{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ctal-pre-training-cross-modal-transformer-for","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","arxiv_id":"2109.00181","date":"2021-09-01","proceeding":"EMNLP 2021 11","authors":["Hang Li","Yu Kang","Tianqiao Liu","Wenbiao Ding","Zitao Liu"],"abstract":"Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms. However, these models are facing challenges of overfitting with limited labels and low model generalization abilities. In this paper, we present a Cross-modal Transformer for Audio-and-Language, i.e., CTAL, which aims to learn the intra-modality and inter-modality connections between audio and language through two proxy tasks on a large amount of audio-and-language pairs: masked language modeling and masked cross-modal acoustic modeling. After fine-tuning our pre-trained model on multiple downstream audio-and-language tasks, we observe significant improvements across various tasks, such as, emotion classification, sentiment analysis, and speaker verification. On this basis, we further propose a specially-designed fusion mechanism that can be used in fine-tuning phase, which allows our pre-trained model to achieve better performance. Lastly, we demonstrate detailed ablation studies to prove that both our novel cross-modality fusion component and audio-language pre-training methods significantly contribute to the promising results.","url_abs":"https://arxiv.org/abs/2109.00181v1","url_pdf":"https://arxiv.org/pdf/2109.00181v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ctal-pre-training-cross-modal-transformer-for","repo_url":"https://github.com/ydkwim/ctal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"emotion-classification","task_name":"Emotion Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"ctal","method_name":"CTAL"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"ctal","name":"CTAL","full_name":"CTAL"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.00181","atlas_url":"https://app.syntology.ai/?focus=2109.00181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00181"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ydkwim/ctal","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tal-ai/CTAL_EMNLP2021","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tal-ai/CTAL_","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":2,"ran_honours":1,"unverified":16},"by_repo_kind":{"official":{"samples":14,"ran":1,"repositories":1},"found_in_text":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"822f2b1124d338bb","entry":"AcousticInputRepresentations","repo":"tal-ai/CTAL_EMNLP2021","repo_kind":"found_in_text","path":"code/m2p_model.py","file_url":"https://github.com/tal-ai/CTAL_EMNLP2021/blob/HEAD/code/m2p_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"822f2b1124d338bb"}},{"code_sha256_prefix":"bc9ad7176f8222c8","entry":"RobertaAMHead","repo":"tal-ai/CTAL_EMNLP2021","repo_kind":"found_in_text","path":"code/m2p_model.py","file_url":"https://github.com/tal-ai/CTAL_EMNLP2021/blob/HEAD/code/m2p_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bc9ad7176f8222c8"}},{"code_sha256_prefix":"142e017e37f584c6","entry":"multiclass_acc","repo":"ydkwim/ctal","repo_kind":"official","path":"code/run_s-reg-mosei.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/run_s-reg-mosei.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"142e017e37f584c6"}},{"code_sha256_prefix":"3a0fda00078a444e","entry":"AcousticModel","repo":"tal-ai/CTAL_EMNLP2021","repo_kind":"found_in_text","path":"code/m2p_model.py","file_url":"https://github.com/tal-ai/CTAL_EMNLP2021/blob/HEAD/code/m2p_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3a0fda00078a444e"}},{"code_sha256_prefix":"76c38b19897f7c7b","entry":"RobertaForMaskedAM","repo":"tal-ai/CTAL_EMNLP2021","repo_kind":"found_in_text","path":"code/m2p_model.py","file_url":"https://github.com/tal-ai/CTAL_EMNLP2021/blob/HEAD/code/m2p_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"76c38b19897f7c7b"}},{"code_sha256_prefix":"85af9ffb207dd2b2","entry":"RobertaM2Model","repo":"tal-ai/CTAL_EMNLP2021","repo_kind":"found_in_text","path":"code/m2p_model.py","file_url":"https://github.com/tal-ai/CTAL_EMNLP2021/blob/HEAD/code/m2p_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"85af9ffb207dd2b2"}},{"code_sha256_prefix":"d3d9401fa2444bc8","entry":"collate","repo":"ydkwim/ctal","repo_kind":"official","path":"code/run_s-iemocap.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/run_s-iemocap.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3d9401fa2444bc8"}},{"code_sha256_prefix":"6ceec151acbbc145","entry":"collate","repo":"ydkwim/ctal","repo_kind":"official","path":"code/run_s-reg-mosei.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/run_s-reg-mosei.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6ceec151acbbc145"}},{"code_sha256_prefix":"1cec2fe099d913d4","entry":"down_sample_frames","repo":"ydkwim/ctal","repo_kind":"official","path":"code/m2p_mask.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/m2p_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1cec2fe099d913d4"}},{"code_sha256_prefix":"402f48cf719e8ff0","entry":"eval_helper","repo":"ydkwim/ctal","repo_kind":"official","path":"code/run_s-reg-mosei.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/run_s-reg-mosei.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"402f48cf719e8ff0"}},{"code_sha256_prefix":"5c03130d658096c8","entry":"get_centroids","repo":"ydkwim/ctal","repo_kind":"official","path":"code/calculate_eer.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/calculate_eer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c03130d658096c8"}},{"code_sha256_prefix":"ddd85402bca56b00","entry":"get_cossim","repo":"ydkwim/ctal","repo_kind":"official","path":"code/calculate_eer.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/calculate_eer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ddd85402bca56b00"}},{"code_sha256_prefix":"a0c7c003d46d7536","entry":"get_utterance_centroids","repo":"ydkwim/ctal","repo_kind":"official","path":"code/calculate_eer.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/calculate_eer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0c7c003d46d7536"}},{"code_sha256_prefix":"e5abd0422f0b516c","entry":"load_acoustic_data","repo":"ydkwim/ctal","repo_kind":"official","path":"code/m2p_dataloader.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/m2p_dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e5abd0422f0b516c"}},{"code_sha256_prefix":"7d4578febace3ca2","entry":"load_semantic_data","repo":"ydkwim/ctal","repo_kind":"official","path":"code/m2p_dataloader.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/m2p_dataloader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d4578febace3ca2"}},{"code_sha256_prefix":"fa1982cd98fbaf9d","entry":"process_train_MAM_data","repo":"ydkwim/ctal","repo_kind":"official","path":"code/m2p_mask.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/m2p_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fa1982cd98fbaf9d"}},{"code_sha256_prefix":"27ab2a9027ec745a","entry":"process_train_MLM_data","repo":"ydkwim/ctal","repo_kind":"official","path":"code/m2p_mask.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/m2p_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27ab2a9027ec745a"}},{"code_sha256_prefix":"f291cb1801e3b2b1","entry":"ua_helper","repo":"ydkwim/ctal","repo_kind":"official","path":"code/run_s-iemocap.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/run_s-iemocap.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f291cb1801e3b2b1"}},{"code_sha256_prefix":"38621d5c1eb92ad6","entry":"wa_helper","repo":"ydkwim/ctal","repo_kind":"official","path":"code/run_s-iemocap.py","file_url":"https://github.com/ydkwim/ctal/blob/HEAD/code/run_s-iemocap.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38621d5c1eb92ad6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}