Microphone calibration method and apparatus

Abstract

The application discloses a microphone calibration method and device, and relates to the field of electronic products. A first smart device and a second smart device with a voice interaction function are in the same local area network. The first smart device sends a second trigger instruction for indicating the second smart device to enter a microphone calibration mode to the second smart device in a microphone calibration mode. Calibration audio played by a target device at a preset distance is collected to obtain first audio data, and the first audio data is sent to the second smart device, so that the second smart device obtains calibration parameters of a microphone of the second smart device according to the first audio data and second audio data. The second audio data is obtained by the second smart device based on the calibration audio played by the target device at the preset distance. The application guarantees the consistency of the sensitivity of the microphones of different smart devices.

Description

Technical Field

[0001] This application relates to the field of electronic products, and more specifically, to a microphone calibration method and apparatus. Background Technology

[0002] With the development of intelligent voice technology, smart devices with voice interaction capabilities (such as smart refrigerators and smart air conditioners) are becoming increasingly popular. Taking smart home devices as an example, users can typically install multiple smart home devices in their homes. Currently, the wake-up commands for multiple smart home devices from the same manufacturer are usually the same. This means that when a user wakes up smart device A using the wake-up command, other smart devices near the user that are from the same manufacturer as smart device A will also be woken up.

[0003] Currently, the main solution to the above problem is that after a user issues a wake-up command, each smart device near the user collects the wake-up command through its own microphone and sends the audio energy of the wake-up command to the device management cloud platform of the corresponding smart device manufacturer. The device management cloud platform can then determine the target smart device that the user wants to wake up based on the audio energy of the wake-up command collected by each smart device's microphone.

[0004] In other words, the target smart device needs to be determined based on the audio energy of the wake-up command collected by the microphone of each smart device. Therefore, ensuring that the microphones of different smart devices have the same sensitivity is crucial. Summary of the Invention

[0005] This application provides a microphone calibration method and apparatus to ensure the consistency of microphone sensitivity across different smart devices.

[0006] In a first aspect, this application provides a microphone calibration method, wherein a first smart device and a second smart device with voice interaction function are located on the same local area network, the method is applied to the first smart device, and the method includes:

[0007] In response to the first trigger command, enter microphone calibration mode;

[0008] In microphone calibration mode, a second trigger command is sent to the second smart device, and the device enters calibration audio detection state; the second trigger command is used to instruct the second smart device to enter microphone calibration mode.

[0009] In the calibration audio detection state, the calibration audio played by the target device at a preset distance is collected, and the first audio data is obtained based on the collected calibration audio.

[0010] The first audio data is sent to the second smart device. The first audio data and the second audio data are used to determine the calibration parameters of the microphone of the second smart device. The second audio data is obtained by the second smart device in the calibration audio detection state of the microphone calibration mode, based on the calibration audio played by the target device at a preset distance.

[0011] Optionally, the second trigger command includes: the microphone calibration status of the first smart device.

[0012] Optionally, the calibration audio includes: a first audio segment, the first audio segment being used to identify the start of playing the calibration audio; the step of obtaining the first audio data based on the acquired calibration audio includes:

[0013] If a first audio segment of the calibration audio is detected, the first audio data is obtained based on the audio following the first audio segment of the calibration audio.

[0014] Optionally, both the first audio data and the second audio data include: at least one acquired audio segment and / or the energy of the at least one audio segment, and the calibration parameters include: parameters for characterizing microphone gain differences and / or parameters for characterizing audio energy differences acquired by the microphone.

[0015] Secondly, this application provides a microphone calibration method, wherein a first smart device and a second smart device with voice interaction function are located on the same local area network, and the method is applied to the second smart device, the method comprising:

[0016] Receive a second trigger command sent by the first smart device in microphone calibration mode, the second trigger command being used to instruct the second smart device to enter microphone calibration mode;

[0017] The system receives first audio data sent by the first smart device. The first audio data is obtained by the first smart device in the calibration audio detection state of microphone calibration mode based on the calibration audio played by the target device at a preset distance.

[0018] In response to the third trigger command, enter the calibration audio detection state;

[0019] In the calibration audio detection state, the calibration audio played by the target device at a preset distance is collected, and second audio data is obtained based on the collected calibration audio;

[0020] Based on the first audio data and the second audio data, obtain the calibration parameters of the microphone of the second smart device.

[0021] Optionally, the second trigger command includes: the microphone calibration status of the first smart device.

[0022] Optionally, the calibration audio includes: a first audio segment, which is used to identify the start of playing the calibration audio; the step of obtaining second audio data based on the acquired calibration audio includes:

[0023] If the first audio segment of the calibration audio is detected, the second audio data is obtained based on the audio following the first audio segment of the calibration audio.

[0024] Optionally, both the first audio data and the second audio data include: at least one acquired audio segment and / or the energy of the at least one audio segment, and the calibration parameters include: parameters for characterizing microphone gain differences and / or parameters for characterizing audio energy differences acquired by the microphone.

[0025] Thirdly, this application provides a microphone calibration device, wherein a first smart device and a second smart device with voice interaction function are located on the same local area network, the device is applied to the first smart device, and the device includes:

[0026] The processing module is used to enter the microphone calibration mode in response to the first trigger command;

[0027] The first sending module is used to send a second trigger command to the second smart device in microphone calibration mode and enter the calibration audio detection state; the second trigger command is used to instruct the second smart device to enter microphone calibration mode;

[0028] The acquisition module is used to acquire calibration audio played by a target device at a preset distance under calibration audio detection state; the processing module is used to obtain first audio data based on the acquired calibration audio.

