The invention provides a multi-modal depression detection method and system based on context awareness. The method comprises the steps of constructing a training sample set, wherein the training sample set comprises topic information, a speech spectrum and corresponding text information; by using a convolutional neural network, in combination with multi-task learning, performing acoustic feature extraction on the speech spectrum of the training sample set to obtain acoustic features with context awareness; by utilizing the training sample set, processing word embedding by using a Transformer model, and extracting text features with context awareness; establishing an acoustic channel subsystem which performs depression detection for the acoustic features with context awareness, and establishing a text channel subsystem which performs depression detection for the text features with context awareness; and fusing outputs of the acoustic channel subsystem and the text channel subsystem to obtain depression classification information. The depression detection accuracy can be improved.