{"id":"https://openalex.org/W4416799749","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249050","title":"Improving Code-Switching Speech Recognition with TTS Data Augmentation","display_name":"Improving Code-Switching Speech Recognition with TTS Data Augmentation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799749","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249050"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5112025134","display_name":"Yue Heng Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yue Heng Yeo","raw_affiliation_strings":["Institute for Infocomm Research I R, A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research I R, A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619807","display_name":"Yuchen Hu","orcid":"https://orcid.org/0000-0002-0696-6434"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shreyas Gopal","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shreyas Gopal","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114025990","display_name":"Yizhou Peng","orcid":"https://orcid.org/0000-0002-5718-570X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091096053","display_name":"Hexin Liu","orcid":"https://orcid.org/0000-0002-3998-9229"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hexin Liu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112025134"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19217303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"992","last_page":"997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8769000172615051,"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":0.8769000172615051,"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":0.06379999965429306,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.012199999764561653,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6216999888420105},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5198000073432922},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5109999775886536},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45559999346733093},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4011000096797943},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.39629998803138733},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3675000071525574}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7919999957084656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487000226974487},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6216999888420105},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.39629998803138733},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W1583636673","https://openalex.org/W2084543186","https://openalex.org/W2936774411","https://openalex.org/W3197380209","https://openalex.org/W4225956675","https://openalex.org/W4375869049","https://openalex.org/W4392902746","https://openalex.org/W4404783499","https://openalex.org/W4410087476","https://openalex.org/W4415433892","https://openalex.org/W4416011273"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speech":[1,7,18,73,76],"recognition":[2],"(ASR)":[3],"for":[4,115],"conversational":[5,52,121],"code-switching":[6,54,122],"remains":[8],"challenging":[9],"due":[10],"to":[11,33,49,86,95],"the":[12,40,46,58,78],"scarcity":[13],"of":[14,63],"realistic,":[15],"high-quality":[16],"labeled":[17],"data.":[19,66],"This":[20],"paper":[21],"explores":[22],"multilingual":[23,41,107],"text-to-speech":[24],"(TTS)":[25],"models":[26],"as":[27],"an":[28,110],"effective":[29,111],"data":[30],"augmentation":[31],"technique":[32],"address":[34],"this":[35],"shortage.":[36],"Specifically,":[37],"we":[38],"fine-tune":[39],"CosyVoice2":[42],"TTS":[43,108],"model":[44],"on":[45,89,98],"SEAME":[47],"dataset":[48],"generate":[50],"synthetic":[51,75],"Chinese-English":[53],"speech,":[55],"significantly":[56],"increasing":[57],"quantity":[59],"and":[60,91,112],"speaker":[61],"diversity":[62],"available":[64],"training":[65],"Our":[67],"experiments":[68],"demonstrate":[69],"that":[70,106],"augmenting":[71],"real":[72],"with":[74],"reduces":[77],"mixed":[79],"error":[80],"rate":[81],"(MER)":[82],"from":[83,92],"12.1":[84],"%":[85,88,94,97],"10.1":[87],"DevMan":[90],"17.8":[93],"16.0":[96],"DevSGE,":[99],"indicating":[100],"performance":[101],"gains.":[102],"These":[103],"results":[104],"confirm":[105],"is":[109],"practical":[113],"tool":[114],"enhancing":[116],"ASR":[117],"robustness":[118],"in":[119],"low-resource,":[120],"scenarios.":[123]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-28T00:00:00"}