Parameter adjustment method and device, voice system, air conditioner and storage medium

Abstract

The application discloses a parameter adjusting method and device, a voice system, an air conditioner and a storage medium, and belongs to the technical field of data processing. The method comprises the following steps: playing a wake-up reply audio according to a current volume parameter; acquiring environmental audio in a current environment; performing echo cancellation processing on the environmental audio according to preset echo cancellation parameters corresponding to the current volume parameter to obtain target environmental audio; and when the target audio text corresponding to the target environmental audio contains audio text corresponding to the wake-up reply audio, adjusting the preset echo cancellation parameters until the target audio text does not contain the audio text. Therefore, the default preset echo cancellation parameters can be adaptively adjusted according to the use environment of a user, the echo cancellation parameters are more in line with the use environment of the user, and the effect of echo cancellation processing is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a parameter adjustment method, apparatus, voice system, air conditioner, and storage medium. Background Technology

[0002] Currently, voice systems typically play wake-up response audio based on the user's wake-up command. However, the voice system may mistakenly interpret the audio it plays as the user's command, resulting in a poor user experience. This is because the echo cancellation performance of the voice system is poor. Even if parameters are adjusted in a standard laboratory setting, differences in home layout, decoration, and space size, as well as variations in the brands and models of appliances used by different users, can cause reverberation parameters to differ across usage environments. This leads to poor echo cancellation and makes the voice system prone to misrecognition. Summary of the Invention

[0003] The main objective of this invention is to provide a parameter adjustment method, device, voice system, air conditioner, and storage medium, aiming to solve the technical problem that some reverberation parameters vary under different usage environments, resulting in poor echo cancellation effects in the prior art.

[0004] To achieve the above objectives, the present invention provides a parameter adjustment method, the parameter adjustment method comprising:

[0005] Play the wake-up response audio based on the current volume parameters;

[0006] Get the ambient audio in the current environment;

[0007] The ambient audio is subjected to echo cancellation processing according to the preset echo cancellation parameters corresponding to the current volume parameters to obtain the target ambient audio.

[0008] When the target audio text corresponding to the target environment audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted until the target audio text does not contain the audio text.

[0009] Optionally, adjusting the preset echo cancellation parameters includes:

[0010] Obtain the reception time and reception volume corresponding to the ambient audio;

[0011] The time interval is determined based on the playback time of the wake-up response audio and the reception time;

[0012] The preset echo cancellation parameter is adjusted according to the time interval and / or the received volume.

[0013] Optionally, when the target audio text corresponding to the target environmental audio contains audio text corresponding to the wake-up response audio, adjusting the preset echo cancellation parameter until the target audio text does not contain the audio text includes:

[0014] When the target audio text corresponding to the target environment audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted;

[0015] Play the wake-up response audio according to the current volume parameters, and perform echo cancellation processing on the ambient audio according to the adjusted echo cancellation parameters to obtain a new target ambient audio.

[0016] If the target audio text corresponding to the new target environment audio contains the audio text, return to the step of adjusting the preset echo cancellation parameters until the target audio text corresponding to the new target environment audio does not contain the audio text.

[0017] Optionally, adjusting the echo cancellation parameters until the target audiotext no longer contains the audiotext further includes:

[0018] The current volume parameter is associated with and saved with the adjusted echo cancellation parameter.

[0019] Optionally, before playing the wake-up response audio according to the current volume parameter, the method further includes:

[0020] Iterate through the volume parameters in the preset volume set and use the encountered volume parameter as the current volume parameter.

[0021] Optionally, the method further includes:

[0022] Once all volume parameters in the preset volume set have corresponding echo cancellation parameters associated with them, stop the adaptive adjustment of the echo cancellation parameters.

[0023] When a user's voice wake-up command is detected, the wake-up response audio is played according to the volume parameters set by the user;

[0024] Echo cancellation is performed on ambient audio in the current environment based on the echo cancellation parameters saved in association with the volume parameters set by the user.

[0025] Furthermore, to achieve the above objectives, the present invention also proposes a parameter adjustment device, the parameter adjustment device comprising:

[0026] The audio playback module is used to play the wake-up response audio based on the current volume parameters;

[0027] The information acquisition module is used to acquire ambient audio within the current environment;

[0028] The echo cancellation module is used to perform echo cancellation processing on the ambient audio according to preset echo cancellation parameters to obtain the target ambient audio.

[0029] The parameter adjustment module is used to adjust the preset echo cancellation parameter when the target audio text corresponding to the target environmental audio contains audio text corresponding to the wake-up response audio, until the target audio text does not contain the audio text.

