Sound Event Detection Using Spatial Features and Convolutional Recurrent Neural Network
This work addresses sound event detection for audio analysis applications, but it is incremental as it builds on existing neural network methods with spatial feature enhancements.
The paper tackles sound event detection in multichannel audio by proposing low-level spatial features and a modified convolutional recurrent neural network that processes features separately rather than concatenated, resulting in absolute F-score improvements of 6.1% on the TUT-SED 2016 dataset and 2.7% on the TUT-SED 2009 dataset.
This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning from each of them separately in the initial stages. We show that instead of concatenating the features of each channel into a single feature vector the network learns sound events in multichannel audio better when they are presented as separate layers of a volume. Using the proposed spatial features over monaural features on the same network gives an absolute F-score improvement of 6.1% on the publicly available TUT-SED 2016 dataset and 2.7% on the TUT-SED 2009 dataset that is fifteen times larger.