Voice control method, device and system, household appliance, storage medium and product

Abstract

The invention relates to a voice control method, device and system, a household appliance, a storage medium and a product, and the method comprises the steps: firstly obtaining an environment noise parameter of a current environment under the condition of detecting that a user sends a voice wake-up word, and then carrying out the adaptation of voice recognition sensitivity and voice reply volume for the current environment through combining with the environment noise parameter. And finally, related actions of voice control are executed according to the adaptive voice recognition sensitivity and the voice reply volume, namely, a voice action instruction is recognized, and a reply signal is fed back to the user based on the voice action instruction. Therefore, the voice action instruction sent by the user can be accurately recognized, the reply signal can be transmitted to the user with enough volume, and the possibility of voice control failure is effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of home appliance technology, and in particular to a voice control method, device, system, home appliance equipment, storage medium and computer program product. Background Art

[0002] With the rapid development of science and technology, voice control technology has gradually been applied to various home appliances, bringing great convenience to people's lives.

[0003] However, in the related art, it is easy for voice control to fail. For example, when the user issues a voice action command, the voice control does not work, or the user independently starts the voice control function without issuing a voice action command. Summary of the invention

[0004] Based on this, it is necessary to provide a voice control method, device, system, home appliance, storage medium and computer program product to address the problem that voice control is prone to failure. The methods can not only accurately identify the voice action commands issued by the user, but also transmit the reply signals to the user with sufficient volume, thereby effectively reducing the possibility of voice control failure.

[0005] A voice control method comprises: when a voice wake-up word is detected, obtaining environmental noise parameters of the current environment; determining a voice recognition sensitivity adapted to the current environment and a voice reply volume adapted to the current environment according to the environmental noise parameters; recognizing a voice action instruction according to the voice recognition sensitivity; and outputting a reply signal at the voice reply volume in response to a recognition result of the voice action instruction.

[0006] In one of the embodiments, determining the speech recognition sensitivity adapted to the current environment and the speech response volume adapted to the current environment based on the environmental noise parameters includes: performing a matching analysis based on the environmental noise parameters and a preset sensitivity database to determine the speech recognition sensitivity adapted to the current environment; the sensitivity database stores the speech recognition sensitivities corresponding to different environmental noise parameters; performing a matching analysis based on the environmental noise parameters and a preset volume database to determine the speech response volume adapted to the current environment; the volume database stores the speech response volumes corresponding to different environmental noise parameters.

[0007] In one embodiment, the noisier the current environment represented by the environmental noise parameter, the lower the adapted speech recognition sensitivity; and / or, the noisier the current environment represented by the environmental noise parameter, the higher the adapted speech reply volume.

[0008] In one embodiment, the environmental noise parameter is an environmental signal-to-noise ratio, and obtaining the environmental noise parameter of the current environment includes: obtaining a first energy parameter of the voice wake-up word and a second energy parameter of the environmental noise; and determining the environmental signal-to-noise ratio based on the first energy parameter and the second energy parameter.

[0009] In one embodiment, the determining, according to the environmental noise parameter, the speech recognition sensitivity adapted to the current environment and the speech reply volume adapted to the current environment comprises: when the environmental signal-to-noise ratio is within a first threshold range, determining that the speech recognition sensitivity adapted to the current environment is the first sensitivity, and the speech reply volume adapted to the current environment is the first reply volume; when the environmental signal-to-noise ratio is within a second threshold range, determining that the speech recognition sensitivity adapted to the current environment is the second sensitivity, and the speech reply volume adapted to the current environment is the second reply volume; wherein the upper limit value of the first threshold range is less than or equal to the lower limit value of the second threshold range, the first sensitivity is less than the second sensitivity, and the first reply volume is greater than the second reply volume; when the environmental signal-to-noise ratio is within a third threshold range, determining that the speech recognition sensitivity adapted to the current environment is the third sensitivity, and the speech reply volume adapted to the current environment is the third reply volume; wherein the upper limit value of the second threshold range is less than or equal to the lower limit value of the third threshold range, the second sensitivity is less than the third sensitivity, and the second reply volume is greater than the third reply volume.

[0010] In one of the embodiments, identifying the voice action instruction according to the voice recognition sensitivity includes: obtaining a first voiceprint feature parameter of the voice wake-up word and timing it with a preset time length; when a voice action instruction is received within the preset time length, identifying the voice action instruction according to the first voiceprint feature parameter and the voice recognition sensitivity.

[0011] In one of the embodiments, after obtaining the first voiceprint feature parameter of the voice wake-up word and timing with a preset time length, it also includes: if no voice action command is received within the preset time length, replying with the voice reply volume to signal a feedback of not receiving the command.

[0012] In one of the embodiments, when a voice action instruction is received within the preset time length, the voice action instruction is identified according to the first voiceprint feature parameter and the voice recognition sensitivity, including: when a voice action instruction is received within the preset time length, obtaining a second voiceprint feature parameter of the voice action instruction; when the first voiceprint feature parameter matches the second voiceprint feature parameter, identifying the voice action instruction according to the voice recognition sensitivity.

