Speech Emotion Dataset for Depression Monitoring

This dataset contains speech recordings collected for depression monitoring and speech emotion recognition research. The dataset consists of audio samples representing different emotional states related to mental health conditions. The recordings were manually collected and organized to support machine learning and deep learning research in depression detection using speech signals. The dataset can be used for developing and evaluating models such as LSTM, GRU, BiLSTM, and other neural network architectures. The dataset is suitable for tasks including speech emotion recognition, mental health analysis, and depression detection. It can also be used for research involving cross-corpus learning, federated learning, and semi-supervised or unsupervised learning methods. All audio files are organized into structured folders based on emotional categories and are provided in a compressed ZIP format for easy download and usage.