{"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/tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","arxiv_id":"2411.05679","date":"2024-11-08","proceeding":null,"authors":["Xiulong Liu","Kun Su","Eli Shlizerman"],"abstract":"The content of visual and audio scenes is multi-faceted such that a video can be paired with various audio and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description of the audio. Such a framework has two advantages: i) Video-to-Audio generation process can be refined and controlled via text which complements the context of visual information, and ii) The model can suggest what audio to generate for the video by generating audio captions. VATT consists of two key modules: VATT Converter, a LLM that is fine-tuned for instructions and includes a projection layer that maps video features to the LLM vector space; and VATT Audio, a transformer that generates audio tokens from visual frames and from optional text prompt using iterative parallel decoding. The audio tokens are converted to a waveform by pretrained neural codec. Experiments show that when VATT is compared to existing video-to-audio generation methods in objective metrics, it achieves competitive performance when the audio caption is not provided. When the audio caption is provided as a prompt, VATT achieves even more refined performance (lowest KLD score of 1.41). Furthermore, subjective studies show that VATT Audio has been chosen as preferred generated audio than audio generated by existing methods. VATT enables controllable video-to-audio generation through text as well as suggesting text prompts for videos through audio captions, unlocking novel applications such as text-guided video-to-audio generation and video-to-audio captioning.","url_abs":"https://arxiv.org/abs/2411.05679v3","url_pdf":"https://arxiv.org/pdf/2411.05679v3.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":"tell-what-you-hear-from-what-you-see-video-to","repo_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"},{"task_slug":"audio-captioning","task_name":"Audio captioning"},{"task_slug":"video-to-sound-generation","task_name":"Video-to-Sound Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vatt","method_name":"VATT"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-to-sound-generation-on-vgg-sound","task":"Video-to-Sound Generation","dataset":"VGG-Sound","model":"VATT-LLama","rank_in_archive_order":8,"of":8,"metrics":{"FAD":"2.38","KLD":"1.41"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.05679","atlas_url":"https://app.syntology.ai/?focus=2411.05679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05679"}},"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/DragonLiu1995/multimodal-llm-for-audio-gen","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":6,"samples":[{"code_sha256_prefix":"dea58d1899ee3c24","entry":"cook_refs_bleu","repo":"DragonLiu1995/multimodal-llm-for-audio-gen","repo_kind":"official","path":"vatt/v2cap/eval_gen_text_nlg_metrics.py","file_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen/blob/HEAD/vatt/v2cap/eval_gen_text_nlg_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dea58d1899ee3c24"}},{"code_sha256_prefix":"d31f3abbe40eaed9","entry":"cook_test_bleu","repo":"DragonLiu1995/multimodal-llm-for-audio-gen","repo_kind":"official","path":"vatt/v2cap/eval_gen_text_nlg_metrics.py","file_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen/blob/HEAD/vatt/v2cap/eval_gen_text_nlg_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d31f3abbe40eaed9"}},{"code_sha256_prefix":"42b7821640dcfbcf","entry":"float32_to_int16","repo":"DragonLiu1995/multimodal-llm-for-audio-gen","repo_kind":"official","path":"vatt/v2cap/eval_gen_audio_clap_score.py","file_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen/blob/HEAD/vatt/v2cap/eval_gen_audio_clap_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"42b7821640dcfbcf"}},{"code_sha256_prefix":"47bbdd629908bce3","entry":"int16_to_float32","repo":"DragonLiu1995/multimodal-llm-for-audio-gen","repo_kind":"official","path":"vatt/v2cap/eval_gen_audio_clap_score.py","file_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen/blob/HEAD/vatt/v2cap/eval_gen_audio_clap_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"47bbdd629908bce3"}},{"code_sha256_prefix":"2b12dc18a056ac9f","entry":"precook_bleu","repo":"DragonLiu1995/multimodal-llm-for-audio-gen","repo_kind":"official","path":"vatt/v2cap/eval_gen_text_nlg_metrics.py","file_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen/blob/HEAD/vatt/v2cap/eval_gen_text_nlg_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2b12dc18a056ac9f"}},{"code_sha256_prefix":"da3b804db775f592","entry":"split_train_val","repo":"DragonLiu1995/multimodal-llm-for-audio-gen","repo_kind":"official","path":"vatt/v2cap/pretrain_visual_audio.py","file_url":"https://github.com/DragonLiu1995/multimodal-llm-for-audio-gen/blob/HEAD/vatt/v2cap/pretrain_visual_audio.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"da3b804db775f592"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}