CN204697289U - Microphone-based sound source recognition system and smart home appliances - Google Patents

Abstract

The utility model relates to the technical field of sound source positioning, in particular to a microphone-based sound source identification system and intelligent home appliances. It includes a microphone body, and also includes: a first MEMS sensor, which is fixedly arranged at one end of the microphone body; a second MEMS sensor, which is used to collect sound signals in the current environment where the microphone is located, and form a second voice signal output; an ASIC chip , is arranged between the first MEMS sensor and the second MEMS sensor. Compared with the prior art, the utility model has the advantages that: in this way, the sound source localization is realized based on the microphone, and only the internal structure of one microphone is changed. The positioning function can be realized, the structure is simple, and the degree of integration is high. The whole system setting can be integrated into the mobile terminal device or other portable devices. The compatibility is high, and there is no need to set up multiple microphones. The cost is low and the power consumption.

Description

Microphone-based sound source recognition system and smart home appliances

technical field

The utility model relates to the technical field of sound source positioning, in particular to a microphone-based sound source identification system and intelligent home appliances.

Background technique

Smart home is based on the residence as a platform, using integrated wiring technology, network communication technology, security technology, automatic control technology, audio and video technology to integrate home life-related facilities to build an efficient management system for residential facilities and family schedules. Existing smart homes mainly include smart lighting, smart appliances, and smart sunshades. Existing smart homes can only make corresponding automatic controls according to the environment. For example, a smart water dispenser turns off its heating function at night, and a smart air conditioner selects its working state according to the current environment. However, these smart homes cannot reflect "people-oriented" For example, when there is no one in the room, smart appliances may still be in a working state, resulting in a great waste of resources and a low degree of intelligence.

In the existing smart home appliances, there are also technical solutions for sound source localization announced. A plurality of microphones, such as 8 and 16 microphones, are installed on smart appliances, and the position of the sound source is analyzed through the change of data collected by each microphone. However, this The structure of this method is relatively complex, which is not conducive to integration, and the number of microphones is large, the cost is high, and the power consumption is also high.

Utility model content

Aiming at the deficiencies of the prior art, the utility model provides a sound source identification system based on a microphone and an intelligent home appliance with simple structure, easy integration, and low power consumption.

A microphone-based sound source identification system, which includes a microphone body, and also includes:

The first MEMS sensor is fixedly arranged at one end of the microphone body; it is used to collect the sound signal in the environment where the microphone is currently located, and form a first voice signal output;

The second MEMS sensor is fixed at the other end of the microphone body at a predetermined distance from the first MEMS sensor; it is used to collect sound signals in the environment where the microphone is currently located, and form a second voice signal output;

An ASIC chip, arranged between the first MEMS sensor and the second MEMS sensor, for receiving the first voice signal and the second voice signal respectively, and according to the first voice signal and the The second voice signal is used to obtain the location information of the current sound source.

The above-mentioned microphone-based sound source identification system, wherein the ASIC chip includes

A comparison unit, connected to the first MEMS sensor and the second MEMS sensor respectively, for comparing the first voice signal output by the first MEMS sensor and the second voice signal output by the second MEMS sensor. Voice signals are compared, and a comparison result is output

A processing unit, connected to the comparison unit, for receiving the comparison result and forming a judgment result according to the comparison result.

In the above microphone-based sound source identification system, wherein the ASIC chip presets a threshold value, forms a differential signal according to the first voice signal and the second voice signal, and when the differential signal is greater than the predetermined threshold and amplifying the differential signal, and suppressing the differential signal when the differential signal is less than or equal to the predetermined threshold.

In the above microphone-based sound source identification system, the predetermined distance is 4 mm to 5 mm.

In the above microphone-based sound source identification system, the first voice signal carries first voice intensity information; the second voice signal carries second voice intensity information.

In the above microphone-based sound source identification system, wherein, when the first voice intensity is greater than the second voice intensity, the ASIC chip judges that the current position of the sound source is close to the first MEMS sensor;

When the first voice intensity is lower than the second voice intensity, the ASIC chip judges that the current position of the sound source is close to the second MEMS sensor;

In the above microphone-based sound source identification system, the microphone body is provided with a first acoustic through hole and a second acoustic through hole respectively matching the first MEMS sensor and the second MEMS sensor.

A smart home appliance based on microphone-based sound source recognition, which includes any one of the microphone-based sound source recognition systems described above.

