Microsoft Technology Licensing, LLC

Diego Hernan Carlomagno

Jonathan Reed Harris

Ashok Kuppusamy

Jaclyn Carley Knapp

Jesse Daniel Eskes Rusak

Richard Leigh Mains

Chad Steven Estes

Michael Francis Palermiti, Ii

Jayant Sivarama Krishnamurthy

Allison Anne O'Mahony

Harris Syed

David Ernesto Heekin Burkett

Talon Edward Ireland

Jose Miguel Rady Allende

Andrew Paul McGovern

Viktoriya Taranov

Tudor Buzasu Klein

Sergiy Gavrylenko

Mini Varkey

Victor Boctor

Andrew Paul Mcgovern

Bernardo Sana

Bernardo S P Sana

Various embodiments discussed herein enable client applications to be heavily integrated with a voice assistant in order to perform commands associated with voice utterances of users via voice assistant functionality and also seamlessly cause client applications to automatically perform native functions as part of executing the voice utterance. Such heavy integration also allows particular embodiments to support multi-modal input from a user for a single conversational interaction. In this way, client application user interface interactions, such as clicks, touch gestures, or text inputs are executed alternative or in addition to the voice utterances.

Voice assistant-enabled client application with user view context and multi-modal input support

Various embodiments discussed herein enable client applications to be heavily integrated with a voice assistant in order to both perform commands associated with voice utterances of users via voice assistant functionality and also seamlessly cause client applications to automatically perform native functions as part of executing the voice utterance. For example, some embodiments can automatically and intelligently cause a switch to a page the user needs and automatically and intelligently cause a population of particular fields of the page the user needs based on a user view context and the voice utterance.

Voice assistant-enabled client application with user view context

Techniques to normalize names for name-based speech recognition grammars are described. Some embodiments are particularly directed to techniques to normalize names for name-based speech recognition grammars more efficiently by caching, and on a per-culture basis. A technique may comprise receiving a name for normalization, during name processing for a name-based speech grammar generating process. A normalization cache may be examined to determine if the name is already in the cache in a normalized form. When the name is not already in the cache, the name may be normalized and added to the cache. When the name is in the cache, the normalization result may be retrieved and passed to the next processing step. Other embodiments are described and claimed.

Techniques to normalize names efficiently for name-based speech recognition grammars

A method for establishing a multimodal telephone call is provided. On a first computing device, a telephone call is received from a second computing device. On the first computing device, a response is sent to the second computing device that a telephony session is established between the first computing device and the second computing device. On the first computing device, a request message is sent to register the first computing device for a data session at an online registry service. On the first computing device, a response message is received indicating that the first computing device is registered at the online registry service. The response message includes a key that uniquely identifies the data session. On the first computing device, the key is used to establish the data session with the second computing device.

Multimodal telephone calls

Growing community of inventors

Redmond, WA, United States of America

Diego Hernan Carlomagno