论文标题
用图神经网络的表示形式学习以识别语音情感
Representation Learning with Graph Neural Networks for Speech Emotion Recognition
论文作者
论文摘要
学习表现力的表现对于深度学习至关重要。在言语情感识别（SER），真空区域或言语中的噪音干扰表达性的表达学习。但是，传统的基于RNN的模型容易受到这种噪音的影响。最近，图神经网络（GNN）证明了其在表示学习方面的有效性，我们为SER采用了此框架。特别是，我们提出了一个基于余弦相似性的图作为SER中表示的理想图形结构。我们提出了一个基于余弦的图形卷积网络（COGCN），该网络对扰动和噪声是可靠的。实验结果表明，我们的方法的表现优于最先进的方法或提供竞争性结果，仅使用1/30个参数降低模型大小。
Learning expressive representation is crucial in deep learning. In speech emotion recognition (SER), vacuum regions or noises in the speech interfere with expressive representation learning. However, traditional RNN-based models are susceptible to such noise. Recently, Graph Neural Network (GNN) has demonstrated its effectiveness for representation learning, and we adopt this framework for SER. In particular, we propose a cosine similarity-based graph as an ideal graph structure for representation learning in SER. We present a Cosine similarity-based Graph Convolutional Network (CoGCN) that is robust to perturbation and noise. Experimental results show that our method outperforms state-of-the-art methods or provides competitive results with a significant model size reduction with only 1/30 parameters.