[0013] In one of the embodiments, when a voice action instruction is received within the preset time length, after obtaining the second voiceprint feature parameter of the voice action instruction, it also includes: when the first voiceprint feature parameter does not match the second voiceprint feature parameter, ending voice control; or, when the first voiceprint feature parameter does not match the second voiceprint feature parameter, waiting to receive the voice action instruction again.

[0014] A voice control device comprises: a noise detection module, which is used to obtain environmental noise parameters of the current environment when a voice wake-up word is detected; an operation matching module, which is used to determine the voice recognition sensitivity adapted to the current environment and the voice reply volume adapted to the current environment according to the environmental noise parameters; an instruction recognition module, which is used to recognize voice action instructions according to the voice recognition sensitivity; and an instruction response module, which is used to respond to the recognition result of the voice action instruction and output a reply signal at the voice reply volume.

[0015] A voice control system comprises a sound receiving component, a processor and a broadcasting component, wherein the sound receiving component and the broadcasting component are respectively connected to the processor, and the processor is used to execute the steps of the above-mentioned voice control method.

[0016] A household appliance comprises the above-mentioned voice control system.

[0017] In one embodiment, the household appliance includes any one of a clothes dryer, a smart clothes drying rack, a refrigerator, a washing machine and an air conditioner.

[0018] A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned voice control method when executed by a processor.

[0019] A computer program product comprises a computer program, which implements the steps of the above-mentioned voice control method when executed by a processor.

[0020] The above-mentioned voice control method, device, system, home appliance, storage medium and computer program product, when detecting that the user sends a voice wake-up word, first obtains the environmental noise parameters of the current environment, and then adapts the voice recognition sensitivity and voice reply volume for the current environment in combination with the environmental noise parameters, and finally performs the relevant actions of voice control with the adapted voice recognition sensitivity and voice reply volume, that is, recognizes the voice action instructions, and feeds back the reply signal to the user based on the voice action instructions. This scheme can adaptively adjust the voice recognition sensitivity in combination with the noise conditions in the current environment, which can not only avoid the situation where the voice recognition sensitivity is too low and the voice action instructions cannot be recognized, but also avoid the situation where the voice recognition sensitivity is too high and is falsely triggered. At the same time, by adaptively adjusting the voice reply volume, it ensures that the reply signal is accurately transmitted to the user and the output of subsequent voice control instructions is guaranteed. In this way, the voice action instructions issued by the user can be accurately recognized, and the reply signal can be transmitted to the user with sufficient volume, effectively reducing the possibility of voice control failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flow chart of a voice control method in one embodiment of the present application;

[0023] Figure 2 This is a flow chart of a voice control method in another embodiment of the present application;

[0024] Figure 3 This is a schematic diagram of the environmental signal-to-noise ratio calculation process in one embodiment of the present application;

[0025] Figure 4 This is a flow chart of a voice control method in another embodiment of the present application;

[0026] Figure 5 This is a flow chart of a voice control method in another embodiment of the present application;

[0027] Figure 6 This is a flow chart of a voice control method in another embodiment of the present application;

[0028] Figure 7 This is a flow chart of a voice control method in another embodiment of the present application;

[0029] Figure 8This is a schematic diagram of the structure of a voice control device in one embodiment of the present application;

[0030] Fig. 9 This is a schematic diagram of the structure of a voice control system in one embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive.

[0032] At present, from the perspective of market development, home appliances are increasingly developing towards intelligence, and for this reason, more and more home appliances are beginning to be equipped with voice control functions. However, in the related art, the voice control function often fails.

[0033] After in-depth research, it was found that the failure of the voice control function is usually caused by the inappropriate voice recognition sensitivity. In some scenarios, if the voice recognition sensitivity is low, the voice action commands (including wake-up commands) issued by the user cannot be effectively recognized. If the voice recognition sensitivity is set high, it is easy to mistake sounds similar to voice action commands for voice action commands, thereby triggering actions by mistake.

[0034] To alleviate the above phenomenon, it is possible to consider adaptively adjusting the voice recognition sensitivity to adapt to different usage scenarios. In this way, the accuracy of voice recognition can be greatly improved.

[0035] Based on the above considerations, the present application provides a voice control method that can adaptively adjust the voice recognition sensitivity in combination with the noise conditions in the current environment, which can avoid the situation where the voice recognition sensitivity is too low and the voice action command cannot be recognized, and can also avoid the situation where the voice recognition sensitivity is too high and false triggering occurs. At the same time, by adaptively adjusting the voice reply volume, it is ensured that the reply signal is accurately transmitted to the user and the output of subsequent voice control commands is guaranteed. In this way, the voice action command issued by the user can be accurately recognized, and the reply signal can be transmitted to the user with sufficient volume, effectively reducing the possibility of voice control failure.

