Characterization of urban sound environments using a comprehensive approach combining open data, measurements, and modeling

Abstract

Urban noise reduction is a societal priority. In this context, the European Directive 2002/49/EC aims at producing strategic noise maps for large cities. However, nowadays the relevance of such maps is questionable, due to considerable uncertainties, which are rarely quantified. Conversely, the development of noise observatories can provide useful information for a more realistic description of the sound environment, but at the expense of insufficient spatial resolution and high costs. Thus, the CENSE project aims at proposing a new methodology for the production of more realistic noise maps, based on an assimilation of simulated and measured data, collected through a dense network of low-cost sensors that rely on new technologies. In addition, the proposed approach tries to take into account the various sources of uncertainty, either from measurements and modeling. Beyond the production of physical indicators, the project also includes advanced sound environments characterization, through sound recognition and perceptual assessments. CENSE is resolutely a multidisciplinary project, bringing together experts from environmental acoustics, data assimilation, statistics, GIS, sensor networks, signal processing, and noise perception. As the project is in launch state, the present communication will focus on a global overview, emphasizing the innovative and key points of the project.

The Internet of Audio Things: State of the Art, Vision, and Challenges

“…The DYNAMAP project [40] study the development of such network in two major cities in Italy. In France, the CENSE project focuses on the deployment of dense networks that transmit high-level spectral features [4], [41] which are designed to 1) respect the privacy of the citizen [26], and 2) permit a quality of the description of the sound scene that goes well beyond the use of averaged acoustic pressure level that is commonly considered for those applications [42].…”

“…Solar panels have been utilized in various systems to cope with this issue (see, e.g., [34]) but advances in miniaturization and power of batteries are necessary. Another possibility would be to augment existing objects deployed in smart cities that are distributed and by default are connected to a power supply, such as smart street lights, as in the CENSE project [41].…”

Privacy Aware Acoustic Scene Synthesis Using Deep Spectral Feature Inversion

“…Together with sound quality concerns in urban environments, the advent of the Internet of Things has led to the implementation of large scale acoustic sensor networks for monitoring purposes in several projects [1,2,3,4]. The aim of these sensor networks is to gather rich information about the sound environment and its content.…”

Road traffic sound level estimation from realistic urban sound mixtures by Non-negative Matrix Factorization

“…Several measurement set-ups have been proposed in the last years, including mobile measurements with high quality microphones [8,9], participative sensing through dedicated smartphone applications [10,11], or the development of fixed-sensor networks. In this latter case, the sensor networks can be based either on high-quality sensors as in [12,13], or low-cost sensors as in the DYNAMAP project [14] or the CENSE project [15]. The costs and benefits of each protocol are discussed.…”