Hypernetworks for sound event detection: a proof-of-concept

Polyphonic sound event detection (SED) involves the prediction of sound events present in an audio recording along with their onset and offset times. Recently, Deep Neural Networks, specifically convolutional recurrent neural networks (CRNN) have achieved impressive results for this task. The convolution part of the architecture is used to extract translational invariant features from the input and the recurrent part learns the underlying temporal relationship between audio frames. Recent studies showed that the weight sharing paradigm of recurrent networks might be a hindering factor in certain kinds of time series data, specifically where there is a temporal conditional shift, i.e. the conditional distribution of a label changes across the temporal scale. This warrants a relevant question - is there a similar phenomenon in polyphonic sound events due to dynamic polyphony level across the temporal axis? In this work, we explore this question and inquire if relaxed weight sharing improves performance of a CRNN for polyphonic SED. We propose to use hypernetworks to relax weight sharing in the recurrent part and show that the CRNN’s performance is improved by ~3% across two datasets, thus paving the way for further exploration of the existence of temporal conditional shift for polyphonic SED