Detecting Depression from Speech through an Attentive LSTM Network

Yan Zhao, Yue Xie, Ruiyu LIANG, Li Zhang, Li Zhao, Chengyu Liu

Research output: Contribution to journalArticlepeer-review

2 Downloads (Pure)

Abstract

Depression endangers people’s health conditions and afffects the social order as a mental disorder. As an efficient diagnosis of depression, automatic depression detection has attracted lots of researcher’s interest. This study presents an attention-based Long Short-Term Memory (LSTM) model for depression detection to make full use of the difference between depression and non-depression between timeframes. The proposed model uses frame-level features, which capture the temporal information of depressive speech, to replace traditional statistical features as an input of the LSTM layers. To achieve more multi-dimensional deep feature representations, the LSTM output is then passed on attention layers on both time and feature dimensions. Then, we concat the output of the attention layers and put the fused feature representation into the fully connected layer. At last, the fully connected layer’s output is passed on to softmax layer. Experiments conducted on the DAIC-WOZ database demonstrate
that the proposed attentive LSTM model achieves an average accuracy rate of 90.2% and outperforms the traditional LSTM network and LSTM with local attention by 0.7% and 2.3%, respectively, which indicates its feasibility.
Original languageEnglish
Pages (from-to)2019-2023
Number of pages5
JournalIEICE Transactions on Information and Systems
VolumeE104.D
Issue number11
DOIs
Publication statusPublished - 1 Nov 2021

Cite this