{"id":"https://openalex.org/W4386857883","doi":"https://doi.org/10.1109/access.2023.3317236","title":"Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring","display_name":"Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386857883","doi":"https://doi.org/10.1109/access.2023.3317236"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3317236","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3317236","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10255657.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10255657.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101509635","display_name":"Ahmed Zahran","orcid":"https://orcid.org/0000-0001-9942-0870"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Ahmed I. Zahran","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010"],"raw_orcid":"https://orcid.org/0000-0001-9942-0870","affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102325651","display_name":"Aly A. Fahmy","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Aly A. Fahmy","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027622725","display_name":"Khaled Wassif","orcid":"https://orcid.org/0000-0002-7401-5219"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Khaled T. Wassif","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010"],"raw_orcid":"https://orcid.org/0000-0002-7401-5219","affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025488260","display_name":"Hanaa Bayomi","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Hanaa Bayomi","raw_affiliation_strings":["Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Orman, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo University, Faculty of Computers and Artificial Intelligence, 26H2+4HP, Ad Doqi, Dokki, Giza Governorate 3750010","institution_ids":["https://openalex.org/I145487455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101509635"],"corresponding_institution_ids":["https://openalex.org/I145487455"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.642,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87137282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"112650","last_page":"112663"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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/pronunciation","display_name":"Pronunciation","score":0.8936986327171326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8481136560440063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6231945753097534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6054136157035828},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5512915849685669},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4594579041004181},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4338605999946594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.400285005569458},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3238253593444824}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8936986327171326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481136560440063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6231945753097534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6054136157035828},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5512915849685669},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4594579041004181},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4338605999946594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.400285005569458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3238253593444824},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3317236","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3317236","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10255657.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0ce4890405f64a7f98192467d71e18bc","is_oa":true,"landing_page_url":"https://doaj.org/article/0ce4890405f64a7f98192467d71e18bc","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 112650-112663 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3317236","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3317236","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10255657.pdf","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386857883.pdf","grobid_xml":"https://content.openalex.org/works/W4386857883.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W576804789","https://openalex.org/W620022615","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W1931766939","https://openalex.org/W2086705963","https://openalex.org/W2091856355","https://openalex.org/W2164810574","https://openalex.org/W2171590421","https://openalex.org/W2526425061","https://openalex.org/W2547875792","https://openalex.org/W2753772285","https://openalex.org/W2842511635","https://openalex.org/W2936774411","https://openalex.org/W2964199361","https://openalex.org/W2972347929","https://openalex.org/W2979476256","https://openalex.org/W2995181338","https://openalex.org/W3013336802","https://openalex.org/W3036601975","https://openalex.org/W3096674206","https://openalex.org/W3119308075","https://openalex.org/W3134482008","https://openalex.org/W3162227798","https://openalex.org/W3167533889","https://openalex.org/W3175898847","https://openalex.org/W3197580070","https://openalex.org/W3197742413","https://openalex.org/W3197816268","https://openalex.org/W3197938691","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4212774754","https://openalex.org/W4223651314","https://openalex.org/W4224928163","https://openalex.org/W4226046739","https://openalex.org/W4283694096","https://openalex.org/W4287854494","https://openalex.org/W4297808394","https://openalex.org/W4312069033","https://openalex.org/W4385245566","https://openalex.org/W4388017359","https://openalex.org/W6600367688","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6728610325","https://openalex.org/W6729448088","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6798110199","https://openalex.org/W6839364956"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W1607396156"],"abstract_inverted_index":{"Automatic":[0],"pronunciation":[1,14,70,113,138,192],"assessment":[2,15],"models":[3,30,44],"are":[4],"regularly":[5],"used":[6,109],"in":[7,55],"language":[8],"learning":[9,27,42,107],"applications.":[10],"Common":[11],"methodologies":[12],"for":[13,69,99,161,189],"use":[16],"feature-based":[17],"approaches,":[18],"such":[19],"as":[20],"the":[21,36,64,81,84,103,124,131,136,153,159,181],"Goodness-of-Pronunciation":[22],"(GOP)":[23],"approach,":[24],"or":[25,170],"deep":[26],"speech":[28,33,51,166,196],"recognition":[29,93],"to":[31,48,95,110,122,128,152],"perform":[32],"assessment.":[34],"With":[35],"rise":[37],"of":[38,130,147,184],"transformers,":[39],"pre-trained":[40,85,186],"self-supervised":[41],"(SSL)":[43],"have":[45],"been":[46],"utilized":[47],"extract":[49],"contextual":[50],"representations,":[52],"showing":[53],"improvements":[54],"various":[56],"downstream":[57],"tasks.":[58],"In":[59,80,102],"this":[60,178],"study,":[61],"we":[62],"propose":[63],"end-to-end":[65,190],"regressor":[66],"(E2E-R)":[67],"model":[68,87,115,156,188],"scoring.":[71],"E2E-R":[72,140],"is":[73,88,108,150],"trained":[74],"using":[75],"a":[76,91,112,118,142,185],"two-step":[77],"training":[78,162],"process.":[79],"first":[82,182],"step,":[83,105],"SSL":[86,187],"fine-tuned":[89],"on":[90,163,194],"phoneme":[92,126],"task":[94],"obtain":[96,111],"better":[97],"representations":[98,127],"pronounced":[100,125],"phonemes.":[101],"second":[104],"transfer":[106],"scoring":[114,193],"that":[116],"uses":[117],"Siamese":[119],"neural":[120],"network":[121],"compare":[123],"embeddings":[129],"canonical":[132],"phonemes":[133],"and":[134],"produce":[135],"final":[137],"scores.":[139],"achieves":[141],"Pearson":[143],"correlation":[144],"coefficient":[145],"(PCC)":[146],"0.68,":[148],"which":[149],"similar":[151],"state-of-the-art":[154],"GOPT-PAII":[155],"while":[157],"eliminating":[158],"need":[160],"additional":[164],"native":[165],"data,":[167],"feature":[168],"engineering,":[169],"external":[171],"forced":[172],"alignment":[173],"modules.":[174],"To":[175],"our":[176],"knowledge,":[177],"work":[179],"presents":[180],"utilization":[183],"phoneme-level":[191],"raw":[195],"waveforms.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-04T09:04:59.091469","created_date":"2025-10-10T00:00:00"}
