{"ID":2871269,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.11124","arxiv_id":"2509.11124","title":"STASE: A spatialized text-to-audio synthesis engine for music generation","abstract":"While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space manipulations, which can limit direct control over psychoacoustic parameters critical to spatial perception. To address this, we introduce STASE, a system that leverages a Large Language Model (LLM) as an agent to interpret spatial cues from text. A key feature of STASE is the decoupling of semantic interpretation from a separate, physics-based spatial rendering engine, which facilitates interpretable and user-controllable spatial reasoning. The LLM processes prompts through two main pathways: (i) Description Prompts, for direct mapping of explicit spatial information (e.g., \"place the lead guitar at 45° azimuth, 10 m distance\"), and (ii) Abstract Prompts, where a Retrieval-Augmented Generation (RAG) module retrieves relevant spatial templates to inform the rendering. This paper details the STASE workflow, discusses implementation considerations, and highlights current challenges in evaluating generative spatial audio.","short_abstract":"While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space manipulations, which can limit direct control over psychoacoustic parameters critical to...","url_abs":"https://arxiv.org/abs/2509.11124","url_pdf":"https://arxiv.org/pdf/2509.11124v1","authors":"[\"Tutti Chi\",\"Letian Gao\",\"Yixiao Zhang\"]","published":"2025-09-14T06:29:18Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}