved":[86],"To":[89],"assess":[90],"we":[92],"fine-tuned":[93],"from":[97],"General":[98],"American":[99],"English":[100,104],"New":[102],"Zealand":[103],"conducted":[106],"perception":[108],"test.":[109],"Our":[110],"results":[111],"show":[112],"formants":[115],"specific":[117],"vowels":[118],"in":[119],"generated":[123],"TTSVowelViz":[125],"align":[126],"with":[127],"human":[128],"perception,":[129],"effectively":[130],"visualising":[131],"perceived":[133],"accent":[134],"shift.":[135],"This":[136],"work":[137],"highlights":[138],"space":[140],"visualisation":[141],"as":[142],"valuable":[144],"interpretability":[145],"for":[147]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-05-05T00:00:00"}
