{"id":"https://openalex.org/W4404782016","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","title":"PolyWER: A Holistic Evaluation Framework for Code-Switched Speech Recognition","display_name":"PolyWER: A Holistic Evaluation Framework for Code-Switched Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782016","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.356"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.356","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","pdf_url":"https://aclanthology.org/2024.findings-emnlp.356.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-emnlp.356.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081068672","display_name":"Karima Kadaoui","orcid":"https://orcid.org/0009-0006-6093-8748","observed_orcids":["https://orcid.org/0009-0006-6093-8748"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karima Kadaoui","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102661225","display_name":"Maryam Al Ali","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maryam Al Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093129978","display_name":"Hawau Olamide Toyin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hawau Olamide Toyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ibrahim Mohammed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Mohammed","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002602581","display_name":"Hanan Aldarmaki","orcid":"https://orcid.org/0000-0003-1706-1777","observed_orcids":["https://orcid.org/0000-0003-1706-1777"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanan Aldarmaki","raw_affiliation_strings":["University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5774,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66764718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6144","last_page":"6153"},"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.7960000038146973},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.7889999747276306},{"id":"https://openalex.org/keywords/transliteration","display_name":"transliteration","score":0.9020000100135803},{"id":"https://openalex.org/keywords/translation","display_name":"translation","score":0.453000009059906},{"id":"https://openalex.org/keywords/arabic-english-code-switching","display_name":"Arabic-English code-switching","score":0.8600000143051147},{"id":"https://openalex.org/keywords/code-mixing","display_name":"code-mixing","score":0.40299999713897705},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.49399998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053644061088562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5458739399909973},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.488474041223526},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16190937161445618},{"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:10.18653/v1/2024.findings-emnlp.356","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","pdf_url":"https://aclanthology.org/2024.findings-emnlp.356.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.356","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.356","pdf_url":"https://aclanthology.org/2024.findings-emnlp.356.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782016.pdf","grobid_xml":"https://content.openalex.org/works/W4404782016.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2914699162","https://openalex.org/W4408356775","https://openalex.org/W7212323543","https://openalex.org/W7161835530","https://openalex.org/W4400397471","https://openalex.org/W3181647671","https://openalex.org/W6931496167","https://openalex.org/W2039387825","https://openalex.org/W4319862283","https://openalex.org/W7204586422"],"abstract_inverted_index":{"Code-switching":[0],"in":[1,15,70,160],"speech,":[2],"particularly":[3],"between":[4],"languages":[5],"that":[6,141],"use":[7,80,93],"different":[8,19,71],"scripts,":[9],"can":[10,157],"potentially":[11],"be":[12,145,158],"correctly":[13],"transcribed":[14],"various":[16],"forms,":[17,72],"including":[18,73],"ways":[20],"of":[21,23,67,94,101,112],"transliteration":[22],"the":[24,28,78,92,99],"embedded":[25],"language":[26,30],"into":[27],"matrix":[29],"script.Traditional":[31],"methods":[32],"for":[33,57,120,148],"measuring":[34],"accuracy,":[35],"such":[36],"as":[37],"Word":[38],"Error":[39],"Rate":[40],"(WER),":[41],"are":[42],"too":[43],"strict":[44],"to":[45,62,131],"address":[46],"this":[47,49,95],"challenge.In":[48],"paper,":[50],"we":[51,97],"introduce":[52],"PolyWER,":[53],"a":[54,102],"proposed":[55],"framework":[56],"evaluating":[58],"speech":[59],"recognition":[60],"systems":[61],"handle":[63],"language-mixing.PolyWER":[64],"accepts":[65],"transcriptions":[66],"code-mixed":[68,113],"segments":[69],"transliterations":[74,109],"and":[75,85,110,124,154],"translations.We":[76],"demonstrate":[77],"algorithms":[79],"cases":[81],"through":[82],"detailed":[83],"examples,":[84],"evaluate":[86],"it":[87],"against":[88],"human":[89],"judgement.To":[90],"enable":[91],"metric,":[96],"appended":[98],"annotations":[100,119,143,156],"publicly":[103],"available":[104],"Arabic-English":[105],"code-switched":[106],"dataset":[107],"with":[108],"translations":[111],"speech.We":[114],"also":[115],"utilize":[116],"these":[117],"additional":[118,155],"fine-tuning":[121,149],"ASR":[122,151],"models":[123],"compare":[125],"their":[126],"performance":[127],"using":[128],"PolyWER.In":[129],"addition":[130],"our":[132,138,161],"main":[133],"finding":[134],"on":[135],"PolyWER's":[136],"effectiveness,":[137],"experiments":[139],"show":[140],"alternative":[142],"could":[144],"more":[146],"effective":[147],"monolingual":[150],"models.Our":[152],"algorithm":[153],"found":[159],"Github":[162],"repo":[163],"1":[164],".":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2024-11-28T00:00:00"}
