{"id":"https://openalex.org/W4372266670","doi":"https://doi.org/10.1109/icassp49357.2023.10096407","title":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","display_name":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266670","doi":"https://doi.org/10.1109/icassp49357.2023.10096407"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104107801","display_name":"Travis Bartley","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Travis M. Bartley","raw_affiliation_strings":["City University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039855217","display_name":"Fei Jia","orcid":"https://orcid.org/0000-0002-4444-1786"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Jia","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069691915","display_name":"Krishna C. Puvvada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna C. Puvvada","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039963047","display_name":"Samuel Kriman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Kriman","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8499038219451904},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7242267727851868},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6280492544174194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5794108510017395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5590784549713135},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5367224812507629},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4637840986251831},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4458249807357788},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.43023407459259033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4072268009185791},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2471274733543396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8499038219451904},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7242267727851868},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6280492544174194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5794108510017395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5590784549713135},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5367224812507629},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4637840986251831},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4458249807357788},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.43023407459259033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4072268009185791},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2471274733543396},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1533946607","https://openalex.org/W2115843962","https://openalex.org/W2696967604","https://openalex.org/W2890964092","https://openalex.org/W2974231335","https://openalex.org/W2995181338","https://openalex.org/W3024182269","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3139878283","https://openalex.org/W3180180466","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3213029956","https://openalex.org/W3213618310","https://openalex.org/W4226380987","https://openalex.org/W4296069321","https://openalex.org/W6632118081","https://openalex.org/W6780218876","https://openalex.org/W6788158735"],"related_works":["https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W2098508228","https://openalex.org/W2624072012","https://openalex.org/W1508853749","https://openalex.org/W4387929264","https://openalex.org/W3105220303","https://openalex.org/W4287903637","https://openalex.org/W2954811041"],"abstract_inverted_index":{"In":[0],"this":[1,85],"paper,":[2],"we":[3,37,70],"extend":[4],"previous":[5],"self-supervised":[6],"approaches":[7],"for":[8,78],"language":[9,30,79],"identification":[10],"by":[11],"experimenting":[12],"with":[13,86],"Conformer":[14,64],"based":[15],"architecture":[16],"in":[17,33],"a":[18,62],"multilingual":[19],"pre-training":[20],"paradigm.":[21],"We":[22,90],"find":[23],"that":[24,39],"pre-trained":[25,63],"speech":[26],"models":[27],"optimally":[28],"encode":[29],"discriminatory":[31],"information":[32],"lower":[34],"layers.":[35],"Further,":[36],"demonstrate":[38],"the":[40,67,92,95],"embeddings":[41],"obtained":[42],"from":[43],"these":[44],"layers":[45],"are":[46],"significantly":[47],"robust":[48],"to":[49,74],"classify":[50],"unseen":[51],"languages":[52],"and":[53],"different":[54],"acoustic":[55],"environments":[56],"without":[57],"additional":[58],"training.":[59],"After":[60],"fine-tuning":[61],"model":[65,83,93],"on":[66],"VoxLin-gua107":[68],"dataset,":[69],"achieve":[71],"results":[72],"similar":[73],"current":[75],"state-of-the-art":[76],"systems":[77],"identification.":[80],"More,":[81],"our":[82],"accomplishes":[84],"5x":[87],"less":[88],"parameters.":[89],"open-source":[91],"through":[94],"NVIDIA":[96],"NeMo":[97],"toolkit.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}