{"id":"https://openalex.org/W4408352524","doi":"https://doi.org/10.1109/icassp49660.2025.10887729","title":"Knowledge Distillation From Ensemble for Spoken Language Identification","display_name":"Knowledge Distillation From Ensemble for Spoken Language Identification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352524","doi":"https://doi.org/10.1109/icassp49660.2025.10887729"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887729","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/A5086205666","display_name":"Raghuveer Peri","orcid":"https://orcid.org/0000-0002-1010-065X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Raghuveer Peri","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051167459","display_name":"Seyed Omid Sadjadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seyed Omid Sadjadi","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080301608","display_name":"Srikanth Vishnubhotla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srikanth Vishnubhotla","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyu J. Han","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086205666"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02009808,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.875,"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":0.875,"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":0.7837398052215576},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5973195433616638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5950936675071716},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5474869608879089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5186569094657898},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5071964263916016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3879459500312805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837398052215576},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5973195433616638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5950936675071716},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5474869608879089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5186569094657898},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5071964263916016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3879459500312805},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887729","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2508418541","https://openalex.org/W2633884958","https://openalex.org/W2747909401","https://openalex.org/W2916297645","https://openalex.org/W3008434450","https://openalex.org/W3024869864","https://openalex.org/W3084783920","https://openalex.org/W3095410713","https://openalex.org/W3119308075","https://openalex.org/W3139878283","https://openalex.org/W4226426325","https://openalex.org/W4292968575","https://openalex.org/W4319862635","https://openalex.org/W4372266670","https://openalex.org/W4385822282","https://openalex.org/W4385822693","https://openalex.org/W4385823376","https://openalex.org/W4392903886","https://openalex.org/W4402111246","https://openalex.org/W6638523607","https://openalex.org/W6771467084","https://openalex.org/W6787473312","https://openalex.org/W6810673746"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2898732673","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2410053581","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2383658677","https://openalex.org/W3123203398","https://openalex.org/W2953684491"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"identification":[2],"(LID)":[3],"has":[4],"seen":[5],"substantial":[6,109],"performance":[7,64],"gains":[8,110],"with":[9,77,103],"the":[10,81,120],"rise":[11],"of":[12,48,83],"large-scale":[13],"models.":[14],"However,":[15],"these":[16],"models":[17,51],"are":[18],"often":[19],"computationally":[20],"expensive":[21],"and":[22,116],"impractical":[23],"for":[24,114],"many":[25],"real-world":[26],"applications.":[27],"In":[28],"this":[29,42],"work,":[30],"we":[31,58],"propose":[32],"a":[33,53,74,84,91],"novel":[34],"knowledge":[35,105],"distillation":[36,101,106],"from":[37],"ensemble":[38,47],"framework":[39],"to":[40,108],"address":[41],"challenge.":[43],"By":[44],"distilling":[45],"an":[46],"large":[49],"LID":[50],"into":[52],"single,":[54],"more":[55],"efficient":[56],"student,":[57],"achieve":[59],"comparable":[60],"or":[61],"even":[62],"superior":[63],"while":[65],"reducing":[66],"computational":[67],"cost":[68],"by":[69,95],"67%.":[70],"Our":[71],"approach":[72],"yields":[73],"student":[75],"model":[76],"less":[78],"than":[79],"10%":[80],"size":[82],"200M+":[85],"parameter":[86,93],"teacher":[87,94],"ensemble,":[88],"yet":[89],"outperforming":[90],"140M":[92],"13%":[96],"relative.":[97],"Additionally,":[98],"combining":[99],"our":[100],"technique":[102],"decoupled":[104],"leads":[107],"(50%":[111],"relative),":[112],"especially":[113],"confusable":[115],"low-resource":[117],"languages":[118],"in":[119],"FLEURS":[121],"dataset.":[122]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}