CN211427840U

CN211427840U - Voiceprint switch

Info

Publication number: CN211427840U
Application number: CN201922492048.XU
Authority: CN
Inventors: 楼一勇
Original assignee: Shenzhen Wanhong Electronic Co ltd
Current assignee: Shenzhen Wanhong Electronic Co ltd
Priority date: 2019-12-31
Filing date: 2019-12-31
Publication date: 2020-09-04
Anticipated expiration: 2029-12-31

Abstract

The utility model discloses a voiceprint switch, including switch, audio acquisition module, audio processing module and switch drive module, wherein: the audio acquisition module is used for acquiring an audio signal and sending the audio signal to the audio processing module; the audio processing module is used for receiving the audio signal, storing or comparing the audio signal, generating a switch signal and sending the switch signal to the switch driving module; the switch driving module is used for receiving the switch signal and controlling the switch to be switched on or switched off according to the switch signal. This design passes through switch, audio acquisition module, audio frequency processing module and switch drive module and accomplishes vocal print detection discernment and control switch, only need two sections specific pronunciation or vocal prints of admission in advance as opening the contrast and closing the contrast during the use, follow-up opening or closing only need can accomplish the control of switch through sending the pronunciation or the vocal prints of admission in advance.

Description

Voiceprint switch

Technical Field

The utility model relates to a voiceprint recognition technology, switch technical field, concretely relates to voiceprint switch.

Background

The sound control switch is an energy-saving electronic switch which adopts sound effect to excite a sound pick-up to carry out sound-electricity conversion under specific ambient light to control the opening of an electric appliance and can automatically cut off a power supply after time delay. The sound control switch consists of a microphone BM, a sound signal amplification circuit, a half-wave rectification circuit, a light control circuit, an electronic switch circuit, a time delay circuit and an alternating current switch circuit. In the daytime or when the light is bright, the voice control switch is in a closed state; at night or in dark light, the voice-operated switch is in a ready working state. When a person passes by the switch, the sound of footstep, speaking and clapping hands can start the sound control switch (the lamp is on), and after a certain time delay, the sound control switch is automatically turned off (the lamp is off).

Above-mentioned prior art can only realize controlling through detecting whether sound and volume size, can not judge through specific pronunciation or voiceprint, and simple voice control is improper house indoor use when in-service use, often can produce the mistake and touch, brings unnecessary trouble, so needs a section can detect the acoustic control switch of pronunciation or voiceprint.

SUMMERY OF THE UTILITY MODEL

To the defect among the prior art, the utility model provides a voiceprint switch reduces complicated structure, does not need the huge pronunciation storehouse of data volume, need not the networking, easy operation, and response speed is fast to reduce manufacturing cost and use cost.

The utility model provides a voiceprint switch, includes switch, audio acquisition module, audio processing module and switch drive module, wherein: the audio acquisition module is used for acquiring an audio signal and sending the audio signal to the audio processing module; the audio processing module is used for receiving the audio signal, storing or comparing the audio signal, generating a switch signal and sending the switch signal to the switch driving module; the switch driving module is used for receiving the switch signal and controlling the switch to be switched on or switched off according to the switch signal.

The design completes voiceprint detection identification and control switch through the switch, the audio acquisition module, the audio processing module and the switch driving module, only two sections of specific voices or voiceprints need to be recorded in advance for opening comparison and closing comparison during use, the control of the switch can be completed only by sending the voices or voiceprints recorded in advance when the switch is subsequently opened or closed, the existing voice identification switch needs to be networked and adopts a cloud voice database for identification comparison, the required comparison steps, the switch structure, the circuit and the like are complex, the cost is too high, and the daily use cannot be met, in the not good condition of communication, adverse effect such as switch failure still can lead to, and the utility model discloses a simple pronunciation or voiceprint recognition mode adopt audio processing module direct contrast, have reduced networking contrast process, have reduced networking module, reduce cost.

