{"id":"https://openalex.org/W4392903468","doi":"https://doi.org/10.1109/icassp48485.2024.10446737","title":"Zero Resource Code-Switched Speech Benchmark Using Speech Utterance Pairs for Multiple Spoken Languages","display_name":"Zero Resource Code-Switched Speech Benchmark Using Speech Utterance Pairs for Multiple Spoken Languages","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903468","doi":"https://doi.org/10.1109/icassp48485.2024.10446737"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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","ASUS Intelligent Cloud Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"ASUS Intelligent Cloud Services","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103117965","display_name":"Chih-Kai Yang","orcid":"https://orcid.org/0009-0003-5955-3910"},"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":"Chih-Kai Yang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071751103","display_name":"Yu-Kuan Fu","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":"Yu-Kuan Fu","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069239428","display_name":"Ewan Dunbar","orcid":"https://orcid.org/0000-0001-9603-953X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ewan Dunbar","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7492,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91078156,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10006","last_page":"10010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.9979000091552734,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8054519891738892},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8029180765151978},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.7213195562362671},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7150632739067078},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7148940563201904},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6030797362327576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5589300990104675},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.49231016635894775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46071678400039673},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4586681127548218},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43106722831726074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3640744686126709},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20594331622123718},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1672113835811615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8054519891738892},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8029180765151978},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7213195562362671},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7150632739067078},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7148940563201904},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6030797362327576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5589300990104675},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.49231016635894775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46071678400039673},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4586681127548218},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43106722831726074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3640744686126709},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20594331622123718},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1672113835811615},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2914304175","https://openalex.org/W2933138175","https://openalex.org/W2996728628","https://openalex.org/W3035390927","https://openalex.org/W3095410713","https://openalex.org/W3097032879","https://openalex.org/W3110458199","https://openalex.org/W3173110011","https://openalex.org/W3180374548","https://openalex.org/W3197259906","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4246076598","https://openalex.org/W4285158365","https://openalex.org/W4287854499","https://openalex.org/W4296068785","https://openalex.org/W4302306287","https://openalex.org/W4319862641","https://openalex.org/W4375869049","https://openalex.org/W4375869224","https://openalex.org/W4385565879","https://openalex.org/W4385822439","https://openalex.org/W4389518325","https://openalex.org/W4389519244","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6845064686","https://openalex.org/W6846997368"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2771594921","https://openalex.org/W2432897346","https://openalex.org/W3177678247","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W1999617572","https://openalex.org/W2944572343"],"abstract_inverted_index":{"We":[0,20,74],"introduce":[1],"a":[2,22,44,50],"new":[3],"zero":[4],"resource":[5],"code-switched":[6,67],"speech":[7,17,38,54,93],"bench-mark":[8],"designed":[9],"to":[10,31],"assess":[11],"the":[12,34,76],"code-switching":[13,35,108,119],"capabilities":[14],"of":[15,25,37,52,65,78],"self-supervised":[16],"encoders":[18,39,94],"directly.":[19],"showcase":[21],"baseline":[23],"system":[24],"language":[26,68],"modeling":[27],"on":[28,62,84],"discrete":[29],"units":[30],"demonstrate":[32,91],"how":[33],"abilities":[36],"can":[40],"be":[41],"assessed":[42],"in":[43,107,117],"zero-resource":[45],"manner.":[46],"Our":[47],"experiments":[48],"encompass":[49],"variety":[51],"well-known":[53],"encoders,":[55],"including":[56],"Wav2vec":[57],"2.0,":[58,105],"HuBERT,":[59],"XLSR,":[60,100],"etc.,":[61],"three":[63],"tracks":[64],"different":[66],"pairs:":[69],"Spanish-English,":[70],"French-English,":[71],"and":[72,81],"Chinese-English.":[73],"examine":[75],"impact":[77],"pre-training":[79],"languages":[80],"model":[82],"size":[83],"benchmark":[85],"performance.":[86],"Notably,":[87],"though":[88],"our":[89],"results":[90],"that":[92],"with":[95],"multilingual":[96],"pre-training,":[97],"exemplified":[98],"by":[99],"outperform":[101],"monolingual":[102],"variants":[103],"(Wav2vec":[104],"HuBERT)":[106],"scenarios,":[109],"there":[110],"is":[111],"still":[112],"substantial":[113],"room":[114],"for":[115],"improvement":[116],"their":[118],"linguistic":[120],"abilities.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
