STASE: A spatialized text-to-audio synthesis engine for music generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chi, Tutti, Gao, Letian, Zhang, Yixiao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912587316199424
author Chi, Tutti
Gao, Letian
Zhang, Yixiao
author_facet Chi, Tutti
Gao, Letian
Zhang, Yixiao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STASE: A spatialized text-to-audio synthesis engine for music generation
Chi, Tutti
Gao, Letian
Zhang, Yixiao
Sound
Audio and Speech Processing
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.
title STASE: A spatialized text-to-audio synthesis engine for music generation
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.11124