Amazon Technologies, Inc.

Vivek Yadav

Pradeep Natarajan

Kiana Hajebi

Yue Wu

Ayush Jaiswal

Aayush Gupta

Premkumar Natarajan

Karthik Ramakrishnan

Rajiv Reddy

Rahul Kamalkishore Agrawal

Mahesh Dhabade

Abhijit Chaudhuri

Visakh Sakthidharan Nair

Gourav Datta

Prateek Singhal

Jianwei Feng

Saravana Perumal

Nagaprasad K P

Pankaj Chawla

Devices and techniques are generally described for inference reduction in natural language processing using semantic similarity-based caching. In various examples, first automatic speech recognition (ASR) data representing a first natural language input may be determined. A cache may be searched using the first ASR data. A first skill associated with the first ASR data may be determined from the cache. In some examples, first intent data representing a semantic interpretation of the first natural language input data may be determined by using a first natural language process associated with the first skill.

Natural language processing

A system configured to perform style-aware listener animation. By representing different listening styles (e.g., facial expressions) using an embedding space, a single model can be trained to generate unique facial animations for a number of distinct listeners. Thus, individual listening styles can be associated with a listener identifier, enabling the system to (i) animate a plurality of different listeners with unique nonverbal behavior and/or (ii) select a particular listener identifier or desired type of listener style with which to animate. This enables the model to be generalized to new listeners to generate additional listener facial responses without needing training data for each new listener. The model may process a listener representation style or listener identifier, along with input data corresponding to a speaker talking, to generate unique facial animation responsive to the speech.

Listener animation

Techniques for masking images based on a particular task are described. A system masks portions of an image that are not relevant to a particular task, thus, reducing the amount of data used by applications for image processing tasks. For example, images to be processed using a hair color classification model are masked so that only portions that show the person's hair are available for the model to analyze. The system configures different masker components to mask images for different tasks. A masker component can be implemented at a user device to mask images prior to sending to an application/task-specific model.

Task-based image masking

A write lock request for a data object on behalf of a first data accessor is received at a lock manager. The data object is currently locked on behalf of a second data accessor. The lock manager modifies lock metadata associated with the data object to indicate the first data accessor as the primary lock owner, and designates the second data accessor as a non-primary owner.

Customizable lock management for distributed resources

Devices and techniques are generally described for three dimensional mesh generation. In various examples, first two-dimensional (2D) image data representing a human may be received. In various further examples, bounding box data identifying a location of the human in the first 2D image data and joint data identifying locations of joints of the human may be received. Second 2D image data representing a cropped portion of the human may be generated using the bounding box data and the joint data. A three-dimensional (3D) mesh prediction model may be used to determine a pose, a shape, and a projection matrix for the human. The 3D mesh prediction model may be used to determine a transformed projection matrix for the portion of the human represented in the second 2D image data.

Three-dimensional mesh generation

Growing community of inventors

Issaquah, WA, United States of America

Vivek Yadav