{"ID":2896784,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07318","arxiv_id":"2507.07318","title":"Generating Moving 3D Soundscapes with Latent Diffusion Models","abstract":"Spatial audio has become central to immersive applications such as VR/AR, cinema, and music. Existing generative audio models are largely limited to mono or stereo formats and cannot capture the full 3D localization cues available in first-order Ambisonics (FOA). Recent FOA models extend text-to-audio generation but remain restricted to static sources. In this work, we introduce SonicMotion, the first end-to-end latent diffusion framework capable of generating FOA audio with explicit control over moving sound sources. SonicMotion is implemented in two variations: 1) a descriptive model conditioned on natural language prompts, and 2) a parametric model conditioned on both text and spatial trajectory parameters for higher precision. To support training and evaluation, we construct a new dataset of over one million simulated FOA caption pairs that include both static and dynamic sources with annotated azimuth, elevation, and motion attributes. Experiments show that SonicMotion achieves state-of-the-art semantic alignment and perceptual quality comparable to leading text-to-audio systems, while uniquely attaining low spatial localization error.","short_abstract":"Spatial audio has become central to immersive applications such as VR/AR, cinema, and music. Existing generative audio models are largely limited to mono or stereo formats and cannot capture the full 3D localization cues available in first-order Ambisonics (FOA). Recent FOA models extend text-to-audio generation but re...","url_abs":"https://arxiv.org/abs/2507.07318","url_pdf":"https://arxiv.org/pdf/2507.07318v2","authors":"[\"Christian Templin\",\"Yanda Zhu\",\"Hao Wang\"]","published":"2025-07-09T22:31:06Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"eess.AS\"]","methods":"[\"Diffusion Model\"]","has_code":false}