Microsoft Technology Licensing, LLC

Molly Rose Suver

Gregory M Smith

Gershom L Payzer

Alejandro Acero

Ivan Jelev Tashev

Lisa Joy Stifelman

Jason S Flaks

Aleksandar Uzelac

Robert Norman Heitkamp

Vishwac Sena Kannan

Daniel J Hwang

Connor Peet

Richard Michael Fox

Mouni Reddy

Hoang T Do

Technologies are described for enabling a network protocol that supports switching between communication modes, including a plain text mode and a compressed mode. Switching between the plain text mode and the compressed mode can be performed without closing a network connection between devices. The network protocol can support communication among the devices interacting with a live interactive video game streaming service. The network protocol can also communicate throttling and/or aggregation messages between the devices of the live interactive video game streaming service.

Network protocol for switching between plain text and compressed modes

Technologies are described for enabling interactivity with video games by viewers of a live video game streaming service. For example, messages can be received indicating interactive control events initiated by remote viewers of a live interactive video game stream. A control state data structure can be maintained that comprises control state for the received interactive control events. The control state data structure can maintain separate control state for each of a plurality of time periods (e.g., each time period corresponding to one or more video frames). Actions in the video game can be activated based on the control state data structure.

Interactive control management for a live interactive video game stream

A method for providing digital personal assistant responses may include receiving, by a digital personal assistant associated with a plurality of reactive agents, a user input initiating a dialog with the digital personal assistant within the computing device. In response to receiving the input, an operation mode of the computing device may be detected from a plurality of available operation modes. One of the plurality of reactive agents can be selected based on the received input. A plurality of response strings associated with the selected reactive agent can be accessed. At least one of the plurality of response strings is selected based at least on the operation mode and at least one hardware characteristic of the computing device. The selected at least one of the plurality of response strings is providing during the dialog, as a response to the user input.

Scaling digital personal assistant agents across devices

Speaker identification techniques are described. In one or more implementations, sample data is received at a computing device of one or more user utterances captured using a microphone. The sample data is processed by the computing device to identify a speaker of the one or more user utterances. The processing involving use of a feature set that includes features obtained using a filterbank having filters that space linearly at higher frequencies and logarithmically at lower frequencies, respectively, features that model the speaker's vocal tract transfer function, and features that indicate a vibration rate of vocal folds of the speaker of the sample data.

Speaker identification

Growing community of inventors

Seattle, WA, United States of America

Molly Rose Suver