arXiv:2610.18597v1 Announce Type: cross Abstract: Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictabl...
arXiv:2506. 20995v4 Announce Type: replace-cross Abstract: We propose a step-by-step video-to-audio (V2A) generation method that provides finer control over the generation process and more realistic audio synthesis.
The paper introduces a new task called video object segmentation‑aware audio generation, which conditions sound synthesis on object‑level segmentation maps. It presents SAGANet, a multimodal generative model that uses visual segmentation masks, video, and textual cues to produce controllable audio for musical instruments, offering fine‑grained, visually localized control. The authors also release the Segmented Music Solos dataset of instrument performance videos with segmentation information to support this task and demonstrate that SAGANet outperforms current state‑of‑the‑art methods in controllable, high‑fidelity Foley synthesis.
arXiv:2509. 15210v2 Announce Type: replace-cross Abstract: Realistic sound simulation plays a critical role in many applications.
SCAPES is a lightweight, resource‑efficient generative model that synthesizes high‑fidelity environmental sounds with high‑level semantic control. It operates on the continuous latent manifold of a neural audio codec, using a segmentation strategy and a Continuous Normalizing Flow to model latent trajectories. A 36‑million‑parameter instance can be trained on limited, uncurated data with a single consumer‑grade GPU, achieving convergence in roughly twice the source audio duration and enabling smooth semantic interpolation.
SsgCaps is a publicly available dataset of human-engineered sound scenes, each paired with a precisely structured prompt that guides the sampling process. The prompts are drawn from a predefined action-based typology, enabling extensive yet plausible sampling. A comparative quantitative analysis shows only small differences between the open and private versions, supporting the recommendation of the open version for benchmarking sound scene generation algorithms.
arXiv:2609.38444v1 Announce Type: new Abstract: Text- and image-conditioned world generators can create visually rich 3D environments, yet these worlds often remain silent or rely on soundtracks synt...
Synth-JEPA introduces a renderer‑free approach to synthesizer parameter search by learning mutually predictive audio and parameter representations from paired synthesizer data. During inference, candidate parameters are scored directly in this learned space, avoiding the need to render each candidate and shaping audio geometry through parameter correspondences. Evaluations on Surge XT and out‑of‑domain datasets show Synth‑JEPA outperforms inverse models, direct search, and learned proxy objectives, with listeners preferring its matches in 85% of pairwise tests.
arXiv:2608. 03742v1 Announce Type: cross Abstract: Sound effects play a crucial role in conveying actions, events, and environmental cues across digital applications, often requiring a high degree of variation and contextual adaptability.
arXiv:2607. 04848v1 Announce Type: cross Abstract: While audio deepfake detection has advanced significantly, representative detectors show limited generalization to synthetic sound effects.
arXiv:2610.00691v1 Announce Type: new Abstract: Recent joint audio-video generative models can synthesize realistic videos with synchronized sound, but typically generate audio as a single mixed trac...
arXiv:2512.23994v5 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to...