# US 2022/0044685 A1 · Voice Recognition Device, Waking-Up and Responding Method of the Same, and Computer Storage Medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0044685 A1
- Document ID: US20220044685A1
- Status: Published application
- Kind: A1
- Application number: 17/452,223
- Filed: 2021-10-25
- Published: 2022-02-10
- Earliest claimed: 2019-04-26
- Assignees: Guangdong Midea White Home Appliance Technology Innovation Center Co., Ltd.; Midea Group Co., Ltd.
- Applicants: Guangdong Midea White Home Appliance Technology Innovation Center Co., Ltd.; Midea Group Co., Ltd.
- Inventors: Ruicheng HE
- Web page: https://patentgrep.com/patent/US20220044685A1

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 15/28: Constructional details of speech recognition systems
- G10L 25/84: for discriminating voice from noise
- G10L 2015/088: {Word spotting}
- Y02D 30/70: in wireless communication networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

The present application discloses a waking-up and responding method for a voice recognition device, a voice recognition device, and a computer storage medium. A plurality of voice recognition devices form an area network. The plurality of voice recognition devices are classified into a central device and at least one non-central device. The waking-up and responding method includes: the central device analyzing the collected voice signal to obtain a response factor of the central device; receiving a response factor of the non-central device, the response factor of the non-central device being obtained by the non-central device analyzing the collected voice signal; comparing the response factor of the central device with the response factor of the non-central device; and determining a pending voice recognition device, the pending voice recognition device being a voice recognition device that is in the area network and responds to the voice signal.

## Claims

### Claim 1

A waking-up and responding method of a voice recognition device, wherein a plurality of voice recognition devices form an area network, the plurality of voice recognition devices comprise one central device and at least one non-central device, and the waking-up and responding method comprises:
analyzing, by the central device, a collected voice signal;
obtaining a response factor of the central device;
receiving a response factor of the non-central device, wherein the response factor of the non-central device is obtained by the non-central device analyzing a collected voice signal;
comparing the response factor of the central device with the response factor of the non-central device; and
determining a pending voice recognition device, wherein the pending voice recognition device is one of the plurality of voice recognition devices in the area network that responds to the voice signal.

### Claim 2 (depends on 1)

The waking-up and responding method according to claim 1, wherein the comparing the response factor of the central device with the response factor of the non-central device, and the determining a pending voice recognition device, comprises:
comparing an energy value of the response factor of the central device with an energy value of the response factor of the non-central device to obtain a response factor having a greatest energy value; and
determining a voice recognition device corresponding to the response factor having the greatest energy value to be the pending voice recognition device.

### Claim 3 (depends on 1)

The waking-up and responding method according to claim 1, wherein the comparing the response factor of the central device with the response factor of the non-central device, and the determining a pending voice recognition device, comprises:
comparing an energy value of the response factor of the central device with an energy value of the response factor of the non-central device to obtain a response factor having a greatest energy value;
determining whether the response factor having the greatest energy value is the response factor of the central device;
determining the central device to be pending voice recognition device in response to the response factor having the greatest energy value being the response factor of the central device;
calculating an energy difference between the response factor having the greatest energy value and the response factor of the central device in response to the response factor having the greatest energy value being not the response factor of the central device;
comparing the energy difference value with a waking-up threshold;
determining the voice recognition device corresponding to the response factor having the greatest energy value to be the pending voice recognition device in response to the energy difference being greater than the waking-up threshold; and
determining the central device to be the pending voice recognition device in response to the energy difference being less than or equal to the waking-up threshold.

### Claim 4 (depends on 2)

The waking-up and responding method according to claim 2, wherein each of the plurality of voice recognition devices has a waking-up priority, and the determining the voice recognition device corresponding to the response factor having the greatest energy value to be the pending voice recognition device, comprises:
determining one voice recognition device from all voice recognition devices corresponding to the response factor having the greatest energy value to be the pending voice recognition device.

