CN-115314826-B - Microphone calibration method and device

CN115314826BCN 115314826 BCN115314826 BCN 115314826BCN-115314826-B

Abstract

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

Inventors

DENG QIUWEI
ZHANG XINSHENG
WANG DI
ZHANG LI

Assignees

青岛海尔科技有限公司
青岛海尔智能家电科技有限公司
海尔智家股份有限公司

Dates

Publication Date: 20260508
Application Date: 20220630

Claims (6)

1. A microphone calibration method, wherein a first smart device and a second smart device having a voice interaction function are in the same local area network, the method being applied to the first smart device, the method comprising: Responding to a first trigger instruction sent to the first intelligent device through a user terminal, and entering a microphone calibration mode; in a microphone calibration mode, a second trigger instruction is sent to the second intelligent device and enters a calibration audio detection state, wherein the second trigger instruction comprises a microphone calibration state of the first intelligent device, and the second trigger instruction is used for indicating the second intelligent device to enter the microphone calibration mode; In a calibration audio detection state, collecting calibration audio played by target equipment with a preset distance, wherein the playing of the calibration audio is triggered by a user through an intelligent home application program of the target equipment, and if a first audio fragment of the calibration audio is detected, obtaining first audio data based on audio after the first audio fragment of the calibration audio; And sending the first audio data to a second intelligent device, wherein the first audio data and the second audio data are used for determining calibration parameters of a microphone of the second intelligent device, and the second audio data are audio after the first audio fragment of the calibration audio, which is obtained by acquiring the calibration audio played by the target device at a preset distance, of the second intelligent device in a calibration audio detection state of a microphone calibration mode.
2. The method according to claim 1, wherein the first audio data and the second audio data each comprise collected at least one audio piece and/or energy of the at least one audio piece, and wherein the calibration parameters comprise parameters for characterizing microphone gain differences and/or parameters for characterizing microphone collected audio energy differences.
3. A microphone calibration method, wherein a first smart device and a second smart device having a voice interaction function are in the same local area network, the method being applied to the second smart device, the method comprising: Receiving a second trigger instruction sent by the first intelligent device in a microphone calibration mode, wherein the second trigger instruction is used for indicating the second intelligent device to enter the microphone calibration mode, and the first intelligent device is in the microphone calibration mode which is entered in response to the first trigger instruction sent to the first intelligent device through a user terminal; Receiving first audio data sent by the first intelligent device, wherein the first audio data is audio after a first audio fragment of calibration audio obtained by collecting the calibration audio played by target equipment with a preset distance in a calibration audio detection state of a microphone calibration mode of the first intelligent device, and the first audio fragment is used for identifying to start playing the calibration audio; responding to a third trigger instruction, and entering a calibration audio detection state; Collecting the calibration audio played by the target equipment at a preset distance in a calibration audio detection state, and if a first audio fragment of the calibration audio is detected, obtaining second audio data based on the audio after the first audio fragment of the calibration audio; And acquiring calibration parameters of a microphone of the second intelligent device according to the first audio data and the second audio data.
4. The method of claim 3, wherein the first audio data and the second audio data each comprise at least one audio segment and/or energy of the at least one audio segment collected, and wherein the calibration parameters comprise parameters for characterizing microphone gain differences and/or parameters for characterizing microphone collected audio energy differences.
5. A microphone calibration apparatus, wherein a first smart device and a second smart device having a voice interaction function are in the same local area network, the apparatus being applied to the first smart device, the apparatus comprising: the processing module is used for responding to a first trigger instruction sent to the first intelligent device through the user terminal and entering a microphone calibration mode; The first intelligent device comprises a first sending module, a second sending module and a second sending module, wherein the first sending module is used for sending a second trigger instruction to the second intelligent device in a microphone calibration mode and entering a calibration audio detection state; The system comprises an acquisition module, a calibration audio acquisition module and a control module, wherein the acquisition module is used for acquiring calibration audio played by target equipment with a preset distance in a calibration audio detection state, and the playing of the calibration audio is triggered by a user through an intelligent home application program of the target equipment; The processing module is used for obtaining first audio data based on the audio after the first audio fragment of the calibration audio if the first audio fragment of the calibration audio is detected; the second sending module is configured to send the first audio data to a second intelligent device, where the first audio data and the second audio data are used to determine calibration parameters of a microphone of the second intelligent device, and the second audio data are audio after the first audio segment of the calibration audio obtained by collecting the calibration audio played by the target device at a preset distance in a calibration audio detection state of a microphone calibration mode of the second intelligent device.
6. A microphone calibration apparatus, wherein a first smart device and a second smart device having a voice interaction function are in the same local area network, the apparatus being applied to the second smart device, the apparatus comprising: The system comprises a receiving module, a processing module and a control module, wherein the receiving module is used for receiving a second trigger instruction sent by the first intelligent device in a microphone calibration mode, and receiving first audio data sent by the first intelligent device, the second trigger instruction is used for indicating the second intelligent device to enter the microphone calibration mode, the first audio data is audio after a first audio fragment of the calibration audio obtained by collecting calibration audio played by target devices with a preset distance in a calibration audio detection state of the microphone calibration mode, the first audio fragment is used for identifying to begin playing the calibration audio, the first intelligent device is in the microphone calibration mode which is entered in response to the first trigger instruction sent to the first intelligent device by a user terminal, and the second trigger instruction comprises the microphone calibration state of the first intelligent device; the system comprises an acquisition module, a calibration audio acquisition module and a control module, wherein the acquisition module is used for acquiring the calibration audio played by the target equipment at a preset distance in a calibration audio detection state; The processing module is used for obtaining second audio data based on the audio after the first audio fragment of the calibration audio if the first audio fragment of the calibration audio is detected, and obtaining the calibration parameters of the microphone of the second intelligent device according to the first audio data and the second audio data.