[0029] The second sending module is used to send the first audio data to the second smart device. The first audio data and the second audio data are used to determine the calibration parameters of the microphone of the second smart device. The second audio data is obtained by the second smart device in the calibration audio detection state of the microphone calibration mode, based on the calibration audio played by the target device at a preset distance.

[0030] Fourthly, this application provides a microphone calibration device, wherein a first smart device and a second smart device with voice interaction function are located on the same local area network, the device is applied to the second smart device, and the device includes:

[0031] The receiving module is configured to receive a second trigger command sent by the first smart device in microphone calibration mode, and to receive first audio data sent by the first smart device. The second trigger command is used to instruct the second smart device to enter microphone calibration mode. The first audio data is obtained by the first smart device in the calibration audio detection state of microphone calibration mode based on the calibration audio played by the target device at a preset distance.

[0032] The processing module is used to enter the calibration audio detection state in response to the third trigger command;

[0033] The acquisition module is used to acquire the calibration audio played by a target device at a preset distance under calibration audio detection state; the processing module is used to obtain second audio data based on the acquired calibration audio; and to obtain the calibration parameters of the microphone of the second smart device according to the first audio data and the second audio data.

[0034] Fifthly, this application provides a computer-readable storage medium comprising a stored program, wherein the program, when executed, performs the method described in either the first or second aspect.

[0035] In a sixth aspect, this application provides an electronic device, including a memory and a processor, as well as a microphone, a transmitter, and a receiver;

[0036] The memory stores a computer program. The receiver, transmitter, and microphone are all coupled to the processor. The processor controls the receiver's receiving action, the transmitter's transmitting action, and the microphone's audio acquisition action.

[0037] The processor is configured to perform the method described in either the first or second aspect via the computer program.

[0038] In a seventh aspect, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any one of the first and second aspects.

[0039] This application provides a microphone calibration method and apparatus. A first smart device can respond to a first trigger command to enter a microphone calibration mode and send a second trigger command to a second smart device to enter the same mode. After acquiring first audio data for calibration, the first smart device can send this data to the second smart device. The second smart device only enters the calibration audio detection state upon responding to a third trigger command. This method allows the second smart device to perform calibration audio detection based on the third trigger command, avoiding interference from other devices or user sounds and improving the accuracy of microphone calibration. Then, the second smart device can determine the calibration parameters of its microphone relative to the first smart device based on the first audio data and second audio data collected while maintaining a preset distance between the target device and the second smart device, ensuring consistency of microphones across the smart devices during subsequent use. This method eliminates the need for consistent microphone hardware structures, achieving software-level assurance of identical microphone sensitivity across different smart devices. This improves the flexibility of microphone installation in smart devices and enhances the accuracy of voice interaction based on the microphone. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram illustrating an application scenario for a smart device.

[0043] Figure 2 A schematic diagram illustrating an application scenario of the microphone calibration method provided in this application;

[0044] Figure 3 A schematic flowchart of a microphone calibration method provided in this application;

[0045] Figure 4 A schematic diagram illustrating a scenario in this application where a user terminal sends a first trigger command to a first smart device;

[0046] Figure 5 A schematic diagram illustrating another application scenario of the microphone calibration method provided in this application;

[0047] Figure 6 A schematic diagram illustrating another application scenario of the microphone calibration method provided in this application;

[0048] Figure 7 A flowchart illustrating another microphone calibration method provided in this application;

[0049] Figure 8 A schematic diagram illustrating another application scenario of the microphone calibration method provided in this application;

[0050] Figure 9 This is a schematic diagram of the structure of a microphone calibration device 20 provided in this application;

[0051] Figure 10 This is a schematic diagram of the structure of a microphone calibration device 30 provided in this application;

[0052] Figure 11 This is a schematic diagram of an electronic device structure provided in this application. Detailed Implementation

[0053] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0054] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0055] With the development of intelligent voice technology, smart devices with voice interaction capabilities (such as smart refrigerators and smart air conditioners) are becoming increasingly popular. Taking these smart devices as examples of smart home devices, users can typically install multiple smart home devices in their homes. For instance, Figure 1 This is a schematic diagram illustrating an application scenario for a smart device. For example... Figure 1As shown, in user A's home, smart devices such as smart TVs, smart washing machines, and smart air conditioners can be installed.

[0056] Currently, multiple smart home devices from the same manufacturer often use the same wake-up command. This means that when a user wakes up one smart device using a wake-up command, other smart devices near the user that belong to the same manufacturer will also be woken up. For example, suppose... Figure 1 The smart TV, smart washing machine, and smart air conditioner shown are all from the same manufacturer, so their wake-up commands are usually the same. If a user wants to wake up the smart washing machine using the same command, the smart TV and smart air conditioner will also be woken up because they share the same wake-up command.

[0057] Currently, the main solution to the above problem is that after a user issues a wake-up command, each smart device near the user collects the wake-up command through its own microphone and sends the audio energy of the wake-up command to the device management cloud platform of the corresponding manufacturer of the smart device.

[0058] The device management cloud platform can determine the target smart device a user wants to wake up based on the audio energy of the wake-up command collected by the microphone of each smart device. For example, based on the audio energy of the wake-up command collected by the microphone of each smart device, the device management cloud platform can determine the distance between the user and each smart device. Then, the device management cloud platform can identify the smart device closest to the user as the target smart device that the user wants to wake up and control that target smart device to start.