### Claim 5 (depends on 1)

The waking-up and responding method according to claim 1, further comprising:
sending, by the central device, a notification to the non-central device, instructing the non-central device whether to respond to the voice signal.

### Claim 6 (depends on 1)

The waking-up and responding method according to claim 1, wherein a plurality of area networks are interconnected, a plurality of central devices in all of the plurality of are networks comprise one first central device and at least one second central device, and the waking-up and responding method further comprises:
sending, by the second central device, a second response factor to the first central device, comparing, by the first central device, the second response factor with a first response factor to determine a voice recognition device that responds to the voice signal;
wherein the first response factor is the response factor of the pending voice recognition device in an area network in which the first central device is located, and the second response factor is the response factor of the pending voice recognition device in an area network in which the second central device is located.

### Claim 7 (depends on 1)

The waking-up and responding method according to claim 1, wherein a plurality of area networks are interconnected, a plurality of central devices in all of the plurality of are networks comprise one first central device and at least one second central device, and the waking-up and responding method further comprises:
receiving, by the first central device, a second response factor, wherein the second response factor is the response factor of the pending voice recognition device in an area network in which the second central device is located; and
comparing the second response factor with a first response factor to determine the voice recognition device that responds to the voice signal, wherein the first response factor is the response factor of the pending voice recognition device in an area network in which the first central device is located.

### Claim 8 (depends on 6)

The waking-up and responding method according to claim 6, wherein the comparing the second response factor with the first response factor to determine the voice recognition device that responds to the voice signal, comprises:
comparing an energy value of the first response factor with an energy value of the second response factor to obtain a response factor having a greatest energy value; and
determining a voice recognition device corresponding to the response factor having the greatest energy value to respond to the voice signal.

### Claim 9 (depends on 8)

The waking-up and responding method according to claim 8, wherein each of the plurality of voice recognition devices has a waking-up priority, and the determining the voice recognition device corresponding to the response factor having the greatest energy value to respond to the voice signal, comprises:
determine one voice recognition device from all voice recognition devices corresponding to the response factor having the greatest energy value to respond to the voice signal.

### Claim 10 (depends on 6)

The waking-up and responding method according to claim 6, wherein the comparing the second response factor with the first response factor to determine the voice recognition device that responds to the voice signal, comprises:
comparing an energy value of the first response factor with an energy value of the second response factor to obtain a response factor having the greatest energy value;
determining whether the response factor having the greatest energy value is the first response factor;
determining the first central device to respond to the voice signal in response to the response factor having the greatest energy value being the first response factor;
calculating an energy difference between the response factor having the greatest energy value and the first response factor in response to the response factor having the greatest energy value being not the first response factor;
comparing the energy difference value with a waking-up threshold;
determining a voice recognition device corresponding to the response factor having the greatest energy value to respond to the voice signal in response to the energy difference being greater than the waking-up threshold; and
determining the first central device to respond to the voice signal in response to the energy difference being less than or equal to the waking-up threshold.

### Claim 11 (depends on 10)

The waking-up and responding method according to claim 10, wherein each of the plurality of voice recognition devices has a waking-up priority, and the determining the voice recognition device corresponding to the response factor having the greatest energy value to respond to the voice signal, comprises:
determine one voice recognition device from all voice recognition devices corresponding to the response factor having the greatest energy value to respond to the voice signal.

### Claim 12 (depends on 6)

The waking-up and responding method according to claim 6, further comprising:
sending, by the first central device, a notification to each of the plurality of voice recognition devices in each of the plurality of area networks, instructing each of the plurality of voice recognition devices whether to respond to the voice signal.

### Claim 13 (depends on 1)

The waking-up and responding method according to claim 1, wherein the response factor is referred to as the response factor of the central device and the response factor of the non-central device, and the analyzing the collected voice signal and obtaining the response factor, comprises:
calculating an energy value of the obtained response factor based on voice characteristics of the voice signal and a matching degree between the voice signal and a waking-up template of the voice recognition device.

