Hear What Matters! Text-conditioned Selective Video-to-Audio Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Junwon, Nam, Juhan, Lee, Jiyoung
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915894183067648
author Lee, Junwon
Nam, Juhan
Lee, Jiyoung
author_facet Lee, Junwon
Nam, Juhan
Lee, Jiyoung
contents This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. We propose SELVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector to distinctly extract prompt-relevant sound-source visual features from the video encoder. To suppress text-irrelevant activations with efficient video encoder finetuning, the proposed supplementary tokens promote cross-attention to yield robust semantic and temporal grounding. SELVA further employs an autonomous video-mixing scheme in a self-supervised manner to overcome the lack of mono audio track supervision. We evaluate SELVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02650
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
Lee, Junwon
Nam, Juhan
Lee, Jiyoung
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Sound
Audio and Speech Processing
This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. We propose SELVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector to distinctly extract prompt-relevant sound-source visual features from the video encoder. To suppress text-irrelevant activations with efficient video encoder finetuning, the proposed supplementary tokens promote cross-attention to yield robust semantic and temporal grounding. SELVA further employs an autonomous video-mixing scheme in a self-supervised manner to overcome the lack of mono audio track supervision. We evaluate SELVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization.
title Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
topic Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2512.02650