Depression Severity Level Classification Using Multitask Learning of Gender Recognition

Speech based classification of depression has been widely used. However, most classification studies focus on binary classification to distinguish depressed subjects from non-depressed subjects. In this paper, we describe the depression classification task as a severity classification problem to provide finer grained classification results. we formulate the Attention deep learning network for Speech Depression Recognition (SDR) using the Mel-frequency cepstral coefficient (MFCC) features as the input. The attention along with the convolutional neural network and the bidirectional long short-term memory network (CNN-BLSTM) embedding jointly attends to information from different representations of the same MFCC input sequence. The CNN-LSTM embedding helps in attending to the dominant depression features by identifying positions of the features in the sequence. In addition to Attention and CNN-LSTM embedding, we apply multi-task learning with gender recognition as an auxiliary task. The auxiliary task helps in learning the gender-specific features that influence the depression characteristics in speech and results in improved accuracy of Speech Depression Recognition, the primary task. We conducted all our experiments on Depression dataset. We can achieve an overall F1sorce of 81.5% and average class accuracy of 89.3%, on SDR for depression classes.