### Claim 14 (depends on 13)

The waking-up and responding method according to claim 13, wherein the calculating the energy value of the obtained response factor based on voice characteristics of the voice signal and the matching degree between the voice signal and the waking-up template of the voice recognition device, comprises:
calculating a waking-up energy based on the voice characteristics of the voice signal, calculating a ground noise energy based on voice characteristics of environmental noise in an environment at which the voice recognition device is located, taking a difference between the waking-up energy and the ground noise energy as an effective energy;
calculating a confidence degree based on the matching degree between the voice signal and the waking-up template; and
performing a weighted summation on the effective energy and the confidence degree to obtain the energy value of the response factor.

### Claim 15

A waking-up and responding method of a voice recognition device, wherein a plurality of voice recognition devices form an area network, the plurality of voice recognition devices comprise one central device and at least one non-central device, and the waking-up and responding method comprises:
analyzing, by the non-central device, a collected voice signal, obtaining a response factor of the non-central device;
sending the response factor of the non-central device to the central device, comparing, by the central device, the response factor of the non-central device with the response factor of the central device to determine a pending voice recognition device, wherein the pending voice recognition device is one of the plurality of voice recognition devices in the area network that responds to the voice signal.

### Claim 16 (depends on 15)

The waking-up and responding method according to claim 15, wherein the comparing, by the central device, the response factor of the non-central device with the response factor of the central device to determine the pending voice recognition device, comprises:
comparing, by the central device, an energy value of the response factor of the central device with an energy value of the response factor of the non-central device to obtain a response factor having a greatest energy value; and
determining a voice recognition device corresponding to the response factor having the greatest energy value to be the pending voice recognition device.

### Claim 17 (depends on 15)

The waking-up and responding method according to claim 15, wherein
the central device compares an energy value of the response factor of the central device with an energy value of the response factor of the non-central device to obtain a response factor having a greatest energy value;
determining whether the response factor having the greatest energy value is the response factor of the central device;
determining the central device to be the pending voice recognition device in response to the response factor having the greatest energy value being the response factor of the central device;
calculating an energy difference between the response factor having the greatest energy value and the response factor of the central device in response to the response factor having the greatest energy value not being the response factor of the central device;
comparing the energy difference with a waking-up threshold;
determining the voice recognition device corresponding to the response factor having the greatest energy value to be the pending voice recognition device in response to the energy difference being greater than the waking-up threshold; and
determining the central device to be the pending voice recognition device in response to the energy difference being less than or equal to the waking-up threshold.

### Claim 18 (depends on 16)

The waking-up and responding method according to claim 16, wherein each of the plurality of voice recognition devices has a waking-up priority, and the determining the voice recognition device corresponding to the response factor having the greatest energy value to be the pending voice recognition device, comprises:
determining one voice recognition device from all voice recognition devices corresponding to the response factor having the greatest energy value to be the pending voice recognition device.

### Claim 19 (depends on 15)

The waking-up and responding method according to claim 15, wherein the response factor is referred to as the response factor of the central device and the response factor of the non-central device, and the analyzing the collected voice signal and obtaining the response factor, comprises:
calculating an energy value of the obtained response factor based on voice characteristics of the voice signal and a matching degree between the voice signal and a waking-up template of the voice recognition device.

### Claim 20 (depends on 19)

The waking-up and responding method according to claim 19, wherein the calculating an energy value of the obtained response factor based on voice characteristics of the voice signal and a matching degree between the voice signal and a waking-up template of the voice recognition device, comprises:
calculating a waking-up energy based on the voice characteristics of the voice signal, calculating a ground noise energy based on voice characteristics of environmental noise in an environment at which the voice recognition device is located, taking a difference between the waking-up energy and the ground noise energy as an effective energy;
calculating a confidence degree based on the matching degree between the voice signal and the waking-up template; and
performing a weighted summation on the effective energy and the confidence degree to obtain the energy value of the response factor.