European cities are adapting soundscape-based urban planning to create better living spaces for residents. Auralization acts as one of the possible tools that provides immersive auditory experiences for urban planners, architects and the community. This paper explores using surrogate background sound generators, combining Text-to-Audio models (TTA) and Binaural Room Impulse Response-based models, highlighting the potential of surrogate audio renderers to support more perceptually grounded, design-oriented decision-making in urban environments.
Coming soonThe word soundscape stems from early sonography works, defining it as the acoustic equivalent to landscape. Modern acousticians have elaborated the definition to emphasize human perception and the built environment. Soundscape is increasingly used as a carrier and assessment criteria for urban planning.
The framework follows context specification, sound file retrieval, and mixing stages. It uses UrbanSound8K dataset, ChromaDB vector database with LAION-CLAP embedding, and SLiCE method for query prompt regularization.
The approach uses surrogate BRIR models fine-tuned for outdoor scenarios, ONNX format for interoperability, and temporal sequencing to knit input contexts with selected audio files.