Realtek Semiconductor Inc.

Chia-Chun Cheng

Ching-Lung Chen

Yen-Hsun Chu

Tai-Shih Chi

Yih-Liang Shen

Ya-Ching Lai

The present invention provides a SoC including a recognition circuit and a processing circuit. The recognition circuit is configured to obtain image data from an image capturing device, and perform a recognition operation on the image data to generate a recognition result. The processing circuit is coupled to the recognition circuit, and is configured to determine a ROI in the image data according to the recognition result, perform image enhancement operation on the ROI to generate an enhanced region, and combine the enhanced region with the image data to generate processed image data.

Video processing method and associated system on chip

The present invention provides a training method of a neural network model, wherein the training method includes the steps of: receiving image data including a plurality of frames, and for first frames in the frames, the image data further includes detection data, and the detection data includes position of at least one person within the corresponding first frame; and for second frames in the frames, the image data further includes person search data, and the person search data includes position and serial number of at least one person within the corresponding second frame; using the neural network model to perform a person recognition operation on the frames to generate a recognition result; and using loss functions to process the recognition result of each frame, the detection result of each first frame and the person search data of each second frame, for adjusting parameters of the neural network model.

Training method of neural network model and associated device

The audio processing method may include: utilizing a first convolution layer circuit and a second convolution layer circuit to perform convolution processing on an audio mixture signal, respectively, in order to generate an input feature map; performing separation processing corresponding to a predetermined neural network model on the input feature map to obtain a first output feature map and a second output feature map respectively corresponding to a first type and a second type; and utilizing a first deconvolution layer circuit and a second deconvolution layer circuit to perform deconvolution processing on different portions of the first output feature map, respectively, and utilizing the first deconvolution layer circuit and the second deconvolution layer circuit to perform deconvolution processing on different portions of the second output feature map, respectively, in order to generate corresponding processing results, for generating multiple audio output signals.

Growing community of inventors

Hsinchu, Taiwan

Chia-Chun Cheng