Yang Z Zhang, 525 Picardy Ln, Dover, MA 02030

2022039, Dec 8, 2022

Jun 3, 2021

17/337518

- Armonk NY, US
Yang Zhang - Cambridge MA, US
Shiyu Chang - Elmsford NY, US
Jinjun Xiong - Goldens Bridge NY, US
Chuang Gan - Cambridge MA, US
David Cox - Somerville MA, US

G10L 13/10
G06N 20/00
G10L 21/013
G10L 17/04
G10L 25/63

A computer-implemented method is provided of using a machine learning model for disentanglement of prosody in spoken natural language. The method includes encoding, by a computing device, the spoken natural language to produce content code. The method further includes resampling, by the computing device without text transcriptions, the content code to obscure the prosody by applying an unsupervised technique to the machine learning model to generate prosody-obscured content code. The method additionally includes decoding, by the computing device, the prosody-obscured content code to synthesize speech indirectly based upon the content code.

2022023, Jul 28, 2022

Jan 25, 2021

17/157832

- San Francisco CA, US
Yang Zhang - Arlington MA, US

G06N 5/04
G06K 9/62
G06N 20/00

Methods, systems, and devices for data processing are described. According to the techniques described herein, a sequential model may be trained using data of different modalities to be used for event recommendation or prediction for an entity or attendee of a future event. Encoders may be used to encode entity data and event data of different data types, and the encoded data may be used to generate vectors for input to a multimodal Transformer. A segment mask may be generated for each of a set of vectors corresponding to the entity and a set of vectors corresponding to an event sequence associated with the entity. The segment masks and sets of vectors may be used to generate embeddings to train the sequential model.

2022018, Jun 9, 2022

Dec 3, 2020

17/110629

- Armonk NY, US
Yang ZHANG - Cambridge MA, US
Shiyu CHANG - Elmsford NY, US

G06N 3/08
G06N 3/04

Techniques for generator model training are provided. A classifier model that was trained using one or more data samples in a target class is received, and a generative adversarial network (GAN) is trained to generate simulated data samples for the target class, comprising: generating a first simulated data sample using a generator model, computing a first discriminator loss by processing the first simulated data sample using a discriminator model, computing a classifier loss by processing the first simulated data sample using the classifier model, and refining the generator model based on the first discriminator loss and the classifier loss.

2023004, Feb 9, 2023

Oct 20, 2022

17/969848

- Armonk NY, US
Yang ZHANG - Cambridge MA, US

G06V 20/40
G06N 3/04
G06N 3/08

A method (and structure and computer product) for an audiovisual source separation processing, including receiving video data including images of a plurality of sound sources, receiving an optical flow data of the video data, the optical flow data indicating motions of pixels between frames of the video data, and encoding the received video data into video localization data comprising information associating pixels in the frames of video data with different channels of sound.

2021032, Oct 21, 2021

Apr 20, 2020

16/852617

- ARMONK NY, US
Yang Zhang - Cambridge MA, US
Shiyu Chang - Elmsford NY, US
Chuang Gan - Cambridge MA, US
David Cox - Somerville MA, US

G10L 25/90

A method, a structure, and a computer system for decomposing speech. The exemplary embodiments may include one or more encoders for generating one or more encodings of a speech input comprising rhythm information, pitch information, timbre information, and content information, and a decoder for decoding the one or more encodings.

2021031, Oct 14, 2021

Apr 12, 2020

16/846338

- San Francisco CA, US
Yang ZHANG - Cambridge MA, US

salesforce.com, inc. - San Francisco CA

G06F 40/274
G06N 3/08
G06F 40/30

There is provided a computer implemented method of context based autocomplete of text, comprising: receiving input text, feeding the input text into a context-prediction component of a machine learning model that predicts a certain context of a plurality of contexts, selecting a certain context-specific component of the machine learning model from a plurality of context-specific components according to the certain context, feeding the input text into the selected context-specific component that outputs autocomplete text, and providing the autocomplete text.

2021025, Aug 19, 2021

Feb 15, 2020

16/792208

- Armonk NY, US
Sijia LIU - Somerville MA, US
Subhro DAS - Cambridge MA, US
Yang ZHANG - Cambridge MA, US

G06F 16/783
G06N 3/04
G06F 16/75
G06K 9/00
G06K 9/62

Method and apparatus that includes receiving a query describing an aspect in a video, the video including a plurality of frames, identifying multiple proposals that potentially correspond to the query where each of the proposals includes a subset of the plurality of frames, ranking the proposals using a graph convolution network that identifies relationships between the proposals, and selecting, based on the ranking, one of the proposals as a video segment that correlates to the query.

2021013, May 6, 2021

Nov 5, 2019

16/674402

- ARMONK NY, US
Yang Zhang - Cambridge MA, US
Xiaoxiao Guo - Mountain View CA, US

G06F 16/73
G06F 16/901
G06F 16/783
G06N 20/00

A method, system, and program product for generating and modifying a video response is provided. The method includes receiving an audio/video file. Parsed video features of the audio/video file are generated with respect to a first graph. Parsed audio features of the audio/video file are generated with respect to a second graph. The first graph is placed overlaying the second graph and at least one intersection point between the first graph and the second graph is determined. A natural language query is executed with respect to the audio/video file and a parsed query entity is generated from the natural language query. The parsed query entity is analyzed with respect to the intersection point and a node of the intersection point comprising similar features is determined with respect to the parsed query entity. A resulting natural language response with respect to the natural language query is generated.