[0030] Furthermore, to achieve the above objectives, the present invention also proposes a voice system, which includes: a memory, a processor, and a parameter adjustment program stored in the memory and executable on the processor. When the parameter adjustment program is executed by the processor, it implements the parameter adjustment method as described above.

[0031] In addition, to achieve the above objectives, the present invention also proposes an air conditioner that includes the voice system described above.

[0032] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a parameter adjustment program, which, when executed by a processor, implements the parameter adjustment method as described above.

[0033] In the parameter adjustment method proposed in this invention, a wake-up response audio is played according to the current volume parameter; ambient audio within the current environment is acquired; echo cancellation processing is performed on the ambient audio according to a preset echo cancellation parameter corresponding to the current volume parameter to obtain a target ambient audio; when the target audio text corresponding to the target ambient audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted until the target audio text no longer contains the audio text. This allows the default preset echo cancellation parameter to adaptively adjust according to the user's usage environment, making the echo cancellation parameter more suitable for the user's environment and improving the echo cancellation processing effect. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the voice system structure of the hardware operating environment involved in the embodiments of the present invention;

[0035] Figure 2 This is a flowchart illustrating the first embodiment of the parameter adjustment method of the present invention;

[0036] Figure 3 This is a schematic diagram illustrating the working principle of an embodiment of the parameter adjustment method of the present invention;

[0037] Figure 4 This is a flowchart illustrating the second embodiment of the parameter adjustment method of the present invention;

[0038] Figure 5 This is a schematic diagram of the functional modules of the first embodiment of the parameter adjustment device of the present invention.

[0039] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0040] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0041] Reference Figure 1 , Figure 1 This is a schematic diagram of the voice system structure of the hardware operating environment involved in the embodiment of the present invention.

[0042] like Figure 1 As shown, the voice system may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and input units such as buttons; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory, such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0043] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the voice system and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0044] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a parameter adjustment program.

[0045] exist Figure 1In the voice system shown, the network interface 1004 is mainly used to connect to the external network and communicate with other network devices; the user interface 1003 is mainly used to connect to the user equipment and communicate with the user equipment; the device of the present invention calls the parameter adjustment program stored in the memory 1005 through the processor 1001 and executes the parameter adjustment method provided in the embodiment of the present invention.

[0046] Based on the above hardware structure, an embodiment of the parameter adjustment method of the present invention is proposed.

[0047] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the parameter adjustment method of the present invention.

[0048] In the first embodiment, the parameter adjustment method includes:

[0049] Step S10: Play the wake-up response audio according to the current volume parameters.

[0050] It should be noted that the execution subject of this embodiment can be a voice system, which may include a processor, at least one sound playback device, and at least one sound detection device. The sound playback device can play audio, the sound detection device can acquire ambient audio, and the processor can analyze and process the ambient audio to perform echo cancellation and adjust echo cancellation parameters. This embodiment does not limit this.

[0051] It is understood that the sound playback device in this embodiment may include, but is not limited to, a speaker, and the sound detection device in this embodiment may include, but is not limited to, a microphone. This embodiment does not impose any restrictions on these.

[0052] It should be noted that the voice system in this embodiment can be used in conjunction with an air conditioner, enabling the air conditioner to adjust its status according to the user's voice commands, thereby allowing the user to control the operation of the air conditioner through voice control.

[0053] In one embodiment, the voice system can be separate from the air conditioner; that is, the voice system can be a separate external device, and the air conditioner can be an air conditioner without a voice module. The external voice system performs audio analysis and generates electrical control commands in response to user voice commands. These commands are then transmitted to the air conditioner's controller via Bluetooth, wireless network, or wired network, enabling the controller to operate the air conditioner according to the commands.

[0054] In another embodiment, the voice system can be integrated with the air conditioner; that is, the voice system can be a built-in device within the air conditioner, and the air conditioner can be an air conditioner containing a voice module. In this case, the speaker of the voice system can be a speaker mounted on the air conditioner, the microphone of the voice system can be a microphone mounted on the air conditioner, and the processor of the voice system can be integrated on the motherboard corresponding to the air conditioner's controller. Audio analysis is performed through the built-in voice system, and electronic control commands are generated in response to user voice commands. These electronic control commands are then transmitted to the air conditioner's controller via circuit connections on the motherboard, enabling the controller to operate the air conditioner according to the electronic control commands.

