{"id":"https://openalex.org/W2983434507","doi":"https://doi.org/10.1109/ssd.2019.8893184","title":"Improving Low Resource Turkish Speech Recognition with Data Augmentation and TTS","display_name":"Improving Low Resource Turkish Speech Recognition with Data Augmentation and TTS","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2983434507","doi":"https://doi.org/10.1109/ssd.2019.8893184","mag":"2983434507"},"language":"en","primary_location":{"id":"doi:10.1109/ssd.2019.8893184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssd.2019.8893184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Multi-Conference on Systems, Signals &amp; Devices (SSD)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5008695406","display_name":"Ramazan G\u00f6kay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141511","display_name":"TUBITAK BILGEM","ror":"https://ror.org/057kvja37","country_code":"TR","type":"government","lineage":["https://openalex.org/I4210141511"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ramazan Gokay","raw_affiliation_strings":["Speech and Language Technologies Laboratory, TUBITAK BILGEM, Kocaeli, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Language Technologies Laboratory, TUBITAK BILGEM, Kocaeli, Turkey","institution_ids":["https://openalex.org/I4210141511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102285234","display_name":"H\u00fclya Yal\u00e7\u0131n","orcid":null},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hulya Yalcin","raw_affiliation_strings":["Visual Intelligence Laboratory, Istanbul Technical University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Intelligence Laboratory, Istanbul Technical University, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0772,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.91042535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"360"},"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":0.9922000169754028,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9904000163078308,"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":0.8138473033905029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7862893342971802},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7027876973152161},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.49761250615119934},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4564206600189209},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.41755837202072144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39743107557296753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37032970786094666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138473033905029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7862893342971802},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7027876973152161},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.49761250615119934},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4564206600189209},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.41755837202072144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39743107557296753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37032970786094666},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssd.2019.8893184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssd.2019.8893184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Multi-Conference on Systems, Signals &amp; Devices (SSD)","raw_type":"proceedings-article"},{"id":"pmh:oai:polen.itu.edu.tr:11527/47480","is_oa":false,"landing_page_url":"https://hdl.handle.net/11527/47480","pdf_url":null,"source":{"id":"https://openalex.org/S4306400460","display_name":"Istanbul Technical University Academic Open Archive (Istanbul Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48912391","host_organization_name":"Istanbul Technical University","host_organization_lineage":["https://openalex.org/I48912391"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1509793305","https://openalex.org/W1979651826","https://openalex.org/W2115407392","https://openalex.org/W2127141656","https://openalex.org/W2141440284","https://openalex.org/W2184343439","https://openalex.org/W2193413348","https://openalex.org/W2407080277","https://openalex.org/W2752143737","https://openalex.org/W2767052532","https://openalex.org/W2799473636","https://openalex.org/W3101648800","https://openalex.org/W6680768788","https://openalex.org/W6686369942","https://openalex.org/W6687566353","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W2537969829","https://openalex.org/W1566586269","https://openalex.org/W1547849677","https://openalex.org/W2123003832","https://openalex.org/W2153664791","https://openalex.org/W2389353568","https://openalex.org/W2889413431","https://openalex.org/W4225304461","https://openalex.org/W2983434507","https://openalex.org/W642007152"],"abstract_inverted_index":{"One":[0],"of":[1,13,27,42,109,157],"the":[2,11,40,107],"major":[3],"problems":[4],"faced":[5],"by":[6,67,102,154],"speech":[7,46,49,64,71,76,88,92,115,129,136],"recognition":[8,116,137],"researchers":[9],"is":[10,20,65,85,100,152],"lack":[12,26],"data.":[14,28,161],"In":[15,74,90,142],"this":[16,58,143],"paper,":[17],"our":[18],"objective":[19],"to":[21,25,38,82,134],"compare":[22],"alternative":[23,112],"solutions":[24],"Some":[29],"experiments":[30],"are":[31,55],"conducted":[32],"with":[33],"very":[34],"limited":[35],"training":[36],"data":[37,43,61,126],"see":[39],"effects":[41,108],"augmentation":[44,127],"and":[45,52,159],"synthesis":[47,72,77,93,130],"on":[48,114],"recognition.":[50],"Speed":[51],"volume":[53],"perturbations":[54],"applied":[56],"in":[57],"study.":[59],"Besides":[60],"augmentation,":[62],"synthetic":[63,160],"generated":[66],"using":[68,155],"two":[69],"different":[70],"methods.":[73],"first":[75],"approach,":[78,94],"Google":[79],"Translate":[80],"Text":[81],"Speech":[83],"(gTTS)":[84],"used":[86],"as":[87],"synthesizer.":[89],"second":[91],"an":[95],"end-to-end":[96],"Turkish":[97],"TTS":[98],"system":[99],"trained":[101],"us.":[103],"Finally,":[104],"we":[105],"examined":[106],"all":[110],"these":[111],"methods":[113],"for":[117,138],"low":[118,139],"resource":[119,140],"languages.":[120,141],"Our":[121],"results":[122],"demonstrate":[123],"that":[124],"some":[125],"or":[128],"techniques":[131],"work":[132],"well":[133],"improve":[135],"study,":[144],"14.8%":[145],"relative":[146],"Word":[147],"Error":[148],"Ratio":[149],"(WER)":[150],"improvement":[151],"obtained":[153],"combination":[156],"augmented":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2025-10-10T00:00:00"}
