Structuring verbal commands to allow concatenation in a voice interface in a mobile device
First Claim
1. A method, comprising:
- receiving a spoken utterance at a computing device, wherein the spoken utterance includes at least a first level of a multi-level command format, wherein the first level relates to an application;
causing speech recognition to be performed on the spoken utterance to obtain text corresponding to the spoken utterance;
based on the text, identifying the application;
displaying a representation of the identified application on a display of the computing device;
determining whether the text includes a second level of the multi-level command format, wherein the second level relates to an action;
if the text includes the second level of the multi-level command format, identifying the action;
if the text does not include the second level of the multi-level command format, waiting by the computing device for a first predetermined period of time to receive an additional spoken utterance that includes the second level of the multi-level command format and, if no spoken utterance that includes the second level is received within the first predetermined period of time, providing at least one of an audible or visual action prompt;
determining whether the text includes a third level of the multi-level command format, wherein the third level relates to slot input;
if the text includes both the second level and the third level of the multi-level command format, populating at least one slot of the identified action with the slot input and initiating the identified action with the at least one slot populated with the slot input; and
if the text includes the second level but not the third level of the multi-level command format, waiting for a second predetermined period of time to receive an additional spoken utterance that includes the third level of the multi-level command format and, if no additional spoken utterance that includes the third level is received within the second predetermined period of time, providing at least one of an audible or visual slot prompt.
2 Assignments
0 Petitions
Accused Products
Abstract
A spoken utterance includes at least a first level of a multi-level command format, in which the first level identifies an application. The spoken utterance may also include a second level of the multi-level command format, in which the second level identifies an action. In response to receiving the spoken utterance at a computing device, a representation of the application identified by the first level is displayed on a display of the computing device. If the spoken utterance includes the second level of the multi-level command format, the action identified by the second level is initiated. If the spoken utterance does not include the second level of the multi-level command format, the computing device waits for a predetermined period of time and provides at least one of an audible or visual action prompt if the second level is not received within the predetermined period of time.
-
Citations
20 Claims
-
1. A method, comprising:
-
receiving a spoken utterance at a computing device, wherein the spoken utterance includes at least a first level of a multi-level command format, wherein the first level relates to an application; causing speech recognition to be performed on the spoken utterance to obtain text corresponding to the spoken utterance; based on the text, identifying the application; displaying a representation of the identified application on a display of the computing device; determining whether the text includes a second level of the multi-level command format, wherein the second level relates to an action; if the text includes the second level of the multi-level command format, identifying the action; if the text does not include the second level of the multi-level command format, waiting by the computing device for a first predetermined period of time to receive an additional spoken utterance that includes the second level of the multi-level command format and, if no spoken utterance that includes the second level is received within the first predetermined period of time, providing at least one of an audible or visual action prompt; determining whether the text includes a third level of the multi-level command format, wherein the third level relates to slot input; if the text includes both the second level and the third level of the multi-level command format, populating at least one slot of the identified action with the slot input and initiating the identified action with the at least one slot populated with the slot input; and if the text includes the second level but not the third level of the multi-level command format, waiting for a second predetermined period of time to receive an additional spoken utterance that includes the third level of the multi-level command format and, if no additional spoken utterance that includes the third level is received within the second predetermined period of time, providing at least one of an audible or visual slot prompt. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A non-transitory computer readable medium having stored thereon instructions that, when executed by a computing device having at least one processor, cause the computing device to perform functions comprising:
-
receiving a spoken utterance, wherein the spoken utterance includes at least a first level of a multi-level command format, wherein the first level identifies an application; in response to receiving the spoken utterance, displaying a representation of the identified application on a display of the computing device; determining whether the spoken utterance includes a second level of the multi-level command format, wherein the second level relates to an action; if the spoken utterance includes the second level of the multi-level command format, identifying the action; if the spoken utterance does not include the second level of the multi-level command format, waiting for a first predetermined period of time to receive an additional spoken utterance that includes the second level of the multi-level command format and, if no additional spoken utterance that includes the second level is received within the first predetermined period of time, providing at least one of an audible or visual action prompt; determining whether the spoken utterance includes a third level of the multi-level command format, wherein the third level identifies slot input; if the spoken utterance includes both the second level and the third level of the multi-level command format, populating at least one slot of the identified action with the slot input and initiating the identified action with the at least one slot populated with the slot input; and if the spoken utterance includes the second level but not the third level of the multi-level command format, waiting for a second predetermined period of time to receive an additional spoken utterance that includes the third level of the multi-level command format and, if no additional spoken utterance that includes the third level is received within the second predetermined period of time, providing at least one of an audible or visual slot prompt. - View Dependent Claims (9, 10, 11, 12, 13)
-
-
14. A computing device, comprising:
-
at least one processor; data storage; a plurality of instructions stored in the data storage and executable by the at least one processor to cause the computing device to perform functions, the functions comprising; receiving a spoken utterance, wherein the spoken utterance includes at least a first level of a multi-level command format, wherein the first level identifies an application; in response to receiving the spoken utterance, displaying a representation of the identified application on a display of the computing device; determining whether the spoken utterance includes a second level of the multi-level command format, wherein the second level relates to an action; if the spoken utterance includes the second level of the multi-level command format, identifying the action; if the spoken utterance does not include the second level of the multi-level command format, waiting for a first predetermined period of time to receive an additional spoken utterance that includes the second level of the multi-level command format and, if no additional spoken utterance that includes the second level is received within the first predetermined period of time, providing at least one of an audible or visual action prompt; determining whether the spoken utterance includes a third level of the multi-level command format, wherein the third level identifies slot input; if the spoken utterance includes both the second level and the third level of the multi-level command format, populating at least one slot of the identified action with the slot input and initiating the identified action with the at least one slot populated with the slot input; and if the spoken utterance includes the second level but not the third level of the multi-level command format, waiting for a second predetermined period of time to receive an additional spoken utterance that includes the third level of the multi-level command format and, if no additional spoken utterance that includes the third level is received within the second predetermined period of time, providing at least one of an audible or visual slot prompt. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
Specification