{"id":"https://openalex.org/W4408351780","doi":"https://doi.org/10.1109/icassp49660.2025.10888575","title":"Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking","display_name":"Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351780","doi":"https://doi.org/10.1109/icassp49660.2025.10888575"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101497013","display_name":"Brian Yan","orcid":"https://orcid.org/0000-0001-5362-806X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vineel Pratap","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01656424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.715399980545044,"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/T12031","display_name":"Speech and dialogue systems","score":0.715399980545044,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.6126000285148621,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.59579998254776,"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/computer-science","display_name":"Computer science","score":0.7010918855667114},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6449028253555298},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5943436622619629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35826051235198975},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3545891046524048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.352044939994812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010918855667114},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6449028253555298},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5943436622619629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35826051235198975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3545891046524048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.352044939994812},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1911935018","https://openalex.org/W2146574666","https://openalex.org/W2327501763","https://openalex.org/W2786835190","https://openalex.org/W2804732445","https://openalex.org/W2962893195","https://openalex.org/W2964309797","https://openalex.org/W3024308166","https://openalex.org/W3096215352","https://openalex.org/W3167533889","https://openalex.org/W3211278025","https://openalex.org/W3217003515","https://openalex.org/W4285077564","https://openalex.org/W4296069143","https://openalex.org/W4319862635","https://openalex.org/W4372259817","https://openalex.org/W4372269995","https://openalex.org/W4385822439","https://openalex.org/W4388017359","https://openalex.org/W4402111386","https://openalex.org/W4408355279","https://openalex.org/W6769255071","https://openalex.org/W6778378460","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6861002869"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W4403053866","https://openalex.org/W2142393343","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multilingual":[0],"Automatic":[1,33],"Speech":[2],"Recognition":[3],"(ASR)":[4],"models":[5,38,74,82,97],"are":[6,39,114],"typically":[7],"evaluated":[8],"in":[9],"a":[10,45,58],"setting":[11],"where":[12],"the":[13,17,27,49,93],"ground-truth":[14],"language":[15,81,85,100],"of":[16,104],"speech":[18],"utterance":[19],"is":[20,24,124],"known,":[21],"however,":[22],"this":[23,54],"often":[25],"not":[26,40],"case":[28],"for":[29,70],"most":[30],"practical":[31],"settings.":[32],"Spoken":[34],"Language":[35],"Identification":[36],"(SLID)":[37],"perfect":[41],"and":[42,60,83,95,106,109,116],"misclassifications":[43],"have":[44],"substantial":[46],"impact":[47],"on":[48,90,119],"final":[50],"ASR":[51,68],"accuracy.":[52],"In":[53],"paper,":[55],"we":[56],"present":[57],"simple":[59],"effective":[61],"N-best":[62],"re-ranking":[63],"approach":[64],"to":[65],"improve":[66],"multilingual":[67],"accuracy":[69,102],"several":[71],"prominent":[72],"acoustic":[73],"by":[75],"employing":[76],"external":[77],"features":[78],"such":[79],"as":[80],"text-based":[84],"identification":[86,101],"models.":[87],"Our":[88],"results":[89],"FLEURS":[91],"using":[92],"MMS":[94],"Whisper":[96],"show":[98],"spoken":[99],"improvements":[103],"8.7%":[105],"6.1%,":[107],"respectively":[108],"word":[110],"error":[111],"rates":[112],"which":[113],"3.3%":[115],"2.0%":[117],"lower":[118],"these":[120],"benchmarks.":[121],"The":[122],"code":[123],"available":[125],"at:":[126],"https://github.com/facebookresearch/fairseq/tree/main/examples/mms/lid_rerank.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}