AUTHOR=Wang Hongbo , Liu Yu , Zhen Xiaoxiao , Tu Xuyan 

TITLE=Depression Speech Recognition With a Three-Dimensional Convolutional Network

JOURNAL=Frontiers in Human Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2021.713823

DOI=10.3389/fnhum.2021.713823

ISSN=1662-5161

ABSTRACT=Depression has become one of the main reasons that threaten people's mental health. However, the current traditional diagnosis methods have certain limitations, so it is necessary to find a method of objective evaluation of depression based on intelligent technology to assist the early diagnosis and treatment of patients. Because the abnormal speech features of patients with depression are related to their mental state to some extent, it is valuable to use speech acoustic features as objective indicators for the diagnosis of depression. In order to solve the problem of the complexity of speech in depression and the limited performance of traditional feature extraction methods for speech signal, this article suggests a Three Dimensional Convolutional filter banks with Highway Networks and Bidirectional GRU (Gated Recurrent Unit) with Attention mechanism (in short 3D-CBHGA), which includes two key strategies. (1) The three-dimensional feature extraction of the speech signal can timely realize expression ability of those depression signal. (2) Based on attention mechanism to GRU network, the frame-level vector is weighted to get the emotion hidden vector by self-learning. Experiments show that the proposed 3D-CBHGA can well establish the mapping from speech signals to depression-related features and improve the accuracy of depression detection in speech signals.