Finished! Looks like this project is out of data at the moment!
Help us address one of the biggest quality of life issues facing urban residents. Identify city sounds to train our sensors’ machine listening model that will automatically monitor and mitigate dangerous noise pollution.
Learn moreVolunteers are presented with a series of anonymized 10 second audio recordings made by sensors placed in locations around New York City. We ask you to identify and label all the sounds present, selecting from a list of up to 30 possible classes of sound-source derived from New York City’s Noise Code. We then ask whether each sound was present in the near foreground or background of the soundscape. To help identify these sounds, each recording is accompanied by a spectrogram visualization.
Zooniverse Talk
Chat with the research team and other volunteers!
Sounds of New York City (SONYC) Statistics
View more statsKeep track of the progress you and your fellow volunteers have made on this project.
Every click counts! Join Sounds of New York City (SONYC)'s community to complete this project and help researchers produce important results. Click "View more stats" to see even more stats.
By the numbers
Message from the researcher
Connect with the research team on Talk to learn more about this project!
About Sounds of New York City (SONYC)
In cities such as New York, noise from sources such as construction work and traffic can produce average street level readings of 73dB, well above the EPA’s 55dB health warning figure. SONYC is a project based at New York University in which we are developing a smart cities sensor network with machine listening capabilities to identify and mitigate the sources of this noise pollution. Your contributions labelling different urban sounds will be crucial to our chances of successfully addressing this important public health concern.
Noise pollution is one of the top quality of life issues for urban residents in the United States. For example, it has been estimated that 9 out of 10 adults in New York City are exposed to excessive noise levels, i.e. beyond the limit of what the EPA considers to be harmful. When applied to U.S. cities of more than 4 million inhabitants, such estimates extend to over 72 million citizens. Taking aim at this, we have launched a first-of-its-kind comprehensive research initiative to understand and address noise pollution. The SONYC project leverages the latest in machine learning technology, big data analytics, and citizen science reporting to more effectively monitor, analyze, and mitigate urban noise pollution. Our multi-year project is supported by the National Science Foundation, and has the backing of New York City health and environmental protection agencies.
Our sensors have been placed in locations around New York City gathering anonymized recordings for up to two years. These recordings have provided us a huge amount and variety of audio data. We need your help to identify and label the different sounds in these recordings. We will present you with a series of 10-second segments of urban audio, and ask that you identify the different sounds present in each segment, from a list of up to 30 classes derived from the New York City Noise Code. This will provide ground truth for training data, so that we can effectively operationalize this resource, and tackle one of the biggest quality of life challenges facing urban citizens.