[0059] In other words, the target smart device is determined based on the audio energy of the wake-up command collected by the microphone of each smart device. When determining the target smart device based on the audio energy of the wake-up command collected by the microphone, each smart device must have the same microphone sensitivity. This means that the wake-up command collected by the microphones of smart devices at the same distance from the user should have the same audio energy to ensure the accuracy of audio collection by the smart device's microphone, thereby ensuring the accuracy of the target smart device determination.

[0060] However, due to differences in hardware, acoustic structure, and manufacturing processes among various microphones, it is almost impossible to ensure that the microphones of all smart devices have the same sensitivity. Therefore, how to calibrate microphones to ensure that the microphones of different smart devices have the same sensitivity is an urgent problem to be solved.

[0061] Therefore, this application proposes a method at the software level to calibrate the microphone of a second smart device located on the same local area network as the first smart device, using a first smart device with voice interaction capabilities, thereby ensuring the consistency of microphone sensitivity across different smart devices. This method eliminates the need for identical hardware structures for different microphones, improving the flexibility of microphone installation in smart devices and enhancing the accuracy of voice interaction based on the microphone.

[0062] For example, Figure 2 This is a schematic diagram illustrating an application scenario of the microphone calibration method provided in this application. For example... Figure 2 As shown, N (N can be an integer greater than or equal to 2) smart devices can be in the same local area network. The first smart device can be any one of the N smart devices. The second smart device can be any one of the N smart devices except the first smart device.

[0063] It should be understood that this application does not limit the types of the aforementioned first smart device and the second smart device. The aforementioned first smart device and second smart device are not limited to PCs, mobile phones, tablets, smart air conditioners, smart range hoods, smart refrigerators, smart ovens, smart stoves, smart washing machines, smart water heaters, smart washing equipment, smart dishwashers, smart projectors, smart TVs, smart clothes racks, smart curtains, smart audio-visual systems, smart sockets, smart speakers, smart speakers, smart fresh air systems, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaners, smart window cleaning robots, smart mopping robots, smart air purifiers, smart steam ovens, smart microwave ovens, smart water heaters, smart air purifiers, smart water dispensers, smart door locks, etc.

[0064] It should be understood that this application does not limit the application scenarios of the aforementioned first and second smart devices. The aforementioned first and second smart devices can be applied, for example, to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems, or to any scenario that uses smart devices, such as smart cities and smart offices.

[0065] The smart devices within this local area network can communicate with each other. For example, such as... Figure 2 As shown, this local area network (LAN) can be implemented based on a router. That is, each smart device can connect to this router and communicate with other routers in the LAN through it.

[0066] It should be understood that the above-described method of enabling multiple smart devices to be on the same local area network via a router is merely one possible implementation provided by this application. This application does not limit the specific implementation of the aforementioned local area network. For example, the local area network can also be implemented via wireless communication methods such as Bluetooth or Zigbee.

[0067] The technical solutions provided in this application will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0068] Figure 3 This is a flowchart illustrating a microphone calibration method provided in this application. Figure 3 As shown, the method includes the following steps:

[0069] S101, The first smart device responds to the first trigger command and enters the microphone calibration mode.

[0070] As mentioned above, the first smart device can be any smart device with voice interaction function in the local area network.

[0071] Optionally, the first smart device can receive a first trigger command from a user terminal. For example, taking a mobile phone or tablet as the user terminal and a smart washing machine as the first smart device... Figure 4 This application provides a schematic diagram of a scenario where a user terminal sends a first trigger command to a first smart device. For example... Figure 4 As shown, the user terminal can display a list of smart devices in the local area network. The user terminal can respond to the user's click on a smart device's icon, identify the first smart device, and display a microphone calibration start interface. Then, the user can trigger a microphone calibration request by clicking the "Start Microphone Calibration" control on this interface. The user terminal responds to the microphone calibration request by sending a first trigger command to the first smart device. It should be understood that this application does not limit the connection method between the user terminal and the first smart device. For example, the user terminal and the first smart device can be connected via Bluetooth.

[0072] Alternatively, the first smart device may also include a predefined microphone calibration button. In this implementation, the user can trigger a first trigger command by pressing the microphone calibration button.

[0073] It should be understood that this application does not limit whether the microphone calibration mode of the first smart device performs other operations besides the microphone calibration operations described below. For example, after entering the microphone calibration mode, the first smart device may also perform at least one of the following operations: playing a voice prompt message to inform the user that the device has entered the microphone calibration mode, controlling the illumination of a predefined color indicator light to indicate that the device has entered the microphone calibration mode, etc. Through the above methods, the user can be notified that the first smart device has entered the microphone calibration mode, avoiding interference from the user during microphone calibration and improving the accuracy of microphone calibration.

[0074] S102. In microphone calibration mode, the first smart device sends a second trigger command to the second smart device and enters the calibration audio detection state.

[0075] The second smart device can be any smart device with voice interaction capabilities that is located on the same local area network as the first smart device. The aforementioned second trigger command is used to instruct the second smart device to enter microphone calibration mode. It should be understood that this application does not limit whether the second smart device performs any other operations besides the microphone calibration operation described below in microphone calibration mode. Accordingly, the second smart device can receive the second trigger command sent by the first smart device in microphone calibration mode.