[0036] The voice control method provided in the embodiment of the present application is applied to any household appliance with a voice control function. The type of household appliance is not limited. It can be any one of a dryer, a smart clothes rack, a refrigerator, a washing machine and an air conditioner, and can also be a range hood, a sweeper and other products, without specific limitation.

[0037] See also Figure 1, a voice control method, including step 102, step 104, step 106 and step 108.

[0038] Step 102: When a voice wake-up word is detected, obtain the ambient noise parameters of the current environment.

[0039] Specifically, the voice wake-up word is the keyword used to wake up the voice control function. The environmental noise parameter is the parameter that characterizes the noise condition of the current voice recognition scene. It should be pointed out that the type of voice wake-up word is not unique and can be set according to the actual scene, for example, "power on", "turn on" or "run", etc., without specific limitation. The type of environmental noise parameter is not unique. In one embodiment, the volume of environmental noise can be used as the environmental noise parameter; in another embodiment, the signal-to-noise ratio can also be used as the environmental noise parameter, without specific limitation.

[0040] In the solution of the present application, the voice control function is performed by a voice control system, wherein the voice control system includes a sound receiving component, a processor and a broadcasting component, the sound receiving component and the broadcasting component are respectively connected to the processor, and the steps related to the voice control method are performed by the processor. Furthermore, the voice control system is configured in a home appliance with voice control requirements.

[0041] It can be understood that the detection of voice wake-up words and the acquisition of environmental noise parameters are not unique. In one embodiment, both can be achieved through the sound receiving component. In the actual operation process, the voice control system is in a waiting state for wake-up. At this time, the sound receiving component is on standby, and voice signals can be collected in real time and sent to the processor. After the processor performs recognition processing, it is compared with the preset voice wake-up word. When the two match, it means that the voice wake-up word is detected. Correspondingly, the processor extracts and analyzes the voice signal currently received to obtain the environmental noise parameters.

[0042] In another embodiment, an environmental noise detection component may be configured for the voice control system. After the sound receiving component and the processor perform analysis and determine that a voice wake-up word has been received, the environmental noise parameters of the current environment may be detected by controlling the operation of the environmental noise detection component.

[0043] Step 104, determining the speech recognition sensitivity adapted to the current environment and the speech reply volume adapted to the current environment according to the environmental noise parameters.

[0044] Specifically, the voice recognition sensitivity is the recognition sensitivity of the voice control system when used to recognize voice control instructions. The voice reply volume is the volume of the voice signal output by the voice broadcast component of the voice control system. In the solution of this embodiment, the voice control system can not only receive the voice control instructions sent by the user, but also play the sound to the user through the broadcast component.

[0045] The voice control system has different sensitivity levels. In actual scenarios, the processor can control the voice control system to operate with different voice recognition sensitivities based on the acquired environmental noise parameters. Specifically, different environmental noise ranges can be configured with a corresponding voice recognition sensitivity, or one environmental parameter can be configured with a corresponding voice recognition sensitivity. I will not go into details here.

[0046] There is not only one way to adjust the voice recognition sensitivity. In one embodiment, the sound receiving component may include multiple microphones with different sensitivities. In actual scenarios, different microphones are controlled to start and operate according to the adapted voice recognition sensitivities. In another embodiment, the sound receiving component may include only one microphone. In this case, different voice recognition sensitivities can be represented by different gains by adjusting the gain of the microphone. In other embodiments, the voice recognition sensitivity can be adjusted by adjusting the relevant parameters of the voice recognition processing in the processor, which is not specifically limited.

[0047] Step 106, recognizing the voice action instruction according to the voice recognition sensitivity.

[0048] Specifically, voice action instructions refer to instructions used to control the home appliance where the voice control system is located to perform related actions. It can be understood that the type of voice action instructions is not unique. Depending on the type of home appliance and the operating requirements, the voice action instructions will also be different, and there is no specific limitation. After the processor analyzes the adapted voice recognition sensitivity in combination with the ambient noise parameters, it will enter a state of waiting to receive voice action instructions. After that, the processor will compare and analyze the voice signal collection results of the sound receiving component with the voice recognition sensitivity to determine whether the voice signal collected at this time is a valid voice action instruction, and finally realize the operation control of the home appliance based on the judgment result.

[0049] Step 108, in response to the recognition result of the voice action instruction, output a reply signal with a voice reply volume.

[0050] Specifically, after the processor recognizes the voice action instruction, it will output a reply signal to the user according to the recognition result to inform the user of the processing result of the voice action instruction sent by the voice control system at this time. Specifically, the processor may output a reply signal to the user only when the voice action instruction is valid, or only when the voice action instruction is invalid. In another embodiment, the reply signal may be output when the voice action instruction is valid or invalid, and the specific embodiment is not limited.

[0051] The above-mentioned voice control method, when detecting that the user sends a voice wake-up word, first obtains the ambient noise parameters of the current environment, and then adapts the voice recognition sensitivity and voice reply volume for the current environment in combination with the ambient noise parameters. Finally, with the adapted voice recognition sensitivity and voice reply volume, the relevant actions of voice control are executed, that is, voice action instructions are recognized, and a reply signal is fed back to the user based on the voice action instructions.

