ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation

• URL: http://arxiv.org/abs/2503.07217v3
• Date: Mon, 02 Jun 2025 10:38:46 GMT
• Title: ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation
• Authors: Zixuan Wang, Chi-Keung Tang, Yu-Wing Tai,
• Abstract summary: This paper proposes a multi-agentic framework for audio generation supervised by an autonomous Sound Director agent.<n>The Foley Artist works cooperatively with the Composer and Voice Actor agents, and together they autonomously generate off-screen sound to complement the overall production.<n>Our framework can generate rich and relevant audio content conditioned on video clips extracted from movies.
• Score: 72.22243595269389
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current audio generation conditioned by text or video focuses on aligning audio with text/video modalities. Despite excellent alignment results, these multimodal frameworks still cannot be directly applied to compelling movie storytelling involving multiple scenes, where "on-screen" sounds require temporally-aligned audio generation, while "off-screen" sounds contribute to appropriate environment sounds accompanied by background music when applicable. Inspired by professional movie production, this paper proposes a multi-agentic framework for audio generation supervised by an autonomous Sound Director agent, engaging multi-turn conversations with other agents for on-screen and off-screen sound generation through multimodal LLM. To address on-screen sound generation, after detecting any talking humans in videos, we capture semantically and temporally synchronized sound by training a prediction model that forecasts interpretable, time-varying audio control signals: loudness, pitch, and timbre, which are used by a Foley Artist agent to condition a cross-attention module in the sound generation. The Foley Artist works cooperatively with the Composer and Voice Actor agents, and together they autonomously generate off-screen sound to complement the overall production. Each agent takes on specific roles similar to those of a movie production team. To temporally ground audio language models, in ReelWave, text/video conditions are decomposed into atomic, specific sound generation instructions synchronized with visuals when applicable. Consequently, our framework can generate rich and relevant audio content conditioned on video clips extracted from movies.

Related papers

• ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing [52.33281620699459]
  ThinkSound is a novel framework that leverages Chain-of-Thought (CoT) reasoning to enable stepwise, interactive audio generation and editing for videos.<n>Our approach decomposes the process into three complementary stages: semantically coherent, interactive object-centric refinement through precise user interactions, and targeted editing guided by natural language instructions.<n> Experiments demonstrate that ThinkSound achieves state-of-the-art performance in video-to-audio generation across both audio metrics and CoT metrics.
  arXiv  Detail & Related papers  (2025-06-26T16:32:06Z)
• Exploiting Temporal Audio-Visual Correlation Embedding for Audio-Driven One-Shot Talking Head Animation [62.218932509432314]
  Inherently, the temporal relationship of adjacent audio clips is highly correlated with that of the corresponding adjacent video frames. We learn audio-visual correlations and integrate the correlations to help enhance feature representation and regularize final generation.
  arXiv  Detail & Related papers  (2025-04-08T07:23:28Z)
• Long-Video Audio Synthesis with Multi-Agent Collaboration [20.332328741375363]
  LVAS-Agent is a novel framework that emulates professional dubbing through collaborative role. Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, sound design and audio synthesis. Central innovations include a discussion-correction mechanism for scene/script refinement and a generation-retrieval loop for temporal-semantic alignment.
  arXiv  Detail & Related papers  (2025-03-13T07:58:23Z)
• Automated Movie Generation via Multi-Agent CoT Planning [20.920129008402718]
  MovieAgent is an automated movie generation via multi-agent Chain of Thought (CoT) planning.<n>It generates multi-scene, multi-shot long-form videos with a coherent narrative, while ensuring character consistency, synchronized subtitles, and stable audio.<n>By employing multiple LLM agents to simulate the roles of a director, screenwriter, storyboard artist, and location manager, MovieAgent streamlines the production pipeline.
  arXiv  Detail & Related papers  (2025-03-10T13:33:27Z)
• Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition [72.22243595269389]
  We introduce Audio-Agent, a framework for audio generation, editing and composition based on text or video inputs.<n>In our method, we utilize a pre-trained TTA diffusion network as the audio generation agent to work in tandem with GPT-4.<n>For video-to-audio (VTA) tasks, most existing methods require training a timestamp detector to synchronize video events with the generated audio.
  arXiv  Detail & Related papers  (2024-10-04T11:40:53Z)
• Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound [6.638504164134713]
  Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video.<n>Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges.<n>We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as an intuitive condition with semantic timbre prompts.
  arXiv  Detail & Related papers  (2024-08-21T18:06:15Z)
• Synthesizing Audio from Silent Video using Sequence to Sequence Modeling [0.0]
  We propose a novel method to generate audio from video using a sequence-to-sequence model. Our approach employs a 3D Vector Quantized Variational Autoencoder (VQ-VAE) to capture the video's spatial and temporal structures. Our model aims to enhance applications like CCTV footage analysis, silent movie restoration, and video generation models.
  arXiv  Detail & Related papers  (2024-04-25T22:19:42Z)
• Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners [69.70590867769408]
  Video and audio content creation serves as the core technique for the movie industry and professional users. Existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from academia to industry. In this work, we aim at filling the gap, with a carefully designed optimization-based framework for cross-visual-audio and joint-visual-audio generation.
  arXiv  Detail & Related papers  (2024-02-27T17:57:04Z)
• WavJourney: Compositional Audio Creation with Large Language Models [38.39551216587242]
  We present WavJourney, a novel framework that leverages Large Language Models to connect various audio models for audio creation. WavJourney allows users to create storytelling audio content with diverse audio elements simply from textual descriptions. We show that WavJourney is capable of synthesizing realistic audio aligned with textually-described semantic, spatial and temporal conditions.
  arXiv  Detail & Related papers  (2023-07-26T17:54:04Z)
• MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images [92.13079696503803]
  We present MovieFactory, a framework to generate cinematic-picture (3072$times$1280), film-style (multi-scene), and multi-modality (sounding) movies. Our approach empowers users to create captivating movies with smooth transitions using simple text inputs.
  arXiv  Detail & Related papers  (2023-06-12T17:31:23Z)
• AudioLM: a Language Modeling Approach to Audio Generation [59.19364975706805]
  We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. We show how existing audio tokenizers provide different trade-offs between reconstruction quality and long-term structure. We demonstrate how our approach extends beyond speech by generating coherent piano music continuations.
  arXiv  Detail & Related papers  (2022-09-07T13:40:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.