关键词: 跨库语音情感识别, 卷积神经网络, 决策边界优化, 域自适应, 特征分布差异

Abstract: Domain adaptation algorithms are widely used for cross-corpus speech emotion recognition. However, many domain adaptation algorithms lose the discrimination of target domain samples while pursuing the minimization of domain discrepancy, resulting in their presence at the decision boundary of the model in a dense form, which degrades the performance of the model. Based on the above problem, a decision boundary optimized domain adaptation (DBODA) based cross-corpus speech emotion recognition method is proposed. The features are firstly processed using convolutional neural networks, and then fed into the maximize n-norm and mean discrepancy (MNMD) module to maximize the nuclear-norm of the sentiment prediction probability matrix of the target domain while reducing the inter-domain discrepancy to enhance the discrimination of the target domain samples and optimize the decision boundary. In six sets of cross-corpus experiments set up with Berlin, eNTERFACE, and CASIA speech datasets, the average recognition accuracy of the proposed method is 1.28%~11.01% ahead of other algorithms, indicating that the model effectively reduces the sample density around the decision boundary and improves the prediction accuracy.

Key words: cross-corpus speech emotion recognition, convolutional neural network, decision boundary optimization, domain adaptation, feature distribution discrepancy