Domain adversarial learning for emotion recognition
This work addresses the domain adaptation challenge in emotion recognition for practical applications where training and testing speakers differ, representing an incremental advance.
The paper tackled the problem of speaker mismatch in emotion recognition by using a domain adversarial neural network to extract emotion-related features while ignoring speaker identity differences, achieving a 3.48% absolute improvement over state-of-the-art methods on the IEMOCAP database.
In practical applications for emotion recognition, users do not always exist in the training corpus. The mismatch between training speakers and testing speakers affects the performance of the trained model. To deal with this problem, we need our model to focus on emotion-related information, while ignoring the difference between speaker identities. In this paper, we look into the use of the domain adversarial neural network (DANN) to extract a common representation between different speakers. The primary task is to predict emotion labels. The secondary task is to learn a common representation where speaker identities can not be distinguished. By using the gradient reversal layer, the gradients coming from the secondary task are used to bring the representations for different speakers closer. To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results demonstrate that the proposed framework shows an absolute improvement of 3.48% over state-of-the-art strategies.