{"id":"https://openalex.org/W3198549210","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.323","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","display_name":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198549210","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.323","mag":"3198549210"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.323","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.323","pdf_url":"https://aclanthology.org/2021.emnlp-main.323.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.323.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100455135","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-3464-3245"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hang Li","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061403523","display_name":"Wenbiao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbiao Ding","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110921685","display_name":"Yu Kang","orcid":"https://orcid.org/0000-0001-5196-0376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Kang","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078859530","display_name":"Tianqiao Liu","orcid":"https://orcid.org/0000-0001-7997-3232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqiao Liu","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009659901","display_name":"Zhongqin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongqin Wu","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014957271","display_name":"Zitao Liu","orcid":"https://orcid.org/0000-0003-0491-307X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zitao Liu","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100455135"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7613,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74279113,"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":"3966","last_page":"3977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.845732569694519},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5713065266609192},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5500961542129517},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5357285141944885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4951430857181549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4806067645549774},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43598008155822754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40378931164741516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15397953987121582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845732569694519},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5713065266609192},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5500961542129517},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5357285141944885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4951430857181549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4806067645549774},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43598008155822754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40378931164741516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15397953987121582},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.323","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.323","pdf_url":"https://aclanthology.org/2021.emnlp-main.323.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.323","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.323","pdf_url":"https://aclanthology.org/2021.emnlp-main.323.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198549210.pdf","grobid_xml":"https://content.openalex.org/works/W3198549210.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1651753422","https://openalex.org/W1840435438","https://openalex.org/W1933349210","https://openalex.org/W2113507809","https://openalex.org/W2131744502","https://openalex.org/W2146334809","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2250539671","https://openalex.org/W2427527485","https://openalex.org/W2518108298","https://openalex.org/W2606964149","https://openalex.org/W2626778328","https://openalex.org/W2738581557","https://openalex.org/W2768282280","https://openalex.org/W2803193013","https://openalex.org/W2896457183","https://openalex.org/W2916113431","https://openalex.org/W2937142395","https://openalex.org/W2937584914","https://openalex.org/W2939710050","https://openalex.org/W2950501607","https://openalex.org/W2950577311","https://openalex.org/W2950761309","https://openalex.org/W2953084091","https://openalex.org/W2962770129","https://openalex.org/W2962788625","https://openalex.org/W2963115613","https://openalex.org/W2963263347","https://openalex.org/W2963341956","https://openalex.org/W2963710346","https://openalex.org/W2963748441","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969862959","https://openalex.org/W2970231061","https://openalex.org/W2970597249","https://openalex.org/W2970608575","https://openalex.org/W2972463723","https://openalex.org/W2972909277","https://openalex.org/W2973049979","https://openalex.org/W2973192491","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2998356391","https://openalex.org/W3015326490","https://openalex.org/W3025035610","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3090449556","https://openalex.org/W3099782249","https://openalex.org/W3148040514","https://openalex.org/W4287634424","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3196747313","https://openalex.org/W3097571385","https://openalex.org/W2359001871","https://openalex.org/W3033862527","https://openalex.org/W4287761227","https://openalex.org/W3033942572","https://openalex.org/W3008110149","https://openalex.org/W4362014186","https://openalex.org/W4381786178","https://openalex.org/W4316012698"],"abstract_inverted_index":{"Existing":[0],"approaches":[1],"for":[2,33],"audio-language":[3],"taskspecific":[4],"prediction":[5],"focus":[6],"on":[7,73,82],"building":[8],"complicated":[9],"late-fusion":[10],"mechanisms.":[11],"However,":[12],"these":[13],"models":[14,138],"face":[15],"challenges":[16],"of":[17,57],"overfitting":[18],"with":[19],"limited":[20],"labels":[21],"and":[22,47,63,90,125,136],"poor":[23],"generalization.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,78,94,111],"present":[29],"a":[30,54,96],"Cross-modal":[31],"Transformer":[32],"Audio-and-Language,":[34],"i.e.,":[35],"CTAL,":[36],"which":[37,103],"aims":[38],"to":[39,106,116,130],"learn":[40],"the":[41,100,131],"intra-and":[42],"inter-modalities":[43],"connections":[44],"between":[45],"audio":[46],"language":[48,61],"through":[49],"two":[50],"proxy":[51],"tasks":[52],"from":[53],"large":[55],"number":[56],"audio-and-language":[58],"pairs:":[59],"masked":[60,64],"modeling":[62],"cross-modal":[65],"acoustic":[66],"modeling.":[67],"After":[68],"fine-tuning":[69,101],"our":[70,120],"CTAL":[71,105],"model":[72],"multiple":[74],"downstream":[75],"audioand-language":[76],"tasks,":[77,84],"observe":[79],"significant":[80],"improvements":[81],"different":[83],"including":[85],"emotion":[86],"classification,":[87],"sentiment":[88],"analysis,":[89],"speaker":[91],"verification.":[92],"Furthermore,":[93],"design":[95],"fusion":[97,123],"mechanism":[98],"in":[99],"phase,":[102],"allows":[104],"achieve":[107],"better":[108],"performance.":[109],"Lastly,":[110],"conduct":[112],"detailed":[113],"ablation":[114],"studies":[115],"demonstrate":[117],"that":[118],"both":[119],"novel":[121],"cross-modality":[122],"component":[124],"audiolanguage":[126],"pre-training":[127],"methods":[128],"contribute":[129],"promising":[132],"results.":[133],"The":[134],"code":[135],"pretrained":[137],"are":[139],"available":[140],"at":[141],"https://":[142],"github.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2025-10-10T00:00:00"}