Compared with the prior art, the utility model has the advantages of:

In this way, the sound source localization is realized based on the microphone, and its positioning function can be realized only by changing the internal structure of a microphone. The structure is simple and the degree of integration is high. The entire system can be integrated into mobile terminal equipment or other portable equipment. Within, the compatibility is high, and there is no need to set up multiple microphones, the cost is low, and the power consumption is greatly reduced.

Description of drawings

FIG. 1 is a structural schematic diagram of the microphone-based sound source identification system of the present invention.

Detailed ways

The utility model will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the utility model.

The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. example. Based on the embodiments of the present utility model, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of the present utility model.

It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

The utility model will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the utility model.

As shown in Figure 1, a kind of sound source recognition system based on microphone, wherein, comprise a microphone body, also comprise:

The first MEMS sensor is fixedly arranged at one end of the microphone body; it is used to collect the sound signal in the environment where the microphone is currently located, and form a first voice signal output;

The second MEMS sensor is fixed at the other end of the microphone body at a predetermined distance from the first MEMS sensor; it is used to collect sound signals in the environment where the microphone is currently located, and form a second voice signal output;

An ASIC chip, arranged between the first MEMS sensor and the second MEMS sensor, for receiving the first voice signal and the second voice signal respectively, and according to the first voice signal and the The second voice signal is used to obtain the location information of the current sound source.

The working principle of the utility model is: the microphone-based sound source identification system is provided with a first MEMS sensor and a second MEMS sensor, and the voice signals sent by the same sound source can be received by the first MEMS sensor and the second MEMS sensor respectively, After the first MEMS sensor receives the voice signal, it forms a first voice signal and outputs it to the ASIC chip. After the second MEMS sensor receives the voice signal, it forms a second voice signal and outputs it to the ASIC chip. The ASIC chip receives the first voice signal and the second voice signal. The second voice signal is analyzed and processed to calculate the position information of the current sound source. To give a specific embodiment, when the first voice signal is greater than a preset intensity of the second voice signal, it can be determined that the position of the sound source is close to the first MEMS sensor, and when the first voice signal is lower than the second voice signal by a preset intensity When the intensity is high, it can be determined that the position of the sound source is close to the second MEMS sensor.

In practical application, this application can cooperate with household appliances, for example, it can cooperate with electric fans (only for explanation, not to limit this application), and the sound source recognition system is integrated inside the electric fan, and the user sends out voice information, and the sound source recognition The system captures the position of the sound source of the voice information and tracks the position of the sound source of the voice information. The fan adjusts the direction of the wind so that the direction of the wind follows the position of the sound source. At the same time, the sound source recognition system matches the voice information according to the voice information. The control signal output, the control signal controls the intensity or time of the fan or other actions.

Among them, the technical solution disclosed in this application can not only identify the location of the sound source, but also identify and execute the semantics of the sound signal. Since the semantic recognition technology is common knowledge of those skilled in the art, this application will not repeat it here. .

In this way, the sound source localization is realized based on the microphone, and its positioning function can be realized only by changing the internal structure of a microphone. The structure is simple and the degree of integration is high. The entire system can be integrated into mobile terminal equipment or other portable equipment. Within, the compatibility is high, and there is no need to set up multiple microphones, the cost is low, and the power consumption is greatly reduced.

The above-mentioned microphone-based sound source identification system, wherein the ASIC chip includes

A comparison unit, connected to the first MEMS sensor and the second MEMS sensor respectively, for comparing the first voice signal output by the first MEMS sensor and the second voice signal output by the second MEMS sensor. Voice signals are compared, and a comparison result is output

A processing unit, connected to the comparison unit, for receiving the comparison result and forming a judgment result according to the comparison result.

By comparing the first voice signal and the second language signal through the comparison unit, the time delay of the signal can be compared, and the signal strength can also be compared. When the time delay between the first voice signal and the second voice signal is relatively short, it can be determined that the sound source is located in the In the middle of the first MEMS sensor and the second MEMS sensor, and the sensor that preferentially detects the voice signal is determined as the sensor close to the sound source position, when the time delay between the first voice signal and the second voice signal is longer, then it can be If it is determined that the sound source is located on either side of the first MEMS sensor or the second MEMS sensor, then the sensor that preferentially detects the voice signal is determined to be the sensor close to the sound source. In the same way, it can also be detected by signal strength, because the signal strength is proportional to the sound propagation time, so its working principle will not be described here.