[0052] Through this solution, the voice recognition sensitivity can be adaptively adjusted in combination with the noise conditions in the current environment, which can avoid the situation where the voice recognition sensitivity is too low and the voice action command cannot be recognized, and can also avoid the situation where the voice recognition sensitivity is too high and false triggering occurs. At the same time, by adaptively adjusting the voice reply volume, it is ensured that the reply signal is accurately transmitted to the user and the output of subsequent voice control commands is guaranteed. In this way, the voice action commands issued by the user can be accurately recognized, and the reply signal can be transmitted to the user at a sufficient volume, effectively reducing the possibility of voice control failure.

[0053] See also Figure 2 In one embodiment, step 104 includes step 202 and step 204 .

[0054] Step 202, performing matching analysis based on environmental noise parameters and a preset sensitivity database to determine the speech recognition sensitivity adapted to the current environment.

[0055] Step 204, performing matching analysis based on the environmental noise parameters and a preset volume database to determine the voice response volume adapted to the current environment.

[0056] Specifically, the sensitivity database stores the speech recognition sensitivities corresponding to different environmental noise parameters; the volume database stores the speech reply volumes corresponding to different environmental noise parameters. The solution of this embodiment determines the speech recognition sensitivity and the speech reply volume by matching the environmental parameters with the corresponding database. Specifically, different environmental noise parameters may be configured with different speech recognition sensitivities; or different environmental noise parameters may be configured with different speech reply volumes. In other embodiments, a speech recognition sensitivity may be configured for environmental noise parameters within a certain range; or a speech reply volume may be configured for environmental noise parameters within a certain range, without specific limitation.

[0057] The above scheme determines the voice recognition sensitivity and voice response volume adapted to the current environment by matching the environmental noise parameters with the preset database respectively, and has high configuration efficiency.

[0058] It is understood that in other embodiments, multiple tests may be performed to perform test analysis, and a functional relationship representing the corresponding relationship between the environmental noise parameter and the voice recognition sensitivity may be fitted, or a functional relationship representing the corresponding relationship between the environmental noise parameter and the voice response volume may be fitted. After obtaining the environmental noise parameter, the corresponding functional relationship is substituted into the corresponding functional relationship for calculation to obtain the adapted voice recognition sensitivity and voice response volume.

[0059] In one of the embodiments, the noisier the current environment represented by the environmental noise parameter is, the lower the adapted speech recognition sensitivity is.

[0060] And / or, in one embodiment, the noisier the current environment represented by the environmental noise parameter is, the higher the adapted voice reply volume is.

[0061] Specifically, the environmental noise parameter characterizes the noisiness of the current environment. If the current environment is relatively noisy, there will be more noise. If the voice recognition sensitivity is set high, it is easy to mistake the noise for a voice recognition command, thereby triggering voice control. Therefore, the solution of this embodiment is to configure a smaller voice recognition sensitivity for the noisier the current environment is, so as to avoid false triggering. When the current environment is relatively quiet, the probability of false triggering is low. At this time, in order to ensure that voice control can be triggered efficiently and accurately, the voice recognition sensitivity can be configured to be relatively high. Correspondingly, in a noisy environment, in order to reduce the impact of noise on the reply signal of the voice control system, the voice control system can be configured to reply with a larger voice reply volume. In this way, it can be ensured that the echo signal of the voice control system is received by the user even in the operating environment. This solution can effectively improve the accuracy of voice recognition and the reliability of voice reply.

[0062] It should be noted that there is not only one way to adjust the voice reply volume. In one embodiment, taking the broadcast component including a speaker as an example, to increase the voice reply volume, the gain of the speaker can be increased accordingly. In another embodiment, the broadcast component can also include multiple speakers with different gains, and the processor can select the corresponding speaker to operate according to the actual required voice reply volume, so as to achieve the adjustment of the voice reply volume.

[0063] See also Figure 3 In one embodiment, the environmental noise parameter is an environmental signal-to-noise ratio, and obtaining the environmental noise parameter of the current environment includes step 302 and step 304.

[0064] Step 302: Obtain a first energy parameter of the voice wake-up word and a second energy parameter of the ambient noise.

[0065] Step 304: Determine an environmental signal-to-noise ratio according to the first energy parameter and the second energy parameter.

[0066] Specifically, the signal-to-noise ratio is the ratio of the signal to the noise. In this application, the environmental signal-to-noise ratio is the ratio of the energy parameter of the sound signal of the voice wake-up word to the energy parameter of the environmental noise signal. Among them, the energy parameter can be power or volume, etc., and is not specifically limited. Taking power as an example, in actual scenarios, in order to ensure that the sound signal can be reliably received, the power of the sound signal is usually required to be as large as possible, and the power value of the environmental noise signal is as small as possible, that is, the signal-to-noise ratio needs to be large enough. Therefore, the smaller the environmental signal-to-noise ratio, the greater the environmental noise at this time, that is, the noisier the current environment.