[0076] In some embodiments, the second trigger instruction may include the microphone calibration status of the first smart device. Optionally, the microphone calibration status may be used to indicate that the first smart device is currently in microphone calibration mode. By including the microphone calibration status of the first smart device in the second trigger instruction, the second smart device can determine that the first smart device is currently in microphone calibration mode after receiving the second trigger instruction. When the second smart device determines that the first smart device is currently in microphone calibration mode, it can enter microphone calibration mode.

[0077] Optionally, the second trigger command may not include the microphone calibration status of the first smart device. In this implementation, for example, the second touch command may include indication information to instruct the second smart device to enter microphone calibration mode.

[0078] S103. In the calibration audio detection state, the first intelligent device collects the calibration audio played by the target device at a preset distance, and obtains the first audio data based on the collected calibration audio.

[0079] For example, the target device can be any user terminal capable of playing audio, such as a mobile phone, tablet, or smartwatch.

[0080] Optionally, taking the example of the target device playing the aforementioned calibration audio through an application installed on the target device, the calibration audio can be pre-set by the application developer. That is, the target device can play the calibration audio provided by the application. Optionally, the calibration audio can also be a pre-input audio clip from the user. For example, the target device can pre-capture an audio clip from the user as the calibration audio. Alternatively, the target device can also receive the calibration audio input by the user through an Application Programming Interface (API) or a Graphical User Interface (GUI).

[0081] Optionally, the first smart device can directly use the aforementioned calibration audio as the first audio data. Alternatively, the first smart device can, for example, obtain the audio energy of the calibration audio based on the calibration audio and use the audio energy of the calibration audio as the first audio data.

[0082] S104, The first smart device sends the first audio data to the second smart device.

[0083] Correspondingly, the second smart device can receive the first audio data sent by the first smart device, which is "obtained based on the calibration audio played by the target device at a preset distance in the calibration audio detection state of the microphone calibration mode".

[0084] S105, the second smart device responds to the third trigger command and enters the calibration audio detection state.

[0085] Optionally, the second smart device may receive the third trigger command in the same way as the first smart device received the first trigger command in step S101, which will not be repeated here. Alternatively, in some embodiments, the second smart device may generate the third trigger command after receiving the first audio data sent by the first smart device, and enter the calibration audio detection state in response to the third trigger command. Furthermore, the second smart device may use the second trigger command sent by the first smart device as the third trigger command.

[0086] S106. In the calibration audio detection state, the second intelligent device collects the calibration audio played by the target device at a preset distance, and obtains the second audio data based on the collected calibration audio.

[0087] Optionally, the second smart device may obtain the second audio data based on the collected calibration audio in a similar manner to the first smart device obtaining the first audio data based on the collected calibration audio, and will not be elaborated further here.

[0088] S107. The second smart device obtains the calibration parameters of its microphone based on the first audio data and the second audio data.

[0089] The calibration parameters can be used to ensure that the microphones of the second smart device and the first smart device are consistent. For example, taking the first audio data as the first volume of the calibration audio collected by the first smart device and the second audio data as the second volume of the calibration audio collected by the second smart device, the standard parameters of the microphone of the second smart device can be, for example, the quotient of the second volume and the first volume.

[0090] In this embodiment, the first smart device can respond to a first trigger command to enter microphone calibration mode and send a second trigger command to the second smart device to cause the second smart device to enter microphone calibration mode. After acquiring the first audio data of the calibration audio, the first smart device can send the first audio data to the second smart device. The second smart device only enters the calibration audio detection state in response to a third trigger command. Through the above method, the second smart device can perform calibration audio detection according to the third trigger command, avoiding interference from sounds emitted by other devices or users on microphone calibration and improving the accuracy of microphone calibration. Then, the second smart device can determine the calibration parameters of the microphone of the second smart device relative to the first smart device based on the first audio data and the second audio data collected when the target device and the second smart device also maintain a preset distance, so as to maintain the consistency of the microphones of each smart device when using the first smart device and the second smart device in the future. Through the above method, there are no consistency requirements for the microphone hardware structure, etc., and the same sensitivity of the microphones of different smart devices is guaranteed at the software level, which improves the flexibility of installing microphones in smart devices and improves the accuracy of voice interaction based on the microphone.

[0091] As one possible implementation, taking a local area network that includes multiple second smart devices as an example, after the microphone calibration of one second smart device is completed by the first smart device, the microphone calibration of the next second smart device can begin.

[0092] Furthermore, as a possible implementation, in step S102, the first smart device, in microphone calibration mode, can also acquire the identifier of at least one second smart device, and then send a second trigger command to each of the second smart devices based on the identifier of the at least one second smart device. Optionally, the first smart device can, for example, receive the identifier of at least one second smart device from the target device.

[0093] For example, taking a mobile phone or tablet as the target device, Figure 5This is a schematic diagram illustrating another application scenario of the microphone calibration method provided in this application. For example... Figure 5 As shown, the target device's interface for selecting smart devices to be calibrated can display multiple second smart devices. The target device can respond to user actions and identify at least one second smart device. Figure 5 (Taking the user selecting two second smart devices as an example). Then, the target device can respond to the user's click of the "Confirm" control by sending the identifiers of the second smart device 1 and the second smart device 2 to the first smart device. Based on the identifiers of the second smart device 1 and the second smart device 2, the first smart device sends a second trigger command to both the second smart device 1 and the second smart device 2, but does not send a second trigger command to the second smart device 2.

[0094] Using the above method, the first smart device can calibrate only some of the microphones of the second smart device, improving the flexibility of microphone calibration and avoiding interference with the operation of the second smart device that does not require microphone calibration.

