Mental-Perceiver: Audio-Textual Multimodal Learning for Mental Health Assessment

Mental disorders, such as anxiety and depression, have become a global issue that affects the regular lives of people across different ages. Without proper detection and treatment, anxiety and depression can hinder the sufferer's study, work, and daily life. Fortunately, recent advancements of digital and AI technologies provide new opportunities for better mental health care and many efforts have been made in developing automatic anxiety and depression assessment techniques. However, this field still lacks a publicly available large-scale dataset that can facilitate the development and evaluation of AI-based techniques. To address this limitation, we have constructed a new large-scale \textbf{M}ulti-\textbf{M}odal \textbf{Psy}chological assessment corpus (MMPsy) on anxiety and depression assessment of Mandarin-speaking adolescents. The MMPsy contains audios and extracted transcripts of responses from automated anxiety or depression assessment interviews along with the self-reported anxiety or depression evaluations of the participants using standard mental health assessment questionnaires. Our dataset contains over 7,700 post-processed recordings of interviews for anxiety assessment and over 4,200 recordings for depression assessment. Using this dataset, we have developed a novel deep-learning based mental disorder estimation model, named \textbf{Mental-Perceiver}, to detect anxious/depressive mental states from recorded audio and transcript data. Extensive experiments on our MMPsy and the commonly-used DAIC-WOZ datasets have shown the effectiveness and superiority of our proposed Mental-Perceiver model in anxiety and depression detection. The MMPsy dataset will be made publicly available later to facilitate the research and development of AI-based techniques in the mental health care field.