{"id":"https://openalex.org/W3196694757","doi":"https://doi.org/10.21437/interspeech.2021-1352","title":"Cascaded Multilingual Audio-Visual Learning from Videos","display_name":"Cascaded Multilingual Audio-Visual Learning from Videos","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196694757","doi":"https://doi.org/10.21437/interspeech.2021-1352","mag":"3196694757"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1352","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5010091252","display_name":"Andrew Rouditchenko","orcid":"https://orcid.org/0000-0002-0063-3612"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rouditchenko","raw_affiliation_strings":["MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086597264","display_name":"Angie Boggust","orcid":"https://orcid.org/0000-0002-9671-5574"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angie Boggust","raw_affiliation_strings":["MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["UT Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011795407","display_name":"Hilde Kuehne","orcid":"https://orcid.org/0000-0003-1079-4441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hilde Kuehne","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060883710","display_name":"Brian Chen","orcid":"https://orcid.org/0000-0001-6384-1673"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Chen","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049734237","display_name":"Rameswar Panda","orcid":"https://orcid.org/0000-0003-4359-2475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rameswar Panda","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052325109","display_name":"Rog\u00e9rio Feris","orcid":"https://orcid.org/0000-0001-6399-0679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rogerio Feris","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["NYU, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3006","last_page":"3010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/T10860","display_name":"Speech and Audio Processing","score":0.9922000169754028,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8337053060531616},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.668697714805603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5357768535614014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4665389358997345},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.41004347801208496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337053060531616},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.668697714805603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5357768535614014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4665389358997345},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.41004347801208496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1352","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2127982613","https://openalex.org/W2134670479","https://openalex.org/W2194775991","https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2796315435","https://openalex.org/W2799316004","https://openalex.org/W2800448574","https://openalex.org/W2899274165","https://openalex.org/W2952132648","https://openalex.org/W2953114965","https://openalex.org/W2962753610","https://openalex.org/W2962862718","https://openalex.org/W2962934715","https://openalex.org/W2962978519","https://openalex.org/W2963330681","https://openalex.org/W2964099072","https://openalex.org/W2965147078","https://openalex.org/W2971709506","https://openalex.org/W2972073579","https://openalex.org/W2972345028","https://openalex.org/W2973132572","https://openalex.org/W2984008963","https://openalex.org/W2988907666","https://openalex.org/W2989322838","https://openalex.org/W2995680346","https://openalex.org/W3015300171","https://openalex.org/W3035276082","https://openalex.org/W3037309139","https://openalex.org/W3095881291","https://openalex.org/W3096372900","https://openalex.org/W3157861865","https://openalex.org/W3161204797","https://openalex.org/W3170972077","https://openalex.org/W3197828817","https://openalex.org/W3198429080","https://openalex.org/W4287199820","https://openalex.org/W4287240590","https://openalex.org/W4287591698","https://openalex.org/W4288595436","https://openalex.org/W4394453761"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2074916782","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,51,80],"explore":[4],"self-supervised":[5],"audio-visual":[6,49,68],"models":[7,18],"that":[8,16,56],"learn":[9,47],"from":[10],"instructional":[11],"videos.Prior":[12],"work":[13],"has":[14],"shown":[15],"these":[17],"can":[19],"relate":[20],"spoken":[21,110],"words":[22],"and":[23,41,64,108],"sounds":[24],"to":[25,67,91,106],"visual":[26],"content":[27],"after":[28],"training":[29,92],"on":[30,43,61,93,103],"a":[31,53,58],"large-scale":[32],"dataset":[33],"of":[34,87,112],"videos,":[35],"but":[36],"they":[37],"were":[38],"only":[39],"trained":[40,60,102],"evaluated":[42],"videos":[44,63,96,105],"in":[45,70,84],"English.To":[46],"multilingual":[48],"representations,":[50],"propose":[52],"cascaded":[54,78],"approach":[55],"leverages":[57],"model":[59,101],"English":[62,104],"applies":[65],"it":[66],"data":[69],"other":[71],"languages,":[72],"such":[73],"as":[74],"Japanese":[75,95,107],"videos.With":[76],"our":[77],"approach,":[79],"show":[81],"an":[82],"improvement":[83],"retrieval":[85],"performance":[86],"nearly":[88],"10x":[89],"compared":[90],"the":[94,100],"solely.We":[97],"also":[98],"apply":[99],"Hindi":[109],"captions":[111],"images,":[113],"achieving":[114],"state-of-the-art":[115],"performance.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}