[0095] In some embodiments, in step S102, the first smart device, in microphone calibration mode, can also treat all smart devices with voice interaction capabilities in the local area network other than itself as second smart devices. Optionally, the first smart device can, for example, broadcast a second trigger command to all smart devices with voice interaction capabilities in the local area network other than itself.

[0096] As one possible implementation, after acquiring the calibration parameters of its microphone, the second smart device can store these parameters and exit microphone calibration mode. Subsequently, when the user wakes up the second smart device via a wake-up command, the second smart device can determine the target audio information corresponding to the wake-up command based on the acquired audio information (e.g., the audio energy or volume of the wake-up command) and the calibration parameters of its microphone.

[0097] Then, the second smart device can upload the target audio information to the device management cloud platform. Based on the target audio information uploaded by multiple smart devices, the device management cloud platform can determine the target smart device that the user wants to wake up.

[0098] The above method enables the device management cloud platform to determine the target smart device that the user wants to wake up based on the target audio information obtained through the calibration parameters of each smart device's microphone, thereby improving the accuracy of the device management cloud platform in determining the target smart device.

[0099] The following provides a detailed explanation of how the first smart device and the second smart device obtain the first audio data based on the collected calibration audio:

[0100] As one possible implementation, the calibration audio may include a first audio segment for identifying the start of playback of the calibration audio. In this implementation, the first smart device, upon detecting the first audio segment of the calibration audio, can obtain first audio data based on the audio following the first audio segment. Similarly, the second smart device, upon detecting the first audio segment of the calibration audio, can obtain second audio data based on the audio following the first audio segment.

[0101] For example, this application does not limit the specific content of the first audio segment. For example, the first audio segment can be a single-frequency signal (e.g., a 1-second single-frequency signal). This application does not limit the frequency of the single-frequency signal, the duration of the calibration audio, or the duration of the first audio segment.

[0102] In this implementation, first audio data and second audio data are obtained based on the audio following the first audio segment. This ensures that the first audio data obtained by the first smart device and the second audio data obtained by the second smart device are based on the same audio (i.e., the audio following the first audio segment of the calibration audio). By ensuring that the first and second audio data are based on the same audio, differences between the first and second audio data caused by audio differences are avoided. This ensures that the differences between the first and second audio data are caused by differences between the microphones of the first and second smart devices. Therefore, through the above method, the calibration parameters of the microphone of the second smart device obtained based on the first and second audio data are determined based on the differences between the microphones, thus improving the accuracy of microphone calibration.

[0103] Optionally, the first audio data and the second audio data may each include: at least one acquired audio segment, or the energy of at least one audio segment, or the energy of at least one acquired audio segment and at least one audio segment. The calibration parameters may include: parameters characterizing microphone gain differences, or parameters characterizing differences in audio energy acquired by the microphone, or parameters characterizing both microphone gain differences and parameters characterizing differences in audio energy acquired by the microphone.

[0104] Taking an example where both the first audio data and the second audio data include a single audio segment, optionally, the first smart device can use the audio following the first audio segment of the calibration audio as the first audio data.

[0105] The second intelligent device can use the audio following the first audio segment of the calibration audio as the second audio data. Alternatively, taking an example where both the first and second audio data include the energy of a collected audio segment, the first intelligent device can also obtain the energy of an audio segment from the audio following the first audio segment of the calibration audio to obtain the first audio data. The second intelligent device can obtain the energy of an audio segment from the audio following the first audio segment of the calibration audio to obtain the second audio data.

[0106] Taking the example that both the first audio data and the second audio data include multiple audio segments, optionally, the target device can play the calibration audio multiple times in a loop, and both the first smart device and the second smart device can periodically collect the calibration audio to obtain multiple audio segments as the first audio data and multiple audio segments as the second audio data.

[0107] Optionally, taking the first audio data and the second audio data as examples, both may include M acquired audio segments. For instance, the second smart device can obtain, for example, the i-th audio segment from the first audio data and the i-th audio segment from the second audio data, an initial parameter for characterizing the microphone gain difference and an initial parameter for characterizing the audio energy difference acquired by the microphone. Here, M can be an integer greater than or equal to 2, and i is an integer greater than or equal to 1 and less than or equal to M.

[0108] Then, the second intelligent device can obtain parameters characterizing the microphone gain difference based on M initial parameters characterizing the microphone gain difference, and parameters characterizing the audio energy difference acquired by the microphone based on M initial parameters characterizing the audio energy difference acquired by the microphone. For example, the second intelligent device can use the average of the M initial parameters characterizing the microphone gain difference as the parameter characterizing the microphone gain difference, and the average of the M initial parameters characterizing the audio energy difference acquired by the microphone as the parameter characterizing the audio energy difference acquired by the microphone.

[0109] Using the above method, the second smart device can determine the calibration parameters of its microphone based on multiple audio segments, further improving the accuracy of maintaining microphone consistency.

[0110] It should be understood that this application does not limit how the second smart device obtains parameters characterizing the microphone gain difference based on the aforementioned first and second audio data, or how it obtains parameters characterizing the audio energy difference captured by the microphone based on the aforementioned first and second audio data. Optionally, existing implementations for obtaining parameters of microphone gain difference can be referred to, and will not be elaborated here.

