{"id":"https://openalex.org/W4416771706","doi":"https://doi.org/10.1109/sped67700.2025.11251954","title":"Towards Hungarian-English Code-Switching Speech Dataset Construction by using Multi Speaker-adaptive Text-to-Speech Synthesis","display_name":"Towards Hungarian-English Code-Switching Speech Dataset Construction by using Multi Speaker-adaptive Text-to-Speech Synthesis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771706","doi":"https://doi.org/10.1109/sped67700.2025.11251954"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11251954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11251954","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/A5120003993","display_name":"Piroska Zs\u00f3fia Barta","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"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Piroska Zs\u00f3fia Barta","raw_affiliation_strings":["Budapest University of Technology and Economics, SpeechTex Ltd,Faculty of E. Eng. and Informatics,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, SpeechTex Ltd,Faculty of E. Eng. and Informatics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"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/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]},{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"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 Technology and Economics, ELTE Research Centre for Linguistics,Dept. of Telecom. and Artificial Int,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, ELTE Research Centre for Linguistics,Dept. of Telecom. and Artificial Int,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179","https://openalex.org/I106118109","https://openalex.org/I2802350943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120003993"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20613119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8137000203132629,"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":0.8137000203132629,"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":0.06530000269412994,"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":0.03840000182390213,"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/set","display_name":"Set (abstract data type)","score":0.6593999862670898},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5329999923706055},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4115999937057495},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.37470000982284546},{"id":"https://openalex.org/keywords/flash","display_name":"Flash (photography)","score":0.35010001063346863}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6593999862670898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579999923706055},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2777526259","wikidata":"https://www.wikidata.org/wiki/Q221836","display_name":"Flash (photography)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.29319998621940613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11251954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11251954","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":10,"referenced_works":["https://openalex.org/W2782717521","https://openalex.org/W2936842814","https://openalex.org/W3019581400","https://openalex.org/W3096263335","https://openalex.org/W3096615836","https://openalex.org/W3119308075","https://openalex.org/W4307823382","https://openalex.org/W4391021542","https://openalex.org/W4402112533","https://openalex.org/W7089618696"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,48],"work,":[2],"we":[3,122],"present":[4],"the":[5,55,63,71,78,95,115,119,127],"first":[6],"version":[7],"of":[8,66,85,91,103],"a":[9,23,28,82,89,100],"novel":[10],"Hungarian\u2013English":[11],"code-switching":[12,39],"dataset":[13,18],"derived":[14],"from":[15],"VoxPopuli.":[16],"The":[17],"includes":[19],"two":[20],"subsets":[21],"\u2013":[22,33],"randomly":[24],"aligned":[25],"set":[26,32],"and":[27,88,108],"partially":[29],"synthesized,":[30],"context-preserving":[31],"each":[34],"specifically":[35],"designed":[36],"to":[37,114,125],"support":[38],"research.":[40],"We":[41],"evaluated":[42],"three":[43],"different":[44],"ASR":[45],"models":[46],"on":[47,94],"dataset.":[49],"Zero-shot":[50],"results":[51,130],"indicated":[52],"that":[53],"among":[54],"examined":[56],"models,":[57],"Canary":[58],"180M":[59],"Flash":[60],"was":[61,75],"inherently":[62],"most":[64],"capable":[65],"handling":[67],"codeswitched":[68],"speech.":[69],"However,":[70],"best":[72],"fine-tuned":[73],"performance":[74],"achieved":[76],"with":[77],"Whisper-large-v3-turbo":[79],"model,":[80],"attaining":[81],"multilingual":[83],"WER":[84,107,129],"$8.07":[86],"\\%$":[87,93,105,110],"CER":[90,112],"$3.74":[92],"test":[96],"set.":[97],"This":[98],"represents":[99],"relative":[101],"improvement":[102],"$89.84":[104],"in":[106,111],"$94.37":[109],"compared":[113],"zero-shot":[116],"results.":[117],"With":[118],"new":[120],"dataset,":[121],"were":[123],"able":[124],"improve":[126],"monolingual":[128],"for":[131],"both":[132],"languages,":[133],"as":[134],"well.":[135]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}