{"id":"https://openalex.org/W7166806359","doi":"https://doi.org/10.18653/v1/2026.mellm-1.24","title":"SN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation","display_name":"SN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166806359","doi":"https://doi.org/10.18653/v1/2026.mellm-1.24"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.mellm-1.24","doi":"https://doi.org/10.18653/v1/2026.mellm-1.24","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.mellm-1.24","pdf_url":"https://aclanthology.org/2026.mellm-1.24.pdf","source":{"id":"https://openalex.org/S7407114466","display_name":"Workshop on Multilinguality in the Era of Large Language Models (MeLLM)","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":"Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)","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/2026.mellm-1.24.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114987850","display_name":"Priyaranjan Pattnayak","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Priyaranjan Pattnayak","raw_affiliation_strings":["Oracle America Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oracle America Inc","institution_ids":["https://openalex.org/I1342911587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5114987850"],"corresponding_institution_ids":["https://openalex.org/I1342911587"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43988252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00019999999494757503,"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/word-error-rate","display_name":"word error rate","score":0.6759999990463257},{"id":"https://openalex.org/keywords/indo-aryan-languages","display_name":"Indo-Aryan languages","score":0.6230000257492065},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.6600000262260437},{"id":"https://openalex.org/keywords/transliteration","display_name":"transliteration","score":0.6740000247955322},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.7139999866485596},{"id":"https://openalex.org/keywords/lexical-substitution","display_name":"lexical substitution","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46239998936653137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3930000066757202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24500000476837158},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24410000443458557},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.22429999709129333},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.21660000085830688},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2151000052690506},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.21289999783039093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.mellm-1.24","doi":"https://doi.org/10.18653/v1/2026.mellm-1.24","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.mellm-1.24","pdf_url":"https://aclanthology.org/2026.mellm-1.24.pdf","source":{"id":"https://openalex.org/S7407114466","display_name":"Workshop on Multilinguality in the Era of Large Language Models (MeLLM)","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":"Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.mellm-1.24","doi":"https://doi.org/10.18653/v1/2026.mellm-1.24","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.mellm-1.24","pdf_url":"https://aclanthology.org/2026.mellm-1.24.pdf","source":{"id":"https://openalex.org/S7407114466","display_name":"Workshop on Multilinguality in the Era of Large Language Models (MeLLM)","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":"Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166806359.pdf","grobid_xml":"https://content.openalex.org/works/W7166806359.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154173041","https://openalex.org/W4402112216","https://openalex.org/W4226207999","https://openalex.org/W7165650565","https://openalex.org/W4323922069","https://openalex.org/W4405300857","https://openalex.org/W2798685342","https://openalex.org/W4385571195","https://openalex.org/W4404792932","https://openalex.org/W4411120531"],"abstract_inverted_index":{"Word":[0],"Error":[1],"Rate":[2],"(WER)":[3],"is":[4,126],"the":[5,18,89,147],"dominant":[6],"ASR":[7,65,165],"metric":[8],"but":[9],"can":[10],"overestimate":[11],"errors":[12,122],"when":[13,168],"references":[14],"and":[15,47,63,139],"hypotheses":[16],"encode":[17],"same":[19],"words":[20],"in":[21,27,146],"different":[22],"scripts,":[23],"a":[24,39,50,160],"common":[25],"issue":[26],"multilingual":[28,175],"settings":[29],"where":[30],"models":[31],"emit":[32],"romanized":[33],"text.We":[34],"propose":[35],"Script-Normalized":[36],"WER":[37,112],"(SN-WER),":[38],"training-free,":[40],"evaluation-only":[41],"scoring":[42],"method":[43],"that":[44,152],"transliterates":[45],"reference":[46],"hypothesis":[48],"into":[49],"language-specific":[51],"canonical":[52],"script":[53,69,102],"before":[54],"computing":[55],"WER.Evaluated":[56],"on":[57,72,85],"5":[58],"Indic":[59,149],"languages,":[60],"2":[61],"datasets,":[62],"3":[64],"models,":[66],"SN-WER":[67,153],"quantifies":[68],"mismatch":[70],"effects:":[71],"curated":[73],"FLEURS":[74],"it":[75],"narrows":[76],"inflated":[77],"model":[78],"gaps":[79],"by":[80],"up":[81],"to":[82,120,128],"12%,":[83],"while":[84,114],"noisy":[86],"Common":[87],"Voice":[88],"reductions":[90],"are":[91],"smaller":[92],"or":[93,174],"inconsistent,":[94],"exposing":[95],"genuine":[96],"recognition":[97],"weaknesses":[98],"rather":[99],"than":[100],"only":[101],"mismatch.Controlled":[103],"stress":[104],"tests":[105],"show":[106,117],"67%":[107],"attenuation":[108],"of":[109],"artificial":[110],"romanization-induced":[111],"inflation,":[113],"lexical-substitution":[115],"controls":[116],"near-identical":[118],"sensitivity":[119],"semantic":[121],"(\u2206SN/\u2206WER":[123],"\u2248":[124],"1.09).SN-WER":[125],"robust":[127],"transliterator":[129],"choice":[130],"(\u2206":[131,136],"<":[132,137],"0.002),":[133],"normalization":[134],"changes":[135],"0.05),":[138],"has":[140],"low":[141],"tokencollision":[142],"rates":[143],"(<":[144],"0.1%)":[145],"evaluated":[148],"setting.We":[150],"argue":[151],"should":[154],"be":[155],"reported":[156],"alongside":[157],"WER/CER":[158],"as":[159],"companion":[161],"score":[162],"for":[163],"script-insensitive":[164],"evaluation,":[166],"especially":[167],"transcripts":[169],"feed":[170],"downstream":[171],"search,":[172],"indexing,":[173],"LLM":[176],"pipelines.":[177]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}