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.

本文提出使用从多通道音频中提取的低级空间特征进行声音事件检测，通过初始阶段从每个通道中单独学习这些多通道特征，扩展了卷积递归神经网络以处理更多类型的这些特征，并表明将特征呈现为体积的单独层，而不是将每个通道的特征串联成单个特征向量，可以更好地学习多通道音频中的声音事件。与单声道特征相比，在相同网络上使用所提出的空间特征，在公开可用的 TUT-SED 2016 数据集上的 F-score 提高了 6.1％，在 TUT-SED 2009 数据集上的 F-score 提高了 2.7％，该数据集是其 15 倍大。