View source for 18380538. LEARNING OFFLINE VOICE COMMANDS BASED ON USAGE OF ONLINE VOICE COMMANDS simplified abstract (GOOGLE LLC)

=LEARNING OFFLINE VOICE COMMANDS BASED ON USAGE OF ONLINE VOICE COMMANDS=


==Organization Name==

[[:Category:GOOGLE LLC|GOOGLE LLC]]


[[Category:GOOGLE LLC]]

==Inventor(s)==

[[:Category:Vikram Aggarwal of Palo Alto CA (US)|Vikram Aggarwal of Palo Alto CA (US)]][[Category:Vikram Aggarwal of Palo Alto CA (US)]]

[[:Category:Moises Morgenstern Gali of San Francisco CA (US)|Moises Morgenstern Gali of San Francisco CA (US)]][[Category:Moises Morgenstern Gali of San Francisco CA (US)]]

==LEARNING OFFLINE VOICE COMMANDS BASED ON USAGE OF ONLINE VOICE COMMANDS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18380538 titled 'LEARNING OFFLINE VOICE COMMANDS BASED ON USAGE OF ONLINE VOICE COMMANDS

==Simplified Explanation==

The patent application describes methods, systems, and apparatus for a user device to learn offline voice actions. The user device detects an utterance when connected to a server, provides the utterance to the server, and receives an update to its grammar. The user device then detects a subsequent utterance when not connected to the server and identifies an operation to perform based on the subsequent utterance and the updated grammar.

* The user device learns offline voice actions by detecting and providing utterances to a server.
* The server updates the grammar of the user device based on the provided utterances.
* The user device can then detect subsequent utterances and identify operations to perform based on the updated grammar.
* The technology enables offline learning of voice actions, reducing reliance on network connectivity.

Potential applications of this technology:

* Voice-controlled devices: This technology can be used in voice-controlled devices such as smart speakers, smartphones, and home automation systems to improve their offline voice recognition capabilities.
* Virtual assistants: Virtual assistants like Siri, Alexa, or Google Assistant can benefit from this technology by learning and performing voice actions offline, providing a seamless user experience even without an internet connection.
* Automotive systems: In-car voice recognition systems can utilize this technology to learn and execute voice commands without relying on a network connection, enhancing the overall user experience and safety.

Problems solved by this technology:

* Offline voice recognition: By enabling offline learning of voice actions, this technology addresses the limitation of relying on network connectivity for voice recognition and command execution.
* Improved user experience: Users can interact with their devices and perform voice actions even when they are offline, enhancing convenience and usability.
* Privacy concerns: Offline learning reduces the need for constant data transmission to a server, addressing privacy concerns related to voice data being sent over the network.

Benefits of this technology:

* Enhanced reliability: Users can rely on their devices to accurately recognize and execute voice commands even in situations where network connectivity is limited or unavailable.
* Improved efficiency: Offline learning allows for faster response times as the user device can process voice commands locally without the need for network communication.
* Increased privacy: By learning and executing voice actions offline, this technology reduces the amount of voice data transmitted over the network, enhancing user privacy.


==Original Abstract Submitted==

Methods, systems, apparatus, including computer programs encoded on a computer storage medium, for a user device to learn offline voice actions. In one aspect, the method includes actions of detecting, by the user device, an utterance at a first time when the user device is connected to a server by a network, providing, by the user device, the utterance to the server using the network, receiving, by the user device and from the server, an update to the grammar of the user device, detecting, by the user device, a subsequent utterance of the utterance at a second time when the user device is not connected to the server by a network, and in response to detecting, by the user device, the subsequent utterance of the utterance at the second time, identifying, by the user device, an operation to perform based on (i) the subsequent utterance, and (ii) the updated grammar.



[[Category:G10L15/07]]
[[Category:G10L15/22]]
[[Category:G10L15/19]]
[[Category:G10L15/32]]
[[Category:G10L15/30]]