Microsoft Technology Licensing, LLC

Carnegie Mellon University

Karan Ashok Ahuja

Christopher Harrison

Gierad Laput

Mayank Goel

Qiang Wu

Andrew David Wilson

Wei W Wang

Eyal Ofek

Yang Li

Shaunak Chatterjee

Wei Guang Lu

Christian Holz

Mar Gonzalez Franco

Souvik Ghosh

Lokesh Pooranmal Bajaj

Paul Fletcher

Befekadu Ayenew Ejigou

Ningfeng Liang

Wei Deng

Embodiments are provided to recognize features and activities from an audio signal. In one embodiment, a model is generated from sound effect data, which is augmented and projected into an audio domain to form a training dataset efficiently. Sound effect data is data that has been artificially created or from enhanced sounds or sound processes to provide a more accurate baseline of sound data than traditional training data. The sound effect data is augmented to create multiple variants to broaden the sound effect data. The augmented sound effects are projected into various audio domains, such as indoor, outdoor, urban, based on mixing background sounds consistent with these audio domains. The model is installed on any computing device, such as a laptop, smartphone, or other device. Features and activities from an audio signal are then recognized by the computing device based on the model without the need for in-situ training.

System and method for acoustic activity recognition

Examples of the present disclosure describe systems and methods for providing real-time motion styling in virtual reality (VR), augmented reality (AR), and/or mixed reality (MR) environments. In aspects, input data corresponding to user interaction with a VR, an AR, or an MR environment may be received. The input data may be featurized to generate a feature set. The feature set may be compared to a set of stored motion data comprising motion capture data representing one or more motion styles for executing an action or activity. Based on the comparison, the feature set may be matched to feature data for one or more motions styles in the stored motion data. The one or more motions styles may then be executed by a virtual avatar or a virtual object in the VR/AR/MR environment.

Real time styling of motion for virtual environments

In an example, first and second machine learned models corresponding to a particular context of a social networking service are obtained, the first machine learned model trained via a first machine learning algorithm to output an indication of importance of a social networking profile field to obtaining results in the particular context, and the second machine learned model trained via a second machine learning algorithm to output a propensity of the user to edit a social networking profile field if requested. One or more missing fields in a social networking profile for the user are identified. For each of one or more of the one or more missing fields, the field and an identification of the user are passed through the first and second machine learned models, and outputs of the first and second machine learned models are combined to identify one or more top missing profile fields.

Machine learned models for contextual editing of social networking profiles

Growing community of inventors

Palo Alto, CA, United States of America

Karan Ashok Ahuja