**Sound Event Detection** (SED) is the task of recognizing the sound events and their respective temporal start and end time in a recording. Sound events in real life do not always occur in isolation, but tend to considerably overlap with each other. Recognizing such overlapping sound events...
Proposed a CRNN for joint sound event localization and detection, taking a seq of consecutive spectrogram time-frames as input and maps it to two outputs in parallel. The usage of such non-method-specific feature (phase and magnitude spectrogram) makes the method generic and easily extendable to...