The general speech recognition mode has the same input mode, uses a sound pickup (MIC), an amplifier and the like, but needs a large amount of sound library support in subsequent processing, can convert the sound into corresponding characters and then achieve the control purpose by character comparison. If the method is suitable for single household appliance control, such as lamps, the method can be realized only by simple words, so that a huge character recognition technology and a voice library are not needed. And analyzing the similarity by using the lines of the small section of sound, and judging and outputting control when the similarity reaches a certain proportion.

Further, the audio acquisition module comprises a microphone, the audio processing module comprises an operational amplifier and a DSP processor, the switch driving module comprises a diode D1, a transistor Q1, a coil KM, a switch K1, and further comprises resistors R1, R2, R3, R4, R5, R6, capacitors C1 and C2, wherein:

the grounding end of the microphone is grounded, the other end of the microphone is sequentially connected with a resistor R2 and a resistor R1 in series, the other end of the resistor R1 is connected with a power supply VCC, the joint of the resistor R2 and the resistor R1 is connected with a capacitor C1, and the other end of the capacitor C1 is grounded;

the inverting input end of the operational amplifier is connected with a resistor R3 and a resistor R4 in parallel, the other end of the resistor R4 is connected with one end of a capacitor C2, the other end of the capacitor C2 is connected with the other end of the microphone, the other end of the resistor R3 is connected with the output end of the operational amplifier, and the forward input end of the operational amplifier is grounded through a resistor R5;

the output end of the operational amplifier is connected with an I/O interface RB0 of the DSP processor, an I/O interface RD0 of the DSP processor is connected with a resistor R6, the other end of the resistor R6 is connected with the base electrode of the triode Q1, the emitter electrode of the triode Q1 is grounded, one end of a collector connecting coil KM of the triode Q1 and the anode of a diode D1, the cathode of the diode D1 and the other end of the coil KM are connected with a power supply, and the coil KM is used for controlling a switch K1 to be turned on or turned off.

Further, the operational amplifier and the DSP processor are powered by a power supply.

Preferably, the operational amplifier is an LM358 dual operational amplifier, and includes two independent operational amplifiers with high gain and internal frequency compensation inside, so that the operational amplifier is suitable for a single power supply with a wide range of power supply voltage, and is also suitable for a dual power supply operation mode, and under the recommended operation condition, the power supply current is independent of the power supply voltage. The application range of the device comprises a sensing amplifier, a direct current gain module and other occasions using an operational amplifier which can be powered by a single power supply.

Preferably, the DSP processor is a dsPIC30F3010, and has the advantages of simple structure, reliable operation, convenient maintenance, reduced volume and cost saving.

Preferably, the diode D1 is 1N 4148.

Preferably, the transistor Q1 is 2N 3904.

Further, the coil KM and the switch K1 are control relays.

The beneficial effects of the utility model are embodied in:

the utility model relates to a voiceprint switch reduces complicated structure, does not need the huge pronunciation storehouse of data volume, need not the networking, easy operation, and response speed is fast to reduce manufacturing cost and use cost.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the technical solutions in the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.

Fig. 1 is a schematic circuit diagram according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.

It is to be noted that unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the present invention belongs.

Examples

As shown in fig. 1, the audio acquisition module includes a microphone, the audio processing module includes an operational amplifier and a DSP processor, the switch driving module includes a diode D1, a transistor Q1, a coil KM, a switch K1, and further includes resistors R1, R2, R3, R4, R5, R6, capacitors C1 and C2, where:

The operational amplifier and the DSP processor are powered by a power supply, and the power supply adopts external power supply or battery power supply.

In this embodiment, the existing speech recognition program is adopted and set in the DSP processor, and the main steps are as follows:

1. analog-to-digital conversion;

2. executing a high-low pass filtering program to control the sound passband signal within 50-10,000 Hz;

3. confirming that the voice is required to be lower than the environmental noise before and after the voice is sent, and the time is not longer than a certain time;

4. fourier analysis (FFT), taking out the characteristic value and storing the characteristic value in an internal EEPROM memory;

5. and comparing the characteristic value with the next section of voice, judging that the ratio is correct to output, and otherwise, not processing (not acting).