[0067] The above scheme uses the signal-to-noise ratio as the environmental noise parameter to characterize the noisiness of the current environment, and has a high accuracy in environmental noise detection.

[0068] See also Figure 4 In one embodiment, step 104 includes step 402 , step 404 , and step 406 .

[0069] Step 402: When the environment signal-to-noise ratio is within a first threshold range, determine that the speech recognition sensitivity adapted to the current environment is the first sensitivity, and the speech reply volume adapted to the current environment is the first reply volume.

[0070] Step 404, when the environmental signal-to-noise ratio is within the second threshold range, determining that the speech recognition sensitivity adapted to the current environment is the second sensitivity, and the speech reply volume adapted to the current environment is the second reply volume.

[0071] Step 406: When the environmental signal-to-noise ratio is within the third threshold range, determine that the voice recognition sensitivity adapted to the current environment is the third sensitivity, and the voice reply volume adapted to the current environment is the third reply volume.

[0072] Specifically, the upper limit value of the first threshold range is less than or equal to the lower limit value of the second threshold range, the first sensitivity is less than the second sensitivity, and the first reply volume is greater than the second reply volume; the upper limit value of the second threshold range is less than or equal to the lower limit value of the third threshold range, the second sensitivity is less than the third sensitivity, and the second reply volume is greater than the third reply volume.

[0073] This embodiment is explained using three gears as an example. The larger the threshold range of the environmental signal-to-noise ratio is, the lower the noisiness of the current environment is, that is, the quieter the current environment is, the greater the required environmental sensitivity is, and the smaller the voice response volume is.

[0074] It can be understood that in other embodiments, the environmental noise parameters can be configured to more than three gears, such as four gears, five gears, etc., without specific limitation, as long as the smaller the environmental signal-to-noise ratio, the higher the corresponding voice response volume and the lower the voice recognition sensitivity.

[0075] See also Figure 5 In one embodiment, step 106 includes step 502 and step 504 .

[0076] Step 502, obtaining the first voiceprint feature parameter of the voice wake-up word and timing it with a preset time length.

[0077] Step 504: When a voice action instruction is received within a preset time period, the voice action instruction is identified according to the first voiceprint feature parameter and the voice recognition sensitivity.

[0078] Specifically, the voiceprint feature parameter refers to a parameter that characterizes the voice characteristics contained in the voice and can characterize and identify the speaker's voice characteristics. It should be noted that the type of voiceprint feature parameter is not unique. In one embodiment, it can include at least one of sound quality parameters, timbre parameters, and pitch parameters, which are not specifically limited. After receiving the voice signal corresponding to the voice wake-up word, the processor extracts and processes the voiceprint feature of the voice signal to obtain the first voiceprint feature parameter of the user who sent the voice signal.

[0079] After that, the timing starts at the preset time length. If a voice action command is received within the preset time length, the voice action command will be verified in combination with the matched voice recognition sensitivity and the first voiceprint feature parameter at this time, and different voice controls will be implemented according to the verification results.

[0080] The above scheme, combined with the first voiceprint feature parameter and the voice recognition sensitivity, performs double verification on the voice action instructions received within a preset time period, thereby further improving the triggering accuracy of voice control.

[0081] It should be noted that the preset duration is not unique and is not specifically limited, as long as it is ensured that the user can effectively send voice control instructions within the preset duration. On this basis, it can be understood that the preset duration should not be set too long or too short. For example, in one embodiment, the preset duration can be set to 5 seconds, 8 seconds or 10 seconds, etc., without specific limitation.

[0082] See also Figure 6 In one embodiment, after step 502, the method further includes step 602.

[0083] Step 602, when no voice action command is received within a preset time period, a feedback signal of not receiving the command is replied with a voice reply volume.

[0084] Specifically, if no voice action command is received within the preset time, it means that the voice control function may be woken up by mistake, or the user's needs have changed, and there is no need to perform voice control at this time. In order to avoid subsequent accidental touch control, a feedback signal of not receiving the command can be returned to the user so that the user can respond in time. Furthermore, in order to ensure that the output feedback signal can be effectively transmitted to the user, the voice reply volume can also be used to transmit the feedback signal.

[0085] In the above scheme, when no voice action command is received within a preset time period, the voice reply volume can also send a feedback signal to the user to prompt the user that no command has been received at this time, thereby effectively improving the reliability of voice control.

[0086] See also Figure 7 In one embodiment, step 504 includes step 702 and step 704.

[0087] Step 702: when a voice action instruction is received within a preset time period, obtain a second voiceprint feature parameter of the voice action instruction.

[0088] Step 704: When the first voiceprint feature parameter matches the second voiceprint feature parameter, the voice action instruction is recognized according to the voice recognition sensitivity.

