{"id":"https://openalex.org/W4401609216","doi":"https://doi.org/10.1109/icasspw62465.2024.10626762","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR And Speech-to-Text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","display_name":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR And Speech-to-Text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609216","doi":"https://doi.org/10.1109/icasspw62465.2024.10626762"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5065400666","display_name":"Chih-Kai Yang","orcid":"https://orcid.org/0000-0002-6708-3176"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Kai Yang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103339163","display_name":"Kuan-Po Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Po Huang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013041579","display_name":"Ke-Han Lu","orcid":"https://orcid.org/0000-0002-5331-0534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ke-Han Lu","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145177","display_name":"Chun-Yi Kuan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Yi Kuan","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104171295","display_name":"Chi-Yuan Hsiao","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Yuan Hsiao","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065400666"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":3.4453,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93358023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"540","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9293000102043152,"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":0.9293000102043152,"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/generalizability-theory","display_name":"Generalizability theory","score":0.8699209690093994},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7867591381072998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6695283651351929},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6653625965118408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5825541019439697},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5350647568702698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.517806887626648},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5019714832305908},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4877699017524719},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48142310976982117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45139002799987793},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.44272732734680176},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2942064702510834},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2546660602092743},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23119986057281494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13149556517601013},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.11720782518386841},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06852734088897705}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8699209690093994},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7867591381072998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6695283651351929},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6653625965118408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5825541019439697},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5350647568702698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.517806887626648},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5019714832305908},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4877699017524719},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48142310976982117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45139002799987793},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.44272732734680176},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2942064702510834},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2546660602092743},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23119986057281494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13149556517601013},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.11720782518386841},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06852734088897705},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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":27,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2914304175","https://openalex.org/W3196434891","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226033575","https://openalex.org/W4285158365","https://openalex.org/W4365799947","https://openalex.org/W4375869049","https://openalex.org/W4378105483","https://openalex.org/W4385573061","https://openalex.org/W4385822890","https://openalex.org/W4387596329","https://openalex.org/W4387838514","https://openalex.org/W4389600306","https://openalex.org/W4391021545","https://openalex.org/W4392902623","https://openalex.org/W4392903468","https://openalex.org/W4392931630","https://openalex.org/W6780218876","https://openalex.org/W6810476118","https://openalex.org/W6810673746","https://openalex.org/W6847363464","https://openalex.org/W6852909395","https://openalex.org/W6857492710","https://openalex.org/W6857817883"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2990005675","https://openalex.org/W4386374060","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"This":[0],"work":[1],"evaluated":[2],"several":[3,74],"cutting-edge":[4],"large-scale":[5],"foundation":[6],"models":[7,28,49,96],"based":[8],"on":[9,20,65],"self-supervision":[10],"or":[11],"weak":[12],"supervision,":[13],"including":[14],"SeamlessM4T,":[15],"SeamlessM4T":[16],"v2,":[17],"and":[18,61,80,91],"Whisper-large-v3,":[19],"three":[21],"code-switched":[22,105],"corpora.":[23],"We":[24,44],"found":[25],"that":[26,47,83],"self-supervised":[27,42,95],"can":[29],"achieve":[30],"performances":[31,64],"close":[32],"to":[33,100],"the":[34,38,71,102],"supervised":[35],"model,":[36],"indicating":[37],"effectiveness":[39],"of":[40,73,76,104],"multilingual":[41],"pre-training.":[43],"also":[45],"observed":[46],"these":[48],"still":[50],"have":[51],"room":[52],"for":[53,94],"improvement":[54],"as":[55],"they":[56,84],"kept":[57],"making":[58],"similar":[59,92],"mistakes":[60],"had":[62],"unsatisfactory":[63],"modeling":[66],"intra-sentential":[67],"code-switching.":[68],"In":[69],"addition,":[70],"validity":[72],"variants":[75],"Whisper":[77],"was":[78],"explored,":[79],"we":[81],"concluded":[82],"remained":[85],"effective":[86],"in":[87],"a":[88],"code-switching":[89],"scenario,":[90],"techniques":[93],"are":[97],"worth":[98],"studying":[99],"boost":[101],"performance":[103],"tasks.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
