Abstract: An audio capture method includes: determining one or more regions of interest (ROIs) pertaining to an image sequence or a video stream; determining position information of the one or more ROIs; converting the position information of the one or more ROIs into direction information of the one or more ROIs; and performing a beamforming processing on a plurality of microphone signals to generate an audio capture signal based on direction information of the one or more ROIs and direction information of one or more sound sources that are captured in the plurality of microphone signals.

Abstract: The image detecting apparatus including an image capturing device, a microphone array and a processing circuit is provided. The image capturing device captures an image. The microphone array detects a voice source. The processing circuit performs a voice activity detection on a first number of voice signals captured by the microphone devices to determine whether the voice source is a preset type voice. The processing circuit performs a beamforming operation on a second number of voice signals captured by the microphone devices to generate a region of interest (ROI) setting signal when the voice source is the preset type voice. The ROI setting signal indicates a location of the voice source in the image. The processing circuit performs an image detecting operation on a ROI image. The ROI image is determined according to the image and the ROI setting signal. The first number is smaller than the second number.

Abstract: A backlight control device for use in an electronic device includes a motion detecting unit, a sound matching unit and a controller. The motion detecting unit is configured to detect motion of a lid section of the electronic device to generate motion data. The sound matching unit is configured to match a soundprint derived from a sound sample that is captured by a sound capture unit, to one or more sound patterns stored within in a sound pattern database to generate a lid state indication signal if the motion data indicates the motion of the lid section corresponds to a predetermined state. The controller is configured to control a backlight module of a display device of the electronic device according to the lid state indication signal.

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.

Abstract: The present invention provides a power control device and a power control method applied to a computer system. The power control device includes a data processing unit, a throughput determining module, and a clock control unit. The data processing unit is utilized for processing and outputting data according to an adjustable clock rate. The throughput determining module is coupled to the data processing unit, and utilized for obtaining an indication value corresponding to a data output rate of the data processing unit and comparing the indication value with at least a predetermined threshold value to generate a comparing result. The clock control unit is coupled between the throughput determining module and the data processing unit, and utilized for adjusting the adjustable clock rate of the data processing unit according to the comparing result.

Abstract: The present invention provides a power control device and a power control method applied to a computer system. The power control device includes a data processing unit, a throughput determining module, and a clock control unit. The data processing unit is utilized for processing and outputting data according to an adjustable clock rate. The throughput determining module is coupled to the data processing unit, and utilized for obtaining an indication value corresponding to a data output rate of the data processing unit and comparing the indication value with at least a predetermined threshold value to generate a comparing result. The clock control unit is coupled between the throughput determining module and the data processing unit, and utilized for adjusting the adjustable clock rate of the data processing unit according to the comparing result.