{"id":"https://openalex.org/W4414426030","doi":"https://doi.org/10.3390/computers14100406","title":"Benchmarking the Responsiveness of Open-Source Text-to-Speech Systems","display_name":"Benchmarking the Responsiveness of Open-Source Text-to-Speech Systems","publication_year":2025,"publication_date":"2025-09-23","ids":{"openalex":"https://openalex.org/W4414426030","doi":"https://doi.org/10.3390/computers14100406"},"language":"en","primary_location":{"id":"doi:10.3390/computers14100406","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14100406","pdf_url":"https://www.mdpi.com/2073-431X/14/10/406/pdf?version=1758630273","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/14/10/406/pdf?version=1758630273","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119295838","display_name":"Ha Pham Thien Dinh","orcid":"https://orcid.org/0009-0000-1605-3332"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ha Pham Thien Dinh","raw_affiliation_strings":["Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076251331","display_name":"Rutherford Agbeshi Patamia","orcid":"https://orcid.org/0000-0002-6397-0974"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rutherford Agbeshi Patamia","raw_affiliation_strings":["Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082969851","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-2160-6111"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028574557","display_name":"Akansel Cosgun","orcid":"https://orcid.org/0000-0003-4203-6477"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Akansel Cosgun","raw_affiliation_strings":["Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia"],"affiliations":[{"raw_affiliation_string":"Faculty of Science, Engineering and Built Environment, School of Information Technology, Deakin University, Burwood, VIC 3125, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082969851"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":2.4057,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91302006,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"14","issue":"10","first_page":"406","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7221999764442444,"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":0.7221999764442444,"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":0.6233999729156494,"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/benchmarking","display_name":"Benchmarking","score":0.8665000200271606},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.63919997215271},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5202999711036682},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.38510000705718994},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.365200012922287},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.35690000653266907},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3409000039100647}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8665000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6514999866485596},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.63919997215271},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C141571065","wikidata":"https://www.wikidata.org/wiki/Q1771949","display_name":"Performance measurement","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/computers14100406","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14100406","pdf_url":"https://www.mdpi.com/2073-431X/14/10/406/pdf?version=1758630273","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:781a9fddda9446e39036034b710ff005","is_oa":true,"landing_page_url":"https://doaj.org/article/781a9fddda9446e39036034b710ff005","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":"Computers, Vol 14, Iss 10, p 406 (2025)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/30252514","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"}],"best_oa_location":{"id":"doi:10.3390/computers14100406","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14100406","pdf_url":"https://www.mdpi.com/2073-431X/14/10/406/pdf?version=1758630273","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414426030.pdf","grobid_xml":"https://content.openalex.org/works/W4414426030.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W658959353","https://openalex.org/W2093107730","https://openalex.org/W2407023693","https://openalex.org/W2783089003","https://openalex.org/W2964243274","https://openalex.org/W3043571714","https://openalex.org/W3144035034","https://openalex.org/W3150572638","https://openalex.org/W3198332267","https://openalex.org/W4200483526","https://openalex.org/W4385822499","https://openalex.org/W4395958010","https://openalex.org/W4402671584","https://openalex.org/W4405601798","https://openalex.org/W4406462026","https://openalex.org/W4411119580","https://openalex.org/W4411119642"],"related_works":[],"abstract_inverted_index":{"Responsiveness\u2014the":[0],"speed":[1],"at":[2],"which":[3],"a":[4,43,49,67,73,101],"text-to-speech":[5],"(TTS)":[6],"system":[7],"produces":[8],"audible":[9],"output\u2014is":[10],"critical":[11],"for":[12,172,180],"real-time":[13],"voice":[14],"assistants":[15],"yet":[16],"has":[17],"received":[18],"far":[19],"less":[20],"attention":[21],"than":[22,134],"perceptual":[23],"quality":[24],"metrics.":[25],"Existing":[26],"evaluations":[27],"often":[28],"touch":[29],"on":[30,128,162],"latency":[31,60],"but":[32],"do":[33],"not":[34],"establish":[35],"reproducible,":[36],"open-source":[37,82],"standards":[38],"that":[39,55,119,184],"capture":[40,109],"responsiveness":[41,163],"as":[42],"first-class":[44],"dimension.":[45],"This":[46],"work":[47],"introduces":[48],"baseline":[50],"benchmark":[51],"designed":[52],"to":[53,96,155],"fill":[54],"gap.":[56],"Our":[57],"framework":[58],"unifies":[59],"distribution,":[61],"tail":[62],"latency,":[63],"and":[64,69,75,99,112,164,176,188],"intelligibility":[65],"within":[66],"transparent":[68],"dataset-diverse":[70],"pipeline,":[71],"enabling":[72],"fair":[74],"replicable":[76],"comparison":[77],"across":[78,144],"13":[79],"widely":[80],"used":[81],"TTS":[83,174],"models.":[84],"By":[85,159],"grounding":[86],"evaluation":[87,161],"in":[88],"structured":[89],"input":[90],"sets":[91],"ranging":[92],"from":[93],"single":[94],"words":[95],"sentence-length":[97],"utterances":[98],"adopting":[100],"methodology":[102],"inspired":[103],"by":[104],"standardized":[105],"inference":[106],"benchmarks,":[107],"we":[108],"both":[110,186],"typical":[111],"worst-case":[113],"user":[114],"experiences.":[115],"Unlike":[116],"prior":[117],"studies":[118],"emphasize":[120],"closed":[121],"or":[122],"proprietary":[123],"systems,":[124],"our":[125],"focus":[126],"is":[127],"establishing":[129],"open,":[130],"reproducible":[131],"baselines":[132],"rather":[133],"ranking":[135],"against":[136],"commercial":[137],"references.":[138],"The":[139],"results":[140],"reveal":[141],"substantial":[142],"variability":[143],"architectures,":[145],"with":[146],"some":[147],"models":[148],"delivering":[149],"near-instant":[150],"responses":[151],"while":[152],"others":[153],"fail":[154],"meet":[156],"interactive":[157],"thresholds.":[158],"centering":[160],"reproducibility,":[165],"this":[166],"study":[167],"provides":[168],"an":[169],"infrastructural":[170],"foundation":[171],"benchmarking":[173],"systems":[175],"lays":[177],"the":[178],"groundwork":[179],"more":[181],"comprehensive":[182],"assessments":[183],"integrate":[185],"fidelity":[187],"speed.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
