{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/ctal","slug":"ctal","name":"CTAL","full_name":"CTAL","full_name_withheld":false,"description_markdown":"**CTAL** is a pre-training framework for strong audio-and-language representations with a [Transformer](https://paperswithcode.com/method/transformer), which aims to learn the intra-modality and inter-modalities 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. The pre-trained model is a Transformer for Audio and Language, i.e., CTAL, which consists of two modules, a language stream encoding module which adapts word as input element, and a text-referred audio stream encoder module which accepts both frame-level Mel-spectrograms and token-level output embeddings from the language stream","description_state":"present","introduced_year":null,"introduced_by":{"title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","paper":"/paper/ctal-pre-training-cross-modal-transformer-for","first_author":"Hang Li","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/ctal-pre-training-cross-modal-transformer-for"},"source":{"url":"https://arxiv.org/abs/2109.00181v1","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Multi-Modal Methods","url":"/methods/category/multi-modal-methods","pwc_aliases":[]},{"area":"Audio","area_id":"audio","collection":"Generative Audio Models","url":"/methods/category/generative-audio-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/ema-net-efficient-multitask-affinity-learning","slug":"ema-net-efficient-multitask-affinity-learning","title":"Cross-Task Affinity Learning for Multitask Dense Scene Predictions","date":"2024-01-20","arxiv_id":"2401.11124","n_code_links":1,"syntology":null},{"paper":"/paper/ctal-pre-training-cross-modal-transformer-for","slug":"ctal-pre-training-cross-modal-transformer-for","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","date":"2021-09-01","arxiv_id":"2109.00181","n_code_links":1,"syntology":{"ran":15,"of":19,"n_ran_checked":15,"n_instrument":0,"unverified":4,"pointer_only":6,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ydkwim/ctal"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}}],"papers_shown":2,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":2,"with_a_code_link":2,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/ctal/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/ctal/papers/ran/1","json":"/method/ctal/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/emotion-classification","name":"Emotion Classification","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1},{"task":"/task/speaker-verification","name":"Speaker Verification","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2021","papers":1},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ctal"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=CTAL","read_at":"2026-10-05T00:54:20+00:00","query":"CTAL","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"CTAL","origin_arxiv_id":"2109.00181"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2109.00181","repositories":{"listed":3,"in_graph":3,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2109.00181","citations":28},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'CTAL'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2109.00181","page":"/paper/ctal-pre-training-cross-modal-transformer-for","syntology_url":"https://syntology.ai/paper/2109.00181","in_graph_layer":true,"samples":19,"ran":15,"n_ran_checked":15,"n_instrument":0,"unverified":4,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 3 listed of 3 in the graph, strongest link: official). This answer is about arXiv:2109.00181, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"5c7e52357424a6cff14e47ee0b1c024a45f61c2c84ff8884196f6db7bee94548","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}