{"id":"https://openalex.org/W4416707462","doi":"https://doi.org/10.1109/access.2025.3637322","title":"How Open Is Open TTS? A Practical Evaluation of Open Source TTS Tools","display_name":"How Open Is Open TTS? A Practical Evaluation of Open Source TTS Tools","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416707462","doi":"https://doi.org/10.1109/access.2025.3637322"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3637322","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637322","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3637322","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120616079","display_name":"Teodora R\u0103gman","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Teodora R\u0103gman","raw_affiliation_strings":["POLITEHNICA Bucharest, Bucharest, Romania","POLITEHNICA Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"POLITEHNICA Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"POLITEHNICA Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093266198","display_name":"Adrian Bogdan St\u00e2nea","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adrian Bogdan St\u00e2nea","raw_affiliation_strings":["Technical University of Cluj-Napoca, Cluj-Napoca, Romania","Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032257745","display_name":"Horia Cucu","orcid":"https://orcid.org/0000-0002-8711-3854"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Horia Cucu","raw_affiliation_strings":["POLITEHNICA Bucharest, Bucharest, Romania","POLITEHNICA Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"POLITEHNICA Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"POLITEHNICA Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["POLITEHNICA Bucharest, Bucharest, Romania","POLITEHNICA Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"POLITEHNICA Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"POLITEHNICA Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120616079"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19298218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"203415","last_page":"203428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6603999733924866,"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":0.6603999733924866,"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":0.1006999984383583,"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":0.05900000035762787,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6789000034332275},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4593000113964081},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4049000144004822},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3894999921321869},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.3628999888896942},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.3562999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565999865531921},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6789000034332275},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4593000113964081},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.2897999882698059},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3637322","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637322","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2603.24116","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.24116","pdf_url":"https://arxiv.org/pdf/2603.24116","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:58d2c1b1d79d49dfad5cc3f1bba237e1","is_oa":true,"landing_page_url":"https://doaj.org/article/58d2c1b1d79d49dfad5cc3f1bba237e1","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 203415-203428 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3637322","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637322","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"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":{"Open-source":[0],"text-to-speech":[1],"(TTS)":[2],"frameworks":[3],"have":[4],"emerged":[5],"as":[6,74,83,85],"highly":[7],"adaptable":[8],"platforms":[9],"for":[10,91],"developing":[11],"speech":[12],"synthesis":[13,89],"systems":[14],"across":[15],"a":[16],"wide":[17],"range":[18],"of":[19,49,76,88,109],"languages.":[20],"However,":[21],"their":[22],"applicability":[23],"is":[24,33],"not":[25],"uniform":[26],"\u2013":[27],"particularly":[28],"when":[29,36],"the":[30,47,110,136,174],"target":[31],"language":[32],"under-resourced":[34],"or":[35],"computational":[37,125],"resources":[38],"are":[39],"constrained.":[40],"In":[41],"this":[42,163],"study,":[43],"we":[44],"systematically":[45],"assess":[46],"feasibility":[48],"building":[50],"novel":[51],"TTS":[52,156],"models":[53],"using":[54],"four":[55],"widely":[56],"adopted":[57],"open-source":[58],"architectures:":[59],"FastPitch,":[60],"VITS,":[61],"Grad-TTS,":[62],"and":[63,80,98,107,124,141,151,167],"Matcha-TTS.":[64],"Our":[65],"evaluation":[66,143],"spans":[67],"multiple":[68],"dimensions,":[69],"including":[70],"qualitative":[71],"aspects":[72],"such":[73],"ease":[75],"installation,":[77],"dataset":[78],"preparation,":[79],"hardware":[81],"requirements,":[82],"well":[84],"quantitative":[86],"assessments":[87],"quality":[90],"Romanian.":[92],"We":[93],"employ":[94],"both":[95],"objective":[96],"metrics":[97],"subjective":[99],"listening":[100],"tests":[101],"to":[102,147,161],"evaluate":[103],"intelligibility,":[104],"speaker":[105],"similarity,":[106],"naturalness":[108],"generated":[111],"speech.":[112],"The":[113],"results":[114],"reveal":[115],"significant":[116],"challenges":[117],"in":[118,131,138],"tool":[119],"chain":[120],"setup,":[121],"data":[122],"preprocessing,":[123],"efficiency,":[126],"which":[127],"can":[128],"hinder":[129],"adoption":[130],"low-resource":[132],"contexts.":[133],"By":[134],"grounding":[135],"analysis":[137],"reproducible":[139],"protocols":[140],"accessible":[142],"criteria,":[144],"thiswork":[145],"aims":[146],"inform":[148],"best":[149],"practices":[150],"promote":[152],"more":[153],"inclusive,":[154],"language-diverse":[155],"development.":[157],"All":[158],"information":[159],"needed":[160],"reproduce":[162],"study":[164],"(i.e.":[165],"code":[166],"data)":[168],"will":[169],"be":[170],"made":[171],"available":[172],"after":[173],"final":[175],"review.":[176]},"counts_by_year":[],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-11-27T00:00:00"}
