{"id":"https://openalex.org/W4410436092","doi":"https://doi.org/10.1142/s1793351x25440027","title":"Bridging Linguistics and Artificial Intelligence: A\u00a0Phoneme-Centric Method for Assessing Synthetic Speech","display_name":"Bridging Linguistics and Artificial Intelligence: A\u00a0Phoneme-Centric Method for Assessing Synthetic Speech","publication_year":2025,"publication_date":"2025-05-16","ids":{"openalex":"https://openalex.org/W4410436092","doi":"https://doi.org/10.1142/s1793351x25440027"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x25440027","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x25440027","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-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":null,"display_name":"Sarah Reynolds","orcid":"https://orcid.org/0009-0006-4482-5719"},"institutions":[{"id":"https://openalex.org/I84475105","display_name":"Embry\u2013Riddle Aeronautical University","ror":"https://ror.org/010jskt71","country_code":"US","type":"education","lineage":["https://openalex.org/I84475105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Reynolds","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, 1 Aerospace Blvd., Daytona Beach, FL 32174, USA"],"raw_orcid":"https://orcid.org/0009-0006-4482-5719","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, 1 Aerospace Blvd., Daytona Beach, FL 32174, USA","institution_ids":["https://openalex.org/I84475105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007729921","display_name":"Omar Ochoa","orcid":"https://orcid.org/0000-0002-2072-5610"},"institutions":[{"id":"https://openalex.org/I84475105","display_name":"Embry\u2013Riddle Aeronautical University","ror":"https://ror.org/010jskt71","country_code":"US","type":"education","lineage":["https://openalex.org/I84475105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Ochoa","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, 1 Aerospace Blvd., Daytona Beach, FL 32174, USA"],"raw_orcid":"https://orcid.org/0000-0002-2072-5610","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Embry-Riddle Aeronautical University, 1 Aerospace Blvd., Daytona Beach, FL 32174, USA","institution_ids":["https://openalex.org/I84475105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84475105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03955685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"03","first_page":"433","last_page":"453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8202999830245972,"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":0.8202999830245972,"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/T12031","display_name":"Speech and dialogue systems","score":0.7989000082015991,"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":0.8522138595581055},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8481484651565552},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5826480388641357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210022926330566},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5184268951416016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4544414281845093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8522138595581055},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8481484651565552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5826480388641357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210022926330566},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5184268951416016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4544414281845093},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x25440027","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x25440027","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1872806465","https://openalex.org/W1970026646","https://openalex.org/W2052819072","https://openalex.org/W2070257144","https://openalex.org/W2075847010","https://openalex.org/W2529403924","https://openalex.org/W3101981467","https://openalex.org/W3107855336","https://openalex.org/W3144293453","https://openalex.org/W4297536219","https://openalex.org/W4385718176","https://openalex.org/W4390468020","https://openalex.org/W4393859250","https://openalex.org/W4404953674"],"related_works":["https://openalex.org/W4408719353","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,100,121,167,222],"study":[1,50],"bridges":[2],"the":[3,19,24,42,49,77,108,129,139,147],"gap":[4],"between":[5,23,175],"traditional":[6],"linguistic":[7,114],"studies,":[8],"particularly":[9,95],"phonology,":[10],"and":[11,36,72,90,111,119,133,141,153,181,239],"modern":[12],"Machine":[13],"Learning":[14],"(ML)":[15],"developments.":[16],"It":[17],"explores":[18],"mutually":[20],"beneficial":[21],"interactions":[22],"two":[25],"domains:":[26],"by":[27,37,68,138],"utilizing":[28],"Speech-To-Text":[29],"(STT)":[30],"models":[31],"to":[32,87,103],"aid":[33],"in":[34,57,92,172,188,205,227],"phonology":[35],"integrating":[38],"phonological":[39,109],"insights":[40,234],"into":[41,116,235],"evaluation":[43,118],"of":[44,51],"Text-To-Speech":[45],"(TTS)":[46],"generation.":[47,191],"Phonology,":[48],"phonemes":[52],"\u2014":[53,60],"fundamental":[54],"sound":[55],"units":[56],"human":[58],"speech":[59,65,70,85,135,190,197,204],"is":[61,126],"pivotal":[62],"for":[63,123,150,155,186,219],"understanding":[64],"variations":[66],"caused":[67],"accents,":[69],"disorders,":[71],"individual":[73],"pronunciation":[74],"differences.":[75],"Leveraging":[76],"International":[78],"Phonetic":[79],"Alphabet":[80],"(IPA),":[81],"this":[82],"work":[83,101],"analyzes":[84],"patterns":[86],"enhance":[88],"explainability":[89],"accuracy":[91,174],"TTS":[93,117,229],"models,":[94],"those":[96],"employing":[97,146],"transformer":[98],"architectures.":[99],"aims":[102],"refine":[104],"ML":[105],"tools,":[106],"expand":[107],"approach,":[110],"further":[112],"integrate":[113],"knowledge":[115],"improvement.":[120,221],"approach":[122,223],"phoneme":[124,151,158,173,207],"analysis":[125,168],"tested":[127],"on":[128],"Speech":[130],"Accent":[131],"Archive":[132],"synthetic":[134,182,189,196,241],"samples":[136],"generated":[137],"OpenAI":[140],"Azure":[142],"text-to-speech":[143],"systems.":[144],"By":[145],"wav2vec":[148],"model":[149],"detection":[152],"DeepPhonemizer":[154],"grapheme-to-phoneme":[156],"conversion,":[157],"distances":[159],"are":[160],"calculated":[161],"using":[162],"an":[163],"adapted":[164],"Levenshtein":[165],"distance.":[166],"reveals":[169],"significant":[170],"differences":[171],"native":[176],"English":[177],"speakers,":[178,180],"nonnative":[179],"speech,":[183],"highlighting":[184],"areas":[185,218],"improvement":[187],"Results":[192],"indicate":[193],"that":[194],"while":[195],"often":[198],"rivals":[199],"or":[200],"slightly":[201],"exceeds":[202],"real":[203],"overall":[206],"distance,":[208],"it":[209],"also":[210,232],"exhibits":[211],"higher":[212],"error":[213],"variability,":[214],"thus":[215],"pinpointing":[216],"specific":[217],"targeted":[220],"not":[224],"only":[225],"aids":[226],"refining":[228],"systems":[230],"but":[231],"offers":[233],"developing":[236],"more":[237],"unique":[238],"personalized":[240],"voices.":[242]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}