How Can Data Collection Be Used to Map City Sounds?

If you want to avoid traffic in a city or congested area, there are applications such as Google Maps and Waze to help you get around. But what about avoiding noise and distracting sounds? The Citygram-Sound Project—a joint collaboration between NYU Steinhardt, NYU’s Center for Urban Studies and Progress, and CalArts—is trying to combat this gap in available data, by mapping the acoustic soundscapes of cities to better understand how noise pollution affects urban dwellers. The project even includes two faculty members from the Center for Data Science, Claudio Silva and Juan Bello.

Citygram was started in 2011, when Tae Hong Park, an Associate Professor of Music Technology and the Director of Music Composition at NYU Steinhardt, began mapping spatio-acoustic energy through a network of sensors spread throughout New York, Los Angeles, and other major cities.

Park said, I observed that there were no soundmaps of the city. It is a challenge because spatio-acoustic information is fleeting and cannot be represented via current spatial mapping techniques and paradigms,

In an interview with the New York Times, Arline Bronzaft, an environmental psychologist, said that learning to live with noise causes a toll on ones body. Aside from hearing impairment, noise also has affects such as hypertension, sleep deprivation, and cardiovascular complications. Quantifying acoustic energy and mapping it could lead to better research on the impact of noise on health, and help dispel the notion that noise is something people can learn to live with.

Previous efforts to collect sound-related data tried to gather information through a small number of sensors that could could track an expansive area. Park said that this approach was lacking, and that his team has embraced the idea that more sensors would produce greater spatially density, and and greater temporal density.

To facilitate this sort of expansive network, Citygram has developed applications that will turn any computing device with an internet connection and a microphone into a sensor that can collect data on acoustic energy. Park said that leveraging public interest would be necessary to creating the spatially and temporally dense sensor network required to accurately map acoustic energy in large spaces.

In exchange for allowing Citygram to collect data through their phones, users would benefit by gaining access to sound visualizations of their respective area. Park envisions the project as a community effort, where Citygram provides the available technological infrastructures, and urbanites contribute by using their smartphones or laptops.

Park said, We will soon release this technology so that everyone can use it, and become an active participant in mapping our urban noisescapes.

One potential hesitation that users may have is the issue of privacy.

Park said, “I think one of the difficulties is the current perception of technologies that are already part of the urban environment, such as cameras. We need to find ways to address concerns that folks may have.

Citygram collects data in the form of feature vectors, which are numerical representations in the field of machine learning, making it is almost impossible to recreate the original sound. The team is also developing a voice blurring approachto obscure human voice signals.

Park said, “I think it is a topic that is still very much sci-fi in a sense, but I think it has great potential.

The Citygram-Sound Project will soon be be showcased at the NoiseGate Festival, which is jointly organized by NYU and the United Nations Global Arts Initiative and supported by NYU’s Global Research Initiatives, Office of the Provost, from September 21st to 25th.