[0055] It should be noted that this embodiment does not impose any restrictions on the hardware and communication interface of the voice system and the air conditioner. In this embodiment, the UART serial port is selected as the pre-selected communication interface for illustration.

[0056] It should be understood that, since the voice system in this embodiment needs to be used in conjunction with the air conditioner, audio analysis is meaningless if the air conditioner is not turned on. Therefore, in order to avoid wasting resources and improve the user experience, the voice system can be set to automatically start when the air conditioner is turned on and automatically turn off when the air conditioner is turned off, so that the voice system can be turned on or off synchronously with the air conditioner. This embodiment does not impose any restrictions on this.

[0057] It should be noted that the wake-up response audio in this embodiment may include, but is not limited to, default wake-up response audio such as "Hello", "I'm here", "Coming", etc., or it may be a personalized wake-up response audio set by the user. This embodiment does not limit this.

[0058] It's understandable that echo cancellation in voice systems generally refers to acoustic echo. For example, after a user says a wake-up word, the voice system might respond with words like "hello," "I'm here," or "coming." Therefore, when a user wakes up an air conditioner, the voice system might interpret its own audio as the user's command, resulting in a poor user experience. This is because the echo cancellation performance of the voice system is poor. Even after adjusting parameters in a standard laboratory setting, differences in home layout, decoration, and space size, as well as variations in appliance brands and models, can cause reverberation parameters to differ across usage environments, leading to poor echo cancellation and misrecognition by the voice system. Therefore, this solution proposes a parameter adjustment method that adaptively adjusts echo cancellation parameters to reduce misrecognition.

[0059] It should be noted that, as Figure 3 As shown, Figure 3As shown in the schematic diagram, the working principle of the adaptive adjustment of echo cancellation parameters in this embodiment can be described as follows: 1. After the user completes the installation, the adaptive adjustment of echo cancellation parameters is triggered through the mobile APP; 2. First, the voice system will play a few specific short audio sentences at the lowest volume. While the speech is being played, the microphone picks up the audio. After echo cancellation, automatic speech recognition (ASR) is performed. If it contains specific short audio text, adaptive adjustment is performed until the audio after echo cancellation does not contain specific short audio text; 3. Repeat the above steps to gradually increase the volume of the voice system.

[0060] It should be understood that since parameter adjustment is not a function in the regular use of the voice system, but rather requires user triggering, the echo cancellation parameters are adjusted accordingly. Therefore, the voice system can monitor parameter adjustment commands when it is enabled, and upon receiving a user-input parameter adjustment command, it can adaptively adjust the echo cancellation parameters based on the command.

[0061] It is understandable that when starting the process of adaptively adjusting the echo cancellation parameters, it is possible to first check whether there is a user-set personalized wake-up response audio. If there is a user-set personalized wake-up response audio, then the personalized wake-up response audio is used as the wake-up response audio to be used now. If there is no user-set personalized wake-up response audio, then the default wake-up response audio is used as the wake-up response audio to be used now. This embodiment does not impose any restrictions on this.

[0062] It should be noted that the voice system in this embodiment is equipped with a corresponding preset volume set, which may contain multiple volume parameters supported by the voice system. This embodiment does not limit the number of volume parameters in the preset volume set.

[0063] In a specific implementation, the voice system in this embodiment may include at least two volume modes, which are as follows: 1. The volume can be freely adjusted between 0 and 100. In this case, the preset volume set may include 100 corresponding volume parameters; 2. It is divided into multiple volume levels, each volume level corresponding to one volume parameter. In this case, the preset volume set may include multiple volume parameters equal to the number of volume levels.

[0064] It should be understood that, since this solution needs to associate and save the corresponding echo cancellation parameter for each volume parameter in the preset volume set, in order to avoid missing some volume parameters and causing incomplete association, the volume parameters in the preset volume set can be traversed sequentially, and the traversed volume parameter can be used as the current volume parameter, thereby controlling the speaker to play the wake-up response audio based on the current volume parameter.

[0065] Step S20: Obtain the ambient audio in the current environment.

[0066] It is understandable that while controlling the speaker to play the wake-up response audio based on the current volume parameters, it is also possible to control the microphone to record ambient audio in the current environment and send the recorded ambient audio to the processor of the voice system.

[0067] Step S30: Perform echo cancellation processing on the ambient audio according to the preset echo cancellation parameters corresponding to the current volume parameters to obtain the target ambient audio.

[0068] It should be understood that the processor of the voice system can find the preset echo cancellation parameters corresponding to the current volume parameters by default, and then perform echo cancellation processing on the ambient audio according to the preset echo cancellation parameters, and obtain the target ambient audio after echo cancellation based on the echo cancellation processing result.

