Microsoft Technology Licensing, LLC

Thomas M Soemo

Eddie L Mays

Brian Kramp

Andrew Lawrence Mattingly

Christian Klein

Pedro Urbina Escos

Gary Paolo Raden

Ishani Chakraborty

Jonathan C Hanzelka

Eduardo Da Fonseca Melo

Lisa M Butler

Richard J Moerloos, Jr

Tolga Bayram Ekmekci

Jason S Flaks

Ali M Vassigh

Lu Yuan

Vanessa Larco

Leo Soong

Jun Ma

Ivan Jelev Tashev

Robert L Chambers

Joseph Wheeler

Aleksandar Uzelac

Adina Magdalena Trufinescu

Vishwac Sena Kannan

Khuram Shahid

Michael H Kim

Daniel J Hwang

Dax H Hawkins

Ali Reza Emami

Ivan Dokmanic

Dennis Mooney, Ii

Chad R Heinemann

Russell D Christensen

Dennis Ii Mooney

Training a multi-object tracking model includes: generating a plurality of training images based at least on scene generation information, each training image comprising a plurality of objects to be tracked; generating, for each training image, original simulated data based at least on the scene generation information, the original simulated data comprising tag data for a first object; locating, within the original simulated data, tag data for the first object, based on at least an anomaly alert (e.g., occlusion alert, proximity alert, motion alert) associated with the first object in the first training image; based at least on locating the tag data for the first object, modifying at least a portion of the tag data for the first object from the original simulated data, thereby generating preprocessed training data from the original simulated data; and training a multi-object tracking model with the preprocessed training data to produce a trained multi-object tracker.

Training multi-object tracking models using simulation

A multimedia entertainment system combines both gestures and voice commands to provide an enhanced control scheme. A user's body position or motion may be recognized as a gesture, and may be used to provide context to recognize user generated sounds, such as speech input. Likewise, speech input may be recognized as a voice command, and may be used to provide context to recognize a body position or motion as a gesture. Weights may be assigned to the inputs to facilitate processing. When a gesture is recognized, a limited set of voice commands associated with the recognized gesture are loaded for use. Further, additional sets of voice commands may be structured in a hierarchical manner such that speaking a voice command from one set of voice commands leads to the system loading a next set of voice commands.

Compound gesture-speech commands

A method and system are disclosed in which a group of people are able to replicate the physical world experience of going with a group of friends to pick a movie, watch the movie together, and provide commentary on the movie itself in the virtual world on a virtual couch while each user is sitting in different physical locations. Additionally, the virtual representation of the destination that the group of people are watching the movie together in can be themed to allow users to watch movies in different locations pivoting on special events or by the users choice.

Avatar integrated shared media experience

A speech recognition system interprets both spoken system commands as well as application commands. Users may speak commands to an open microphone of a computing device that may be interpreted by at least two speech recognizers operating simultaneously. The first speech recognizer interprets operating system commands and the second speech recognizer interprets application commands. The system commands may include at least opening and closing an application and the application commands may include at least a game command or navigation within a menu. A reserve word may be used to identify whether the command is for the operation system or application. A user's cadence may also indicate whether the speech is a global command or application command. A speech recognizer may include a natural language software component located in a remote computing device, such as in the so-called cloud.

System with multiple simultaneous speech recognizers

Techniques are described for headlessly completing a task of an application in the background of a digital personal assistant. For example, a method can include receiving a voice input via a microphone. Natural language processing can be performed using the voice input to determine a user voice command. The user voice command can include a request to perform a task of the application. The application can be caused to execute the task as a background process without a user interface of the application appearing. A user interface of the digital personal assistant can provide a response to the user, based on a received state associated with the task, so that the response comes from within a context of the user interface of the digital personal assistant without surfacing the user interface of the application.

Headless task completion within digital personal assistants

Examples are disclosed herein that relate to depth imaging techniques using ultrasound One example provides an ultrasonic depth sensing system configured to, for an image frame, emit an ultrasonic pulse from each of a plurality of transducers, receive a reflection of each ultrasonic pulse at a microphone array, perform transmit beamforming and also receive beamforming computationally after receiving the reflections, form a depth image, and output the depth image for the image frame.

Ultrasonic depth imaging

A system for integrating local speech recognition with cloud-based speech recognition in order to provide an efficient natural user interface is described. In some embodiments, a computing device determines a direction associated with a particular person within an environment and generates an audio recording associated with the direction. The computing device then performs local speech recognition on the audio recording in order to detect a first utterance spoken by the particular person and to detect one or more keywords within the first utterance. The first utterance may be detected by applying voice activity detection techniques to the audio recording. The first utterance and the one or more keywords are subsequently transferred to a server which may identify speech sounds within the first utterance associated with the one or more keywords and adapt one or more speech recognition techniques based on the identified speech sounds.

Integrated local and cloud based speech recognition

Scalable empirical testing of media file playback utilizes test hooks in each media player to support simulated human interaction and playback monitoring. A media crawler catalogs media files accumulated in a media file database to create a wordlist. One or more scalable instances of media tester accesses the wordlist to select items of work linked to media files. Work items and/or operating modes of media tester specify test parameters such as performance profiles or further define testing such as specifying repetitious playback on one or more media players. Media files are downloaded to and played by a scalable number of media players. Playback performance is monitored, analyzed and reported. Failure reports are accompanied by instructions to reproduce failures and cross-references to content or source code in media files. Failures can be audited by additional work items for follow-up testing.

Scalable automated empirical testing of media files on media players

Display screen with an animated avatar

Growing community of inventors

Redmond, WA, United States of America

Thomas M Soemo