Abstract: A multi-task deep learning network and a generation method thereof are provided. The generation method of a multi-task deep learning network includes: building at least one shared layer, where the shared layer is configured to receive a plurality of pieces of input information and generate a plurality of pieces of processed feature information; building a plurality of groups of task-specific layers, wherein the groups of task-specific layers compute and generate a plurality of groups of output information corresponding to a plurality of different tasks according to the pieces of processed feature information; and activating at least one of the groups of task-specific layers in stages according to a power supply state of an electronic apparatus.

Abstract: A semantic recognition method and a semantic recognition device are provided. A spectrogram of a speech signal is generated. At least one keyword of the spectrogram is detected by inputting the spectrogram into a neural network model. A semantic category to which each of the at least one keyword belongs is distinguished. A semantic intention of the speech signal is determined according to the at least one keyword and the semantic category of the at least one keyword.

Abstract: A semantic recognition method and a semantic recognition device are provided. A spectrogram of a speech signal is generated. At least one keyword of the spectrogram is detected by inputting the spectrogram into a neural network model. A semantic category to which each of the at least one keyword belongs is distinguished. A semantic intention of the speech signal is determined according to the at least one keyword and the semantic category of the at least one keyword.

Abstract: An object recognition method and system thereof are provided. A recognition result of a first object of a (i?1)th frame of a video stream is obtained. A ith frame is received, and a second object is detected from the ith frame. Whether the first object and the second object are corresponding to the same target object is determined according to a position of the first object in the (i?1)th frame and a position of the second object in the ith frame. If the first object and the second object are corresponding to the same target object, whether a recognition confidence level is greater than a predetermined threshold is determined so as to perform the object recognition on the second object or assign the recognition result of the first object to the second object.

Abstract: An object recognition method and system thereof are provided. A recognition result of a first object of a (i?1)th frame of a video stream is obtained. A ith frame is received, and a second object is detected from the ith frame. Whether the first object and the second object are corresponding to the same target object is determined according to a position of the first object in the (i?1)th frame and a position of the second object in the ith frame. If the first object and the second object are corresponding to the same target object, whether a recognition confidence level is greater than a predetermined threshold is determined so as to perform the object recognition on the second object or assign the recognition result of the first object to the second object.