{"id":"https://openalex.org/W4297841629","doi":"https://doi.org/10.21437/interspeech.2022-264","title":"Visualising Model Training via Vowel Space for Text-To-Speech Systems","display_name":"Visualising Model Training via Vowel Space for Text-To-Speech Systems","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841629","doi":"https://doi.org/10.21437/interspeech.2022-264"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-264","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-264","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035899583","display_name":"Binu Nisal Abeysinghe","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Binu Nisal Abeysinghe","raw_affiliation_strings":["Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082577862","display_name":"Jesin James","orcid":"https://orcid.org/0000-0003-0024-9597"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jesin James","raw_affiliation_strings":["Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043249487","display_name":"Catherine Watson","orcid":"https://orcid.org/0000-0001-9010-5188"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Catherine Watson","raw_affiliation_strings":["Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079047465","display_name":"Felix Marattukalam","orcid":"https://orcid.org/0000-0003-1457-696X"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Felix Marattukalam","raw_affiliation_strings":["Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical, Computer, and Software Engineering, The University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079047465"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55276227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9641000032424927,"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/T12031","display_name":"Speech and dialogue systems","score":0.9641000032424927,"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":0.9581000208854675,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9469000101089478,"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":0.7818021178245544},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.76725172996521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6610368490219116},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6136234998703003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46366173028945923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42973294854164124},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41828495264053345},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4100314676761627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818021178245544},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.76725172996521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6610368490219116},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6136234998703003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46366173028945923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42973294854164124},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41828495264053345},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4100314676761627},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-264","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-264","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1871004397","https://openalex.org/W1995803408","https://openalex.org/W2084609288","https://openalex.org/W2085703180","https://openalex.org/W2091578674","https://openalex.org/W2120329663","https://openalex.org/W2165798176","https://openalex.org/W2182866171","https://openalex.org/W2343674250","https://openalex.org/W2396366106","https://openalex.org/W2401267703","https://openalex.org/W2519091744","https://openalex.org/W2586516948","https://openalex.org/W2889106678","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972803756","https://openalex.org/W3129017987","https://openalex.org/W3135273601","https://openalex.org/W3158817671","https://openalex.org/W3163757888","https://openalex.org/W3208625370","https://openalex.org/W3209383001","https://openalex.org/W4233131682","https://openalex.org/W4361745739"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2047879039","https://openalex.org/W2794438528","https://openalex.org/W2346634343","https://openalex.org/W2167951753","https://openalex.org/W2031429550","https://openalex.org/W1969449618","https://openalex.org/W2183770253","https://openalex.org/W2073541007","https://openalex.org/W2126584718"],"abstract_inverted_index":{"With":[0],"the":[1,26,33,74,77,94,101,104,127,131,152,159,175],"recent":[2],"developments":[3],"in":[4,41,76],"speech":[5,21,48,52,82,123,145,153,180],"synthesis":[6,49,53,124,146,181],"via":[7],"machine":[8],"learning,":[9],"this":[10,44],"study":[11],"explores":[12],"incorporating":[13],"linguistics":[14,185],"knowledge":[15,45],"to":[16,25,71,98,171,174],"visualise":[17,120],"and":[18,28,39,86,178],"evaluate":[19],"synthetic":[20,42,81],"model":[22,54,102,125,147],"training.If":[23],"changes":[24,75],"first":[27],"second":[29],"formant":[30],"(in":[31],"turn,":[32],"vowel":[34,78,88,108,113,128,160],"space)":[35],"can":[36,46,119],"be":[37,84,172],"seen":[38,85],"heard":[40],"speech,":[43],"inform":[47],"technology":[50],"developers.A":[51],"trained":[55,135],"on":[56,112,184],"a":[57,66,122,144],"large":[58],"General":[59],"American":[60],"English":[61,69,107],"database":[62,132,154,177],"was":[63],"fine-tuned":[64],"into":[65],"New":[67,105],"Zealand":[68,106],"voice":[70],"identify":[72],"if":[73,100],"space":[79,114,129,161],"of":[80,130,151],"could":[83,141],"heard.The":[87],"spaces":[89],"at":[90],"different":[91],"intervals":[92],"during":[93],"fine-tuning":[95],"were":[96],"analysed":[97],"determine":[99],"learned":[103,149],"space.Our":[109],"findings":[110],"based":[111,183],"analysis":[115],"show":[116],"that":[117,139],"we":[118],"how":[121],"learns":[126],"it":[133,155],"is":[134,156],"on.Perception":[136],"tests":[137],"confirmed":[138],"humans":[140],"perceive":[142],"when":[143],"has":[148],"characteristics":[150],"training":[157,176],"on.Using":[158],"as":[162],"an":[163],"intermediary":[164],"evaluation":[165],"helps":[166],"understand":[167],"what":[168],"sounds":[169],"are":[170],"added":[173],"build":[179],"models":[182],"knowledge.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}