Audio-Sync Video Generation with Multi-Stream Temporal Control

• URL: http://arxiv.org/abs/2506.08003v1
• Date: Mon, 09 Jun 2025 17:59:42 GMT
• Title: Audio-Sync Video Generation with Multi-Stream Temporal Control
• Authors: Shuchen Weng, Haojie Zheng, Zheng Chang, Si Li, Boxin Shi, Xinlong Wang,
• Abstract summary: We introduce MTV, a versatile framework for video generation with precise audio-visual synchronization.<n>MTV separates audios into speech, effects, and tracks, enabling control over lip motion, event timing, and visual mood.<n>To support the framework, we additionally present DEmix, a dataset of high-quality cinematic videos and demixed audio tracks.
• Score: 64.00019697525322
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video generation. MTV explicitly separates audios into speech, effects, and music tracks, enabling disentangled control over lip motion, event timing, and visual mood, respectively -- resulting in fine-grained and semantically aligned video generation. To support the framework, we additionally present DEMIX, a dataset comprising high-quality cinematic videos and demixed audio tracks. DEMIX is structured into five overlapped subsets, enabling scalable multi-stage training for diverse generation scenarios. Extensive experiments demonstrate that MTV achieves state-of-the-art performance across six standard metrics spanning video quality, text-video consistency, and audio-video alignment. Project page: https://hjzheng.net/projects/MTV/.

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)
• Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation [27.20097004987987]
  We propose a large-scale multimodal Video-to-Audio generation model that synthesizes high-quality audio synchronized with video content.<n>Our experiments show that Kling-Foley trained with the flow matching objective achieves new audio-visual SOTA performance.
  arXiv  Detail & Related papers  (2025-06-24T16:39:39Z)
• Let Your Video Listen to Your Music! [62.27731415767459]
  We propose a novel framework, MVAA, that automatically edits video to align with the rhythm of a given music track.<n>We modularize the task into a two-step process in our MVAA: aligning motion with audio beats, followed by rhythm-aware video editing.<n>This hybrid approach enables adaptation within 10 minutes with one on a single NVIDIA 4090 GPU using CogVideoX-5b-I2V as the backbone.
  arXiv  Detail & Related papers  (2025-06-23T17:52:16Z)
• MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis [56.01110988816489]
  We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio.<n> MMAudio is jointly trained with larger-scale, readily available text-audio data to learn to generate semantically aligned high-quality audio samples.<n> MMAudio achieves surprisingly competitive performance in text-to-audio generation, showing that joint training does not hinder single-modality performance.
  arXiv  Detail & Related papers  (2024-12-19T18:59:55Z)
• MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization [52.498942604622165]
  This paper presents MuVi, a framework to generate music that aligns with video content. MuVi analyzes video content through a specially designed visual adaptor to extract contextually and temporally relevant features. We show that MuVi demonstrates superior performance in both audio quality and temporal synchronization.
  arXiv  Detail & Related papers  (2024-10-16T18:44:56Z)
• VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos [32.741262543860934]
  We present a framework for learning to generate background music from video inputs. We develop a generative video-music Transformer with a novel semantic video-music alignment scheme. New temporal video encoder architecture allows us to efficiently process videos consisting of many densely sampled frames.
  arXiv  Detail & Related papers  (2024-09-11T17:56:48Z)
• VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling [71.01050359126141]
  We propose VidMuse, a framework for generating music aligned with video inputs.<n> VidMuse produces high-fidelity music that is both acoustically and semantically aligned with the video.
  arXiv  Detail & Related papers  (2024-06-06T17:58:11Z)
• Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model [32.801213106782335]
  We develop a generative music AI framework, Video2Music, that can match a provided video. In a thorough experiment, we show that our proposed framework can generate music that matches the video content in terms of emotion.
  arXiv  Detail & Related papers  (2023-11-02T03:33:00Z)

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.