Speaker-dependent voice-activated camera system
View Patent ↗A voice-activated camera system for a computing device. The voice-activated camera system includes a processor, a camera module, a speech recognition module and a microphone for accepting user voice input. The voice-activated camera system includes authorized for only a specific user's voice, so that a camera function may be performed when the authorized user speaks the keyword, but the camera function is not performed when an unauthorized user speaks the keyword.
1. A speaker-dependent voice-activated system, comprising:
at least a processor;
a function module coupled to the at least processor, the function module configured to execute a plurality of functions, wherein each of the plurality of functions is associated with a function keyword, and wherein the module is configured to execute each function in response to user input; and
a speech recognition module coupled to the at least processor and the function module, the speech recognition module configured to analyze and store voice characteristics, receive voice input, and determine, using previously stored voice characteristics, whether received voice input is from an authorized user and whether the received voice input includes at least one function keyword,
wherein the speech recognition module is configured to perform the steps of:
receive a first voice input;
determine whether the first input is from the authorized user;
upon determining that the first voice input is not from the authorized user, returning to the function module an unauthorized user indication;
upon determining that the first voice input is from the authorized user, returning to the function module an authorized user indication and determining if the first voice input includes one function keyword;
upon determining that the first voice input does not match one function keyword, returning to the function module an unmatched keyword indication; and
upon determining that the first voice input matches one function keyword, returning to the function module an indication of the function associated with the matched function keyword, whereby the function module executes the
function associated with the matched function keyword.
2. The speaker-dependent voice-activated system of claim 1 , the function module further comprising a user interface.
3. The speaker-dependent voice-activated system of claim 2 , wherein upon receiving the unauthorized user indication the function module indicates to the user, via the user interface, that the first voice input does not match the authorized user.
4. The speaker-dependent voice-activated system of claim 3 , wherein the indication to the user includes indicating on a display of the user interface that the first voice input did not match the authorized user.
5. The speaker-dependent voice-activated system of claim 3 , wherein the indication to the user includes returning the user interface to a general menu.
6. The speaker-dependent voice-activated system of claim 2 , wherein upon receiving the unmatched keyword indication the function module indicates to the user, via the user interface, that the first voice input did not include one function keyword.
7. The speaker-dependent voice-activated system of claim 6 , wherein the indication to the user includes requesting another voice input.
8. The speaker-dependent voice-activated system of claim 6 , wherein the indication to the user includes displaying that the voice input was not recognized.
9. A method for operating a speaker-dependent voice-activated system, comprising the steps of:
receiving of a first voice input by a speech recognition module of the system, the speech recognition module configured to analyze and store voice characteristics, receive voice input, and determine, using previously stored voice characteristics, whether received voice input is from an authorized user and whether the received voice input includes at least one function keyword;
determining whether the first input is from the authorized user;
upon determining that the first voice input is not from the authorized user, returning to a function module an unauthorized user indication, wherein the function module is coupled to the speech recognition module, and wherein the function module is configured to execute a plurality of functions, wherein each of the plurality of functions is associated with a function keyword, and wherein the function module is configured to execute each function in response to user input;
upon determining that the first voice input is from the authorized user, returning to the function module an authorized user indication and determining if the first voice input includes one function keyword;
upon determining that the first voice input does not match one function keyword, returning to the function module an unmatched keyword indication; and
upon determining that the first voice input matches one function keyword, returning to the function module an indication of the function associated with the matched function keyword, whereby the function module executes the function associated with the matched function keyword.
10. The method for operating the speaker-dependent voice-activated system of claim 9 , the function module further comprising a user interface.
11. The method for operating the speaker-dependent voice-activated system of claim 10 , wherein upon receiving the unauthorized user indication the function module indicates to the user, via the user interface, that the first voice input does not match the authorized user.
12. The method for operating the speaker-dependent voice-activated system of claim 11 , wherein the indication to the user includes indicating on a display of the user interface that the first voice input did not match the authorized user.
13. The method for operating the speaker-dependent voice-activated system of claim 11 , wherein the indication to the user includes returning the user interface to a general menu.
14. The method for operating the speaker-dependent voice-activated system of claim 10 , wherein upon receiving the unmatched keyword indication the function module indicates to the user, via the user interface, that the first voice input did not include one function keyword.
15. The method for operating the speaker-dependent voice-activated system of claim 14 , wherein the indication to the user includes requesting another voice input.
16. The method for operating the speaker-dependent voice-activated system of claim 14 , wherein the indication to the user includes displaying that the voice input was not recognized.