음성신호를 이용한 딥러닝 기반 우울증 진단 연구 동향 분석

다국어 초록 (Multilingual Abstract)

Depression is a common mental illness in modern society, and research on technologies that depression diagnosis using artificial intelligence has actively proceeded recently. In this paper, of the many artificial intelligence technologies, we analyze research trends on techniques for diagnosing depression based on deep learning models using speech signals. Specifically, deep learning models are presented such as CNN(Convolutional Neural Networks) and LSTM(Long-Short Term Memory), and methods for applying speech signals to deep learning models. Also, databases are described such as DAIC-WOZ(Distress Analysis Interview Corpus) database and AVEC2013(Audio-Visual Emotion recognition Challenge) depression database used for speech signal-based depression diagnosis.