A survey of deep learning for polyphonic sound event detection

Deep learning has achieved state of the art in various machine learning problems, such as computer vision, speech recognition, and natural language processing. Sound event detection (SED), which is about recognizing audio events in real-life environments, has attracted a lot of attention recently. Many works have been successful when applying deep learning techniques for the SED problem as can be seen in Detection and Classification of Acoustic Scenes and Events (DCASE) challenge 2016–2017. In this paper, we present a review of the SED problem and discuss different deep learning approaches for the problem.