VOICE WAKE-UP METHOD AND DEVICE

• US 20170287480A1
• Filed: 04/13/2015
• Published: 10/05/2017
• Est. Priority Date: 08/19/2014
• Status: Abandoned Application

• Current Assignee: ZTE Corporation
• Original Assignee: ZTE Corporation
• Inventors: Liu, Fengpeng, Liu, Dongmei
• Application Number:
  US15/512,692
• Publication Number:
  US 20170287480A1
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/0316 by changing the amplitude
• CPC Class Codes: G10L 21/0364 for improving intelligibility
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04B 1/40 Circuits
• CPC Class Codes: H04M 1/725 Cordless telephones user interfaces specially adapted therefor H04M1/724
• CPC Class Codes: H04W 52/0254 detecting a user operation or a tactile contact or a motion of the device
• CPC Class Codes: H04W 52/028 switching on or off only a part of the equipment circuit blocks
• CPC Class Codes: Y02B 70/3225 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y02D 30/70 in wireless communication networks
• CPC Class Codes: Y04S 20/222 Demand response systems, e.g. load shedding, peak shaving

Abstract

Disclosed is a terminal, comprising a microphone, a power supply switching control circuit, a data switching control circuit, a voice wake-up circuit and a voice wake-up power supply; the microphone is configured to acquire a voice signal and input the voice signal to the data switching control circuit; the power supply switching control circuit is configured to supply power for the microphone via the voice wake-up power supply when receiving a voice wake-up instruction; the data switching control circuit is configured to input the voice signal to the voice wake-up circuit when receiving the voice wake-up instruction; and the voice wake-up circuit is configured to preprocess and match the input voice signal, and execute a corresponding operation according to a matching result.

Also disclosed is a voice wake-up method.

Claims

1. A terminal, comprising a microphone, a power supply switching control circuit, a data switching control circuit, a wake-on-voice circuit, and a wake-on-voice power supply,

wherein the microphone is arranged to acquire a voice signal and input the voice signal to the data switching control circuit;

the power supply switching control circuit is arranged to, when receiving an wake-on-voice instruction, supply the microphone through the wake-on-voice power supply;

the data switching control circuit is arranged to, when receiving the wake-on-voice instruction, input the voice signal to the wake-on-voice circuit; and

the wake-on-voice circuit is arranged to preprocess and match the input voice signal, and perform an operation according to a matching result.

2. The terminal according to claim 1, wherein the wake-on-voice circuit comprises a wake-on-voice preprocessing circuit and a wake-on-voice matching circuit,

wherein the wake-on-voice preprocessing circuit is arranged to preprocess the input voice signal and input the preprocessed voice signal to the wake-on-voice matching circuit;

and

the wake-on-voice matching circuit is arranged to match the preprocessed voice signal and perform the operation according to the matching result.

3. The terminal according to claim 1, further comprising a terminal main control processing circuit and a terminal main control power supply,

wherein the power supply switching control circuit is further arranged to, when receiving an instruction indicating normal voice operation, supply the microphone through the terminal main control power supply;

and

the data switching control circuit is further arranged to, when receiving the instruction indicating normal voice operation, input the voice signal to the terminal main control processing circuit; and

the terminal main control processing circuit is arranged to process the input voice signal to perform the normal voice operation.

4. The terminal according to claim 3, wherein

the power supply switching control circuit is implemented by a first switching circuit comprising a first switch, a first capacitor, a first reference power supply and a first signal amplifier, the first switch comprising a Common (COM) terminal, a Normally Open (NO) terminal, a Normally Closed (NC) terminal, a control (CTR) terminal, a power supply terminal and a ground terminal;

and/or

the data switching control circuit is implemented by a second switching circuit and a third switching circuit, wherein the second switching circuit comprises a second switch, a second capacitor, a second reference power supply and a second signal amplifier, the second switch comprising a COM terminal, an NO terminal , an NC terminal and a CTR terminal; and

the third switching circuit comprises a third switch, a third capacitor, a third reference power supply and a third signal amplifier, the third switch comprising a COM terminal, an NO terminal, an NC terminal, a CTR terminal, a power supply terminal and a ground terminal.

