Back to results
US 9,870,196 B2Granted
Selective aborting of online processing of voice inputs in a voice-enabled electronic device
AssigneeGoogle Inc.
InventorsSangsoo Sung, Yuli Gao, Prathab Murugesan
Life of this patent
Estimating the term…
Abstract
Online processing of a voice input directed to a voice-enabled electronic device is selectively aborted whenever it is determined that a voice input directed to the voice-enabled electronic device can be successfully processed locally by the device. Doing so may in some instances reduce the latency of responding to a voice input.
Claims19
A method, comprising:
- receiving a voice input with a voice-enabled electronic device;
- and
- in the voice-enabled electronic device, and responsive to receiving at least a portion of the voice input:
- initiating both local processing of the at least a portion of the voice input in the voice-enabled electronic device and online processing of the at least a portion of the voice input by the online voice-based query processor in response to receiving the at least a portion of the voice input;
- performing local processing of the at least a portion of the voice input to dynamically build at least a portion of a voice action prior to completely receiving the voice input with the voice-enabled electronic device;
- determining during the local processing and after initiating the online processing whether the voice action can be completed by the local processing without data received from the online voice-based query processor;
- in response to a determination that the voice action can be completed by the local processing without data received from the online voice-based query processor, aborting online processing of the at least a portion of the voice input by the online voice-based query processor and completing building of the voice action with the local processing;
- and
- after aborting online processing and completing building of the voice action with the local processing, receiving data from the online voice-based query processor, verifying the voice action based upon the data received from the online voice-based query processor, and if not verified, updating the voice action using at least a portion of the data received from the online voice-based query processor.
6 more elements
An apparatus including memory and one or more processors operable to execute instructions stored in the memory, comprising instructions to:
- receive a voice input with a voice-enabled electronic device;
- and
- in the voice-enabled electronic device, and responsive to receiving at least a portion of the voice input:
- initiate both local processing of the at least a portion of the voice input in the voice-enabled electronic device and online processing of the at least a portion of the voice input by the online voice-based query processor in response to receiving the at least a portion of the voice input;
- perform local processing of the at least a portion of the voice input to dynamically build at least a portion of a voice action prior to completely receiving the voice input with the voice-enabled electronic device;
- determine during the local processing and after initiating the online processing whether the voice action can be completed by the local processing without data received from the online voice-based query processor;
- in response to a determination that the voice action can be completed by the local processing without data received from the online voice-based query processor, abort online processing of the at least a portion of the voice input by the online voice-based query processor and complete building of the voice action with the local processing;
- and
- after aborting online processing and completing building of the voice action with the local processing, receive data from the online voice-based query processor, verify the voice action based upon data received from the online voice-based query processor, and if not verified, update the voice action using at least a portion of the data received from the online voice-based query processor.
6 more elements
A non-transitory computer readable storage medium storing computer instructions executable by one or more processors to perform a method comprising:
- receiving a voice input with a voice-enabled electronic device;
- and
- in the voice-enabled electronic device, and responsive to receiving at least a portion of the voice input:
- initiating both local processing of the at least a portion of the voice input in the voice-enabled electronic device and online processing of the at least a portion of the voice input by the online voice-based query processor in response to receiving the at least a portion of the voice input;
- performing local processing of the at least a portion of the voice input to dynamically build at least a portion of a voice action prior to completely receiving the voice input with the voice-enabled electronic device;
- determining during the local processing and after initiating the online processing whether the voice action can be completed by the local processing without data received from the online voice-based query processor;
- in response to a determination that the voice action can be completed by the local processing without data received from the online voice-based query processor, aborting online processing of the at least a portion of the voice input by the online voice-based query processor and completing building of the voice action with the local processing;
- and
- after aborting online processing and completing building of the voice action with the local processing, receiving data from the online voice-based query processor, verifying the voice action based upon the data received from the online voice-based query processor, and if not verified, updating the voice action using at least a portion of the data received from the online voice-based query processor.
6 more elements
Dependencies are inferred from the claim text.