{"id":"https://openalex.org/W4416034657","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.715","title":"UniCoM: A Universal Code-Switching Speech Generator","display_name":"UniCoM: A Universal Code-Switching Speech Generator","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034657","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.715"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.715","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.715","pdf_url":"https://aclanthology.org/2025.findings-emnlp.715.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.715.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100319597","display_name":"Sangmin Lee","orcid":"https://orcid.org/0000-0001-6648-6099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sangmin Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054584660","display_name":"Woojin Chung","orcid":"https://orcid.org/0000-0003-0736-3624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Woojin Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seyun Um","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13273","last_page":"13288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.804099977016449,"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":0.804099977016449,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.04879999905824661,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.040800001472234726,"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/generator","display_name":"Generator (circuit theory)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34529998898506165},{"id":"https://openalex.org/keywords/signal-generator","display_name":"Signal generator","score":0.31630000472068787},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.2865000069141388},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.28619998693466187},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2842000126838684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5950999855995178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49219998717308044},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4578000009059906},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C207912722","wikidata":"https://www.wikidata.org/wiki/Q1259123","display_name":"Signal generator","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C178076193","wikidata":"https://www.wikidata.org/wiki/Q6124455","display_name":"Immittance","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.715","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.715","pdf_url":"https://aclanthology.org/2025.findings-emnlp.715.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.715","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.715","pdf_url":"https://aclanthology.org/2025.findings-emnlp.715.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034657.pdf","grobid_xml":"https://content.openalex.org/works/W4416034657.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Code-switching":[0],"(CS),":[1],"the":[2,38],"alternation":[3],"between":[4],"two":[5],"or":[6],"more":[7,142],"languages":[8],"within":[9],"a":[10,51,98],"single":[11],"speaker's":[12],"utterances,":[13],"is":[14],"common":[15],"in":[16],"real-world":[17],"conversations":[18],"and":[19,108,119,129,140],"poses":[20],"significant":[21],"challenges":[22],"for":[23,54,103],"multilingual":[24,99,144],"speech":[25,78,105,138],"technology.However,":[26],"systems":[27],"capable":[28],"of":[29,40,90],"handling":[30],"this":[31,44],"phenomenon":[32],"remain":[33],"underexplored,":[34],"primarily":[35],"due":[36],"to":[37,123,135],"scarcity":[39],"suitable":[41],"datasets.To":[42],"resolve":[43],"issue,":[45],"we":[46,68,93],"propose":[47],"Universal":[48],"Code-Mixer":[49],"(UniCoM),":[50],"novel":[52],"pipeline":[53],"generating":[55],"high-quality,":[56],"natural":[57],"CS":[58,77,100,137],"samples":[59],"without":[60],"altering":[61],"sentence":[62],"semantics.Our":[63],"approach":[64,134],"utilizes":[65],"an":[66],"algorithm":[67],"call":[69],"Substituting":[70],"WORDs":[71],"with":[72,83],"Synonyms":[73],"(SWORDS),":[74],"which":[75],"generates":[76],"by":[79],"replacing":[80],"selected":[81],"words":[82],"their":[84,88],"translations":[85],"while":[86],"considering":[87],"parts":[89],"speech.Using":[91],"UniCoM,":[92],"construct":[94],"Code-Switching":[95],"FLEURS":[96],"(CS-FLEURS),":[97],"corpus":[101],"designed":[102],"automatic":[104],"recognition":[106],"(ASR)":[107],"speech-to-text":[109],"translation":[110],"(S2TT).Experimental":[111],"results":[112],"show":[113],"that":[114],"CS-FLEURS":[115],"achieves":[116],"high":[117],"intelligibility":[118],"naturalness,":[120],"performing":[121],"comparably":[122],"existing":[124],"datasets":[125],"on":[126],"both":[127],"objective":[128],"subjective":[130],"metrics.We":[131],"expect":[132],"our":[133],"advance":[136],"technology":[139],"enable":[141],"inclusive":[143],"systems.":[145]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}