{"id":"https://openalex.org/W4400285910","doi":"https://doi.org/10.3390/a17070292","title":"Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training","display_name":"Central Kurdish Text-to-Speech Synthesis with Novel End-to-End Transformer Training","publication_year":2024,"publication_date":"2024-07-03","ids":{"openalex":"https://openalex.org/W4400285910","doi":"https://doi.org/10.3390/a17070292"},"language":"en","primary_location":{"id":"doi:10.3390/a17070292","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17070292","pdf_url":"https://www.mdpi.com/1999-4893/17/7/292/pdf?version=1720082572","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"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":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/17/7/292/pdf?version=1720082572","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038016921","display_name":"Hawraz A. Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I46208956","display_name":"Salahaddin University-Erbil","ror":"https://ror.org/02124dd11","country_code":"IQ","type":"education","lineage":["https://openalex.org/I46208956"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Hawraz Ahmad","raw_affiliation_strings":["Department of Software and Informatics Engineering, Salahaddin University-Erbil, Erbil 44001, Iraq"],"raw_orcid":"https://orcid.org/0009-0009-4932-3795","affiliations":[{"raw_affiliation_string":"Department of Software and Informatics Engineering, Salahaddin University-Erbil, Erbil 44001, Iraq","institution_ids":["https://openalex.org/I46208956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065801825","display_name":"Tarik A. Rashid","orcid":"https://orcid.org/0000-0002-8661-258X"},"institutions":[{"id":"https://openalex.org/I3151615967","display_name":"University of Kurdistan Hewler","ror":"https://ror.org/00268wk31","country_code":"IQ","type":"education","lineage":["https://openalex.org/I3151615967"]}],"countries":["IQ"],"is_corresponding":true,"raw_author_name":"Tarik Rashid","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Kurdistan Hawler, Erbil 44001, Iraq"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Kurdistan Hawler, Erbil 44001, Iraq","institution_ids":["https://openalex.org/I3151615967"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065801825"],"corresponding_institution_ids":["https://openalex.org/I3151615967"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.486,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70430684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"17","issue":"7","first_page":"292","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7777994871139526},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.7669677734375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6446542739868164},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.612223207950592},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5950247645378113},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.49965882301330566},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49474188685417175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590548276901245},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.423308789730072},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4220365285873413},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2929472029209137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777994871139526},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.7669677734375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6446542739868164},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.612223207950592},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5950247645378113},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.49965882301330566},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49474188685417175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590548276901245},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.423308789730072},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4220365285873413},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2929472029209137},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a17070292","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17070292","pdf_url":"https://www.mdpi.com/1999-4893/17/7/292/pdf?version=1720082572","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"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":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6f802759061349ceac2a1998b2e02a93","is_oa":false,"landing_page_url":"https://doaj.org/article/6f802759061349ceac2a1998b2e02a93","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 17, Iss 7, p 292 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a17070292","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17070292","pdf_url":"https://www.mdpi.com/1999-4893/17/7/292/pdf?version=1720082572","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"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":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320318812","display_name":"Salahaddin University-Erbil","ror":"https://ror.org/02124dd11"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400285910.pdf","grobid_xml":"https://content.openalex.org/works/W4400285910.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1534255124","https://openalex.org/W2116747411","https://openalex.org/W2141683828","https://openalex.org/W2747874407","https://openalex.org/W2914180170","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W3026874504","https://openalex.org/W3036601975","https://openalex.org/W3090831112","https://openalex.org/W3092028330","https://openalex.org/W3144035034","https://openalex.org/W3150572638","https://openalex.org/W3196584150","https://openalex.org/W3198213150","https://openalex.org/W3198769980","https://openalex.org/W3214500341","https://openalex.org/W4226332109","https://openalex.org/W4313148337","https://openalex.org/W4385823163","https://openalex.org/W4392124090","https://openalex.org/W6748409065","https://openalex.org/W6757079273","https://openalex.org/W6759433755","https://openalex.org/W6777694618","https://openalex.org/W6779871621","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6887757276","https://openalex.org/W7005508552"],"related_works":["https://openalex.org/W2799713421","https://openalex.org/W3109498233","https://openalex.org/W3164858600","https://openalex.org/W2031768607","https://openalex.org/W2902064555","https://openalex.org/W4200068392","https://openalex.org/W4205278983","https://openalex.org/W4298324454","https://openalex.org/W3192805203","https://openalex.org/W2152669512"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,25,61,160],"text-to-speech":[3,42,63],"(TTS)":[4],"models":[5,21],"have":[6],"aimed":[7],"to":[8,40,128],"streamline":[9],"the":[10,45,50,102,107,111,115,142,146,150,167,177],"two-stage":[11],"process":[12],"into":[13],"a":[14,37,82,122,173,190,200],"single-stage":[15,20],"training":[16],"approach.":[17],"However,":[18],"many":[19],"still":[22],"lag":[23],"behind":[24],"audio":[26,90],"quality,":[27],"particularly":[28,48],"when":[29],"handling":[30],"Kurdish":[31,46,76,131,155],"text":[32,116],"and":[33,58,93,140,162,193],"speech.":[34],"There":[35],"is":[36,59,87,94,126],"critical":[38],"need":[39],"enhance":[41],"conversion":[43],"for":[44,49,72,89],"language,":[47],"Sorani":[51],"dialect,":[52],"which":[53],"has":[54],"been":[55],"relatively":[56],"neglected":[57],"underrepresented":[60],"recent":[62],"advancements.":[64],"This":[65,99],"study":[66],"introduces":[67],"an":[68],"end-to-end":[69],"TTS":[70],"model":[71],"efficiently":[73],"generating":[74],"high-quality":[75],"audio.":[77],"The":[78],"proposed":[79,147],"method":[80,148],"leverages":[81],"variational":[83],"autoencoder":[84],"(VAE)":[85],"that":[86,188],"pre-trained":[88,108],"waveform":[91],"reconstruction":[92],"augmented":[95],"by":[96,106],"adversarial":[97],"training.":[98],"involves":[100],"aligning":[101,137],"prior":[103],"distribution":[104,113],"established":[105],"encoder":[109,117],"with":[110,133,187],"posterior":[112],"of":[114,153,180,184,189],"within":[118],"latent":[119,138],"variables.":[120],"Additionally,":[121],"stochastic":[123,143],"duration":[124,144],"predictor":[125],"incorporated":[127],"imbue":[129],"synthesized":[130],"speech":[132,156],"diverse":[134],"rhythms.":[135,163],"By":[136],"distributions":[139],"integrating":[141],"predictor,":[145],"facilitates":[149],"real-time":[151],"generation":[152],"natural":[154],"audio,":[157],"offering":[158],"flexibility":[159],"pitches":[161],"Empirical":[164],"evaluation":[165],"via":[166],"mean":[168],"opinion":[169],"score":[170],"(MOS)":[171],"on":[172],"custom":[174],"dataset":[175],"confirms":[176],"superior":[178],"performance":[179],"our":[181],"approach":[182],"(MOS":[183],"3.94)":[185],"compared":[186],"one-stage":[191],"system":[192],"other":[194],"two-staged":[195],"systems":[196],"as":[197],"assessed":[198],"through":[199],"subjective":[201],"human":[202],"evaluation.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
