Microsoft Technology Licensing, LLC

Duncan James McKay

Jason S Flaks

Christian Klein

John Allen Tardif

Ivan Jelev Tashev

Tommer Leyvand

Cesare John Saretto

Michael Baseflug

Wei Guo

Ali M Vassigh

Robert Norman Heitkamp

Robert A Williams

Sandra Lemon

Dax H Hawkins

Mitchell Stephen Dernis

Dugan O Porter

Stephen R Handley

Ashutosh Vidyadhar Tatake

Adam Spencer Callens

Kiki Wolfkill

Leo Shing

Tony Hau

Jesse Paul Roberts

Michael Raymond Gerhardt

Xudong Ni

Daniel J Chosich

In various embodiments, methods and systems for generating interactive videos based on a layered interactive video platform are provided. An interactive graphics track is received using a layered video platform that supports interactive graphics tracks functionality on interactivity content editor components, content management components, and interactivity components on end-user media devices. The interactive graphics track comprises interactivity instructions that initialize cloud-based interactivity services. An interactivity content editor component can be used to generate interactive graphics tracks and develop interactivity instructions for composing the interactive graphics elements. Composing the interactive graphics elements is based on executing the interactivity instructions that define features of the interactive graphics elements. Composing the interactive graphics elements comprises accessing cloud-based interactivity services corresponding to the interactivity instructions. The interactive graphics tracks can be maintained separately from the video content. The interactive graphics elements are supported using the cloud-based interactivity services and layered over the video content.

Layered interactive video platform for interactive video experiences

Embodiments are disclosed that relate to the use of identity information to help avoid the occurrence of false positive speech recognition events in a speech recognition system. One embodiment provides a method comprising receiving speech recognition data comprising a recognized speech segment, acoustic locational data related to a location of origin of the recognized speech segment as determined via signals from the microphone array, and confidence data comprising a recognition confidence value, and also receiving image data comprising visual locational information related to a location of each person in an image. The acoustic locational data is compared to the visual locational data to determine whether the recognized speech segment originated from a person in the field of view of the image sensor, and the confidence data is adjusted depending on this determination.

Speech recognition analysis via identification information

A device for suppressing ambient sounds from speech received by a microphone array is provided. One embodiment of the device comprises a microphone array, a processor, an analog-to-digital converter, and memory comprising instructions stored therein that are executable by the processor. The instructions stored in the memory are configured to receive a plurality of digital sound signals, each digital sound signal based on an analog sound signal originating at the microphone array, receive a multi-channel speaker signal, generate a monophonic approximation signal of the multi-channel speaker signal, apply a linear acoustic echo canceller to suppress a first ambient sound portion of each digital sound signal, generate a combined directionally-adaptive sound signal from a combination of each digital sound signal by a combination of time-invariant and adaptive beamforming techniques, and apply one or more nonlinear noise suppression techniques to suppress a second ambient sound portion of the combined directionally-adaptive sound signal.

Adaptive ambient sound suppression and speech tracking

An audio application programming interface (API) enables an audio processing graph to be modified during processing. If they are received while the audio graph is playing or paused, graph modifying commands may be inserted into either an asynchronous command queue or a deferred command queue. The audio API may also include a clock manager for synchronizing clocks from a number of different connected audio rendering devices, applications, processors, functions, operations, modules, or other resources. The clock manager may provide an interface that enables a number of control groups to be defined. Each such control group may include a master clock, a slave clock, and a control.

Audio application programming interface

Growing community of inventors

Woodinville, WA, United States of America

Duncan James McKay