Zoom Video Communications, Inc. patent applications on December 19th, 2024
Patent Applications by Zoom Video Communications, Inc. on December 19th, 2024
Zoom Video Communications, Inc.: 5 patent applications
Zoom Video Communications, Inc. has applied for patents in the areas of G06F3/16 (1), G06F40/40 (1), G06F40/169 (1), G06F40/58 (1), G06F40/284 (1) G06F3/165 (1), G06F40/40 (1), G06F40/58 (1), H04L51/224 (1), H04N19/119 (1)
With keywords such as: communication, communications, audio, user, video, based, subblocks, client, device, and record in patent application abstracts.
Patent Applications by Zoom Video Communications, Inc.
Inventor(s): Yuhui CHEN of San Jose CA (US) for zoom video communications, inc., Qiang GAO of Charlotte NC (US) for zoom video communications, inc., Zhaofeng JIA of Saratoga CA (US) for zoom video communications, inc., Shiwei WANG of Hefei (CN) for zoom video communications, inc.
IPC Code(s): G06F3/16
CPC Code(s): G06F3/165
Abstract: techniques for adaptive audio processing during video conferencing are provided. in an example method, a client device joins a video conference hosted by a video conference provider, the video conference including a plurality of client devices. the client device receives, from an audio input device, an audio stream. the client device then processes, using an audio processing component, the audio stream. the client device determines, using a trained machine learning model, one or more characteristics of the audio stream. the client device then determines, based on the one or more characteristics of the audio stream, an audio configuration operation comprising one or more instructions. the client device executes the audio configuration operation. the client device then outputs the audio stream to the video conference provider.
20240419923. DISTILLING LANGUAGE MODELS_simplified_abstract_(zoom video communications, inc.)
Inventor(s): Shamil Chollampatt Muhammed Ashraf of Singapore (SG) for zoom video communications, inc., Sathish Reddy Indurthi of Cupertino CA (US) for zoom video communications, inc., Minh-Quang Pham of Karlsruhe (DE) for zoom video communications, inc., Marco Turchi of Pergine Valsugana (IT) for zoom video communications, inc.
IPC Code(s): G06F40/40, G06F40/169
CPC Code(s): G06F40/40
Abstract: one example method includes selecting an entry from a validation set based on similarity to a first communication record, wherein the entry from the validation set includes a second communication record and a corresponding summary of the second communication record; generating a prompt that includes the first communication record, the second communication record, and the corresponding summary of the second communication record; inputting the prompt to a first language model to obtain a generated summary of the first communication record; and training a second language model based on the first communication record and the generated summary.
Inventor(s): Ravi Agrawal of San Francisco CA (US) for zoom video communications, inc., Shamil Chollampatt Muhammed Ashraf of Singapore (SG) for zoom video communications, inc., Sathish Reddy Indurthi of Cupertino CA (US) for zoom video communications, inc., Marco Turchi of Pergine Valsugana (IT) for zoom video communications, inc.
IPC Code(s): G06F40/58, G06F40/284
CPC Code(s): G06F40/58
Abstract: systems and methods are disclosed for contrastive learning with adversarial data for robust speech translation. for example, a method may include inputting a speech signal to an automatic speech recognition model to obtain a transcript hypothesis including a first sequence of tokens, wherein the speech signal is associated with a golden transcript including a second sequence of tokens; inputting the first sequence of tokens to an encoder of a neural machine translation model to obtain a first sentence representation; inputting the second sequence of tokens to the encoder of the neural machine translation model to obtain a second sentence representation; determining a contrastive loss function based on the first sentence representation and the second sentence representation; and training the encoder of the neural machine translation model based on the contrastive loss function.
Inventor(s): Jonathan Kwan Hong of Brooklyn NY (US) for zoom video communications, inc., Michael Richard Williams of Brooklyn Park MN (US) for zoom video communications, inc.
IPC Code(s): H04L51/224, H04L51/56
CPC Code(s): H04L51/224
Abstract: a communications monitoring software identifies first communications between a user and other users. the communications monitoring software associates respective communication scores with the first communications based on respective identified communications features of the first communications. with respect to each audio-only communication of the first communications, the identified communications features include at least two of a number of users in the each audio-only communication; whether the user enabled a microphone associated with the user; whether another user in the each audio-only communication enabled a microphone associated with the another user; a total amount of time that the user spoke; or a total amount of time that the another user spoke. the communications monitoring software identifies a subset of second communications based on the respective communication scores associated with the first communications. the subset of the second communications are presented in a user interface to the user.
Inventor(s): Yi Guo of Hangzhou (CN) for zoom video communications, inc., Zhichu He of Hangzhou (CN) for zoom video communications, inc., Rui Li of Hangzhou (CN) for zoom video communications, inc., Bo Ling of Saratoga CA (US) for zoom video communications, inc., Jing Wu of Hangzhou (CN) for zoom video communications, inc., Minxia Yang of Hangzhou (CN) for zoom video communications, inc., YiChen Zhang of Hangzhou (CN) for zoom video communications, inc.
IPC Code(s): H04N19/119, H04N19/176, H04N21/4402, H04N21/4788
CPC Code(s): H04N19/119
Abstract: in one example, a video encoder divides a superblock of a video frame into subblocks. the dividing includes dividing the superblock according to a first and second partitioning schemes to generate a first and second combination of subblocks, respectively. the number of non-zero residuals in each subblock in the first and second combinations of subblocks is less than a corresponding threshold set for a size of the subblock. the encoder determines the subblocks for the superblock as the first combination of subblocks based on a first cost value associated with the first combination of subblocks being lower than a second cost value associated with the second combination of subblocks. the encoder further encodes the superblock into a video bitstream representing the video by encoding the subblocks.
Zoom Video Communications, Inc. patent applications on December 19th, 2024
