Waking other devices for additional data

• US 9,842,489 B2
• Filed: 02/14/2013
• Issued: 12/12/2017
• Est. Priority Date: 02/14/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Shires, Glen
• Primary Examiner(s): Leland, III, Edwin S
• Application Number:
  US13/766,878
• Publication Number:
  US 20140229184A1
• Time in Patent Office: 1,762 Days
• Field of Search: None
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G08C 17/00 Arrangements for transmitting signals characterised by the use of a wireless electrical link
• CPC Class Codes: G08C 2201/12 Power saving techniques of remote control or controlled devices
• CPC Class Codes: G08C 2201/32 Remote control based on movements, attitude of remote control device
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: H04L 12/12 Arrangements for remote connection or disconnection of substations or of equipment thereof
• CPC Class Codes: H04L 12/282 based on user interaction within the home receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204
• CPC Class Codes: Y02D 30/50 in wire-line communication networks, e.g. low power modes or reduced link rate

Abstract

The disclosed subject matter provides a main device and at least one secondary device. The at least one secondary device and the main device may operate in cooperation with one another and other networked components to provide improved performance, such as improved speech and other signal recognition operations. Using the improved recognition results, a higher probability of generating the proper commands to a controllable device is provided.

Claims

1. A method comprising:

receiving, by a main device, a trigger input signal;

in response to the received trigger input signal, outputting a wake-up signal from the main device to a secondary device;

receiving, by the main device from the secondary device in response to the wake-up signal, buffered input data;

subsequent to receiving the buffered input data by the main device, receiving input signals collected in real time from the secondary device;

receiving a signal indicating that a user is in proximity to the main device so as to enable a main device sensor of the main device;

receiving an input signal from the main device sensor;

separately recognizing the input signal from the main device sensor of the main device and the input signals from a secondary device using speech recognition algorithms and providing recognition results for each device, wherein the input signal from the main device sensor of the main device is recognized as a first recognition result and the input signals from the secondary device are recognized as a second recognition result;

generating a final recognition result based on the first and second recognition results, wherein the second recognition result is used to verify the first recognition result as the final recognition result if the main device is closer to the source of the input than the secondary device, and the first recognition result is used to verify the second recognition result as the final recognition result if the secondary device is closer to the source of the input signal than the main device; and

in response to the recognized input signals, generating a command signal to perform an action related to the recognized input signals based on the generated final recognition result.

2. The method of claim 1, further comprising:

comparing the trigger input to a list of trigger input signals; and

determining a wake-up signal to be sent to the secondary device.

3. The method of claim 1, further comprising:

in response to receiving the wake-up signal, detecting input signals from the environment by the secondary device.

4. The method of claim 1, wherein the buffered input data is input data collected for a predetermined time period prior to receiving the wake-up signal.

5. The method of claim 4, wherein the predetermined time period is approximately 0.5 seconds to approximately five minutes.

6. The method of claim 1, further comprising:

verifying a final recognition result using the recognized main device input signals and the input data from the secondary devices.

7. The method of claim 1, wherein the input signals to the main device and the secondary device are spoken language inputs.

8. The method of claim 1, wherein the trigger signal is a specific spoken word.

9. The method of claim 1, wherein the trigger signal is an infrared signal;

and the input signal to the secondary device is a spoken language.

10. The method of claim 1, wherein the trigger signal is a radio-frequency signal;

and

the input signals to the main device and the secondary device are a spoken language.

11. The method of claim 1, wherein the trigger signal is a motion;

and the input signals to the main device and the secondary device are a spoken language.

12. A system, comprising:

a main device including a first-duration power supply, a sensor and a processor configured to;

receive a trigger input signal from an external source;

output a wake-up signal to a secondary device;

receive, from the secondary device in response to the wake-up signal, buffered input data;

subsequent to receiving the buffered input data, receive input signals collected in real time from the secondary device;

receive a signal indicating that a user is in proximity to the main device so as to enable the main device sensor;

receive an input signal from the main device sensor;

separately recognizing the input signal from the main device sensor and the input signals from a secondary device using speech recognition algorithms and providing recognition results for each device, wherein the input signal from the main device sensor of the main device is recognized as a first recognition result and the input signals from secondary device are recognized as a second recognition result;

generate a final recognition result based on the first and second recognition results, wherein the second recognition result is used to verify the first recognition result as the final recognition result if the main device is closer to the source of the input than the secondary device, and the first recognition result is used to verify the second recognition result as the final recognition result if the secondary device is closer to the source of the input signal than the main device; and

in response to the recognized input signals, generate a command signal to perform an action related to the recognized input signals based on the generated final recognition result.

13. The system of claim 12, wherein the main device further comprises at least one of a Wi-Fi transceiver, a Bluetooth transceiver, or a near-field communication transceiver.

14. The system of claim 12, further comprising:

a secondary device including a second-duration power supply, a sensor, a memory, and a processor wherein the processor is configured to;

in response to receiving the wake-up signal from the main device, enable transmission of an input signal detected by the sensor.

15. A system, comprising:

a main device including a first-duration power supply, a sensor and a processor configured to receive inputs and transmit signals, wherein the processor is configured to send a wake-up signal in response to receiving a trigger signal and is configured to send a signal indicating that the user is in proximity to a main device so as to enable the sensor; and

a secondary device including a second-duration power supply, a sensor, a memory, and a processor wherein the processor is configured to, in response to receiving the wake-up signal from the main device, transmit buffered input data prior to transmitting input signals collected in real time,

wherein the processor of the main device separately recognizes the input signal from the sensor and the input signals from a secondary device using speech recognition algorithms provides separate recognition results for each device, wherein the input signal from the main device sensor of the main device is recognized as a first recognition result and the input signals from secondary device are recognized as a second recognition result,

wherein the processor of the main device generates a final recognition result based on the first and second recognition results, wherein the second recognition result is used to verify the first recognition result as the final recognition result if the main device is closer to the source of the input than the secondary device, and the first recognition result is used to verify the second recognition result as the final recognition result if the secondary device is closer to the source of the input signal than the main device,

wherein the processor of the main device generates a command signal to perform an action related to the recognized input signals based on the generated final recognition result.

16. The system of claim 15, wherein the main device sensor and the secondary device sensor are microphones, and the main device processor is further configured to:

recognize speech received by the main device sensor; and

receive audio data signals transmitted from the secondary device, wherein the audio data signals represent speech received by the secondary device sensor;

analyze the audio data signals and the recognized speech to provide an enhanced speech recognition result; and

determine if the enhanced speech recognition result contains a voice command to perform an action.

17. The system of claim 15, wherein the main device sensor is a microphone, and the main device processor is further configured to:

store audio data received by the main device sensor;

receive audio data transmitted from the secondary device, wherein the audio data represent speech received by the secondary device sensor; and

transmit the main device audio data and the secondary device audio data to a controller.

18. The system of claim 15, wherein the main device sensor further includes at least one of a motion sensor, an infrared sensor, a Bluetooth or near field communication detector, and the main device processor is further configured to:

generate a wake-up signal in response to a trigger signal received by the at least one of a motion sensor, an infrared sensor, a Bluetooth or near field communication detector.

19. The system of claim 15, wherein the first-duration power supply is selectable from an AC/DC wired power supply or a battery that has a longer duration than a battery in the secondary device.