Control method of voice recognition module, voice recognition module and household appliance

Abstract

A control method for a speech recognition module, a speech recognition module and a household appliance, wherein the speech recognition module is in a dormant state, and the speech recognition module includes a microphone array and a speaker, and the method steps include: at least one microphone is in an awake state, and when the at least one microphone receives a sound, the speaker is controlled to send a sound wave signal; the at least one microphone receives the echo of the sound wave signal and obtains the current echo spectrum in the space where the speech recognition module is located; and the current echo spectrum is compared with a preset echo spectrum to control the speech recognition module. Through this solution, the speech recognition module can be awakened when it is detected that the user needs to use the speech recognition function, thereby saving energy consumption and reducing costs.

Description

Technical Field

[0001] The present invention relates to the technical field of household appliances, and in particular to a control method of a speech recognition module, a speech recognition module and a household appliance. Background Art

[0002] With the development of smart home appliance technology, voice recognition control technology is increasingly used in home appliances. Generally, the voice module of a home appliance has two modes: working mode and standby mode. When the voice module is in standby mode, the existing method uses sensors to activate or wake up the voice module to put it in working mode. Obviously, this method requires the installation of sensors on the home appliance, which increases the cost of the home appliance. Summary of the invention

[0003] One of the purposes of the embodiment of the present invention is to use its own microphone array and speaker to wake up the voice recognition module without the need for additional sensors, simplify the structural circuit design, and reduce equipment costs.

[0004] In order to solve the above problems, the present invention provides a control method for a speech recognition module, wherein the speech recognition module is in a dormant state, and the speech recognition module includes a microphone array and a speaker, at least one microphone is in an awake state, and when the at least one microphone receives sound, the speaker is controlled to send a sound wave signal; the at least one microphone receives the echo of the sound wave signal and obtains the current echo spectrum in the space where the speech recognition module is located; the current echo spectrum is compared with the preset echo spectrum to control the speech recognition module. Through this solution, it is possible to wake up the speech recognition module when it is detected that the user needs to use the speech recognition function, thereby saving energy consumption and reducing costs.

[0005] In a possible embodiment, the method includes, before the voice recognition module is located in an empty room, obtaining a preset echo spectrum. The echo spectrum formed by sound waves in different spaces is different, and by comparing with the spectrum formed in an empty room, it is possible to identify whether a user has entered the space.

[0006] In a possible embodiment, the method further includes controlling to wake up the entire speech recognition module when the current echo spectrum is different from the preset echo spectrum.

[0007] In a possible embodiment, the method further includes controlling to wake up the entire speech recognition module when the difference between the current echo spectrum and the preset echo spectrum exceeds a preset value.

[0008] An embodiment of the present invention also discloses a speech recognition module, including a microphone array, a speaker and a controller; the controller is configured to put at least one microphone in an awake state, and when the at least one microphone receives sound, the speaker sends a sound wave pulse signal; and enables at least one microphone to receive the sound wave pulse signal; and is also configured to obtain a current echo spectrum in the space where the speech recognition module is located, and compare the current echo spectrum with a preset echo spectrum to control the speech recognition module.

[0009] In a possible embodiment, the preset echo spectrum is obtained when the space is an empty room.

[0010] In a possible embodiment, the controller is further configured to wake up the entire speech recognition module when the current echo spectrum is different from the preset echo spectrum.

[0011] In a possible embodiment, the controller is further configured to wake up the entire speech recognition module when the difference between the current echo spectrum and the preset echo spectrum exceeds a preset value.

[0012] A household appliance comprises a speech recognition module as described in any one of the above items. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of the structure of a speech recognition module in an embodiment of the present invention;

[0014] Figure 2 It is a flow chart of a control method of a speech recognition module in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] like Figure 1 A speech recognition module 100 includes a controller 101, a microphone array 102 and a speaker 103 connected to the controller 101, and a power supply unit 104 for supplying power to the controller 101, the microphone array 102, the speaker 103, etc.

[0016] Generally, the working modes of the speech recognition module 100 include a standby mode and a wake-up mode. When the speech recognition function is not needed, the speech recognition module is in the standby mode to reduce energy consumption. When the speech recognition function is needed, the speech recognition module 100 is woken up.

[0017] The controller 101 may be used to control the working state of the microphone array 102 and the speaker 103. For example, in one embodiment, the microphone array 102 may include two or more microphones. The controller 101 may be used to enable at least one microphone to be in a wake-up state, so as to wake up the remaining microphones to work according to different working scenarios.

[0018] The microphone layout of the microphone array 102 is not limited, and can be a linear array, or a two-dimensional or three-dimensional array.

[0019] Specifically, in one embodiment, the speech recognition module 100 may include four microphones and a speaker 103. In standby mode, the controller 101 is configured to control one of the microphones to be in an awake state. When the microphone receives any sound, the controller 101 controls the speaker 103 to send a sound wave pulse signal. The microphone receives the echo of the sound wave pulse signal, and the controller 102 stores the echo spectrum and compares the echo spectrum with a preset echo spectrum. The controller 101 controls the working state of the speech recognition module according to the comparison result.

