INTELLECTUAL ANALYSIS OF THE SOUND LANDSCAPE OF AN URBAN TERRITORY

Abstract

For many years, urban planning focused on visual elements: composition, color, etc., while the sound of the city was relegated to the background. Meanwhile, sound elements are an essential component of the city's cultural landscape. This article analyzes existing approaches to shaping the soundscape of urban areas in Russia and abroad, identifying key areas for development. Modern information technologies make it possible to automate the process of assessing the current state of a city's soundscape through the use of machine learning, and subsequently manage individual sound elements to create a comfortable urban environment. The authors propose a process for analyzing and processing the original urban sound using neural networks and spectrogram analysis. This process separates the track into individual components, such as car sounds, construction site sounds, etc., and also allows for the creation of a set of sound files that take into account changes made by urban planners. The resulting files containing urban noise can be used in sociological research to identify the preferences of residents in various neighborhoods. An example of the application of the proposed solutions for shaping a soundscape is provided, using a section of Volgograd as an example.