{"id":"https://openalex.org/W4416771688","doi":"https://doi.org/10.1109/sped67700.2025.11252042","title":"Impact of Text Origin and Real-Synthetic Data Ratio in TTS-Augmented Low-Resource ASR","display_name":"Impact of Text Origin and Real-Synthetic Data Ratio in TTS-Augmented Low-Resource ASR","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771688","doi":"https://doi.org/10.1109/sped67700.2025.11252042"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11252042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-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":"https://openalex.org/A5116627870","display_name":"Dalai Mengke","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I4210161853","display_name":"Budapest Institute","ror":"https://ror.org/050hvq478","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210161853"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Dalai Mengke","raw_affiliation_strings":["Budapest University of Tech. & Econ,Dept. of Telecom. and AI,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Tech. & Econ,Dept. of Telecom. and AI,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179","https://openalex.org/I4210161853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120388178","display_name":"Wuyerigen","orcid":null},"institutions":[{"id":"https://openalex.org/I64222039","display_name":"National University of Mongolia","ror":"https://ror.org/04855bv47","country_code":"MN","type":"education","lineage":["https://openalex.org/I64222039"]},{"id":"https://openalex.org/I29266178","display_name":"Mongolian National University","ror":"https://ror.org/00qcnss81","country_code":"MN","type":"education","lineage":["https://openalex.org/I29266178"]}],"countries":["MN"],"is_corresponding":false,"raw_author_name":"Wuyerigen","raw_affiliation_strings":["National University of Mongolia,Dept. of Mongolian Language and Linguistics,Ulaanbaatar,Mongolia"],"affiliations":[{"raw_affiliation_string":"National University of Mongolia,Dept. of Mongolian Language and Linguistics,Ulaanbaatar,Mongolia","institution_ids":["https://openalex.org/I64222039","https://openalex.org/I29266178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[{"id":"https://openalex.org/I4210161853","display_name":"Budapest Institute","ror":"https://ror.org/050hvq478","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210161853"]},{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"P\u00e9ter Mihajlik","raw_affiliation_strings":["Budapest University of Tech. & Econ,Dept. of Telecom. and AI,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Tech. & Econ,Dept. of Telecom. and AI,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179","https://openalex.org/I4210161853"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5116627870"],"corresponding_institution_ids":["https://openalex.org/I29770179","https://openalex.org/I4210161853"],"apc_list":null,"apc_paid":null,"fwci":2.5147,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92417344,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.875,"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":0.875,"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/T13194","display_name":"ICT in Developing Communities","score":0.04259999841451645,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.01119999960064888,"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/training-set","display_name":"Training set","score":0.5530999898910522},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5303999781608582},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5202999711036682},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4345000088214874},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.38940000534057617},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.353300005197525},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3476000130176544},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3314000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749000191688538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6590999960899353},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47999998927116394},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.353300005197525},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11252042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2091746061","https://openalex.org/W2127141656","https://openalex.org/W2936774411","https://openalex.org/W2937197076","https://openalex.org/W3015449694","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3198836239","https://openalex.org/W4296070422","https://openalex.org/W4362458233","https://openalex.org/W4388075511","https://openalex.org/W4402112533","https://openalex.org/W4406249136","https://openalex.org/W4408345790","https://openalex.org/W4408460210","https://openalex.org/W4411654054","https://openalex.org/W4416036575"],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,16,57,124],"automatic":[3],"speech":[4,36,63,70,94,107,128],"recognition":[5,98],"(ASR)":[6],"for":[7,43,62,100,146,170,185],"low-resource":[8,101,171],"languages":[9,102,172],"is":[10],"severely":[11],"hindered":[12],"by":[13,83],"the":[14,55,96,167,182],"lack":[15],"sufficient":[17],"training":[18,144],"data.":[19],"While":[20],"traditional":[21],"data":[22,148],"augmentation":[23],"methods":[24],"have":[25,39],"long":[26],"been":[27],"employed":[28],"to":[29,126,173,188],"alleviate":[30],"this":[31,81],"issue,":[32],"recent":[33],"advances":[34],"in":[35,192],"synthesis":[37,64],"technologies":[38],"shown":[40],"promising":[41],"potential":[42],"further":[44],"boosting":[45],"ASR":[46,76,115,168,194],"performance.":[47,116],"However,":[48,176],"a":[49,121,161],"key":[50],"research":[51],"gap":[52,82],"remains":[53],"regarding":[54],"impact":[56],"different":[58,110],"textual":[59],"sources":[60,112],"used":[61],"and":[65,68,92,103,135,150],"how":[66,105],"synthetic":[67,93,106,127],"real":[69,91,125],"should":[71],"be":[72],"optimally":[73],"combined":[74],"during":[75],"training.":[77],"This":[78],"study":[79],"addresses":[80],"systematically":[84],"investigating":[85],"(1)":[86],"what":[87],"mixing":[88],"strategy":[89],"between":[90],"yields":[95],"best":[97],"results":[99,118,154],"(2)":[104],"generated":[108],"from":[109,160],"text":[111,158,183],"affects":[113],"downstream":[114,193],"Our":[117],"show":[119,156],"that":[120,157],"1:1":[122],"ratio":[123],"achieves":[129],"strong":[130],"performance":[131,169,191],"across":[132],"both":[133],"in-domain":[134],"out-of-domain":[136],"test":[137],"sets,":[138],"suggesting":[139],"it":[140],"as":[141,181],"an":[142],"optimal":[143],"configuration":[145],"balancing":[147],"quality":[149],"quantity.":[151],"Furthermore,":[152],"our":[153],"also":[155],"translated":[159],"high-resource":[162],"language":[163],"can":[164],"indeed":[165],"improve":[166],"some":[174],"extent.":[175],"using":[177],"native":[178],"spoken":[179],"utterances":[180],"source":[184],"TTS":[186],"leads":[187],"consistently":[189],"better":[190],"tasks.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-11-27T00:00:00"}