Microsoft Technology Licensing, LLC

Devis Lucato

Umesh Madan

Timothy A Laverty

Prasanna Chromepet Padmanabhan

Shawn Cantin Callegari

Adrian Bonar

Tun-Jan Chuang

Samuel Edward Schillace

Koichi Hirao

Nicholas Becker

Brian Scott Krabach

Ryan H Volum

Mark Karle

Tara Eve Walker

LeRoy F Miller

Mollie Munoz

Nicole E Berdy

Jennifer Fox

Alexander Chao

Abby Harrison

Gina Elizabeth Triolo

Timothy Alan Laverty

The techniques disclosed herein enable systems for spoken natural stylistic conversations with large language models. In contrast to many existing modalities for interacting with large language models that are limited to text, the techniques presented herein enable users to carry a fully spoken conversation with a large language model. This is accomplished by converting a user speech audio input to text and utilizing a prompt engine to analyze a sentiment expressed by the user. A large language model, having been trained on example conversations, by generating a text response as well as a style cue to express emotion in response to the sentiment expressed by speech audio input. A text-to-speech engine can subsequently interpret the text response and style cue to generate an audio output which emulates the sensation of human conversation.

Real-time system for spoken natural stylistic conversations with large language models

Methods, systems, and media for storing entries in and/or retrieving information from an embedding object memory are provided. In some examples, a content item is received that has content data. The content data associated with the content item may be provided to one or more semantic embedding models that generate semantic embeddings. From one or more of the semantic embedding models, one or semantic embeddings may be received. The one or more semantic embeddings may then be inserted into the embedding object memory. The semantic embeddings may be associated with respective indications corresponding to a reference to source data associated with the semantic embeddings. Further, the insertion may trigger a spatial storage operation to store a vector representation of the one or more semantic embeddings. A plurality of collections of stored embeddings may be received from the embedding object memory, based on a provided input, to determine an action.

Storing entries in and retrieving information from an embedding object memory

In accordance with examples of the present disclosure, a collaborative platform provides a digital collaboration assistant that continuously monitors and analyzes shared meeting contents (e.g., voice, text chat messages, shared links and documents, presentation materials, and the like) by participants during a collaborative meeting in near real-time, periodically updates a structure summary log of the meeting contents that are deemed important during the collaborative meeting, and interacts with the participants throughout the collaborative meeting in near real-time, for example, to answer questions or provide additional information.

Meeting insights with large language models

Methods and devices for an automated Internet of Things (IoT) certification service to verify plug and play capabilities of one or more IoT devices for use with a cloud service provider may include receiving a device identification of an IoT device to certify with the cloud service provider. The methods and devices may include receiving a selection of one or more certification tests to perform to plug and play capabilities of the IoT device. The methods and devices may include performing the one or more certification tests. The methods and devices may include generating a device certification for the plug and play capabilities of the IoT device in response to the one or more certification tests passing.

Internet of things (IoT) device and solution certification as a service

Internet of things (IOT) device and solution certification as a service

Growing community of inventors

Kirkland, WA, United States of America

Devis Lucato