Attention-based convolutional neural network and long short-term memory for short-term detection of mood disorders based on elicited speech responses

作者：

Highlights：

• Short-term detection of mood disorder based on elicited speech responses.

• Attention-based CNN outputs the emotion profile of each speech response.

• Long-Short Term Memory characterizes the temporal evolution of the emotion profile.

• Attention-based LSTM focuses on the pertinent responses of the entire response.

摘要

•Short-term detection of mood disorder based on elicited speech responses.•Attention-based CNN outputs the emotion profile of each speech response.•Long-Short Term Memory characterizes the temporal evolution of the emotion profile.•Attention-based LSTM focuses on the pertinent responses of the entire response.

论文关键词：Mood disorder detection,Convolutional neural network,Long short-term memory,Attention model

论文评审过程：Received 12 March 2018, Revised 23 November 2018, Accepted 15 December 2018, Available online 17 December 2018, Version of Record 21 December 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.12.016