{"id":"https://openalex.org/W7214316575","doi":"https://doi.org/10.21437/interspeech.2026-2966","title":"BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge","display_name":"BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214316575","doi":"https://doi.org/10.21437/interspeech.2026-2966"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2026-2966","doi":"https://doi.org/10.21437/interspeech.2026-2966","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-2966","pdf_url":"https://www.isca-archive.org/interspeech_2026/subedi26_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":null,"license_id":null,"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":"bronze","oa_url":"https://www.isca-archive.org/interspeech_2026/subedi26_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061307722","display_name":"Prakriti Subedi","orcid":"https://orcid.org/0000-0001-7768-4453","observed_orcids":["https://orcid.org/0000-0001-7768-4453"]},"institutions":[{"id":"https://openalex.org/I137853757","display_name":"Howard University","ror":"https://ror.org/05gt1vc06","country_code":"US","type":"education","lineage":["https://openalex.org/I137853757"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prakriti Subedi","raw_affiliation_strings":["Howard University , Washington D .C. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Howard University , Washington D .C. , USA","institution_ids":["https://openalex.org/I137853757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047149523","display_name":"Howard Prioleau","orcid":"https://orcid.org/0000-0002-8078-9704","observed_orcids":["https://orcid.org/0000-0002-8078-9704"]},"institutions":[{"id":"https://openalex.org/I137853757","display_name":"Howard University","ror":"https://ror.org/05gt1vc06","country_code":"US","type":"education","lineage":["https://openalex.org/I137853757"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Prioleau","raw_affiliation_strings":["Howard University , Washington D .C. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Howard University , Washington D .C. , USA","institution_ids":["https://openalex.org/I137853757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055936582","display_name":"Saurav Keshari Aryal","orcid":"https://orcid.org/0000-0001-9815-9295","observed_orcids":["https://orcid.org/0000-0001-9815-9295"]},"institutions":[{"id":"https://openalex.org/I137853757","display_name":"Howard University","ror":"https://ror.org/05gt1vc06","country_code":"US","type":"education","lineage":["https://openalex.org/I137853757"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurav Aryal","raw_affiliation_strings":["Howard University , Washington D .C. , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Howard University , Washington D .C. , USA","institution_ids":["https://openalex.org/I137853757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137853757"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64067337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"986","last_page":"990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.9932000041007996,"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":0.003700000001117587,"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/T11309","display_name":"Music and Audio Processing","score":0.0010999999940395355,"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/multilingual-speech","display_name":"multilingual speech","score":0.7419999837875366},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.7860000133514404},{"id":"https://openalex.org/keywords/speaker-clustering","display_name":"speaker clustering","score":0.9440000057220459},{"id":"https://openalex.org/keywords/hubert","display_name":"HuBERT","score":0.4440000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170999884605408},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5777000188827515},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47519999742507935},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46369999647140503},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2026-2966","doi":"https://doi.org/10.21437/interspeech.2026-2966","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-2966","pdf_url":"https://www.isca-archive.org/interspeech_2026/subedi26_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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.28758","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.28758","pdf_url":"https://arxiv.org/pdf/2609.28758","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.28758","doi":"https://doi.org/10.48550/arxiv.2609.28758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.28758","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2026-2966","doi":"https://doi.org/10.21437/interspeech.2026-2966","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-2966","pdf_url":"https://www.isca-archive.org/interspeech_2026/subedi26_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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1729356799","display_name":null,"funder_award_id":"N00014-22-1-2714","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320332923","display_name":"U.S. Navy","ror":"https://ror.org/03ar0mv07"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338403","display_name":"Common Fund","ror":"https://ror.org/001d55x84"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214316575.pdf","grobid_xml":"https://content.openalex.org/works/W7214316575.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2908510526","https://openalex.org/W2970903692","https://openalex.org/W3134652006","https://openalex.org/W3184414142","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4286695273","https://openalex.org/W4311000453","https://openalex.org/W4312048190","https://openalex.org/W4319862635","https://openalex.org/W4389326242","https://openalex.org/W4391013663","https://openalex.org/W4399317989"],"related_works":["https://openalex.org/W2402913640","https://openalex.org/W4287591426","https://openalex.org/W3196514189","https://openalex.org/W3170928308","https://openalex.org/W3015547233","https://openalex.org/W3165666670","https://openalex.org/W2590856265","https://openalex.org/W4285192675","https://openalex.org/W113268911","https://openalex.org/W2395670750"],"abstract_inverted_index":{"We":[0],"describe":[1],"our":[2],"submission":[3],"to":[4],"the":[5,9,27,43,68],"Unsupervised":[6,45],"Speech":[7,47],"in":[8,99],"Wild":[10],"(UPS)":[11],"Challenge":[12],"at":[13],"Interspeech":[14],"2026,":[15],"a":[16,96],"bidirectional":[17],"Mamba-2":[18],"(BiMamba2)":[19],"encoder":[20],"trained":[21,33],"with":[22,49,59],"masked":[23,55],"discreteunit":[24],"prediction":[25,58],"following":[26],"HuBERT-style":[28],"paradigm.The":[29],"47.88M-parameter":[30],"model":[31],"is":[32],"on":[34,80],"250":[35],"hours":[36],"of":[37,75,107],"speech":[38],"across":[39],"67":[40],"languages":[41],"from":[42],"MLCommons":[44],"People's":[46],"dataset,":[48],"no":[50],"labeled":[51],"data.The":[52],"objective":[53],"combines":[54],"k-means":[56],"pseudo-label":[57],"language":[60],"identification":[61,83],"supervision":[62],"and":[63,86,102],"VICReg":[64],"regularization.On":[65],"official":[66],"evaluation,":[67],"system":[69],"achieves":[70],"an":[71],"Adjusted":[72],"Rand":[73],"Index":[74],"0.735,":[76],"exceeding":[77],"four":[78],"baselines":[79],"speaker":[81],"clustering.Language":[82],"macro-F1":[84],"(0.073)":[85],"character":[87],"error":[88],"rate":[89],"(0.870)":[90],"remain":[91],"below":[92],"supervised":[93],"baselines.We":[94],"analyze":[95],"local-official":[97],"discrepancy":[98],"metric":[100],"scale":[101],"checkpoint":[103],"ranking,":[104],"highlighting":[105],"limitations":[106],"in-distribution":[108],"diagnostics":[109],"for":[110],"predicting":[111],"Dynabench":[112],"probe":[113],"outcomes.":[114]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-26T00:00:00"}