Natural language control of secondary device
First Claim
1. A computing system comprising:
- one or more processors;
one or more non-transitory computer-readable storage media storing computer-executable instructions; and
secondary device control instructions maintained in the one or more non-transitory computer-readable storage media and executed by the one or more processors to;
detect a secondary device;
communicate with the secondary device to enable the secondary device to connect to a network and to obtain information related to the secondary device;
cause, based at least in part on detection of the secondary device, output of first audio, the first audio indicating the detection of the secondary device and requesting a user to supply a name for the secondary device;
receive first audio input data comprising the name from the user;
cause first speech processing to be performed on the first audio input data, wherein an output of the first speech processing comprises recognition data;
assign the name to the secondary device;
confirm the name assigned to the secondary device by causing output of second audio, the second audio requesting the user to speak the name of the secondary device and a command for the secondary device to execute;
receive second audio input data comprising the name of the secondary device and the command for the secondary device;
cause second speech processing to be performed on the second audio input data, wherein the second speech processing uses the recognition data; and
cause, based at least in part on the second speech processing, the secondary device to execute at least part of the command.
2 Assignments
0 Petitions
Accused Products
Abstract
Natural language controlled devices may be configured to activate command recognition in response to one or more wake words. Techniques are provided to enable a voice controlled system to detect or receive an indication of a secondary device available to be controlled. The voice controlled system communicates with the secondary device to obtain information related to the secondary device. The voice controlled system may output of an audio query requesting audio input data related to controlling the secondary device from a user and generate, based on the requested audio input data, recognition data utilized to recognize of at least part of one or more commands to issue one or more controls to the secondary device.
301 Citations
21 Claims
-
1. A computing system comprising:
-
one or more processors; one or more non-transitory computer-readable storage media storing computer-executable instructions; and secondary device control instructions maintained in the one or more non-transitory computer-readable storage media and executed by the one or more processors to; detect a secondary device; communicate with the secondary device to enable the secondary device to connect to a network and to obtain information related to the secondary device; cause, based at least in part on detection of the secondary device, output of first audio, the first audio indicating the detection of the secondary device and requesting a user to supply a name for the secondary device; receive first audio input data comprising the name from the user; cause first speech processing to be performed on the first audio input data, wherein an output of the first speech processing comprises recognition data; assign the name to the secondary device; confirm the name assigned to the secondary device by causing output of second audio, the second audio requesting the user to speak the name of the secondary device and a command for the secondary device to execute; receive second audio input data comprising the name of the secondary device and the command for the secondary device; cause second speech processing to be performed on the second audio input data, wherein the second speech processing uses the recognition data; and cause, based at least in part on the second speech processing, the secondary device to execute at least part of the command. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method comprising:
-
receiving an indication of a secondary device available to be controlled; communicating with the secondary device to obtain information related to the secondary device; based at least in part on receiving the indication, causing output of first audio requesting a user to supply a name for the secondary device; receiving first audio input data comprising the name from the user; causing first speech processing to be performed on the first audio input data, wherein an output of the first speech processing comprises recognition data associated with the secondary device; causing output of second audio, the second audio requesting that the user provide a name for the secondary device and a command for the secondary device to execute; receiving second audio input data comprising at least the name of the secondary device and the command for the secondary device to execute; causing second speech processing to be performed on the second audio input data, wherein the second speech processing uses the recognition data; and confirming that the secondary device is capable of being controlled based at least in part on the secondary device executing at least part of the command. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. One or more non-transitory computer-readable storage media storing computer-executable instructions executable in at least one computing device, whereupon execution of the computer-executable instructions causes performing of operations comprising:
-
detecting that a secondary device is available to be controlled; communicating with the secondary device to obtain information related to controlling the secondary device; based at least in part on detecting that the secondary device is available to be controlled, causing output of a first request for a user to supply a name that is to be used subsequently to control the secondary device; receiving first natural language input data comprising the name from the user; cause first speech processing to be performed on the first natural language input data, wherein an output of the first speech processing comprises recognition data; assigning the name to the secondary device; and confirming the name assigned to the secondary device, the confirming based at least in part on; causing output of a second request, the second request requesting the user to provide the name of the secondary device and a command for the secondary device to execute, receiving second natural language input data comprising at least the name of the secondary device and the command for the secondary device to execute, causing second speech processing to be performed on the second natural language input data, the second speech processing using the recognition data, and causing the secondary device to execute at least part of the command. - View Dependent Claims (16, 17, 18, 19, 20, 21)
-
Specification