5. The terminal according to claim 4, wherein

in the first switching circuit, the COM terminal of the first switch is connected to a COM terminal of a power supply of the microphone, the NC terminal of the first switch is connected to the wake-on-voice power supply, the NO terminal of the first switch is connected to the terminal main control power supply, the CTR terminal of the first switch is connected to an output of the first signal amplifier, the power supply terminal of the first switch is connected to the first reference power supply and to an end of the first capacitor, the ground terminal of the first switch is grounded, and the other end of the first capacitor is grounded;

in the second switching circuit, the COM terminal of the second switch is connected to a P signal terminal of the microphone, the NC terminal of the second switch is connected to a P signal input of the wake-on-voice circuit, the NO terminal of the second switch is connected to a P signal input of the terminal main control processing circuit, the CTR terminal of the second switch is connected to an output of the second signal amplifier, the power supply terminal of the second switch is connected to the second reference power supply and to an end of the second capacitor, the ground terminal of the second switch is grounded, and the other end of the second capacitor is grounded;

in the third switching circuit, the COM terminal of the third switch is connected to an N signal terminal of the microphone, the NC terminal of the third switch is connected to an N signal input of the wake-on-voice circuit, the NO terminal of the third switch is connected to an N signal input of the terminal main control processing circuit, the CTR terminal of the third switch is connected to an output of the third signal amplifier, the power supply terminal of the third switch is connected to the third reference power supply and to an end of the third capacitor, the ground terminal of the third switch is grounded, and the other end of the third capacitor is grounded.

6. The terminal according to claim 2, wherein

the wake-on-voice preprocessing circuit comprises a fourth capacitor, a fifth capacitor, a sixth capacitor, a seventh capacitor, an eighth capacitor, a ninth capacitor, a fourth signal amplifier, a fifth signal amplifier, a first low pass filter, a second low pass filter;

and/or, the wake-on-voice matching circuit comprises an analog-to-digital converter (ADC), a Micro Controller Unit (MCU) and a memory.

7. The terminal according to claim 6, wherein

in the wake-on-voice preprocessing circuit, an input of the fourth capacitor is connected to a P signal input, an output of the fourth capacitor is connected to an input of the fourth signal amplifier;

an output of the fourth signal amplifier is connected to an input of the sixth capacitor;

an output of the sixth capacitor is connected to an input of the first low pass filter;

an output of the first low pass filter is connected to an input of the eighth capacitor;

an output of the eighth capacitor is connected to an input of the wake-on-voice matching circuit;

an input of the fifth capacitor is connected to an N signal input, and an output of the fifth capacitor is connected to an input of the fifth signal amplifier;

an output of the fifth signal amplifier is connected to an input of the seventh capacitor;

an output of the seventh capacitor is connected to an input of the second low pass filter;

an output of the second low pass filter is connected to an input of the ninth capacitor;

an output of the ninth capacitor is connected to the input of the wake-on-voice matching circuit;

in the wake-on-voice matching circuit, an input of the ADC is connected an output of the wake-on-voice preprocessing circuit, an output of the ADC is connected to an input of the MCU, and the memory is connected to the input of the MCU.

8. A wake-on-voice method for a terminal, comprising:

upon reception of an wake-on-voice instruction, supplying a microphone through a wake-on-voice power supply, and acquiring a voice signal through the microphone;

preprocessing and matching the voice signal, and performing an operation according to a matching result.

9. The method according to claim 8, wherein the step of preprocessing and matching the voice signal and performing the operation according to the matching result comprises:

performing amplification and low pass filtering on the voice signal to obtain the preprocessed voice signal;

performing analog-to-digital conversion on the preprocessed voice signal to obtain a digitalized voice signal;

comparing the digitalized voice signal with a plurality of stored voice template signals;

if a degree of matching between the digitalized voice signal and one of the stored voice template signals is greater than a matching degree threshold, waking up the terminal;

if degrees of matching between the digitalized voice signal and all of the stored voice template signals are smaller than the matching degree threshold, ending the processing.

10. The method according to claim 8, further comprising:

upon reception of an instruction indicating normal voice operation, supplying the microphone through a terminal main control power supply; and

acquiring the voice signal through the microphone, and processing the voice signal to perform the normal voice operation.

11. The method according to claim 9, further comprising:

upon reception of an instruction indicating normal voice operation, supplying the microphone through a terminal main control power supply; and

acquiring the voice signal through the microphone, and processing the voice signal to perform the normal voice operation.