Speech recognition and interpretation system
View Patent ↗A method of providing a task assistant comprising starting to receive speech input from a user, and identifying a format associated with a destination for speech input based on a flag associated with the destination field. When the format comprises dictation, converting the speech to text, and inserting it into the destination location, and when the format comprises an intent, determining a meaning of the input, and sending a formatted query to an application. The method further comprising receiving data from the application in response to the intent and providing a response to the user through multimodal output.
1. A method of providing a task assistant associated with an application comprising:
receiving a speech input from a user;
associating the speech input with a destination field in the application;
categorizing the speech input as either a dictation or a command based on a flag associated with the destination field, wherein:
if the speech input is categorized as a dictation, converting the speech input to text and inserting the text into the destination field in the application;
if the speech input is categorized as a command:
interpreting the command;
translating the interpreted command into a format native to the application and sending the translated command to the application;
receiving data from the application in response to the translated command; and
providing a response to the user through a multimodal output.
2. The method of claim 1 , further comprising:
providing a visual indicator of the categorization to the user.
3. The method of claim 1 , wherein interpreting the command comprises analyzing the user's prior interactions with the application.
4. The method of claim 1 , wherein interpreting the command comprises analyzing whether the user has marked a previous interpretation of the command as a favorite.
5. The method of claim 1 , wherein interpreting the command comprises analyzing context associated with the application.
6. The method of claim 5 , wherein the context is updated with the interpretation of the command.
7. A system comprising: a processor, and memory storing computer readable instructions that, when executed by the processor, configure the system to provide:
an input user interface that receives a speech input from a user, wherein the speech input is associated with a destination field in an application;
a field recognition system that categorizes the speech input as either a dictation or a command, based on a flag associated with the destination field;
dictation logic that, if the speech input is categorized as a dictation, converts the speech to text, and inserts the text into the destination field;
a command interpreter that, if the speech input is categorized as a command, interprets the command;
a query logic that, if the speech input is categorized as a command, translates the interpreted command into a format native to the application and sends the translated command to the application;
communication logic that receives data from the application in response to the translated command; and
an output user interface to provide a response to the user through multimodal output.
8. The system of claim 7 , wherein
the output user interface further provides a visual indicator of the categorization to the user.
9. The system of claim 7 , wherein interpreting the command comprises analyzing the user's prior interactions with the application.
10. The system of claim 7 , wherein interpreting the command comprises analyzing whether the user has marked a previous interpretation of the command as a favorite.
11. The system of claim 7 , wherein interpreting the command comprises analyzing context associated with the application.
12. The system of claim 11 wherein the context is updated with the interpretation of the command.
13. One or more non-transitory computer readable media comprising computer readable instructions that, when executed by a data processing device, cause a system to perform:
receiving a speech input from a user;
associating the speech input with a destination field in an application;
categorizing the speech input as either a dictation or a command based on a flag associated with the destination field, wherein;
if the speech input is categorized as a dictation, converting the speech input to text and inserting the text into the destination field in the application;
if the speech input is categorized as a command,
interpreting the command;
translating the interpreted command into a format native to the application and sending the translated command to the application;
receiving-data from the application in response to the translated command; and
providing -a response to the user through a multimodal-output.
14. The one or more non-transitory computer readable media of claim 13 , further comprising:
providing a visual indicator of the categorization to the user.
15. The one or more non-transitory computer readable media of claim 13 , wherein interpreting the command comprises analyzing the user's prior interactions with the application.
16. The one or more non-transitory computer readable media of claim 13 , wherein interpreting the command comprises analyzing whether the user has marked a previous interpretation of the command as a favorite.
17. The one or more non-transitory computer readable media of claim 13 , wherein interpreting the command comprises analyzing context associated with the application.
18. The one or more non-transitory computer readable media of claim 17 , wherein the context is updated with the interpretation of the command.