[0069] Step S40: When the target audio text corresponding to the target environment audio contains audio text corresponding to the wake-up response audio, adjust the preset echo cancellation parameter until the target audio text does not contain the audio text.

[0070] It should be understood that after obtaining the target environment audio, ASR recognition can be performed on the target environment audio to obtain the target audiotext corresponding to the target environment audio. Furthermore, the audiotext corresponding to the wake-up response audio can be searched, and then the target audiotext can be compared with the audiotext to determine whether the target audiotext contains the aforementioned audiotext. If the target audiotext does not contain the aforementioned audiotext, it indicates that the echo cancellation processing is effective, and the current audio parameters can be associated and saved with the corresponding preset echo cancellation parameters. The next audio parameter in the preset volume set can then be processed. If the target audiotext contains the aforementioned audiotext, it indicates that the echo cancellation processing is ineffective, and the speech system may misrecognize the audiotext. Therefore, the preset echo cancellation parameters can be adjusted until the target audiotext does not contain the audiotext, and then the current audio parameters can be associated and saved with the adjusted echo cancellation parameters.

[0071] In one embodiment, in order to adjust the preset echo cancellation parameters more accurately and achieve better parameter adjustment effect, the reception time when the microphone receives ambient audio and the playback time when the speaker plays wake-up response audio can be obtained. The time interval is calculated based on the playback time and the reception time, and then the preset echo cancellation parameters can be adjusted according to the time interval.

[0072] In another embodiment, the received volume of the ambient audio received by the microphone can also be obtained, and then the preset echo cancellation parameters can be adjusted according to the received volume.

[0073] In another embodiment, the receiving time when the microphone receives ambient audio, the receiving volume corresponding to the ambient audio, and the playback time when the speaker plays wake-up response audio can also be obtained. The time interval is calculated based on the playback time and the receiving time, and then the preset echo cancellation parameters can be adjusted according to the time interval and the receiving volume.

[0074] It should be understood that, since a single parameter adjustment may not be sufficient to eliminate the audio text from the target audio text, the preset echo cancellation parameters can be adjusted. A wake-up response audio can be played based on the current volume parameters, and then echo cancellation processing is applied to the ambient audio using the adjusted echo cancellation parameters to obtain a new target ambient audio. The new target audio text can then be compared with the existing audio text to determine if it contains the aforementioned audio text. If the new target audio text does not contain the aforementioned audio text, the echo cancellation parameter adjustment is effective, and the current audio parameters can be associated with and saved with the adjusted echo cancellation parameters. The process continues by iterating through the next audio parameter in the preset volume set. If the new target audio text contains the aforementioned audio text, the echo cancellation parameter adjustment is ineffective, and further adjustment of the echo cancellation parameters is necessary.

[0075] Understandably, after the parameters are adaptively adjusted in the above way, when the user uses the voice system, the voice system can perform echo cancellation processing based on these associated and saved echo cancellation parameters, which can achieve better echo cancellation effect and avoid misrecognition.

[0076] Understandably, the adjustment process of this solution can be kept quiet, requiring only user triggering and no further user intervention, making the operation simple. By adjusting each machine individually, the influence of each device's installation environment can be eliminated, making it universally applicable. Compared to traditional factory preset parameters, which only consider the effect in small spaces and floor-standing air conditioners only consider the effect in large spaces such as living rooms, this method is not affected by space and is equivalent to making independent customized parameters for each user, making it more suitable for the user's usage environment.

[0077] In this embodiment, a wake-up response audio is played according to the current volume parameter; ambient audio within the current environment is acquired; echo cancellation processing is performed on the ambient audio according to a preset echo cancellation parameter corresponding to the current volume parameter to obtain a target ambient audio; when the target audio text corresponding to the target ambient audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted until the target audio text no longer contains the audio text. This allows the default preset echo cancellation parameter to adaptively adjust according to the user's usage environment, making the echo cancellation parameter more suitable for the user's environment and improving the echo cancellation processing effect.

[0078] In one embodiment, such as Figure 4 As shown, based on the first embodiment, a second embodiment of the parameter adjustment method of the present invention is proposed. After step S40, it further includes:

[0079] Step S50: Associate and save the current volume parameter with the adjusted echo cancellation parameter.