[0111] Taking the aforementioned smart refrigerator as the first smart device, and smart washing machines, smart water heaters, smart air conditioners, and smart speakers as examples, Figure 6 This is a schematic diagram illustrating another application scenario of the microphone calibration method provided in this application. For example... Figure 6 As shown, the smart refrigerator can serve as a reference device, which is the aforementioned first smart device. The smart washing machine, smart water heater, smart air conditioner, and smart speaker can all be smart devices to be calibrated, which are the aforementioned second smart devices.

[0112] Figure 7 A flowchart illustrating another microphone calibration method provided in this application. Figure 7 As shown, the method may include the following steps:

[0113] Step 1: After all smart devices are powered on, they can connect to the network with all other devices.

[0114] All smart devices can connect to the router and automatically form a network with other smart devices to create a local area network (LAN). Specifically, when smart device A powers on and connects to the user-configured network, its device information (e.g., its IP address) can be sent to other smart devices on the LAN. These other smart devices can then store this device information. Similarly, any smart device on the LAN will store information about all other smart devices on that LAN, thus establishing a LAN that includes all smart devices.

[0115] Step 2: The user selects any smart device as the reference smart device to begin microphone calibration.

[0116] Users can select any smart device on the local area network as a reference device. The target device can be activated into microphone calibration mode via a smart home application (APP) or by long-pressing a predefined button on the smart device. At this time, the smart device can provide corresponding voice prompts, and a predefined color LED indicator light will illuminate to notify the user that microphone calibration mode has been entered.

[0117] Step 3: The reference device sends the microphone calibration status (i.e., the aforementioned second trigger command) to all other smart devices on the local area network that need to be calibrated.

[0118] At the same time, the reference device can enter the calibration audio detection state, waiting for the user to play the calibration audio through the target device.

[0119] Step 4: The smart device to be calibrated enters microphone calibration mode, but does not perform calibration audio detection.

[0120] After receiving the command to enter microphone calibration mode from the reference device, the smart device to be calibrated enters microphone calibration mode, at which point an LED of a predefined color illuminates. During this time, the smart device to be calibrated does not perform calibration audio detection.

[0121] Step 5: The reference device detects a single-frequency signal in the calibration audio that indicates the start of the audio.

[0122] Users can play pre-installed calibration audio from a preset distance away from the reference device via a smart home app installed on the target device. Since the distances between the target and reference devices, and between the target and the smart device to be calibrated, must be equal when playing the calibration audio, users can use the augmented reality (AR) ranging function within the smart home app installed on the target device to detect the distances between the target and reference devices, and between the target and the device to be calibrated.

[0123] For example, taking a mobile phone as the target device, Figure 8 This is a schematic diagram illustrating another application scenario of the microphone calibration method provided in this application. For example... Figure 8 As shown, the phone can respond to actions used to activate AR ranging, such as... Figure 8 The device shown (either the first or second smart device) performs AR ranging. Figure 8 As shown, the AR ranging page displays the current distance between the phone and the device. As the distance changes, when the distance equals a preset distance, the phone can output a prompt to the user to start playing calibration audio. Optionally, the phone can output this prompt via a sound. Or, as... Figure 8 As shown, when the distance between the phone and the device is equal to a preset distance, the phone can also display a control to play the calibration audio. The phone can directly respond to the user's click on the control to play the calibration audio and play the calibration audio.

[0124] The very beginning of the calibration audio can be a single-frequency signal, used to indicate the start of the calibration audio playback. The reference device can then begin the actual calibration process after detecting the single-frequency signal in the calibration audio.

[0125] Step 6: The reference device sends the recorded audio or the audio energy calculated from the audio to the smart device to be calibrated.

[0126] The reference device can periodically acquire calibration audio signals, thus generating multiple recorded audio or audio energy signals. The reference device can then send these audio or audio energy signals to the smart device being calibrated. Correspondingly, the reference device's LED light will flash periodically in sync to indicate to the user that the calibration process is proceeding normally.

[0127] Step 7: The smart device to be calibrated receives the audio or audio energy sent by the reference device and stores it in the cache.

[0128] Step 8: The user can use the smart home control APP or long press a button on the smart device to put the smart device to be calibrated into the calibration audio detection state.

[0129] When a user approaches the smart device to be calibrated, they can activate the device's audio detection mode via a smart home app or by long-pressing a predefined button on the device. The device will then provide a corresponding voice prompt and illuminate a predefined color LED, indicating to the user that the device is ready for audio calibration.

[0130] Step 9: The smart device to be calibrated detects the single-frequency signal in the calibration audio that indicates the start of the audio.

[0131] The specific implementation process can be referred to in step 5, and will not be repeated here.

[0132] Step 10: The smart device to be calibrated uses its own and cached reference device's audio or audio energy to calculate the microphone gain difference or audio energy difference, and saves it to the memory of the device to be calibrated.

[0133] The smart device to be calibrated periodically acquires calibration audio signals, generating multiple recorded volume levels or audio energy levels. After the calibration audio playback is complete, calibration calculations are performed against the cached reference device's audio or audio energy to determine the microphone gain difference or audio energy difference, which is then saved to memory.

[0134] After calibrating one smart device, the user can move on to the next smart device and repeat steps 8 to 10 to calibrate the microphone of that device.

[0135] In this embodiment, the above method allows users to perform calibration at home without the need for professional calibration equipment (any smart device with voice interaction capabilities can serve as a reference device), professional repair personnel, or specialized calibration knowledge. This resolves hardware and structural differences between microphone models of the same type and between different microphone models, and enables automatic calibration of microphones from different smart devices while automatically saving calibration parameters. Furthermore, the calculation and storage of calibration parameters are distributed across each device to be calibrated, eliminating the need for a device management center or cloud platform, thus reducing the complexity and hardware cost of microphone calibration.