[0020] If the comparison result is that the current echo pattern is the same as the preset echo pattern, it indicates that there is no need to wake up the voice recognition module 100; if the comparison result is that the two are different, it indicates that a user has entered the current space where the voice recognition module 100 is located and the voice recognition function may need to be used, and the controller 101 controls the activation of the remaining three microphones.

[0021] In one embodiment, the preset echo spectrum can be an echo spectrum of an empty room obtained through testing or experiment. In this embodiment, when the current echo spectrum is different from the echo spectrum of the empty room, it is considered that a user has entered the same space and the voice recognition function needs to be enabled, and the controller 101 controls the corresponding microphone to start.

[0022] In one embodiment, the operation of the microphones may be controlled by setting a threshold of the difference between the current echo spectrum and the echo spectrum of the empty room, that is, when the difference exceeds the threshold, the remaining microphones are activated.

[0023] Through the above solution, the module can be awakened when the user needs to use the voice recognition module, thereby reducing energy consumption and costs.

[0024] like Figure 2 In an embodiment of the present invention, a control method for a speech recognition module is applicable to the above-mentioned speech recognition module 100. The steps of the method include:

[0025] S100, at least one microphone is in an awake state, and when the at least one microphone receives sound, the speaker is controlled to send a sound wave signal.

[0026] In one embodiment, one microphone in the microphone array may be awakened to activate the speaker by any sound received.

[0027] In one embodiment, the speaker can send an array of sound wave pulse signals to form a clear and accurate sound wave echo spectrum.

[0028] S102, at least one microphone receives the echo of the sound wave signal and obtains the current echo spectrum in the space where the speech recognition module is located.

[0029] S104, comparing the current echo spectrum with the preset echo spectrum to control the speech recognition module.

[0030] In one embodiment, when the current echo pattern is different from the preset echo pattern, it indicates that a user may have entered the space where the speech recognition module is located, and the entire speech recognition module is controlled to be awakened, that is, the remaining microphones in a dormant state.

[0031] In one embodiment, when the difference between the current echo spectrum and the preset echo spectrum exceeds a preset value, the entire speech recognition module is controlled to wake up.

[0032] Among them, when the space where the voice recognition module is located is an empty room, a preset echo spectrum in the empty room state is obtained.

[0033] The embodiment of the present invention further discloses a household appliance including the above-mentioned voice recognition module 100. The household appliance may be a refrigerator, a washing machine, a range hood, a stove, a coffee machine, a dishwasher, etc.

[0034] Taking a refrigerator as an example, the refrigerator is placed in room 1, and a voice recognition module 100 is provided on the refrigerator, through which voice recognition and voice control functions can be realized. When no one is in room 1, an empty room echo spectrum X of room 1 is obtained and stored.

[0035] Normally, the voice recognition module 100 of the refrigerator is in standby mode to solve the problem of power, and at least one microphone is left in working mode. When the microphone 102 receives any sound, the speaker 103 is controlled to send a sound wave pulse signal, and the microphone 102 receives the echo of the pulse signal and obtains the sound spectrum Y, and compares it with the preset empty room echo spectrum X. If Y is different from X, it means that someone has entered the room 1, and the voice recognition function needs to be enabled, and the controller 101 wakes up the remaining microphones. Otherwise, the voice recognition module 100 continues to standby.

[0036] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, which can include: ROM, RAM, disk or CD, etc.

[0037] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

Claims

1. A control method for a speech recognition module, wherein the speech recognition module is in a dormant state and comprises a microphone array and a speaker, characterized in that: At least one microphone is in an awake state. When the at least one microphone receives sound, the speaker is controlled to send a sound wave signal; the at least one microphone receives the echo of the sound wave signal and obtains the current echo spectrum in the space where the voice recognition module is located; the current echo spectrum is compared with the preset echo spectrum to control the voice recognition module.

2. The method according to claim 1, characterized in that The method includes, before, obtaining a preset echo spectrum when the space where the speech recognition module is located is an empty room.

3. The method according to claim 1, characterized in that The method further includes controlling to wake up the entire speech recognition module when the current echo spectrum is different from the preset echo spectrum.

4. The method according to claim 1 or 3, characterized in that The method further includes controlling to wake up the entire speech recognition module when the difference between the current echo spectrum and the preset echo spectrum exceeds a preset value.

5. A speech recognition module, comprising a microphone array, a speaker and a controller; characterized in that: The controller is configured to wake up at least one microphone, and when the at least one microphone receives sound, cause the speaker to send a sound wave pulse signal; and cause the at least one microphone to receive the sound wave pulse signal; and is also configured to obtain a current echo map in the space where the speech recognition module is located, and compare the current echo map with a preset echo map to control the speech recognition module.

6. The speech recognition module according to claim 5, characterized in that: The preset echo spectrum is obtained when the space is an empty room.

7. The speech recognition module according to claim 5, characterized in that: The controller is also configured to wake up the entire speech recognition module when the current echo spectrum is different from the preset echo spectrum.

8. The speech recognition module according to claim 5 or 7, characterized in that: The controller is also configured to wake up the entire speech recognition module when the difference between the current echo spectrum and the preset echo spectrum exceeds a preset value.

9. A household appliance, comprising the speech recognition module according to any one of claims 5 to 8.

Images