In the above microphone-based sound source identification system, wherein the ASIC chip presets a threshold value, forms a differential signal according to the first voice signal and the second voice signal, and when the differential signal is greater than the predetermined threshold and amplifying the differential signal, and suppressing the differential signal when the differential signal is less than or equal to the predetermined threshold. In the state of amplifying the differential signal, the ASIC chip can drive the subsequent circuit according to the differential signal, for example, drive the mechanical device through the differential signal to make adjustments, which is conducive to better collection of voice signals. In the state of suppressing the differential signal, that is, the position of the sound source is close to the sound source identification system, no further adjustment is required. The differential signal can be obtained through comparison by a comparison unit, or through calculation by an ASIC chip, and the method of obtaining it is not limited.

In the above microphone-based sound source identification system, the predetermined distance is 4 mm to 5 mm. Setting a predetermined distance between the first MEMS sensor and the second MEMS sensor, on the one hand, can make the voice signals obtained by the first MEMS sensor and the second MEMS sensor inconsistent, thereby forming signal time delay or signal strength difference; An appropriate space is reserved for the ASIC chip between the first MEMS sensor and the second MEMS sensor, so as to facilitate the installation of the ASIC chip and improve the degree of integration.

In the above microphone-based sound source identification system, the first voice signal carries first voice intensity information; the second voice signal carries second voice intensity information.

In the above microphone-based sound source identification system, wherein, when the first voice intensity is greater than the second voice intensity, the ASIC chip judges that the current position of the sound source is close to the first MEMS sensor;

When the first voice intensity is lower than the second voice intensity, the ASIC chip judges that the current position of the sound source is close to the second MEMS sensor;

When the first voice intensity is equal to the second voice intensity, the ASIC chip determines that the current position of the sound source is between the first MEMS sensor and the second MEMS sensor.

In the above microphone-based sound source identification system, the microphone body is provided with a first acoustic through hole and a second acoustic through hole respectively matching the first MEMS sensor and the second MEMS sensor. There are two acoustic through holes, the purpose of which is to obtain sound signals more accurately.

A smart home appliance based on microphone sound source identification, which includes any one of the microphone-based sound source identification systems described above.

The working principle of the smart home appliance based on microphone sound source recognition is similar to the above-mentioned principle, and will not be repeated here. Wherein, the smart home appliance may be an electrical appliance for daily life or an electrical appliance for office use, and there is no specific limitation here.

The above descriptions are only preferred embodiments of the present utility model, and are not intended to limit the implementation and protection scope of the present utility model. For those skilled in the art, they should be aware The schemes obtained by making equivalent replacements and obvious changes shall all be included in the protection scope of the present utility model.

Claims (6)

1. based on an identification of sound source system for microphone, it is characterized in that, comprise a microphone body, also comprise:

First MEMS sensor, is fixedly installed on one end of described microphone body; In order to gather the voice signal in the current residing environment of described microphone, and form the first voice signal output;

Second MEMS sensor, and described first MEMS sensor interval one preset distance is fixedly installed on the other end of described microphone body; In order to gather the voice signal in the current residing environment of described microphone, and form the second voice signal output;

One asic chip, be arranged between described first MEMS sensor and described second MEMS sensor, in order to receive described first voice signal and described second voice signal respectively, and process is compared to described first voice signal and described second voice signal, obtain the positional information of current sound source.

2. the identification of sound source system based on microphone according to claim 1, it is characterized in that, described asic chip comprises

One comparing unit, connect described first MEMS sensor, described second MEMS sensor respectively, described second voice signal in order to export described first voice signal and described second MEMS sensor of described first MEMS sensor output compares, and forms a comparative result output;

One processing unit, connects described comparing unit, in order to receive described comparative result, and forms judged result according to described comparative result.

3. the identification of sound source system based on microphone according to claim 1, it is characterized in that, described asic chip is preset with a threshold value, forms a differential signal according to described first voice signal and described second voice signal.

4. the identification of sound source system based on microphone according to claim 1, is characterized in that, described preset distance is 4 ㎜ ~ 5 ㎜.

5. the identification of sound source system based on microphone according to claim 1, is characterized in that, described microphone body is provided with the first acoustics through hole, the second acoustics through hole that mate described first MEMS sensor and described second MEMS sensor respectively.

6. based on an intelligent appliance equipment for the identification of sound source of microphone, it is characterized in that, comprise the identification of sound source system based on microphone described in any one of the claims 1 ~ 5.