Description

Microphone calibration method and device Technical Field The application relates to the field of electronic products, in particular to a microphone calibration method and device. Background With the development of intelligent voice technology, intelligent devices (such as intelligent refrigerators, intelligent air conditioners, etc.) with voice interaction function are becoming popular. Taking the above-mentioned smart devices as smart home devices as an example, in general, a user may install a plurality of smart home devices in a home. At present, wake-up instructions of a plurality of smart home devices of the same manufacturer are generally the same, so that when a user wakes up a smart device a through the wake-up instructions, other smart devices, which belong to the same manufacturer as the smart device a, near the user are also woken up. At present, the method for solving the problems mainly comprises the steps that after a user sends a wake-up instruction, each intelligent device nearby the user collects the wake-up instruction through a microphone, and audio energy of the wake-up instruction is sent to a device management cloud platform of a manufacturer corresponding to the intelligent device. The device management cloud platform can determine the target intelligent device which the user wants to wake up according to the audio energy of the wake-up instruction acquired by the microphone of each intelligent device. That is, the target smart device needs to be determined based on the audio energy of the wake-up instruction collected by the microphone of each smart device. It is therefore important to ensure that the sensitivity of the microphones of different smart devices is the same. Disclosure of Invention The application provides a microphone calibration method and device, which are used for guaranteeing the consistency of the sensitivity of microphones of different intelligent devices. In a first aspect, the present application provides a microphone calibration method, where a first smart device and a second smart device having a voice interaction function are located in the same local area network, the method being applied to the first smart device, the method including: responding to a first trigger instruction, and entering a microphone calibration mode; in a microphone calibration mode, a second trigger instruction is sent to the second intelligent device and enters a calibration audio detection state; in a calibration audio detection state, collecting calibration audio played by target equipment with a preset distance, and obtaining first audio data based on the collected calibration audio; and sending the first audio data to a second intelligent device, wherein the first audio data and the second audio data are used for determining calibration parameters of a microphone of the second intelligent device, and the second audio data are obtained based on acquisition of the calibration audio played by the target device at a preset distance in a calibration audio detection state of a microphone calibration mode of the second intelligent device. Optionally, the second trigger instruction comprises a microphone calibration state of the first smart device. Optionally, the calibration audio comprises a first audio fragment, wherein the first audio fragment is used for identifying the start of playing the calibration audio, and the first audio data is obtained based on the collected calibration audio, and comprises the following steps: And if the first audio fragment of the calibration audio is detected, obtaining the first audio data based on the audio after the first audio fragment of the calibration audio. Optionally, the first audio data and the second audio data each comprise at least one audio segment and/or energy of the at least one audio segment acquired, and the calibration parameters comprise parameters for characterizing microphone gain differences and/or parameters for characterizing microphone acquired audio energy differences. In a second aspect, the present application provides a microphone calibration method, where a first smart device and a second smart device having a voice interaction function are located in the same local area network, the method being applied to the second smart device, the method including: receiving a second trigger instruction sent by the first intelligent device in a microphone calibration mode, wherein the second trigger instruction is used for indicating the second intelligent device to enter the microphone calibration mode; Receiving first audio data sent by the first intelligent device, wherein the first audio data is obtained by the first intelligent device based on acquisition of calibration audio played by the target device at a preset distance in a calibration audio detection state of a microphone calibration mode; responding to a third trigger instruction, and entering a calibration audio detection state; in a calibration audio detection state, co