[0136] Furthermore, by playing calibration audio through a smart home app and using AR ranging to ensure that the preset distances between the target device and the first smart device are the same as those between the target device and the second smart device, the accuracy and convenience of microphone calibration are further improved. Using this method, pressing a button again on the device to be calibrated is required to enter audio detection mode, avoiding accidental acquisition of audio played on other calibration devices. Therefore, calibration for practical use scenarios can be completed without moving the installed smart devices to the same location, improving the practicality of microphone calibration.

[0137] Figure 9 This is a schematic diagram of a microphone calibration device 20 provided in this application. The device 20 is applied to a first smart device. Figure 9 As shown, the device 20 includes: a processing module 21, a first transmitting module 22, a data acquisition module 23, and a second transmitting module 24. Among them,

[0138] Processing module 21 is used to enter microphone calibration mode in response to the first trigger command.

[0139] The first sending module 22 is used to send a second trigger command to the second smart device in microphone calibration mode and enter the calibration audio detection state. The second trigger command is used to instruct the second smart device to enter microphone calibration mode.

[0140] Acquisition module 23 is used to acquire calibration audio played by a target device at a preset distance during calibration audio detection. Processing module 21 is used to obtain first audio data based on the acquired calibration audio.

[0141] The second transmitting module 24 is used to transmit the first audio data to the second smart device. The first audio data and the second audio data are used to determine the calibration parameters of the microphone of the second smart device. The second audio data is obtained by the second smart device in the calibration audio detection state of microphone calibration mode, based on the calibration audio played by the target device at a preset distance.

[0142] Optionally, the second trigger command includes: the microphone calibration status of the first smart device.

[0143] Optionally, the calibration audio includes a first audio segment, which is used to identify the start of playing the calibration audio. Optionally, the processing module 21 is specifically configured to, upon detecting the first audio segment of the calibration audio, obtain the first audio data based on the audio following the first audio segment of the calibration audio.

[0144] Optionally, both the first audio data and the second audio data include: at least one acquired audio segment and / or the energy of the at least one audio segment, and the calibration parameters include: parameters for characterizing microphone gain differences and / or parameters for characterizing audio energy differences acquired by the microphone.

[0145] The microphone calibration device 20 provided in this application is used to execute the microphone calibration method embodiment executed by the aforementioned first smart device. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0146] Figure 10 This is a schematic diagram of a microphone calibration device 30 provided in this application. This device 30 is applied to a second smart device. For example... Figure 10 As shown, the device 30 includes: a receiving module 31, a processing module 32, and a data acquisition module 33. Among them,

[0147] The receiving module 31 is configured to receive a second trigger command sent by the first smart device in microphone calibration mode, and to receive first audio data sent by the first smart device. The second trigger command instructs the second smart device to enter microphone calibration mode; the first audio data is obtained by the first smart device in the calibration audio detection state of microphone calibration mode, based on collecting calibration audio played by the target device at a preset distance.

[0148] Processing module 32 is used to enter the calibration audio detection state in response to the third trigger command.

[0149] Acquisition module 33 is used to acquire the calibration audio played by a target device at a preset distance during calibration audio detection.

[0150] The processing module 32 is used to obtain second audio data based on the collected calibration audio; and to obtain the calibration parameters of the microphone of the second smart device based on the first audio data and the second audio data.

[0151] Optionally, the second trigger command includes: the microphone calibration status of the first smart device.

[0152] Optionally, the calibration audio includes a first audio segment, which is used to identify the start of playing the calibration audio. Optionally, the processing module 21 is specifically configured to, upon detecting the first audio segment of the calibration audio, obtain the second audio data based on the audio following the first audio segment of the calibration audio.

[0153] Optionally, both the first audio data and the second audio data include: at least one acquired audio segment and / or the energy of the at least one audio segment, and the calibration parameters include: parameters for characterizing microphone gain differences and / or parameters for characterizing audio energy differences acquired by the microphone.

[0154] The microphone calibration device 30 provided in this application is used to execute the microphone calibration method embodiment executed by the aforementioned second smart device. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0155] Figure 11 This is a schematic diagram of an electronic device provided in this application. The electronic device is a smart device with voice interaction capabilities. This electronic device can be either the aforementioned first smart device or the second smart device. Figure 11 As shown, the electronic device 400 may include: at least one processor 401 and memory 402, as well as a microphone 404, a transmitter 405 and a receiver 406.

[0156] The memory 402 is used to store programs. Specifically, the program may include program code, which includes computer operation instructions.

[0157] Memory 402 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0158] Receiver 406, transmitter 405, and microphone 404 are all coupled to processor 401. Processor 401 controls the receiving action of receiver 406, the transmitting action of transmitter 405, and the audio acquisition action of microphone 404.

[0159] The processor 401 is used to execute computer execution instructions stored in the memory 402 to implement the microphone calibration method described in the foregoing method embodiments. The processor 401 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0160] Optionally, the electronic device 400 may also include a communication interface 403. In specific implementations, if the communication interface 403, memory 402, and processor 401 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0161] Optionally, in a specific implementation, if the communication interface 403, memory 402 and processor 401 are integrated on a single chip, then the communication interface 403, memory 402 and processor 401 can communicate through an internal interface.

[0162] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Specifically, the computer-readable storage medium stores program instructions, which are used in the methods described in the above embodiments.

