{"id":"https://openalex.org/W4385572970","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.38","title":"NatiQ: An End-to-end Text-to-Speech System for Arabic","display_name":"NatiQ: An End-to-end Text-to-Speech System for Arabic","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385572970","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.38"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.wanlp-1.38","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.38","pdf_url":"https://aclanthology.org/2022.wanlp-1.38.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.wanlp-1.38.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047182137","display_name":"Ahmed Abdelal\u00ed","orcid":"https://orcid.org/0000-0002-4160-8181","observed_orcids":["https://orcid.org/0000-0002-4160-8181"]},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","aabdelali ,","aabdelali,ndurrani,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"aabdelali ,","institution_ids":[]},{"raw_affiliation_string":"aabdelali,ndurrani,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689067","display_name":"Nadir Durrani","orcid":"https://orcid.org/0000-0002-9378-4128","observed_orcids":["https://orcid.org/0000-0002-9378-4128"]},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nadir Durrani","raw_affiliation_strings":["Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","aabdelali ,","aabdelali,ndurrani,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"aabdelali ,","institution_ids":[]},{"raw_affiliation_string":"aabdelali,ndurrani,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016845689","display_name":"Cenk Demiro\u011flu","orcid":"https://orcid.org/0000-0002-6160-3169","observed_orcids":["https://orcid.org/0000-0002-6160-3169"]},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cenk Demiroglu","raw_affiliation_strings":["\u00d6zyegin University, Istanbul, T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00d6zyegin University, Istanbul, T\u00fcrkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002245931","display_name":"Fahim Dalvi","orcid":"https://orcid.org/0000-0003-1183-7837","observed_orcids":["https://orcid.org/0000-0003-1183-7837"]},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Fahim Dalvi","raw_affiliation_strings":["Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","aabdelali ,","aabdelali,ndurrani,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"aabdelali ,","institution_ids":[]},{"raw_affiliation_string":"aabdelali,ndurrani,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240","observed_orcids":["https://orcid.org/0000-0002-9051-6240"]},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","aabdelali ,","aabdelali,ndurrani,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute -Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"aabdelali ,","institution_ids":[]},{"raw_affiliation_string":"aabdelali,ndurrani,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Mohamed Darwish","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kareem Darwish","raw_affiliation_strings":["aiXplain Inc. Los Gatos, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain Inc. Los Gatos, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.105,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81510942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"394","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.847000002861023},{"id":"https://openalex.org/keywords/arabic-speech-synthesis","display_name":"Arabic speech synthesis","score":0.9929999709129333},{"id":"https://openalex.org/keywords/tacotron","display_name":"Tacotron","score":0.7960000038146973},{"id":"https://openalex.org/keywords/waveglow","display_name":"WaveGlow","score":0.7879999876022339},{"id":"https://openalex.org/keywords/espnet","display_name":"ESPnet","score":0.6729999780654907},{"id":"https://openalex.org/keywords/attention-based-encoder-decoder","display_name":"attention-based encoder-decoder","score":0.7590000033378601},{"id":"https://openalex.org/keywords/mel-spectrogram-generation","display_name":"mel-spectrogram generation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/vocoder","display_name":"vocoder","score":0.5149999856948853},{"id":"https://openalex.org/keywords/journalistic-narrative","display_name":"journalistic narrative","score":0.43299999833106995},{"id":"https://openalex.org/keywords/speech-quality-assessment","display_name":"speech quality assessment","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.836978554725647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172463536262512},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7107055187225342},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6499757766723633},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.626447319984436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5548504590988159},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5356559157371521},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.44823968410491943},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4374425709247589},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3804210424423218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2995206117630005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22329223155975342},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1141539216041565},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07505613565444946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07282465696334839},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2022.wanlp-1.38","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.38","pdf_url":"https://aclanthology.org/2022.wanlp-1.38.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.07373","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07373","pdf_url":"https://arxiv.org/pdf/2206.07373","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/8557","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10679/8557","pdf_url":null,"source":{"id":"https://openalex.org/S7407064130","display_name":"eResearch@Ozyegin","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I44925452","host_organization_name":"\u00d6zye\u011fin University","host_organization_lineage":["https://openalex.org/I44925452"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conferenceObject"},{"id":"doi:10.48550/arxiv.2206.07373","doi":"https://doi.org/10.48550/arxiv.2206.07373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.07373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wanlp-1.38","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.wanlp-1.38","pdf_url":"https://aclanthology.org/2022.wanlp-1.38.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572970.pdf","grobid_xml":"https://content.openalex.org/works/W4385572970.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2471147443","https://openalex.org/W2758788159","https://openalex.org/W2788851830","https://openalex.org/W2886769154","https://openalex.org/W2894295011","https://openalex.org/W2898847420","https://openalex.org/W2903739847","https://openalex.org/W2943731990","https://openalex.org/W2963499843","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2981934523","https://openalex.org/W3001899777","https://openalex.org/W3007095894","https://openalex.org/W3015338123","https://openalex.org/W3124014937","https://openalex.org/W3168542456"],"related_works":["https://openalex.org/W3045249863","https://openalex.org/W3216879078","https://openalex.org/W6922514487","https://openalex.org/W4401338106","https://openalex.org/W4416251749","https://openalex.org/W4386056881","https://openalex.org/W4247287309","https://openalex.org/W4210849413","https://openalex.org/W2156560366","https://openalex.org/W4327652477"],"abstract_inverted_index":{"NatiQ":[0],"is":[1,132],"end-to-end":[2,128],"text-to-speech":[3],"system":[4],"for":[5,27,61,97],"Arabic.Our":[6],"speech":[7,59],"synthesizer":[8],"uses":[9],"an":[10,87],"encoder-decoder":[11],"architecture":[12,129],"with":[13,34,39,46],"attention.We":[14],"used":[15,57],"both":[16],"tacotron-based":[17],"models":[18],"(tacotron-1":[19],"and":[20,22,43,70,72,95,99,109,114],"tacotron-2)":[21],"the":[23,35,40,47,55,105,119,127],"faster":[24],"transformer":[25,45],"model":[26],"generating":[28],"mel-spectrograms":[29],"from":[30,54],"characters.We":[31],"concatenated":[32],"Tacotron1":[33],"WaveRNN":[36],"vocoder,":[37],"Tacotron2":[38],"WaveGlow":[41],"vocoder":[42,50],"ESPnet":[44],"parallel":[48],"wavegan":[49],"to":[51,80],"synthesize":[52],"waveforms":[53],"spectrograms.We":[56],"in-house":[58],"data":[60],"two":[62],"voices:":[63],"1)":[64],"neutral":[65],"male":[66],"\"Hamza\"-narrating":[67],"general":[68],"content":[69],"news,":[71],"2)":[73],"expressive":[74],"female":[75],"\"Amina\"narrating":[76],"children":[77],"story":[78],"books":[79],"train":[81],"our":[82],"models.Our":[83],"best":[84],"systems":[85,106],"achieve":[86],"average":[88],"Mean":[89],"Opinion":[90],"Score":[91],"(MOS)":[92],"of":[93,104],"4.21":[94],"4.40":[96],"Amina":[98],"Hamza":[100],"respectively.The":[101],"objective":[102],"evaluation":[103],"using":[107],"word":[108],"character":[110],"error":[111],"rate":[112],"(WER":[113],"CER)":[115],"as":[116,118],"well":[117],"response":[120],"time":[121],"measured":[122],"by":[123],"real-time":[124],"factor":[125],"favored":[126],"ESPnet.NatiQ":[130],"demo":[131],"available":[133],"online":[134],"at":[135],"https://tts.qcri.org.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}
