{"id":"https://openalex.org/W3161302809","doi":"https://doi.org/10.1109/icassp39728.2021.9414558","title":"St-Bert: Cross-Modal Language Model Pre-Training for End-to-End Spoken Language Understanding","display_name":"St-Bert: Cross-Modal Language Model Pre-Training for End-to-End Spoken Language Understanding","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161302809","doi":"https://doi.org/10.1109/icassp39728.2021.9414558","mag":"3161302809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100416234","display_name":"Minjeong Kim","orcid":"https://orcid.org/0009-0004-7712-1684"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minjeong Kim","raw_affiliation_strings":["NAVER CLOVA"],"affiliations":[{"raw_affiliation_string":"NAVER CLOVA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028017938","display_name":"Gyuwan Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyuwan Kim","raw_affiliation_strings":["NAVER CLOVA"],"affiliations":[{"raw_affiliation_string":"NAVER CLOVA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436186","display_name":"Sang\u2010Woo Lee","orcid":"https://orcid.org/0000-0002-0642-5064"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Woo Lee","raw_affiliation_strings":["NAVER CLOVA","NAVER AI LAB"],"affiliations":[{"raw_affiliation_string":"NAVER CLOVA","institution_ids":[]},{"raw_affiliation_string":"NAVER AI LAB","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074393185","display_name":"Jung-Woo Ha","orcid":"https://orcid.org/0000-0002-7400-7681"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Woo Ha","raw_affiliation_strings":["NAVER CLOVA","NAVER AI LAB"],"affiliations":[{"raw_affiliation_string":"NAVER CLOVA","institution_ids":[]},{"raw_affiliation_string":"NAVER AI LAB","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100416234"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.786,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92099673,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7478","last_page":"7482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.8559982776641846},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6563072800636292},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6278213262557983},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6086442470550537},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5574213862419128},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5368760824203491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210482478141785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5110458135604858},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5047429800033569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4546026885509491},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4499727487564087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559982776641846},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6563072800636292},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6278213262557983},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6086442470550537},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5574213862419128},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5368760824203491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210482478141785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5110458135604858},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5047429800033569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4546026885509491},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4499727487564087},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1933349210","https://openalex.org/W2296073425","https://openalex.org/W2525778437","https://openalex.org/W2747874407","https://openalex.org/W2803609229","https://openalex.org/W2804648901","https://openalex.org/W2891229414","https://openalex.org/W2895976713","https://openalex.org/W2896457183","https://openalex.org/W2898771141","https://openalex.org/W2914120296","https://openalex.org/W2963115613","https://openalex.org/W2963288440","https://openalex.org/W2963340922","https://openalex.org/W2963341956","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2966715458","https://openalex.org/W2970608575","https://openalex.org/W2971207485","https://openalex.org/W2971863715","https://openalex.org/W2972314145","https://openalex.org/W2972584841","https://openalex.org/W2977838803","https://openalex.org/W2981458636","https://openalex.org/W2998356391","https://openalex.org/W3015267417","https://openalex.org/W3015412890","https://openalex.org/W3015586639","https://openalex.org/W3034238904","https://openalex.org/W3034571331","https://openalex.org/W3096589040","https://openalex.org/W3097414768","https://openalex.org/W3099944122","https://openalex.org/W3176896803","https://openalex.org/W4297683418","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6751425476","https://openalex.org/W6751433836","https://openalex.org/W6754850772","https://openalex.org/W6755207826","https://openalex.org/W6755871579","https://openalex.org/W6759455113","https://openalex.org/W6766904570","https://openalex.org/W6776020682","https://openalex.org/W6776527912"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Language":[0,57,63],"model":[1],"pre-training":[2,53,107],"has":[3],"shown":[4],"promising":[5],"results":[6,67],"in":[7],"various":[8,78],"downstream":[9],"tasks.":[10,33],"In":[11],"this":[12],"context,":[13],"we":[14],"introduce":[15],"a":[16,45,83],"cross-modal":[17,47],"pre-trained":[18],"language":[19,29],"model,":[20],"called":[21],"Speech-Text":[22],"BERT":[23],"(ST-BERT),":[24],"to":[25],"tackle":[26],"end-to-end":[27],"spoken":[28],"understanding":[30],"(E2E":[31],"SLU)":[32],"Taking":[34],"phoneme":[35],"posterior":[36],"and":[37,60,81],"subword-level":[38],"text":[39],"as":[40],"an":[41],"input,":[42],"ST-BERT":[43],"learns":[44],"contextualized":[46],"alignment":[48],"via":[49,105],"our":[50,73,98],"two":[51],"proposed":[52],"tasks:":[54],"Cross-modal":[55,61],"Masked":[56],"Modeling":[58,64],"(CM-MLM)":[59],"Conditioned":[62],"(CM-CLM).":[65],"Experimental":[66],"on":[68],"three":[69],"benchmarks":[70],"present":[71],"that":[72],"approach":[74],"is":[75],"effective":[76],"for":[77],"SLU":[79,102],"datasets":[80],"shows":[82,100],"surprisingly":[84],"marginal":[85],"performance":[86,103],"degradation":[87],"even":[88],"when":[89],"1%":[90],"of":[91],"the":[92],"training":[93],"data":[94],"are":[95],"available.":[96],"Also,":[97],"method":[99],"further":[101],"gain":[104],"domain-adaptive":[106],"with":[108],"domain-specific":[109],"speech-text":[110],"pair":[111],"data.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}