{"id":"https://openalex.org/W4392909315","doi":"https://doi.org/10.1109/icassp48485.2024.10448215","title":"Multimodal Modeling for Spoken Language Identification","display_name":"Multimodal Modeling for Spoken Language Identification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909315","doi":"https://doi.org/10.1109/icassp48485.2024.10448215"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448215","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5067162151","display_name":"Shikhar Bharadwaj","orcid":"https://orcid.org/0009-0003-7202-0502"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shikhar Bharadwaj","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706633","display_name":"Min Ma","orcid":"https://orcid.org/0000-0002-3132-4898"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Ma","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001421193","display_name":"Shikhar Vashishth","orcid":"https://orcid.org/0000-0002-6258-2494"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shikhar Vashishth","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Bapna","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090245882","display_name":"Vera Axelrod","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vera Axelrod","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Dalmia","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750907","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-4201-9645"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013810382","display_name":"Daan Van Esch","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daan Van Esch","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022400856","display_name":"Sandy Ritchie","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandy Ritchie","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033696194","display_name":"Partha Talukdar","orcid":"https://orcid.org/0000-0001-8825-589X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Partha Talukdar","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015547427","display_name":"Jason Riesa","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Riesa","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5067162151"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61744045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"11526","last_page":"11530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9623000025749207,"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":0.9623000025749207,"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":0.7829486131668091},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5788871645927429},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5690345168113708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46923404932022095},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.45529770851135254},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4441677927970886},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.413105309009552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38107943534851074},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2898816764354706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829486131668091},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5788871645927429},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5690345168113708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46923404932022095},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.45529770851135254},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4441677927970886},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.413105309009552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38107943534851074},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2898816764354706},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448215","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W151003953","https://openalex.org/W2104457544","https://openalex.org/W2127141656","https://openalex.org/W2807627734","https://openalex.org/W2888924726","https://openalex.org/W2948902769","https://openalex.org/W3096215352","https://openalex.org/W3097777922","https://openalex.org/W3115778530","https://openalex.org/W3136330474","https://openalex.org/W3139878283","https://openalex.org/W3167533889","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W3213618310","https://openalex.org/W4221141648","https://openalex.org/W4221155340","https://openalex.org/W4226120743","https://openalex.org/W4296070359","https://openalex.org/W4319862218","https://openalex.org/W4319862635","https://openalex.org/W4323066695","https://openalex.org/W4361745846","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385822567","https://openalex.org/W4385823052","https://openalex.org/W4391021510","https://openalex.org/W4394647634","https://openalex.org/W6691371945","https://openalex.org/W6752435643","https://openalex.org/W6755207826","https://openalex.org/W6791192960","https://openalex.org/W6810259195","https://openalex.org/W6850218400"],"related_works":["https://openalex.org/W2924380321","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W178568469","https://openalex.org/W1985349217","https://openalex.org/W4386302218","https://openalex.org/W2098508228","https://openalex.org/W2532974797","https://openalex.org/W4205371571"],"abstract_inverted_index":{"Spoken":[0,65],"language":[1,12,24,80,102,124,142],"identification":[2,25,125],"refers":[3],"to":[4,32,78,98],"the":[5,10,38,72,100,104,123,135],"task":[6],"of":[7,40,47,74,103,115,138],"automatically":[8],"predicting":[9],"spoken":[11,101],"in":[13,37],"a":[14,22,33,45,63],"given":[15],"utterance.":[16],"Conventionally,":[17],"it":[18],"is":[19,44],"modeled":[20],"as":[21,88],"speech-based":[23],"task.":[26,56,126],"Prior":[27],"techniques":[28],"have":[29],"been":[30],"constrained":[31],"single":[34],"modality;":[35],"however":[36],"case":[39],"video":[41,89],"data":[42],"there":[43],"wealth":[46],"other":[48],"metadata":[49,76,86],"that":[50,85,133],"may":[51],"be":[52],"beneficial":[53],"for":[54,141],"this":[55,58],"In":[57],"work,":[59],"we":[60],"propose":[61],"MuSeLI,":[62],"Multimodal":[64],"Language":[66],"Identification":[67],"method,":[68],"which":[69],"delves":[70],"into":[71],"use":[73],"various":[75],"sources":[77],"enhance":[79],"identification.":[81],"Our":[82],"study":[83,132],"reveals":[84],"such":[87],"title,":[90],"description":[91],"and":[92,118],"geographic":[93],"location":[94],"provide":[95],"substantial":[96],"information":[97],"identify":[99],"multimedia":[105],"recording.":[106],"We":[107,127],"conduct":[108,129],"experiments":[109],"using":[110],"two":[111],"diverse":[112],"public":[113],"datasets":[114],"YouTube":[116],"videos,":[117],"obtain":[119],"state-of-the-art":[120],"results":[121],"on":[122],"additionally":[128],"an":[130],"ablation":[131],"describes":[134],"distinct":[136],"contribution":[137],"each":[139],"modality":[140],"recognition.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
