Patents by Inventor Xiaozheng HUANG

Xiaozheng HUANG has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11935517
    Abstract: A speech decoding method is performed by a computer device, the speech including a current audio frame and a previous audio frame. The method includes: obtaining a target token corresponding to a smallest decoding score from a first token list including first tokens obtained by decoding the previous audio frame, each first token including a state pair and a decoding score, the state pair being used for characterizing a correspondence between a first state of the first token in a first decoding network corresponding to a low-order language model and a second state of the first token in a second decoding network corresponding to a differential language model; determining pruning parameters according to the target token and an acoustic vector of the current audio frame when the current audio frame is decoded; and decoding the current audio frame according to the first token list, the pruning parameters, and the acoustic vector.
    Type: Grant
    Filed: March 3, 2021
    Date of Patent: March 19, 2024
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Yiheng Huang, Xiaozheng Jian, Liqiang He
  • Publication number: 20220222831
    Abstract: A method for processing images includes: acquiring at least one first video image in a video to be processed; determining a first target region of the at least one first video image by performing region recognition on the at least one first video image; and determining, based on the first target region of the at least one first video image, a second target region of at least one second video image in the video to be processed other than the first video images, wherein the second video image is associated with the first video image.
    Type: Application
    Filed: March 28, 2022
    Publication date: July 14, 2022
    Inventors: Xiaozheng HUANG, Yunfei ZHENG, Xing WEN
  • Publication number: 20220191574
    Abstract: A method for uploading video, executed by a client and including: determining encoding complexity of a target video; determining a target encoding parameter corresponding to difference information based on the difference information between the encoding complexity and a complexity threshold; and encoding the target video based on the target encoding parameter and uploading an encoded target video to a server.
    Type: Application
    Filed: March 2, 2022
    Publication date: June 16, 2022
    Inventors: Xing WEN, Yunfei ZHENG, Bing YU, Xiaonan WANG, Min CHEN, Yue HUANG, Yucong CHEN, Xiaozheng HUANG, Mingfei ZHAO, Lei GUO, Bo HUANG, Jiejun ZHANG, Bin CHEN
  • Patent number: 11012716
    Abstract: A picture file processing method, apparatus, and computer readable medium are provided. The method includes parsing a picture file, to obtain a picture header information data segment, first stream data, and second stream data of a first image thereof. The first stream data of the first image is decoded to generate red-green-blue (RGB) data of the first image. The second stream data of the first image is decoded to generate Alpha data of the first image. Red-green-blue-alpha (RGBA) data corresponding to the first image are generated according to the RGB data and the Alpha data.
    Type: Grant
    Filed: April 3, 2019
    Date of Patent: May 18, 2021
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LTD
    Inventors: Shitao Wang, Xiaoyu Liu, Jiajun Chen, Xiaozheng Huang, Piao Ding, Haijun Liu, Binji Luo, Xinxing Chen
  • Patent number: 11012489
    Abstract: A picture file processing method is provided. The method includes determining, by a computing device, during a process of encoding transparency data of a picture, transparency input values according to the transparency data of the picture. The method also includes encoding, by the computing device using a video encoder, the transparency input values as data of a preset target channel of the video encoder, to obtain transparency stream data of the picture; and encoding color data of the picture, to obtain color stream data of the picture. The method also includes outputting, by the computing device, compressed image data of the picture. The compressed image data includes the transparency stream data of the picture and the color stream data of the picture.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: May 18, 2021
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Xiaozheng Huang
  • Patent number: 10904542
    Abstract: Embodiments of this application disclose an image transcoding method performed at a computing device. The image transcoding method includes: obtaining a source image quality parameter of a source image, the source image being a to-be-transcoded image, and the source image quality parameter being associated with a source image format and used for indicating image quality of the source image; obtaining, according to the source image quality parameter and a preset mapping relationship, a target image quality parameter that is associated with a target image format and that corresponds to the source image quality parameter of the source image; and transcoding the source image in the source image format according to the target image quality parameter to obtain a target image in the target image format.
    Type: Grant
    Filed: July 8, 2019
    Date of Patent: January 26, 2021
    Assignee: Tencent Technology (Shenzhen) Company Limited
    Inventors: Xiaozheng Huang, Shitao Wang, Binji Luo, Haijun Liu, Piao Ding, Xinxing Chen
  • Publication number: 20200036983
    Abstract: Embodiments of this application disclose an image file processing method performed at a computing device. The method includes: obtaining RGBA data corresponding to a first image in an image file, and separating the RGBA data to obtain RGB data and transparency data of the first image; encoding the RGB data of the first image according to a first video encoding mode, to generate first stream data; encoding the transparency data of the first image according to a second video encoding mode, to generate second stream data; and combining the first stream data and the second stream data into a stream data segment of the image file.
    Type: Application
    Filed: October 7, 2019
    Publication date: January 30, 2020
    Inventors: Shitao WANG, Xiaoyu LIU, Jiajun CHEN, Xiaozheng HUANG, Piao DING, Haijun LIU, Binji LUO, Xinxing CHEN
  • Publication number: 20190335186
    Abstract: Embodiments of this application disclose an image transcoding method performed at a computing device. The image transcoding method includes: obtaining a source image quality parameter of a source image, the source image being a to-be-transcoded image, and the source image quality parameter being associated with a source image format and used for indicating image quality of the source image; obtaining, according to the source image quality parameter and a preset mapping relationship, a target image quality parameter that is associated with a target image format and that corresponds to the source image quality parameter of the source image; and transcoding the source image in the source image format according to the target image quality parameter to obtain a target image in the target image format.
    Type: Application
    Filed: July 8, 2019
    Publication date: October 31, 2019
    Inventors: Xiaozheng HUANG, Shitao WANG, Binji LUO, Haijun LIU, Piao DING, Xinxing CHEN
  • Publication number: 20190230382
    Abstract: A picture file processing method, apparatus, and computer readable medium are provided. The method includes parsing a picture file, to obtain a picture header information data segment, first stream data, and second stream data of a first image thereof. The first stream data of the first image is decoded to generate red-green-blue (RGB) data of the first image. The second stream data of the first image is decoded to generate Alpha data of the first image. Red-green-blue-alpha (RGBA) data corresponding to the first image are generated according to the RGB data and the Alpha data.
    Type: Application
    Filed: April 3, 2019
    Publication date: July 25, 2019
    Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Shitao WANG, Xiaoyu LIU, Jiajun CHEN, Xiaozheng HUANG, Piao DING, Haijun LIU, Binji LUO, Xinxing CHEN
  • Publication number: 20190222623
    Abstract: A picture file processing method is provided. The method includes determining, by a computing device, during a process of encoding transparency data of a picture, transparency input values according to the transparency data of the picture. The method also includes encoding, by the computing device using a video encoder, the transparency input values as data of a preset target channel of the video encoder, to obtain transparency stream data of the picture; and encoding color data of the picture, to obtain color stream data of the picture. The method also includes outputting, by the computing device, compressed image data of the picture. The compressed image data includes the transparency stream data of the picture and the color stream data of the picture.
    Type: Application
    Filed: March 22, 2019
    Publication date: July 18, 2019
    Inventor: Xiaozheng HUANG