[0080] It should be noted that during the process of iterating through the volume parameters in the preset volume set and adaptively adjusting the echo cancellation parameters in the manner described above, if the target audio text contains audio text, it means that the current echo cancellation parameters can achieve a good effect at this volume. Therefore, the adjusted echo cancellation parameters can be associated with and saved with the current volume parameters.

[0081] Understandably, to further improve accuracy, multiple parameter adjustments can be performed. After obtaining several suitable values ​​through adjustments, the final value is determined based on the average of these values. In addition, at least one more test can be conducted based on the obtained average value to verify it. If the verification is successful, this average value is used as the final value, and the final values ​​of the current volume parameter and echo cancellation parameter are associated and saved. This embodiment does not impose any limitations on this approach.

[0082] Understandably, after the volume parameters have been processed, all volume parameters in the preset volume set should have corresponding echo cancellation parameters associated with them. Therefore, after the processing is complete, it is possible to check whether all volume parameters have corresponding echo cancellation parameters associated with them. If not, it indicates that there may have been omissions or errors during the processing, and the processing needs to be restarted. If yes, it means that the processing has been successfully completed, and the adaptive adjustment of the echo cancellation parameters can be stopped.

[0083] It should be understood that the voice system can also monitor the user's voice wake-up command when the echo cancellation parameter adaptive adjustment is stopped, so as to respond to the user's voice wake-up at any time and control the operation status of the air conditioner according to the user's voice command.

[0084] Understandably, users can freely adjust the volume of the voice system when using it. Therefore, if the voice system detects the user's voice wake-up command, it can obtain the latest user-set volume parameters and play the wake-up response audio according to the user-set volume parameters.

[0085] Understandably, the voice system can also look up echo cancellation parameters associated with the volume parameters set by the user, and perform echo cancellation processing on the ambient audio in the current environment based on the associated and saved echo cancellation parameters. This can prevent the audio played by the voice system from affecting the user's voice commands and avoid voice misrecognition.

[0086] In this embodiment, the volume parameters can be associated with and saved with echo cancellation parameters that match the current usage environment. During normal use, after the voice system plays the wake-up response volume, it will use the echo cancellation parameters associated with the user-set volume parameters to perform echo cancellation processing on the ambient audio. This can prevent the audio played by the voice system from affecting the user's voice commands, improve the sensitivity of the voice system, and bring a better user experience.

[0087] Furthermore, this embodiment of the invention also proposes a storage medium storing a parameter adjustment program, which, when executed by a processor, implements the steps of the parameter adjustment method described above.

[0088] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0089] In addition, refer to Figure 5 The present invention also proposes a parameter adjustment device, the parameter adjustment device comprising:

[0090] The audio playback module 10 is used to play wake-up response audio according to the current volume parameters.

[0091] It is understood that the sound playback device in this embodiment may include, but is not limited to, a speaker, and the sound detection device in this embodiment may include, but is not limited to, a microphone. This embodiment does not impose any restrictions on these.

[0092] It should be noted that the voice system in this embodiment can be used in conjunction with an air conditioner, enabling the air conditioner to adjust its status according to the user's voice commands, thereby allowing the user to control the operation of the air conditioner through voice control.

[0093] In one embodiment, the voice system can be separate from the air conditioner; that is, the voice system can be a separate external device, and the air conditioner can be an air conditioner without a voice module. The external voice system performs audio analysis and generates electrical control commands in response to user voice commands. These commands are then transmitted to the air conditioner's controller via Bluetooth, wireless network, or wired network, enabling the controller to operate the air conditioner according to the commands.

[0094] In another embodiment, the voice system can be integrated with the air conditioner; that is, the voice system can be a built-in device within the air conditioner, and the air conditioner can be an air conditioner containing a voice module. In this case, the speaker of the voice system can be a speaker mounted on the air conditioner, the microphone of the voice system can be a microphone mounted on the air conditioner, and the processor of the voice system can be integrated on the motherboard corresponding to the air conditioner's controller. Audio analysis is performed through the built-in voice system, and electronic control commands are generated in response to user voice commands. These electronic control commands are then transmitted to the air conditioner's controller via circuit connections on the motherboard, enabling the controller to operate the air conditioner according to the electronic control commands.

[0095] It should be noted that this embodiment does not impose any restrictions on the hardware and communication interface of the voice system and the air conditioner. In this embodiment, the UART serial port is selected as the pre-selected communication interface for illustration.

