{"id":"https://openalex.org/W4415097571","doi":"https://doi.org/10.21437/interspeech.2026-1902","title":"Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation","display_name":"Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W4415097571","doi":"https://doi.org/10.21437/interspeech.2026-1902"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2026-1902","doi":"https://doi.org/10.21437/interspeech.2026-1902","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-1902","pdf_url":"https://www.isca-archive.org/interspeech_2026/srivastav26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.isca-archive.org/interspeech_2026/srivastav26_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020996120","display_name":"Vaibhav Srivastav","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]},{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Srivastav","raw_affiliation_strings":["Hugging Face, Inc. , France","OpenAI , United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face, Inc. , France","institution_ids":["https://openalex.org/I4387154989"]},{"raw_affiliation_string":"OpenAI , United States of America","institution_ids":["https://openalex.org/I4210161460"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Steven Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Zheng","raw_affiliation_strings":["Hugging Face, Inc. , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face, Inc. , France","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019234378","display_name":"Eric Bezzam","orcid":"https://orcid.org/0000-0003-4837-5031","observed_orcids":["https://orcid.org/0000-0003-4837-5031"]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Bezzam","raw_affiliation_strings":["Hugging Face, Inc. , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face, Inc. , France","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093356390","display_name":"Eustache Le Bihan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":"US","type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eustache Le Bihan","raw_affiliation_strings":["Hugging Face, Inc. , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hugging Face, Inc. , France","institution_ids":["https://openalex.org/I4387154989"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nithin Rao Koluguri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":["NVIDIA , United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Piotr \u017belasko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["NVIDIA , United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027823948","display_name":"Somshubra Majumdar","orcid":"https://orcid.org/0000-0001-5635-4893","observed_orcids":["https://orcid.org/0000-0001-5635-4893"]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somshubra Majumdar","raw_affiliation_strings":["NVIDIA , United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066586567","display_name":"Adel Moumen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adel Moumen","raw_affiliation_strings":["University of Cambridge , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge , United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045815686","display_name":"Sanchit Gandhi","orcid":"https://orcid.org/0000-0001-6552-6976","observed_orcids":["https://orcid.org/0000-0001-6552-6976"]},"institutions":[{"id":"https://openalex.org/I4390039361","display_name":"Mistral AI (France)","ror":"https://ror.org/05w9p7918","country_code":"FR","type":"company","lineage":["https://openalex.org/I4390039361"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sanchit Gandhi","raw_affiliation_strings":["Mistral AI , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mistral AI , France","institution_ids":["https://openalex.org/I4390039361"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":67.4289,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.99897034,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6692","last_page":"6697"},"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/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.9959999918937683},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.8560000061988831},{"id":"https://openalex.org/keywords/real-time-factor","display_name":"real-time factor","score":0.8820000290870667},{"id":"https://openalex.org/keywords/conformer-encoder","display_name":"Conformer encoder","score":0.6240000128746033},{"id":"https://openalex.org/keywords/connectionist-temporal-classification","display_name":"connectionist temporal classification","score":0.8999999761581421},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226000070571899},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.612500011920929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.521399974822998},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4404999911785126},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.27390000224113464}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2026-1902","doi":"https://doi.org/10.21437/interspeech.2026-1902","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-1902","pdf_url":"https://www.isca-archive.org/interspeech_2026/srivastav26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.06961","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06961","pdf_url":"https://arxiv.org/pdf/2510.06961","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.06961","doi":"https://doi.org/10.48550/arxiv.2510.06961","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06961","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2026-1902","doi":"https://doi.org/10.21437/interspeech.2026-1902","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-1902","pdf_url":"https://www.isca-archive.org/interspeech_2026/srivastav26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415097571.pdf","grobid_xml":"https://content.openalex.org/works/W4415097571.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2962780374","https://openalex.org/W2974231335","https://openalex.org/W2980282514","https://openalex.org/W3054645415","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3158977306","https://openalex.org/W3198587774","https://openalex.org/W4221146809","https://openalex.org/W4388275972","https://openalex.org/W4402712116","https://openalex.org/W4404260607","https://openalex.org/W4415310554","https://openalex.org/W4415337281","https://openalex.org/W4416240515","https://openalex.org/W6966821115","https://openalex.org/W7125811016","https://openalex.org/W7126278909","https://openalex.org/W7128773640","https://openalex.org/W7148522013"],"related_works":["https://openalex.org/W4409800820","https://openalex.org/W7165650565","https://openalex.org/W7204436142","https://openalex.org/W3150390140","https://openalex.org/W7154480097","https://openalex.org/W4415433636","https://openalex.org/W7154280776","https://openalex.org/W6885130910","https://openalex.org/W7213918543","https://openalex.org/W4417299656"],"abstract_inverted_index":{"We":[0],"present":[1,108],"the":[2,71],"Open":[3],"ASR":[4,117],"Leaderboard,":[5],"a":[6],"reproducible":[7],"benchmarking":[8,115],"platform":[9],"with":[10,26,64],"community":[11],"contributions":[12],"from":[13],"academia":[14],"and":[15,20,30,39,52,80,94,98,118],"industry.It":[16],"compares":[17],"85+":[18],"open-source":[19],"proprietary":[21],"systems":[22],"across":[23,49],"11":[24],"datasets,":[25],"English":[27],"short-and":[28],"long-form":[29,93],"multilingual":[31],"short-form":[32],"tracks.We":[33],"standardize":[34],"word":[35],"error":[36],"rate":[37],"(WER)":[38],"inverse":[40],"real-time":[41],"factor":[42],"(RTFx)":[43],"evaluation":[44,110],"for":[45,92],"consistent":[46],"accuracy-efficiency":[47],"comparisons":[48],"model":[50,67],"architectures":[51],"toolkits":[53],"(e.g.,":[54],"ESPNet,":[55],"NeMo,":[56],"SpeechBrain,":[57],"Transformers).We":[58],"observe":[59],"that":[60],"Conformer-based":[61],"encoders":[62],"paired":[63],"large":[65],"language":[66],"(LLM)-based":[68],"decoders":[69,84],"achieve":[70],"best":[72],"average":[73],"WER,":[74],"while":[75],"connectionist":[76],"temporal":[77],"classification":[78],"(CTC)":[79],"token-and-duration":[81],"transducer":[82],"(TDT)":[83],"offer":[85],"superior":[86],"RTFx,":[87],"making":[88],"them":[89],"better":[90],"suited":[91],"batched":[95],"processing.All":[96],"code":[97],"dataset":[99],"loaders":[100],"are":[101],"open-sourced":[102],"to":[103,112],"support":[104],"transparent,":[105],"extensible":[106],"evaluation.We":[107],"our":[109],"methodology":[111],"facilitate":[113],"communitydriven":[114],"in":[116],"other":[119],"tasks.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":51},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2025-10-13T00:00:00"}