[0089] Specifically, the method for obtaining the second voiceprint feature parameter of the voice action instruction is the same as the method for obtaining the first voiceprint feature parameter, which will not be described in detail here. In the solution of this embodiment, a voiceprint feature comparison is first performed. When the first voiceprint feature parameter matches the second voiceprint feature parameter, it is considered that the user who issued the voice wake-up word is the same user as the user who issued the voice action instruction. At this time, the action of identifying the voice action instruction according to the voice recognition sensitivity will continue to be executed.

[0090] It is understood that in another embodiment, the action of identifying the voice action instruction according to the voice recognition sensitivity can be performed first, and after the recognition is passed, the voiceprint feature comparison is performed, and the voiceprint feature comparison result is used to determine whether the voice action instruction is qualified. Correspondingly, when the recognition according to the voice recognition sensitivity fails, there is no need to continue the voiceprint comparison. At this time, the voice control can be ended, or it can return to wait for the voice action instruction again, and there is no specific limitation.

[0091] It should be pointed out that the method for confirming the match between the first voiceprint feature parameter and the second voiceprint feature parameter is not unique. In one embodiment, the two are considered to match when they are consistent; in another embodiment, the two are considered to match when the difference between them is less than or equal to the allowable error range, without specific limitation.

[0092] The above scheme uses two methods, voiceprint feature comparison and voice recognition sensitivity recognition, to double-check whether the voice action command is a valid command, thereby improving the recognition reliability of the voice action command.

[0093] In one of the embodiments, when a voice action instruction is received within a preset time length, after obtaining the second voiceprint feature parameter of the voice action instruction, it also includes: when the first voiceprint feature parameter does not match the second voiceprint feature parameter, ending the voice control; or, when the first voiceprint feature parameter does not match the second voiceprint feature parameter, waiting to receive the voice action instruction again.

[0094] Specifically, when comparing and analyzing the second voiceprint feature parameter of the voice action instruction with the first voiceprint feature parameter of the voice wake-up word, there will be a mismatch between the two. Correspondingly, in this case, it can be considered that the wake-up user and the user who sends the voice action instruction belong to different users. This situation may be caused by the noisy environment, and the voice control system mistakes the sounds made by other users for voice action instructions. Therefore, in this case, the processor can directly end the voice action and wait for the next round of wake-up, or enter the state of waiting to receive the voice action instruction. When the voice action instruction is received next time, the voiceprint recognition and comparison are performed in the same way, and the details will not be repeated.

[0095] It should be noted that when the processor enters the state of waiting to receive the voice action instruction again, the timing may be restarted, that is, the timing is restarted with the preset time length, and it is judged again whether the voice action instruction is received again within the preset time length. In another embodiment, the timing may not be restarted, because the last time the voice action instruction is received and the voiceprint comparison is performed, it is executed when the voice action instruction is received within the preset time length. Therefore, when the voiceprint comparison fails, the timing generally does not reach the preset time length, and it only needs to judge whether the voice action instruction is received again within the remaining timing length.

[0096] The above scheme can end the voice control or wait for receiving the voice action command again when the voiceprint comparison of the received voice action command fails, which can effectively ensure that the voice control function is realized with accurate voice control commands and improve the control accuracy.

[0097] In order to facilitate understanding of the technical solution of the present application, the present application is explained below in conjunction with more detailed embodiments.

[0098] The voice control method of the embodiment of the present application includes 1. the control logic of recognition sensitivity and reply volume, and the voice voiceprint recognition logic. The two are independent of each other and can run in parallel, or only one of the logics can be run, without specific limitation.

[0099] Identification sensitivity and response volume control logic:

[0100] The voice control system is equipped with three different voice recognition sensitivities, namely low sensitivity, medium sensitivity, and high sensitivity, and three different voice reply volumes, namely low volume, medium volume, and high volume. When the product recognizes the voice wake-up word, the system starts to operate, obtains the volume of the voice wake-up word and the volume of the ambient noise, and calculates the ambient signal-to-noise ratio x. Here, the system sets three ambient signal-to-noise ratio value intervals, namely low, medium, and high, which are the first threshold range, the second threshold range, and the third threshold range. Determine which range the ambient signal-to-noise ratio is in:

[0101] If 0≤x<x2 (i.e., in the first threshold range), it is in the low signal-to-noise ratio range, and the environment is determined to be a noisy environment, and low sensitivity is used to recognize subsequent voice action commands, and a high volume is used to reply;

[0102] If x2≤x<x3 (i.e., it is in the second threshold range), it is in the medium signal-to-noise ratio interval, and the environment is determined to be a normal environment, and the subsequent voice action command is recognized with medium sensitivity, and the reply is made with medium volume;

[0103] If x≥x3 (that is, it is in the third threshold range), it is in a high signal-to-noise ratio interval, and the environment is determined to be a quiet environment. High sensitivity is used to identify subsequent voice action commands, and a low volume is used for reply.