[0096] It should be understood that, since the voice system in this embodiment needs to be used in conjunction with the air conditioner, audio analysis is meaningless if the air conditioner is not turned on. Therefore, in order to avoid wasting resources and improve the user experience, the voice system can be set to automatically start when the air conditioner is turned on and automatically turn off when the air conditioner is turned off, so that the voice system can be turned on or off synchronously with the air conditioner. This embodiment does not impose any restrictions on this.

[0097] It should be noted that the wake-up response audio in this embodiment may include, but is not limited to, default wake-up response audio such as "Hello", "I'm here", "Coming", etc., or it may be a personalized wake-up response audio set by the user. This embodiment does not limit this.

[0098] It's understandable that echo cancellation in voice systems generally refers to acoustic echo. For example, after a user says a wake-up word, the voice system might respond with words like "hello," "I'm here," or "coming." Therefore, when a user wakes up an air conditioner, the voice system might interpret its own audio as the user's command, resulting in a poor user experience. This is because the echo cancellation performance of the voice system is poor. Even after adjusting parameters in a standard laboratory setting, differences in home layout, decoration, and space size, as well as variations in appliance brands and models, can cause reverberation parameters to differ across usage environments, leading to poor echo cancellation and misrecognition by the voice system. Therefore, this solution proposes a parameter adjustment method that adaptively adjusts echo cancellation parameters to reduce misrecognition.

[0099] It should be noted that, as Figure 3 As shown, Figure 3 As shown in the schematic diagram, the working principle of the adaptive adjustment of echo cancellation parameters in this embodiment can be described as follows: 1. After the user completes the installation, the adaptive adjustment of echo cancellation parameters is triggered through the mobile APP; 2. First, the voice system will play a few specific short audio sentences at the lowest volume. While the speech is being played, the microphone picks up the audio. After echo cancellation, automatic speech recognition (ASR) is performed. If it contains specific short audio text, adaptive adjustment is performed until the audio after echo cancellation does not contain specific short audio text; 3. Repeat the above steps to gradually increase the volume of the voice system.

[0100] It should be understood that since parameter adjustment is not a function in the regular use of the voice system, but rather requires user triggering, the echo cancellation parameters are adjusted accordingly. Therefore, the voice system can monitor parameter adjustment commands when it is enabled, and upon receiving a user-input parameter adjustment command, it can adaptively adjust the echo cancellation parameters based on the command.

[0101] It is understandable that when starting the process of adaptively adjusting the echo cancellation parameters, it is possible to first check whether there is a user-set personalized wake-up response audio. If there is a user-set personalized wake-up response audio, then the personalized wake-up response audio is used as the wake-up response audio to be used now. If there is no user-set personalized wake-up response audio, then the default wake-up response audio is used as the wake-up response audio to be used now. This embodiment does not impose any restrictions on this.

[0102] It should be noted that the voice system in this embodiment is equipped with a corresponding preset volume set, which may contain multiple volume parameters supported by the voice system. This embodiment does not limit the number of volume parameters in the preset volume set.

[0103] In a specific implementation, the voice system in this embodiment may include at least two volume modes, which are as follows: 1. The volume can be freely adjusted between 0 and 100. In this case, the preset volume set may include 100 corresponding volume parameters; 2. It is divided into multiple volume levels, each volume level corresponding to one volume parameter. In this case, the preset volume set may include multiple volume parameters equal to the number of volume levels.

[0104] It should be understood that, since this solution needs to associate and save the corresponding echo cancellation parameter for each volume parameter in the preset volume set, in order to avoid missing some volume parameters and causing incomplete association, the volume parameters in the preset volume set can be traversed sequentially, and the traversed volume parameter can be used as the current volume parameter, thereby controlling the speaker to play the wake-up response audio based on the current volume parameter.

[0105] The information acquisition module 20 is used to acquire ambient audio within the current environment.

[0106] It is understandable that while controlling the speaker to play the wake-up response audio based on the current volume parameters, it is also possible to control the microphone to record ambient audio in the current environment and send the recorded ambient audio to the processor of the voice system.

[0107] The echo cancellation module 30 is used to perform echo cancellation processing on the ambient audio according to preset echo cancellation parameters to obtain the target ambient audio.

[0108] It should be understood that the processor of the voice system can find the preset echo cancellation parameters corresponding to the current volume parameters by default, and then perform echo cancellation processing on the ambient audio according to the preset echo cancellation parameters, and obtain the target ambient audio after echo cancellation based on the echo cancellation processing result.

[0109] The parameter adjustment module 40 is used to adjust the preset echo cancellation parameter when the target audio text corresponding to the target environmental audio contains audio text corresponding to the wake-up response audio, until the target audio text does not contain the audio text.

