{"id":"https://openalex.org/W4287890956","doi":"https://doi.org/10.18653/v1/2022.naacl-main.376","title":"Cross-modal Contrastive Learning for Speech Translation","display_name":"Cross-modal Contrastive Learning for Speech Translation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4287890956","doi":"https://doi.org/10.18653/v1/2022.naacl-main.376"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.naacl-main.376","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.naacl-main.376","pdf_url":"https://aclanthology.org/2022.naacl-main.376.pdf","source":{"id":"https://openalex.org/S4363608774","display_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.naacl-main.376.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100624645","display_name":"Rong Ye","orcid":"https://orcid.org/0000-0002-4171-5964"},"institutions":[{"id":"https://openalex.org/I4210126929","display_name":"CE Technologies (United Kingdom)","ror":"https://ror.org/02pw67e25","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210126929"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Rong Ye","raw_affiliation_strings":["ByteDance AI Lab,"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,","institution_ids":["https://openalex.org/I4210126929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693712","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0000-9738-4263"},"institutions":[{"id":"https://openalex.org/I4210126929","display_name":"CE Technologies (United Kingdom)","ror":"https://ror.org/02pw67e25","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210126929"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":["ByteDance AI Lab,"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,","institution_ids":["https://openalex.org/I4210126929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["University of California, Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100624645"],"corresponding_institution_ids":["https://openalex.org/I4210126929"],"apc_list":null,"apc_paid":null,"fwci":6.9598,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.97726783,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5099","last_page":"5113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.8139696717262268},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7414714694023132},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6405456066131592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6182178258895874},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5888159275054932},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5883628129959106},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5635257363319397},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.557819664478302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5096302032470703},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4539766311645508},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44869473576545715},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4485887885093689},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4319906234741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139696717262268},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7414714694023132},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6405456066131592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182178258895874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5888159275054932},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5883628129959106},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5635257363319397},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.557819664478302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5096302032470703},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4539766311645508},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44869473576545715},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4485887885093689},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4319906234741211},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.naacl-main.376","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.naacl-main.376","pdf_url":"https://aclanthology.org/2022.naacl-main.376.pdf","source":{"id":"https://openalex.org/S4363608774","display_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.naacl-main.376","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.naacl-main.376","pdf_url":"https://aclanthology.org/2022.naacl-main.376.pdf","source":{"id":"https://openalex.org/S4363608774","display_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4287890956.pdf","grobid_xml":"https://content.openalex.org/works/W4287890956.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1494198834","https://openalex.org/W1689711448","https://openalex.org/W2118020555","https://openalex.org/W2152790380","https://openalex.org/W2157364932","https://openalex.org/W2187089797","https://openalex.org/W2419539795","https://openalex.org/W2512924740","https://openalex.org/W2555897561","https://openalex.org/W2758950307","https://openalex.org/W2892009249","https://openalex.org/W2914120296","https://openalex.org/W2933138175","https://openalex.org/W2939710050","https://openalex.org/W2945260553","https://openalex.org/W2949328740","https://openalex.org/W2963250244","https://openalex.org/W2963259843","https://openalex.org/W2963532001","https://openalex.org/W2964172053","https://openalex.org/W2964187781","https://openalex.org/W2966715458","https://openalex.org/W2972894903","https://openalex.org/W2973049979","https://openalex.org/W2982157312","https://openalex.org/W2986963494","https://openalex.org/W2997591391","https://openalex.org/W3005680577","https://openalex.org/W3015325583","https://openalex.org/W3017454464","https://openalex.org/W3034571331","https://openalex.org/W3035060554","https://openalex.org/W3035252911","https://openalex.org/W3036601975","https://openalex.org/W3037217258","https://openalex.org/W3037625699","https://openalex.org/W3089659770","https://openalex.org/W3090449556","https://openalex.org/W3095706145","https://openalex.org/W3096490862","https://openalex.org/W3097787369","https://openalex.org/W3099206234","https://openalex.org/W3105825505","https://openalex.org/W3107826490","https://openalex.org/W3113676066","https://openalex.org/W3113908264","https://openalex.org/W3118578889","https://openalex.org/W3156636935","https://openalex.org/W3162037819","https://openalex.org/W3162471442","https://openalex.org/W3168212167","https://openalex.org/W3172698324","https://openalex.org/W3173190788","https://openalex.org/W3174446152","https://openalex.org/W3175362188","https://openalex.org/W3175809709","https://openalex.org/W3176382501","https://openalex.org/W3176455679","https://openalex.org/W3176711365","https://openalex.org/W3176967746","https://openalex.org/W3186200218","https://openalex.org/W3196790170","https://openalex.org/W3198526264","https://openalex.org/W3199926081","https://openalex.org/W4221163209","https://openalex.org/W4223490341","https://openalex.org/W4223622550","https://openalex.org/W4249573750","https://openalex.org/W4256701369","https://openalex.org/W4287213456","https://openalex.org/W4287329822","https://openalex.org/W4287547182","https://openalex.org/W4287629556","https://openalex.org/W4287812705","https://openalex.org/W4288817190","https://openalex.org/W4294619240","https://openalex.org/W4297808394","https://openalex.org/W4300558631","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W3011059803","https://openalex.org/W2026860389","https://openalex.org/W8219677","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"How":[0],"can":[1],"we":[2,30],"learn":[3],"unified":[4],"representations":[5,15],"for":[6,16,24,38],"spoken":[7],"utterances":[8],"and":[9,20,45,67,103],"their":[10],"written":[11],"text?":[12],"Learning":[13],"similar":[14,18],"semantically":[17],"speech":[19,25],"text":[21],"is":[22],"important":[23],"translation.":[26,41],"To":[27],"this":[28],"end,":[29],"propose":[31],"ConST,":[32],"a":[33,46,52],"cross-modal":[34,95],"contrastive":[35],"learning":[36],"method":[37],"end-to-end":[39],"speech-to-text":[40],"We":[42],"evaluate":[43],"ConST":[44,61,79],"variety":[47],"of":[48,72,85,94],"previous":[49,65],"baselines":[50],"on":[51],"popular":[53],"benchmark":[54],"MuST-C.":[55],"Experiments":[56],"show":[57],"that":[58,78],"the":[59,64,82,92],"proposed":[60],"consistently":[62],"outperforms":[63],"methods,":[66],"achieves":[68],"an":[69],"average":[70],"BLEU":[71],"29.4.":[73],"The":[74],"analysis":[75],"further":[76],"verifies":[77],"indeed":[80],"closes":[81],"representation":[83,90],"gap":[84],"different":[86],"modalities":[87],"-its":[88],"learned":[89],"improves":[91],"accuracy":[93],"speechtext":[96],"retrieval":[97],"from":[98],"4%":[99],"to":[100],"88%.":[101],"Code":[102],"models":[104],"are":[105],"available":[106],"at":[107],"https://github.":[108],"com/ReneeYe/ConST.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}