[0104] The logic of voiceprint recognition:

[0105] At the beginning, the system is in a state of waiting for the voice wake-up word. When the voice wake-up word is recognized, the system starts to operate, records the time node at this time, identifies and records the voiceprint features of the voice wake-up word, that is, records the sound quality, timbre and tone of the sound input, and then the system enters a state of waiting for voice action instructions.

[0106] When a voice action command is recognized, the time node at this time is recorded to determine whether the voiceprint characteristics of this voice action command are the same as the record. If the voiceprint characteristics are different from the record, the product will not respond; if the voiceprint characteristics are the same as the record, the action command will be executed and the voice will reply.

[0107] Each time the system recognizes a wake-up word or a voice action command, it will record the time node and enter the waiting state for the next voice action command. If the waiting time exceeds 5 seconds and the command word is not recognized, the system will re-enter the state of waiting for the voice wake-up word or voice action command.

[0108] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0109] Based on the same inventive concept, the embodiment of the present application also provides a voice control device for implementing the voice control method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more voice control device embodiments provided below can refer to the limitations of the voice control method above, and will not be repeated here.

[0110] See also Figure 8 , a voice control device includes a noise detection module 802, an operation matching module 804, an instruction recognition module 806 and an instruction response module 808.

[0111] The noise detection module 802 is used to obtain the environmental noise parameters of the current environment when a voice wake-up word is detected; the operation matching module 804 is used to determine the voice recognition sensitivity adapted to the current environment and the voice reply volume adapted to the current environment according to the environmental noise parameters; the instruction recognition module 806 is used to identify the voice action instructions according to the voice recognition sensitivity; the instruction response module 808 is used to respond to the recognition result of the voice action instruction and output a reply signal with the voice reply volume.

[0112] In one embodiment, the running matching module 804 is also used to perform a matching analysis based on environmental noise parameters and a preset sensitivity database to determine the speech recognition sensitivity adapted to the current environment; and perform a matching analysis based on environmental noise parameters and a preset volume database to determine the speech response volume adapted to the current environment.

[0113] In one of the embodiments, the noise detection module 802 is further used to obtain a first energy parameter of the voice wake-up word and a second energy parameter of the ambient noise; and determine the ambient signal-to-noise ratio according to the first energy parameter and the second energy parameter.

[0114] In one of the embodiments, the running matching module 804 is also used to determine that the speech recognition sensitivity adapted to the current environment is the first sensitivity, and the speech reply volume adapted to the current environment is the first reply volume when the environmental signal-to-noise ratio is within the first threshold range; when the environmental signal-to-noise ratio is within the second threshold range, determine that the speech recognition sensitivity adapted to the current environment is the second sensitivity, and the speech reply volume adapted to the current environment is the second reply volume; when the environmental signal-to-noise ratio is within the third threshold range, determine that the speech recognition sensitivity adapted to the current environment is the third sensitivity, and the speech reply volume adapted to the current environment is the third reply volume.

[0115] In one embodiment, the instruction recognition module 806 is also used to obtain the first voiceprint feature parameter of the voice wake-up word and count the time with a preset time length; when a voice action instruction is received within the preset time length, the voice action instruction is identified according to the first voiceprint feature parameter and the voice recognition sensitivity.

[0116] In one embodiment, the instruction recognition module 806 is further configured to respond with a feedback signal of not receiving the instruction using a voice response volume when no voice action instruction is received within a preset time period.

[0117] In one of the embodiments, the instruction recognition module 806 is also used to obtain a second voiceprint feature parameter of the voice action instruction when a voice action instruction is received within a preset time period; and to recognize the voice action instruction according to the voice recognition sensitivity when the first voiceprint feature parameter matches the second voiceprint feature parameter.

[0118] In one embodiment, the instruction recognition module 806 is further used to end the voice control when the first voiceprint feature parameter does not match the second voiceprint feature parameter; or, when the first voiceprint feature parameter does not match the second voiceprint feature parameter, wait for receiving the voice action instruction again.

[0119] Each module in the above-mentioned voice control device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0120] The above-mentioned voice control device, when detecting that the user sends a voice wake-up word, first obtains the environmental noise parameters of the current environment, and then adapts the voice recognition sensitivity and voice reply volume for the current environment in combination with the environmental noise parameters, and finally performs the relevant actions of voice control with the adapted voice recognition sensitivity and voice reply volume, that is, recognizes the voice action instructions, and feeds back the reply signal to the user based on the voice action instructions. Through this scheme, the voice recognition sensitivity can be adaptively adjusted in combination with the noise conditions in the current environment, which can avoid the situation where the voice recognition sensitivity is too low and the voice action instructions cannot be recognized, and the situation where the voice recognition sensitivity is too high and false triggering can be avoided. At the same time, by adaptively adjusting the voice reply volume, it is ensured that the reply signal is accurately transmitted to the user, and the output of subsequent voice control instructions is guaranteed. In this way, the voice action instructions issued by the user can be accurately recognized, and the reply signal can be transmitted to the user with sufficient volume, effectively reducing the possibility of voice control failure.

