Microsoft Technology Licensing, LLC

George Valavanis

Ines Khelifi

Ted Tai-Yu Chen

Laurentiu Titi Nedelcu

Thomas Charles Butcher

Ted T Chen

Wesley Hodgson

Adam Thomas Mollis

Duncan Og MacConnell

Brendan Mitchel Walsh

Jonathan A Adams

Eric Paul Nichols

Ahmed Raouf Merouche

Sourabh Bansal

Mark Fenwick Wheeler

Sung-Hon Wu

Stacey W Y Law

An Artificial Intelligence (AI) driven content generation system is configured to interact with and inject user inputs into the decision-making process to navigate the user through the boundless creative space offered by content generation algorithms powered by AI. A content generation application may generate an initial collection of artifacts (e.g., multimedia) for exposure to a user, which may be generated based on user input, context awareness, or randomly generated. Responsive to user selection of one of the initial artifacts, a subsequent collection of artifacts is generated based on characteristics of the selected artifact. The generative process is recursive in that the generative application and the user continue to interact until the user decides to use one of the generated artifacts. The generative process enables the user to navigate the virtually infinite creative space of artifacts which may be generated by AI algorithms.

System for generation of novel artifacts with user-guided discovery and navigation of the creative space

A system for enabling spatial delivery of multi-source audio data to a user based on a multi-layer audio stack is provided. The multi-layer audio stack includes a central layer located within a predetermined vertical distance from a reference line associated with the user, such as the horizon line of the user. The multi-layer audio stack can also include an upper layer located above the central layer and/or a lower layer located below the central layer. Audio data from multiple sources are collected and prioritized based on context data gathered for the user. Audio data on which the user would like to focus is assigned the highest priority and delivered on the central layer. Audio data that the user does not currently focus on, but would like to visit next, can be assigned a lower priority and be delivered in the upper layer or the lower layer. The user can shift the multi-layer audio stack up or down to navigate through the audio data rendered at different layers of the stack.

Spatial delivery of multi-source audio content

A digital audio processing system determines characteristics of an electronic presentation to generate a musical composition that is unique to the electronic presentation by adjoining digital audio stems in accordance with the characteristics of the electronic presentation. Embodiments enable a user to define an order for displaying images and a level of importance of the images with respect to one another. For example, the user may designate a specific one of the multiple images as a 'highlight image' for emphasizing during the electronic presentation. Then, the system may arrange numerous musical segments adjacent to one another so that the intensity (e.g., energy level) of a resulting musical composition coincides with key events (e.g., a highlight image being shown) of the particular electronic presentation. The intensity of a particular musical segment may indicate a relative note structure density as compared to other musical segments that are defined within the stem data.

Digital audio processing system for adjoining digital audio stems based on computed audio intensity/characteristics

A system for enabling spatial delivery of multi-source audio data to a user based on a multi-layer audio stack is provided. The multi-layer audio stack includes a central layer located within a predetermined vertical distance from a reference line associated with the user, such as the horizon line of the user. The multi-layer audio stack can also include an upper layer located above the central layer and/or a lower layer located below the central layer. Audio data from multiple sources are collected and prioritized based on context data gathered for the user. Audio data on which the user would like to focus is assigned the highest priority and delivered on the central layer. Audio data that the user does not currently focus on, but would like to visit next, can be assigned a lower priority and be delivered in the upper layer or the lower layer.

Growing community of inventors

Seattle, WA, United States of America

George Valavanis