Power-efficient voice activation
First Claim
Patent Images
1. A voice activation system, comprising:
- a first module configured to receive an audio signal and output a first activation signal if at least one energy characteristic of the audio signal satisfies at least one threshold of one or more thresholds stored in a memory;
a second module configured to transition from a first state to a second state in response to the first activation signal, compute one or both of a time and frequency profile of the audio signal when in the second state, and output a second activation signal if at least a portion of the computed time or frequency profile of the audio signal substantially matches at least one predetermined time or frequency profile indicative of speech in the audio signal; and
a speech recognition engine coupled to the second module and configured to transition from a first state to a second state based on the second activation signal and if a wake-up word determination state is enabled, or transition from the first state to a third state based on the second activation signal and if the wake-up word determination state is disabled, wherein the speech recognition engine is configured to receive the audio signal and determine a speech content of the received audio signal;
wherein the first module is configured to consume less power than the second module, wherein the second module is configured to consume less power than both the second and third states of the speech recognition engine, wherein the second state of the speech recognition engine is configured to consume less power than the third state of the speech recognition engine, and wherein the first module, second module, and speech recognition engine are implemented on one or more computing devices, and wherein the voice activation system includes the one or more computing devices.
9 Assignments
0 Petitions
Accused Products
Abstract
A voice activation system is provided. The voice activation system includes a first stage configured to output a first activation signal if at least one energy characteristic of a received audio signal satisfies at least one threshold and a second stage configured to transition from a first state to a second state in response to the first activation signal and, when in the second state, to output a second activation signal if at least a portion of a profile of the audio signal substantially matches at least one predetermined profile.
32 Citations
16 Claims
-
1. A voice activation system, comprising:
-
a first module configured to receive an audio signal and output a first activation signal if at least one energy characteristic of the audio signal satisfies at least one threshold of one or more thresholds stored in a memory; a second module configured to transition from a first state to a second state in response to the first activation signal, compute one or both of a time and frequency profile of the audio signal when in the second state, and output a second activation signal if at least a portion of the computed time or frequency profile of the audio signal substantially matches at least one predetermined time or frequency profile indicative of speech in the audio signal; and a speech recognition engine coupled to the second module and configured to transition from a first state to a second state based on the second activation signal and if a wake-up word determination state is enabled, or transition from the first state to a third state based on the second activation signal and if the wake-up word determination state is disabled, wherein the speech recognition engine is configured to receive the audio signal and determine a speech content of the received audio signal; wherein the first module is configured to consume less power than the second module, wherein the second module is configured to consume less power than both the second and third states of the speech recognition engine, wherein the second state of the speech recognition engine is configured to consume less power than the third state of the speech recognition engine, and wherein the first module, second module, and speech recognition engine are implemented on one or more computing devices, and wherein the voice activation system includes the one or more computing devices. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A voice activation method, comprising:
-
comparing at least one energy characteristic of an audio signal to at least one threshold of one more thresholds using a first module of a voice activation system; transitioning a second module of the voice activation system from a first state to a second state if the audio signal satisfies the threshold; computing one or both of a time and frequency profile of the audio signal in the second state; comparing at least a portion of one or both of the computed time and frequency profiles of the audio signal to at least one predetermined time or frequency profile indicative of speech in an audio signal using the second module of the voice activation system while the second module of the voice activation system is in the second state; and transitioning a speech recognition engine of the voice activation system from a first state to a second state if the least a portion of a profile of the audio signal substantially matches the at least one predetermined profile and if a wake-up word determination state is enabled, or transitioning the speech recognition engine from the first state to a third state if the portion of the profile of the audio signal substantially matches the at least one pre-determined profile and if the wake-up word determination state is disabled, wherein the second state of the second module consumes less power than the second state of the speech recognition engine, and wherein the second state of the speech recognition engine consumes less power than the third state of the speech recognition engine. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. A voice activation system, comprising:
-
a microphone configured to output an analog electrical signal corresponding to received sound waves; an analog-to-digital converter configured to covert the analog electrical signal to a digital signal; a first module configured to output a first activation signal if at least one energy characteristic of the digital signal satisfies at least one threshold; a second module configured to transition from a stand-by state to a fully-operational state in response to the first activation signal, compute one or both of a time and frequency profile of the digital signal when in the fully-operational state, and output a second activation signal if at least a portion of the computed time or frequency profile of the digital signal substantially matches at least one predetermined time or frequency profile indicative of speech in an audio signal; and a speech recognition engine configured to transition from a first state to a second state based on the second activation signal and if a wake-up word determination state is enabled, or transition from the first state to a third state based on the second activation signal and if the wake-up word determination state is disabled, wherein the speech recognition engine is configured to receive the digital signal and determine a speech content of the received sound waves; and wherein the first module is configured to consume less power than the second module, wherein the second module is configured to consume less power than both the second and third states of the speech recognition engine, wherein the second state of the speech recognition engine is configured to consume less power than the third state of the speech recognition engine, and wherein the first module, second module, and speech recognition engine are implemented on one or more computing devices, and wherein the voice activation system includes the one or more computing devices.
-
Specification