{"id":"https://openalex.org/W4372266917","doi":"https://doi.org/10.1109/icassp49357.2023.10095091","title":"Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples","display_name":"Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266917","doi":"https://doi.org/10.1109/icassp49357.2023.10095091"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095091","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":"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/A5014059162","display_name":"Hyeonggon Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyeonggon Ryu","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070707693","display_name":"Arda Senocak","orcid":"https://orcid.org/0000-0001-9141-3270"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012455275","display_name":"In So Kweon","orcid":"https://orcid.org/0000-0001-9626-5983"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In So Kweon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014059162"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.9825,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77150848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8251585364341736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6233435273170471},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.6191816329956055},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5930588245391846},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5358724594116211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258486866950989},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43910717964172363},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.43446481227874756},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.4260587692260742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251585364341736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6233435273170471},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6191816329956055},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5930588245391846},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5358724594116211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258486866950989},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43910717964172363},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.43446481227874756},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.4260587692260742},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095091","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2586850765","https://openalex.org/W2842511635","https://openalex.org/W2938991416","https://openalex.org/W2962753610","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963525826","https://openalex.org/W2963902314","https://openalex.org/W2964001192","https://openalex.org/W2964099072","https://openalex.org/W2995680346","https://openalex.org/W3015300171","https://openalex.org/W3094454579","https://openalex.org/W3095881291","https://openalex.org/W3100813302","https://openalex.org/W3158714121","https://openalex.org/W3168851777","https://openalex.org/W3196694757","https://openalex.org/W3197828817","https://openalex.org/W3198411039","https://openalex.org/W3207750165","https://openalex.org/W4224875474","https://openalex.org/W4224925617","https://openalex.org/W4287812705","https://openalex.org/W4297808394","https://openalex.org/W4312528757","https://openalex.org/W6729977899","https://openalex.org/W6770596778","https://openalex.org/W6776700526","https://openalex.org/W6779340355","https://openalex.org/W6784660784","https://openalex.org/W6803728867"],"related_works":["https://openalex.org/W2384553807","https://openalex.org/W1557888283","https://openalex.org/W3089999372","https://openalex.org/W2738278463","https://openalex.org/W2265245145","https://openalex.org/W4308939443","https://openalex.org/W4298033291","https://openalex.org/W4299528489","https://openalex.org/W2497085487","https://openalex.org/W2248218532"],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,10,29,62,77,89,127],"this":[3,55],"work":[4,56],"is":[5,57],"to":[6,58,73,85,123],"explore":[7],"the":[8,44,47,60,75,87,120,125],"learning":[9],"visually":[11,69],"grounded":[12,70],"speech":[13,71],"models":[14,21],"(VGS)":[15],"from":[16,32],"multilingual":[17],"perspective.":[18],"Bilingual":[19],"VGS":[20],"are":[22],"generally":[23],"trained":[24],"with":[25],"an":[26,41],"equal":[27],"number":[28],"spoken":[30,49,108],"captions":[31],"both":[33],"languages.":[34],"However,":[35],"in":[36,54,66],"reality,":[37],"there":[38],"can":[39],"be":[40],"imbalance":[42],"among":[43],"languages":[45],"for":[46,132],"available":[48],"captions.":[50,109],"Our":[51,110],"key":[52],"contribution":[53],"leverage":[59],"power":[61],"a":[63,67,78,97],"high-resource":[64,90,100],"language":[65,91,101,122],"bilingual":[68,130],"model":[72],"improve":[74],"performance":[76],"low-resource":[79,93,121],"language.":[80],"We":[81],"introduce":[82],"two":[83,116],"methods":[84],"distill":[86],"knowledge":[88],"into":[92],"languages:":[94],"(1)":[95],"incorporating":[96],"strong":[98],"pre-trained":[99],"encoder":[102],"and":[103,129],"(2)":[104],"using":[105],"semantically":[106],"similar":[107],"experiments":[111],"show":[112],"that":[113],"combining":[114],"these":[115],"approaches":[117],"effectively":[118],"enables":[119],"surpass":[124],"performances":[126],"monolingual":[128],"counterparts":[131],"cross-modal":[133],"retrieval":[134],"tasks.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}