Configurable output data formats
First Claim
Patent Images
1. A computer-implemented method, comprising:
- receiving, from a device, first audio data corresponding to an utterance;
performing speech on the audio data to determine a command;
determining a category of content associated with the command;
determining a default content type associated with the category;
identifying a user profile associated with the first audio data;
determining, using the user profile, a non-default content type associated with the category;
generating an output data format including a first portion to be populated with the default content type and a second portion to be populated with the non-default content type;
receiving, from a first content source, first text data associated with the default content type;
populating the first portion with the first text data;
receiving, from a second content source, second text data associated with the non-default content type;
populating the second portion with the second text data;
performing text-to-speech (TTS) processing on the output data format, populated with the first text data and the second text data, to generate second audio data; and
causing the device to output audio corresponding to the second audio data.
1 Assignment
0 Petitions
Accused Products
Abstract
Configurable core domains of a speech processing system are described. A core domain output data format for a given command is originally configured with default content portions. When a user indicates additional content should be output for the command, the speech processing system creates a new output data format for the core domain. The new output data format is user specific and includes both default content portions as well as user preferred content portions.
25 Citations
20 Claims
-
1. A computer-implemented method, comprising:
-
receiving, from a device, first audio data corresponding to an utterance; performing speech on the audio data to determine a command; determining a category of content associated with the command; determining a default content type associated with the category; identifying a user profile associated with the first audio data; determining, using the user profile, a non-default content type associated with the category; generating an output data format including a first portion to be populated with the default content type and a second portion to be populated with the non-default content type; receiving, from a first content source, first text data associated with the default content type; populating the first portion with the first text data; receiving, from a second content source, second text data associated with the non-default content type; populating the second portion with the second text data; performing text-to-speech (TTS) processing on the output data format, populated with the first text data and the second text data, to generate second audio data; and causing the device to output audio corresponding to the second audio data. - View Dependent Claims (2, 3, 4)
-
-
5. A system, comprising:
-
at least one processor; and at least one memory including instructions that, when executed by the at least one processor, cause the system to; receive text data representing a command; determine, based at least in part on the text data, a first content source associated with the command, the first content source configured to provide a first type of content; identify a user profile associated with the text data; determine, based at least in part on the user profile, a second content source associated with the command, the second content source configured to provide a second type of content different from the first type of content; generate an output data format including a first data field to be populated with data received from the first content source and a second data field to be populated with data received from the second content source; receive first data from the first content source; associate the first data with the first data field; receive second data from the second content source; associate the second data with the second data field; and cause a device to output data corresponding to the output data format, the output data including the first data and the second data. - View Dependent Claims (6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer-implemented method, comprising:
-
receiving text data representing a command; determining, based at least in part on the text data, a first content source associated with the command the first content source configured to provide a first type of content; identifying a user profile associated with the text data; determining, based at least in part on the user profile, a second content source associated with the command, the second content source configured to provide a second type of content different from the first type of content; generating an output data format including a first data field to be populated with data received from the first content source and a second data field to be populated with data received from the second content source; receiving first data from the first content source; associating the first data with the first data field; receiving second data from the second content source; associating the second data with the second data field; and causing a device to output data corresponding to the output data format, the output data including the first data and the second data. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20)
-
Specification