{"id":"https://openalex.org/W4214813806","doi":"https://doi.org/10.1109/ieeeconf53345.2021.9723367","title":"A Translation Framework for Visually Grounded Spoken Unit Discovery","display_name":"A Translation Framework for Visually Grounded Spoken Unit Discovery","publication_year":2021,"publication_date":"2021-10-31","ids":{"openalex":"https://openalex.org/W4214813806","doi":"https://doi.org/10.1109/ieeeconf53345.2021.9723367"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf53345.2021.9723367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf53345.2021.9723367","pdf_url":null,"source":{"id":"https://openalex.org/S4363607877","display_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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/A5058722770","display_name":"Liming Wang","orcid":"https://orcid.org/0000-0002-5562-8386"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liming Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1313,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53194842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"19","issue":null,"first_page":"1419","last_page":"1425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.8331515789031982},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8060829639434814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6352803111076355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5710058808326721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5655128955841064},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5463978052139282},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5354383587837219},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5352030396461487},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5139071941375732},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44041427969932556},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3685912489891052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331515789031982},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8060829639434814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352803111076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5710058808326721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5655128955841064},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5463978052139282},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5354383587837219},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5352030396461487},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5139071941375732},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44041427969932556},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3685912489891052},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf53345.2021.9723367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf53345.2021.9723367","pdf_url":null,"source":{"id":"https://openalex.org/S4363607877","display_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W2006969979","https://openalex.org/W2064675550","https://openalex.org/W2148876114","https://openalex.org/W2556930864","https://openalex.org/W2568262903","https://openalex.org/W2736876693","https://openalex.org/W2962753610","https://openalex.org/W2962832640","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963620343","https://openalex.org/W2963902314","https://openalex.org/W2963966654","https://openalex.org/W2988907666","https://openalex.org/W2995680346","https://openalex.org/W3095293218","https://openalex.org/W3096656254","https://openalex.org/W3161204797","https://openalex.org/W3161215977","https://openalex.org/W3196459653","https://openalex.org/W4287591426","https://openalex.org/W4385245566","https://openalex.org/W6602812831","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6652311901","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6750194919","https://openalex.org/W6770596778","https://openalex.org/W6785385881","https://openalex.org/W6786696081","https://openalex.org/W6917638038","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Multimodal":[0],"acoustic":[1],"unit":[2],"discovery":[3,45,61],"(MAUD)":[4],"is":[5],"a":[6],"key":[7],"task":[8],"in":[9],"self-supervised":[10],"spoken":[11],"language":[12],"learning":[13],"and":[14,36,40,58],"low-resource":[15],"speech":[16,35],"recognition.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,33],"proposed":[22],"two":[23],"models":[24,31],"for":[25],"MAUD":[26],"inspired":[27],"by":[28,51,67],"machine":[29],"translation":[30],"where":[32],"treat":[34],"image":[37],"as":[38],"source":[39],"target":[41],"languages.":[42],"Our":[43],"word":[44],"model":[46,62],"outperforms":[47,63],"previous":[48,64],"state-of-the-art":[49,65],"approach":[50,66],"5.3%":[52],"alignment":[53],"F1":[54],"on":[55,72],"SpeechCOCO":[56],"dataset":[57],"our":[59],"phoneme":[60],"7%":[68],"normalized":[69],"mutual":[70],"information":[71],"TIMIT":[73],"dataset.":[74]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}