Systems and methods for determining whether to trigger a voice capable device based on speaking cadence
Systems and methods are described for determining whether to activate a voice activated device based on a speaking cadence of the user. When the user speaks with a first cadence the system may determine that the user does not intend to activate the device and may accordingly not to trigger a voice activated device. When the user speaks with a second cadence the system may determine that the user does wish to trigger the device and may accordingly trigger the voice activated device.
1. A method comprising:
receiving a voice input from a user, wherein the voice input comprises a wake word;
analyzing the voice input for a first plurality of characteristics associated with the voice of the user;
identifying a profile of the user stored in a memory, wherein the profile of the user comprises a region for the user and a language based on the region, and wherein a second plurality of characteristics associated with the profile of the user corresponds to the region and the language;
retrieving, from the profile of the user, the region and the language spoken by the user;
identifying, from the profile of the user, a voice model that matches the region and language associated with the user;
retrieving a template set of characteristics associated with the voice model;
updating the second plurality of characteristics associated with the profile of the user based on the template set of characteristics; and
activating a voice system based on detecting that the first plurality of characteristics match the updated second plurality of characteristics associated with the profile of the user.
2. The method of claim 1 , further comprising:
in response to the analyzing, determining to not activate the voice system based on detecting that the first plurality of characteristics associated with the voice of the user fails to match at least one of the second plurality of characteristics associated with the profile of the user.
3. The method of claim 1 , wherein the first plurality of characteristics associated with the voice of the user comprises at least one of a tone, a pitch and a pace of the user.
4. The method of claim 1 , wherein the analyzing comprises comparing the first plurality of characteristics associated with the voice of the user to the second plurality of characteristics associated with the profile of the user.
5. The method of claim 1 , further comprising detecting the wake word based on a fingerprint associated with the wake word.
6. The method of claim 1 , wherein the profile of the user comprises a voice model that comprises a mapping between the first plurality of characteristics associated with the voice of the user and a corresponding textual representation of the voice input.
7. The method of claim 1 , further comprising:
generating the template set of characteristics uniquely identifying the voice of the user;
comparing the generated template set of characteristics to the second plurality of characteristics associated with the profile of the user;
determining, based on the comparing, that the generated template set of characteristics matches the second plurality of characteristics associated with the profile of the user; and
in response to determining that the generated template set of characteristics matches the second plurality of characteristics associated with the profile of the user, retrieving the profile of the user from the memory.
8. The method of claim 1 , wherein the voice input is detected at a microphone of the voice system and is transcribed into speech using a voice-to-text algorithm.
9. A system comprising:
a memory configured to store a profile of a user; and
control circuitry configured to:
receive a voice input from the user, wherein the voice input comprises a wake word;
analyze the voice input for a first plurality of characteristics associated with the voice of the user; and
identify the profile of the user stored in the memory, wherein the profile of the user comprises a region for the user and a language based on the region, and wherein a second plurality of characteristics associated with the profile of the user corresponds to the region and the language;
retrieve, from the profile of the user, the region and the language spoken by the user;
identify, from the profile of the user, a voice model that matches the region and language associated with the user;
retrieve a template set of characteristics associated with the voice model;
update the second plurality of characteristics associated with the profile of the user based on the template set of characteristics; and
activate a voice system based on detecting that the first plurality of characteristics match the updated second plurality of characteristics associated with the profile of the user.
10. The system of claim 9 , wherein control circuitry is further configured to:
in response to the analyzing, determine not to activate the voice system based on detecting that the first plurality of characteristics associated with the voice of the user fails to match at least one of the second plurality of characteristics associated with the profile of the user.
11. The system of claim 9 , wherein the first plurality of characteristics associated with the voice of the user comprises at least one of a tone, a pitch and a pace of the user.
12. The system of claim 9 , wherein control circuitry is further configured to:
compare the first plurality of characteristics associated with the voice of the user to the second plurality of characteristics associated with the profile of the user.
13. The system of claim 9 , wherein control circuitry is further configured to detect the wake word based on a fingerprint associated with the wake word.
14. The system of claim 9 , wherein the profile of the user comprises a voice model that comprises a mapping between the first plurality of characteristics associated with the voice of the user and a corresponding textual representation of the voice input.
15. The system of claim 9 , wherein control circuitry is further configured to:
generate the template set of characteristics uniquely identifying the voice of the user;
compare the generated template set of characteristics to the second plurality of characteristics associated with the profile of the user;
determine, based on the comparing, that the generated template set of characteristics matches the second plurality of characteristics associated with the profile of the user; and
in response to determining that the generated template set of characteristics matches the second plurality of characteristics associated with the profile of the user, retrieve the profile of the user from the memory.
16. The system of claim 9 , wherein the voice input is detected at a microphone of the voice system and is transcribed into speech using a voice-to-text algorithm.