Voice sensing and keyword analysis
View Patent ↗Methods for voice sensing and keyword analysis are provided. An example method allows for causing a mobile device to transition to a second power mode, from a first power mode, in response to a first acoustic signal. The method includes authenticating a user based at least in part on a second acoustic signal. While authenticating the user, the second acoustic signal is compared to a spoken keyword. The spoken keyword is analyzed for authentication strength based on the length of the spoken keyword, quality of a series of phonemes used to represent the spoken keyword, and likelihood of the series of phonemes to be detected by a voice sensing. While receiving the first and second acoustic signals, a signal to noise ratio (SNR) is determined. The SNR is used to adjust sensitivity of a detection threshold of a voice sensing.
1. A method for voice sensing and authentication, the method comprising:
causing a peripheral device to transition to a second power mode, from a first power mode, in response to a first acoustic signal, the first acoustic signal representing at least one captured sound;
determining a signal to noise ratio based on at least one of the first acoustic signal and a second acoustic signal, the second acoustic signal representing another at least one captured sound;
adapting, based on the signal to noise ratio, sensitivity of a detection threshold of voice sensing;
in the second power mode, authenticating a user, using at least one hardware processor, based at least in part on the second acoustic signal, the authenticating of the user comprising matching the second acoustic signal to a spoken keyword previously obtained using keyword analysis; and
applying noise reduction to the second acoustic signal prior to the authenticating of the user.
2. The method of claim 1 , wherein the first power mode consumes less power than the second power mode.
3. The method of claim 1 , wherein
the first acoustic signal includes one of the following: a first user-defined spoken keyword and a stock keyword; and
the second acoustic signal includes a second user-defined spoken keyword.
4. The method of claim 1 , wherein the voice sensing is more readily triggered under a noisy environment condition and less readily triggered under a clean environment condition.
5. The method of claim 1 , wherein the keyword analysis comprises:
receiving the spoken keyword from the user;
analyzing the spoken keyword for authentication strength; and
reporting the authentication strength to the user.
6. The method of claim 5 , wherein the authentication strength is determined based on one or more of the following:
a length of the spoken keyword;
a quality of a series of phonemes used to represent the spoken keyword;
a likelihood of the series of phonemes to be detected by a voice sensing; and
an evaluation of a frequency of the series of phonemes in a standard dictionary.
7. A computer program product comprising a non-transitory computer-readable storage medium having embodied thereon instructions, which when executed by one or more processors, perform a method for voice sensing and keyword analysis, the method comprising:
receiving a first acoustic signal while operating in a first power mode;
entering a second power mode in response to receiving the first acoustic signal;
receiving a second acoustic signal;
determining a signal to noise ratio based on at least one of the first and second acoustics signals;
adapting, based on the signal to noise ratio, sensitivity of a detection threshold of voice sensing;
authenticating a user based at least in part on the second acoustic signal, the authenticating of the user comprising matching the second acoustic signal to a spoken keyword previously obtained using keyword analysis; and
applying noise reduction to the second acoustic signal prior to the authenticating of the user.
8. The computer program product of claim 7 , wherein the first power mode consumes less power than the second power mode.
9. The computer program product of claim 7 , wherein
the first acoustic signal includes one of the following: a first user-defined spoken keyword and a stock keyword; and
the second acoustic signal includes a second user-defined spoken keyword.
10. The computer program product of claim 7 , wherein the voice sensing is more readily triggered under a noisy environment condition and is less readily triggered under a clean environment condition.
11. The computer program product of claim 7 , wherein the keyword analysis comprises:
receiving the spoken keyword from the user;
analyzing the spoken keyword for authentication strength; and
reporting the authentication strength to the user.
12. The computer program product of claim 11 , wherein the authentication strength is determined based on one or more of the following:
a length of the spoken keyword;
a quality of a series of phonemes used to represent the spoken keyword;
a likelihood of the series of phonemes to be detected by a voice sensing; and
an evaluation of a frequency of the series of phonemes in a standard dictionary.
13. The computer program product of claim 12 , wherein selected features of a mobile device are activated or deactivated based, at least in part, on the authentication strength.
14. A system for voice sensing and authentication, the system comprising:
a wakeup module configured to be stored in memory and executable, using at least one hardware processor, for causing electronic hardware to transition to a second power mode, from a first power mode, in response to a first acoustic signal, the first acoustic signal representing at least one captured sound, the wakeup module further configured for determining a signal to noise ratio based on at least one of the first acoustic signal and a second acoustic signal, the second acoustic signal representing another at least one captured sound; and adapting, based on the determined signal to noise ratio, sensitivity of a detection threshold of a voice sensing;
an authentication module configured to be stored in memory and executable, using at least one hardware processor, for, in the second power mode, authenticating a user, using at least one hardware processor, based at least in part on the second acoustic signal, the authenticating of the user comprising matching the second acoustic signal to a spoken keyword previously obtained using keyword analysis; and
a noise reduction module configured to be stored in memory and executable, using at least one hardware processor, for applying noise reduction to the second acoustic signal prior to the authenticating of the user.
15. The method of claim 1 , wherein the peripheral device comprises an audio processor.
16. The system of claim 14 , wherein the electronic hardware is selected from a group comprising a receiver, graphic display system, processor, and peripheral device.
17. The system of claim 14 , wherein the electronic hardware comprises an audio processor.
18. The system of claim 14 , wherein the electronic hardware comprises a peripheral device.