[0110] It should be understood that after obtaining the target environment audio, ASR recognition can be performed on the target environment audio to obtain the target audiotext corresponding to the target environment audio. Furthermore, the audiotext corresponding to the wake-up response audio can be searched, and then the target audiotext can be compared with the audiotext to determine whether the target audiotext contains the aforementioned audiotext. If the target audiotext does not contain the aforementioned audiotext, it indicates that the echo cancellation processing is effective, and the current audio parameters can be associated and saved with the corresponding preset echo cancellation parameters. The next audio parameter in the preset volume set can then be processed. If the target audiotext contains the aforementioned audiotext, it indicates that the echo cancellation processing is ineffective, and the speech system may misrecognize the audiotext. Therefore, the preset echo cancellation parameters can be adjusted until the target audiotext does not contain the audiotext, and then the current audio parameters can be associated and saved with the adjusted echo cancellation parameters.

[0111] In one embodiment, in order to adjust the preset echo cancellation parameters more accurately and achieve better parameter adjustment effect, the reception time when the microphone receives ambient audio and the playback time when the speaker plays wake-up response audio can be obtained. The time interval is calculated based on the playback time and the reception time, and then the preset echo cancellation parameters can be adjusted according to the time interval.

[0112] In another embodiment, the received volume of the ambient audio received by the microphone can also be obtained, and then the preset echo cancellation parameters can be adjusted according to the received volume.

[0113] In another embodiment, the receiving time when the microphone receives ambient audio, the receiving volume corresponding to the ambient audio, and the playback time when the speaker plays wake-up response audio can also be obtained. The time interval is calculated based on the playback time and the receiving time, and then the preset echo cancellation parameters can be adjusted according to the time interval and the receiving volume.

[0114] It should be understood that, since a single parameter adjustment may not be sufficient to eliminate the audio text from the target audio text, the preset echo cancellation parameters can be adjusted. A wake-up response audio can be played based on the current volume parameters, and then echo cancellation processing is applied to the ambient audio using the adjusted echo cancellation parameters to obtain a new target ambient audio. The new target audio text can then be compared with the existing audio text to determine if it contains the aforementioned audio text. If the new target audio text does not contain the aforementioned audio text, the echo cancellation parameter adjustment is effective, and the current audio parameters can be associated with and saved with the adjusted echo cancellation parameters. The process continues by iterating through the next audio parameter in the preset volume set. If the new target audio text contains the aforementioned audio text, the echo cancellation parameter adjustment is ineffective, and further adjustment of the echo cancellation parameters is necessary.

[0115] Understandably, after the parameters are adaptively adjusted in the above way, when the user uses the voice system, the voice system can perform echo cancellation processing based on these associated and saved echo cancellation parameters, which can achieve better echo cancellation effect and avoid misrecognition.

[0116] Understandably, the adjustment process of this solution can be kept quiet, requiring only user triggering and no further user intervention, making the operation simple. By adjusting each machine individually, the influence of each device's installation environment can be eliminated, making it universally applicable. Compared to traditional factory preset parameters, which only consider the effect in small spaces and floor-standing air conditioners only consider the effect in large spaces such as living rooms, this method is not affected by space and is equivalent to making independent customized parameters for each user, making it more suitable for the user's usage environment.

[0117] In this embodiment, a wake-up response audio is played according to the current volume parameter; ambient audio within the current environment is acquired; echo cancellation processing is performed on the ambient audio according to a preset echo cancellation parameter corresponding to the current volume parameter to obtain a target ambient audio; when the target audio text corresponding to the target ambient audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted until the target audio text no longer contains the audio text. This allows the default preset echo cancellation parameter to adaptively adjust according to the user's usage environment, making the echo cancellation parameter more suitable for the user's environment and improving the echo cancellation processing effect.

[0118] Other embodiments or specific implementation methods of the parameter adjustment device described in this invention can refer to the above-described method embodiments, and will not be repeated here.

[0119] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0120] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This estimation machine software product is stored in an estimation machine readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a smart device (which may be a mobile phone, estimation machine, voice system, or network voice system, etc.) to execute the methods described in the various embodiments of the present invention.

