{"id":"https://openalex.org/W4406858895","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849308","title":"Adapting OpenAI\u2019s Whisper for Speech Recognition on Code-Switch Mandarin-English SEAME and ASRU2019 Datasets","display_name":"Adapting OpenAI\u2019s Whisper for Speech Recognition on Code-Switch Mandarin-English SEAME and ASRU2019 Datasets","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858895","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849308"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5011571577","display_name":"Yuhang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Yang","raw_affiliation_strings":["Hunan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]},{"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/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071426656","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6212-5448"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","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":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100681425","display_name":"Xionghu Zhong","orcid":"https://orcid.org/0000-0002-7533-2347"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xionghu Zhong","raw_affiliation_strings":["Hunan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.878600001335144,"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":0.878600001335144,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7882145643234253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473272085189819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6430591940879822},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.5582660436630249},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46478888392448425},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35656851530075073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3323935866355896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2934659719467163},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22748830914497375},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04608085751533508}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7882145643234253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473272085189819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6430591940879822},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.5582660436630249},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46478888392448425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35656851530075073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3323935866355896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2934659719467163},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22748830914497375},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04608085751533508},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":40,"referenced_works":["https://openalex.org/W880632652","https://openalex.org/W2038116248","https://openalex.org/W2939757332","https://openalex.org/W2952638691","https://openalex.org/W2963240019","https://openalex.org/W2972702443","https://openalex.org/W3034430025","https://openalex.org/W3096122506","https://openalex.org/W3097894798","https://openalex.org/W3163135964","https://openalex.org/W3185341429","https://openalex.org/W3197144816","https://openalex.org/W3204687321","https://openalex.org/W3205644108","https://openalex.org/W3217003515","https://openalex.org/W4226093136","https://openalex.org/W4297841426","https://openalex.org/W4297841499","https://openalex.org/W4375869049","https://openalex.org/W4384767314","https://openalex.org/W4385807419","https://openalex.org/W4385807453","https://openalex.org/W4385822324","https://openalex.org/W4385822342","https://openalex.org/W4385822810","https://openalex.org/W4385822890","https://openalex.org/W4385822953","https://openalex.org/W4385823150","https://openalex.org/W4391021440","https://openalex.org/W6622259991","https://openalex.org/W6745245109","https://openalex.org/W6755207826","https://openalex.org/W6780815891","https://openalex.org/W6794037546","https://openalex.org/W6797037654","https://openalex.org/W6802398075","https://openalex.org/W6839144119","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"on":[3,13,55],"SOTA":[4],"results":[5,62,107,136],"achieved":[6],"using":[7,35],"openAI\u2019s":[8],"Whisper":[9,56,120,144],"model":[10,121],"with":[11,94],"adaptation":[12,15,36,68,96,142],"different":[14,51,114],"corpus":[16,23],"sizes":[17],"for":[18],"two":[19],"established":[20],"code-switch":[21,147],"Mandarin/English":[22],"-":[24],"namely":[25],"SEAME":[26],"and":[27,126],"ASRU2019":[28],"corpora.Two":[29],"key":[30],"experiments":[31],"were":[32],"conducted:":[33],"a)":[34],"data":[37,69,97],"from":[38],"1":[39,75],"to":[40,43,79,91,145],"100/200":[41],"hours":[42,78],"demonstrate":[44],"the":[45,65,87,101,106,119,141],"effectiveness":[46],"of":[47,67,143],"adaptation,":[48,105,118],"b)":[49],"examining":[50],"language":[52,102,127],"ID":[53],"setups":[54],"prompt.":[57],"The":[58],"Mixed":[59],"Error":[60],"Rate":[61],"show":[63,92,108],"that":[64,109,134],"amount":[66],"may":[70],"be":[71],"as":[72,74],"low":[73],"~":[76],"10":[77],"achieve":[80],"saturation":[81],"in":[82],"performance":[83,93],"gain":[84],"(SEAME),":[85],"while":[86],"ASRU":[88],"task":[89],"continued":[90],"more":[95],"(>100":[98],"hours).":[99],"For":[100],"prompt":[103,128],"without":[104],"various":[110],"prompting":[111],"strategies":[112],"produce":[113],"outcomes.":[115],"However,":[116],"after":[117],"uniformly":[122],"improves":[123],"its":[124],"performance,":[125],"becomes":[129],"not":[130],"critical.":[131],"We":[132],"believe":[133],"these":[135],"can":[137],"help":[138],"researchers":[139],"study":[140],"other":[146],"Languages.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}