{"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/tavgbench-benchmarking-text-to-audible-video","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","arxiv_id":"2404.14381","date":"2024-04-22","proceeding":null,"authors":["Yuxin Mao","Xuyang Shen","Jing Zhang","Zhen Qin","Jinxing Zhou","Mochu Xiang","Yiran Zhong","Yuchao Dai"],"abstract":"The Text to Audible-Video Generation (TAVG) task involves generating videos with accompanying audio based on text descriptions. Achieving this requires skillful alignment of both audio and video elements. To support research in this field, we have developed a comprehensive Text to Audible-Video Generation Benchmark (TAVGBench), which contains over 1.7 million clips with a total duration of 11.8 thousand hours. We propose an automatic annotation pipeline to ensure each audible video has detailed descriptions for both its audio and video contents. We also introduce the Audio-Visual Harmoni score (AVHScore) to provide a quantitative measure of the alignment between the generated audio and video modalities. Additionally, we present a baseline model for TAVG called TAVDiffusion, which uses a two-stream latent diffusion model to provide a fundamental starting point for further research in this area. We achieve the alignment of audio and video by employing cross-attention and contrastive learning. Through extensive experiments and evaluations on TAVGBench, we demonstrate the effectiveness of our proposed model under both conventional metrics and our proposed metrics.","url_abs":"https://arxiv.org/abs/2404.14381v1","url_pdf":"https://arxiv.org/pdf/2404.14381v1.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":"tavgbench-benchmarking-text-to-audible-video","repo_url":"https://github.com/opennlplab/tavgbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.14381","atlas_url":"https://app.syntology.ai/?focus=2404.14381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14381"}},"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/opennlplab/tavgbench","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_violates":2,"ran":5,"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":11,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/ldm.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/ldm.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/utils.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"33e4f7a8bf80ee3a","entry":"get_bit_depth","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/utils.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33e4f7a8bf80ee3a"}},{"code_sha256_prefix":"159fc130dc64d332","entry":"get_duration","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/utils.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"159fc130dc64d332"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/hifigan/models.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"cb49209c125de1b4","entry":"get_timestep_embedding","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb49209c125de1b4"}},{"code_sha256_prefix":"04291fe9256fbb11","entry":"load_pretrained_unet","repo":"opennlplab/tavgbench","repo_kind":"official","path":"inference.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04291fe9256fbb11"}},{"code_sha256_prefix":"409a71c470a245cd","entry":"make_batch_for_text_to_audio","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/pipeline.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/pipeline.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"409a71c470a245cd"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/variational_autoencoder/modules.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/variational_autoencoder/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"444fd0303f1aff5a","entry":"round_up_duration","repo":"opennlplab/tavgbench","repo_kind":"official","path":"audioldm/pipeline.py","file_url":"https://github.com/opennlplab/tavgbench/blob/HEAD/audioldm/pipeline.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"444fd0303f1aff5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}