We present a graph convolutional network with 2D pose estimation for the first time on child action recognition task achieving on par results with an RGB modality based model on a novel benchmark dataset containing unconstrained environment based videos.

This paper presents an implementation on child activity recognition (CAR) with a graph convolution network (GCN) based deep learning model since prior implementations in this domain have been dominated by CNN, LSTM and other methods despite the superior performance of GCN. To the best of our knowledge, we are the first to use a GCN model in child activity recognition domain. In overcoming the challenges of having small size publicly available child action datasets, several learning methods such as feature extraction, fine-tuning and curriculum learning were implemented to improve the model performance. Inspired by the contradicting claims made on the use of transfer learning in CAR, we conducted a detailed implementation and analysis on transfer learning together with a study on negative transfer learning effect on CAR as it hasn't been addressed previously. As the principal contribution, we were able to develop a ST-GCN based CAR model which, despite the small size of the dataset, obtained around 50% accuracy on vanilla implementations. With feature extraction and fine-tuning methods, accuracy was improved by 20%-30% with the highest accuracy being 82.24%. Furthermore, the results provided on activity datasets empirically demonstrate that with careful selection of pre-train model datasets through methods such as curriculum learning could enhance the accuracy levels. Finally, we provide preliminary evidence on possible frame rate effect on the accuracy of CAR models, a direction future research can explore.

本文提出了一种单通道语音增强方法，以减少低信噪比（SNR）水平和非平稳噪声条件下的噪声并增强语音。具体而言，我们专注于使用高斯混合模型（GMM）基于具有参数Wiener滤波器的多阶段过程来建模噪声。提出的噪声模型估计了更准确的噪声功率频谱密度（PSD），并且与传统的Wiener滤波方法相比，在各种噪声条件下可以更好地概括。模拟表明，所提出的方法可以在低SNR级别的语音质量（PESQ）和清晰度（Stoi）方面取得更好的性能。