[0122] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A parameter adjustment method, characterized in that, The parameter adjustment method includes: Play the wake-up response audio according to the current volume parameters. The steps for determining the wake-up response audio include: checking whether a user-set personalized wake-up response audio exists; if a user-set personalized wake-up response audio exists, use the personalized wake-up response audio as the wake-up response audio to be used; if no user-set personalized wake-up response audio exists, use the default wake-up response audio as the wake-up response audio to be used. Get the ambient audio in the current environment; The ambient audio is subjected to echo cancellation processing according to the preset echo cancellation parameter corresponding to the current volume parameter to obtain the target ambient audio. The target ambient audio is then subjected to ASR recognition to obtain the target audio text corresponding to the target ambient audio. When the target audio text corresponding to the target environment audio contains audio text corresponding to the wake-up response audio, adjust the preset echo cancellation parameter until the target audio text does not contain the audio text. The adjustment of the preset echo cancellation parameters includes: Obtain the reception time and reception volume corresponding to the ambient audio; The time interval is determined based on the playback time of the wake-up response audio and the reception time; and Adjust the preset echo cancellation parameter according to the time interval and / or the received volume; When the target audio text corresponding to the target environmental audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted until the target audio text no longer contains the audio text, including: When the target audio text corresponding to the target environment audio contains audio text corresponding to the wake-up response audio, the preset echo cancellation parameter is adjusted; Play the wake-up response audio according to the current volume parameters, and perform echo cancellation processing on the ambient audio according to the adjusted echo cancellation parameters to obtain a new target ambient audio; and If the target audio text corresponding to the new target environment audio contains the audio text, return to the step of adjusting the preset echo cancellation parameters until the target audio text corresponding to the new target environment audio does not contain the audio text.

2. The parameter adjustment method as described in claim 1, characterized in that, After adjusting the echo cancellation parameters until the target audio text no longer contains the audio text, the process further includes: The current volume parameter is associated with and saved with the adjusted echo cancellation parameter.

3. The parameter adjustment method as described in claim 2, characterized in that, Before playing the wake-up response audio based on the current volume parameters, the method further includes: Iterate through the volume parameters in the preset volume set and use the encountered volume parameter as the current volume parameter.

4. The parameter adjustment method as described in claim 3, characterized in that, The method further includes: Once all volume parameters in the preset volume set have corresponding echo cancellation parameters associated with them, stop the adaptive adjustment of the echo cancellation parameters. Upon detecting a user's voice wake-up command, the wake-up response audio is played according to the volume parameters set by the user; and Echo cancellation is performed on ambient audio in the current environment based on the echo cancellation parameters saved in association with the volume parameters set by the user.

5. A parameter adjustment device, characterized in that, The parameter adjustment device includes: The audio playback module is used to play a wake-up response audio according to the current volume parameters. The steps for determining the wake-up response audio include: checking whether a user-set personalized wake-up response audio exists; if a user-set personalized wake-up response audio exists, using the personalized wake-up response audio as the wake-up response audio to be used; if no user-set personalized wake-up response audio exists, using the default wake-up response audio as the wake-up response audio to be used. The information acquisition module is used to acquire ambient audio within the current environment; The echo cancellation module is used to perform echo cancellation processing on the ambient audio according to preset echo cancellation parameters to obtain target ambient audio, and to perform ASR recognition on the target ambient audio to obtain target audio text corresponding to the target ambient audio. The parameter adjustment module is used to adjust the preset echo cancellation parameter when the target audio text corresponding to the target environmental audio contains audio text corresponding to the wake-up response audio, until the target audio text does not contain the audio text. The parameter adjustment module is also used to obtain the reception time and reception volume corresponding to the ambient audio; determine the time interval based on the playback time of the wake-up response audio and the reception time; and adjust the preset echo cancellation parameter based on the time interval and / or the reception volume. The parameter adjustment module is further configured to: adjust the preset echo cancellation parameter when the target audio text corresponding to the target ambient audio contains audio text corresponding to the wake-up response audio; play the wake-up response audio according to the current volume parameter, and perform echo cancellation processing on the ambient audio according to the adjusted echo cancellation parameter to obtain a new target ambient audio; and return to the step of adjusting the preset echo cancellation parameter when the target audio text corresponding to the new target ambient audio contains the audio text, until the target audio text corresponding to the new target ambient audio does not contain the audio text.

6. A voice system, characterized in that, The voice system includes: a memory, a processor, and a parameter adjustment program stored in the memory and executable on the processor, wherein the parameter adjustment program, when executed by the processor, implements the parameter adjustment method as described in any one of claims 1 to 4.

7. An air conditioner, characterized in that, The air conditioner includes the voice system as described in claim 6.

8. A storage medium, characterized in that, The storage medium stores a parameter adjustment program, which, when executed by a processor, implements the parameter adjustment method as described in any one of claims 1 to 4.

Images