[0163] This application also provides a program product including executable instructions stored in a readable storage medium. At least one processor of an electronic device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the electronic device to implement the microphone calibration methods provided in the various embodiments described above.

[0164] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A microphone calibration method, characterized in that, A first smart device and a second smart device with voice interaction capabilities are located on the same local area network. The method is applied to the first smart device, and the method includes: In response to a first trigger command sent from the user terminal to the first smart device, the microphone calibration mode is entered. In microphone calibration mode, a second trigger command is sent to the second smart device, and the device enters calibration audio detection state; the second trigger command includes: the microphone calibration state of the first smart device, and the second trigger command is used to instruct the second smart device to enter microphone calibration mode; In the calibration audio detection state, the calibration audio played by the target device at a preset distance is collected. The playback of the calibration audio is triggered by the user through the smart home application of the target device. If the first audio segment of the calibration audio is detected, the first audio data is obtained based on the audio after the first audio segment of the calibration audio. The first audio segment is used to identify the start of playing the calibration audio. The first audio data is sent to the second smart device. The first audio data and the second audio data are used to determine the calibration parameters of the microphone of the second smart device. The second audio data is the audio after the first audio segment of the calibration audio obtained by the second smart device in the calibration audio detection state of the microphone calibration mode, based on the calibration audio played by the target device at a preset distance.

2. The method according to claim 1, characterized in that, Both the first audio data and the second audio data include: at least one audio segment acquired and / or the energy of the at least one audio segment, and the calibration parameters include: parameters for characterizing microphone gain differences and / or parameters for characterizing audio energy differences acquired by the microphone.

3. A microphone calibration method, characterized in that, A first smart device and a second smart device with voice interaction capabilities are located on the same local area network. The method is applied to the second smart device, and the method includes: The system receives a second trigger command sent by the first smart device in microphone calibration mode. The second trigger command is used to instruct the second smart device to enter microphone calibration mode, wherein the first smart device enters the microphone calibration mode in response to a first trigger command sent to the first smart device via a user terminal. The second trigger command includes the microphone calibration status of the first smart device. The system receives first audio data sent by the first smart device. The first audio data is the audio following the first audio segment of the calibration audio obtained by the first smart device in the calibration audio detection state of the microphone calibration mode, based on the calibration audio played by the target device at a preset distance. The first audio segment is used to identify the start of playing the calibration audio. The playback of the calibration audio is triggered by the user through the smart home application of the target device. In response to the third trigger command, enter the calibration audio detection state; In the calibration audio detection state, the calibration audio played by the target device at a preset distance is acquired. If the first audio segment of the calibration audio is detected, the second audio data is obtained based on the audio following the first audio segment of the calibration audio. Based on the first audio data and the second audio data, obtain the calibration parameters of the microphone of the second smart device.

4. The method according to claim 3, characterized in that, Both the first audio data and the second audio data include: at least one audio segment acquired and / or the energy of the at least one audio segment, and the calibration parameters include: parameters for characterizing microphone gain differences and / or parameters for characterizing audio energy differences acquired by the microphone.

5. A microphone calibration device, characterized in that, A first smart device and a second smart device with voice interaction capabilities are located on the same local area network. The device is applied to the first smart device, and the device includes: The processing module is configured to enter microphone calibration mode in response to a first trigger command sent to the first smart device via the user terminal; The first sending module is used to send a second trigger command to the second smart device in microphone calibration mode and enter the calibration audio detection state; the second trigger command includes: the microphone calibration state of the first smart device, and the second trigger command is used to instruct the second smart device to enter the microphone calibration mode; The acquisition module is used to acquire calibration audio played by a target device at a preset distance during calibration audio detection; the playback of the calibration audio is triggered by the user through the smart home application of the target device. The processing module is configured to, if a first audio segment of the calibration audio is detected, obtain first audio data based on the audio following the first audio segment of the calibration audio; the first audio segment is used to identify the start of playing the calibration audio. The second sending module is used to send the first audio data to the second smart device. The first audio data and the second audio data are used to determine the calibration parameters of the microphone of the second smart device. The second audio data is the audio after the first audio segment of the calibration audio obtained by the second smart device in the calibration audio detection state of the microphone calibration mode, based on the calibration audio played by the target device at a preset distance.

6. A microphone calibration device, characterized in that, A first smart device and a second smart device with voice interaction capabilities are located on the same local area network. The device is applied to the second smart device, and the device includes: A receiving module is configured to receive a second trigger command sent by the first smart device in microphone calibration mode, and to receive first audio data sent by the first smart device. The second trigger command is used to instruct the second smart device to enter microphone calibration mode. The first audio data is audio following a first audio segment of the calibration audio obtained by the first smart device in calibration audio detection state of microphone calibration mode, based on the calibration audio played by a target device at a preset distance. The first audio segment is used to identify the start of playing calibration audio. The first smart device enters the microphone calibration mode in response to a first trigger command sent to the first smart device via a user terminal. The second trigger command includes: the microphone calibration state of the first smart device. A processing module is configured to enter calibration audio detection state in response to a third trigger command. The acquisition module is used to acquire the calibration audio played by the target device at a preset distance during calibration audio detection; the playback of the calibration audio is triggered by the user through the smart home application of the target device. The processing module is configured to, if a first audio segment of the calibration audio is detected, obtain second audio data based on the audio following the first audio segment of the calibration audio; and obtain the calibration parameters of the microphone of the second smart device based on the first audio data and the second audio data.

Images