New Tools & Data for Soundscape Synthesis and Online Audio Annotation

We’re glad to announce the release of two open-source tools and a new dataset developed as part of the SONYC project we hope will be of use to the community:  Scaper: a library for soundscape synthesis and augmentation Automatically synthesize soundscapes with corresponding ground truth annotations  Useful for running controlled ML experiments (ASR, sound event detection, bioacoustic…

Read more

SONYC featured in Daily Mail, La Croix, AFP, and more

After an interview with Agence France-Presse (AFP), SONYC was featured in news outlets around the world. In the interview, SONYC P.I. Juan Pablo Bello discusses the problem of urban noise pollution, SONYC’s innovative solution, and how SONYC’s approach could be applied in cities around the world that suffer from noise pollution. Watch a video here (in…

Read more

New publication: Deep Convolutional Neural Networks and Data Augmentation For Environmental Sound Classification

Our paper “Deep Convolutional Neural Networks and Data Augmentation For Environmental Sound Classification” has been accepted for publication in IEEE Signal Processing Letters. The ability of deep convolutional neural networks (CNN) to learn discriminative spectro-temporal patterns makes them well suited to environmental sound classification. However, the relative scarcity of labeled data has impeded the exploitation of this family…

Read more

SONYC is hiring!

SONYC is hiring! Interested in cutting-edge research in cyber-physical systems, urban informatics, data science, machine listening, citizen science, digital media or the internet of things? Are you skilled, self-motivated and able to successfully work in teams? are you interested in doing work that can contribute to addressing one of the most important quality-of-life issues for…

Read more