In this embodiment, the operational amplifier is an LM358 dual operational amplifier, and includes two independent operational amplifiers with high gain and internal frequency compensation inside, so that the operational amplifier is suitable for a single power supply with a wide power supply voltage range, and is also suitable for a dual power supply operating mode. The application range of the device comprises a sensing amplifier, a direct current gain module and other occasions using an operational amplifier which can be powered by a single power supply.

In the embodiment, the DSP processor is a dsPIC30F3010, and has a simple structure, reliable operation, convenient maintenance, a reduced volume, and cost saving.

In this embodiment, the diode D1 is 1N4148, which is a small high-speed switching diode that switches relatively quickly and is widely used for unidirectional conduction isolation of a circuit with a high signal frequency, and the parameters are as follows:

current:

normal forward current If: the flow rate of the liquid is 150mA,

maximum forward current Imax: the flow rate of the mixed gas is 300mA,

maximum repetitive peak current Ifs: the flow rate of the mixed gas is 450mA,

voltage:

maximum repetitive peak voltage Umax: the voltage of the water is 100V,

maximum continuous reverse voltage Urrm: the voltage of the water is 75V,

maximum forward voltage Uf: 1V.

The triode Q1 is 2N3904 with the following parameters:

current, collector (Ic) (max): the flow rate of the liquid is 200mA,

voltage, collector emitter breakdown (maximum): the pressure of the mixture is 40V,

packaging/housing: TO-39-3, TO-205 AD.

The coil KM and the switch K1 are control relays, for example, the coil KM is electrified, the switch K1 is closed, and the power supply of the electric appliance can be switched on when the switch is closed.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the scope of the embodiments of the present invention, and are intended to be covered by the claims and the specification.

Claims

1. A voiceprint switch, comprising: including switch, audio acquisition module, audio frequency processing module and switch drive module, wherein:

the audio acquisition module is used for acquiring an audio signal and sending the audio signal to the audio processing module;

the audio processing module is used for receiving the audio signal, storing or comparing the audio signal, generating a switch signal and sending the switch signal to the switch driving module;

the switch driving module is used for receiving the switch signal and controlling the switch to be switched on or switched off according to the switch signal.

2. A voiceprint switch according to claim 1, wherein: the audio acquisition module comprises a microphone, the audio processing module comprises an operational amplifier and a DSP processor, the switch driving module comprises a diode D1, a triode Q1, a coil KM and a switch K1, and further comprises resistors R1, R2, R3, R4, R5, R6, capacitors C1 and C2, wherein:

the output end of the operational amplifier is connected with an I/O interface RB0 of the DSP processor, an I/O interface RD0 of the DSP processor is connected with a resistor R6, the other end of the resistor R6 is connected with a base electrode of the triode Q1, an emitting electrode of the triode Q1 is grounded, one end of a collector connecting coil KM of the triode Q1 and the anode of a diode D1 are connected, the cathode of the diode D1 and the other end of the coil KM are connected with a power supply, and the coil KM is used for controlling a switch K1 to be closed or opened.

3. A voiceprint switch according to claim 2, wherein: the operational amplifier and the DSP processor are powered by a power supply.

4. A voiceprint switch according to claim 2, wherein: the operational amplifier is an LM358 dual operational amplifier.

5. A voiceprint switch according to claim 2, wherein: the DSP processor is a dsPIC30F 3010.

6. A voiceprint switch according to claim 2, wherein: the diode D1 is 1N 4148.

7. A voiceprint switch according to claim 2, wherein: the triode Q1 is 2N 3904.

8. A voiceprint switch according to claim 2, wherein: the coil KM and the switch K1 are control relays.