[0121] See also Fig. 9 The present application provides a voice control system, including a sound receiving component 901, a processor 903 and a broadcasting component 905, wherein the sound receiving component 901 and the broadcasting component 905 are respectively connected to the processor 903, and the processor 903 is used to execute the steps of the above-mentioned voice control method.

[0122] Specifically, the implementation method of the voice control method is as shown in the above embodiments and the accompanying drawings, which will not be repeated here. The voice control system, when detecting that the user sends a voice wake-up word, first obtains the environmental noise parameters of the current environment, and then adapts the voice recognition sensitivity and the voice reply volume for the current environment in combination with the environmental noise parameters, and finally performs the relevant actions of voice control with the adapted voice recognition sensitivity and voice reply volume, that is, recognizes the voice action instructions, and feeds back the reply signal to the user based on the voice action instructions. Through this scheme, the voice recognition sensitivity can be adaptively adjusted in combination with the noise conditions in the current environment, which can avoid the situation where the voice recognition sensitivity is too low and the voice action instructions cannot be recognized, and the situation where the voice recognition sensitivity is too high and the trigger is false can be avoided. At the same time, by adaptively adjusting the voice reply volume, it is ensured that the reply signal is accurately transmitted to the user, and the output of subsequent voice control instructions is guaranteed. In this way, the voice action instructions issued by the user can be accurately identified, and the reply signal can be transmitted to the user with sufficient volume, effectively reducing the possibility of voice control failure.

[0123] The present application also provides a household appliance, comprising the above-mentioned voice control system.

[0124] Specifically, the structure of the voice control system and its voice control method are shown in the above-mentioned embodiments, which will not be repeated here. When the home appliance detects that the user sends a voice wake-up word, it first obtains the environmental noise parameters of the current environment, and then adapts the voice recognition sensitivity and voice reply volume for the current environment in combination with the environmental noise parameters. Finally, the adapted voice recognition sensitivity and voice reply volume are used to perform the relevant actions of voice control, that is, recognize the voice action instructions, and feedback the reply signal to the user based on the voice action instructions. Through this scheme, the voice recognition sensitivity can be adaptively adjusted in combination with the noise conditions in the current environment, which can avoid the situation where the voice recognition sensitivity is too low and the voice action instructions cannot be recognized, and the situation where the voice recognition sensitivity is too high and the voice recognition is falsely triggered. At the same time, by adaptively adjusting the voice reply volume, it is ensured that the reply signal is accurately transmitted to the user and the output of subsequent voice control instructions is guaranteed. In this way, the voice action instructions issued by the user can be accurately recognized, and the reply signal can be transmitted to the user with sufficient volume, effectively reducing the possibility of voice control failure.

[0125] It is understandable that the types of home appliances are not limited, and any home appliance that is configured with a voice control function can be used. For example, in one embodiment, the home appliance includes any one of a dryer, a smart clothes drying rack, a refrigerator, a washing machine, and an air conditioner.

[0126] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the following voice control method are implemented:

[0127] When a voice wake-up word is detected, the ambient noise parameters of the current environment are obtained; based on the ambient noise parameters, the voice recognition sensitivity adapted to the current environment and the voice reply volume adapted to the current environment are determined; the voice action instructions are recognized based on the voice recognition sensitivity; in response to the recognition result of the voice action instructions, a reply signal is output at the voice reply volume.

[0128] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing a matching analysis based on environmental noise parameters and a preset sensitivity database to determine a speech recognition sensitivity adapted to the current environment; performing a matching analysis based on environmental noise parameters and a preset volume database to determine a speech response volume adapted to the current environment.

[0129] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a first energy parameter of the voice wake-up word and a second energy parameter of the ambient noise; and determining the ambient signal-to-noise ratio based on the first energy parameter and the second energy parameter.

[0130] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the environmental signal-to-noise ratio is within a first threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the first sensitivity, and the speech reply volume adapted to the current environment is the first reply volume; when the environmental signal-to-noise ratio is within a second threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the second sensitivity, and the speech reply volume adapted to the current environment is the second reply volume; when the environmental signal-to-noise ratio is within a third threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the third sensitivity, and the speech reply volume adapted to the current environment is the third reply volume.

[0131] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the first voiceprint feature parameter of the voice wake-up word and timing it with a preset time length; when a voice action instruction is received within the preset time length, identifying the voice action instruction according to the first voiceprint feature parameter and the voice recognition sensitivity.

[0132] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when no voice action instruction is received within a preset time period, a feedback signal of not receiving the instruction is replied with a voice reply volume.

[0133] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when a voice action instruction is received within a preset time length, a second voiceprint feature parameter of the voice action instruction is obtained; when the first voiceprint feature parameter matches the second voiceprint feature parameter, the voice action instruction is identified according to the voice recognition sensitivity.

[0134] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the first voiceprint feature parameter does not match the second voiceprint feature parameter, ending the voice control; or, when the first voiceprint feature parameter does not match the second voiceprint feature parameter, waiting to receive the voice action instruction again.

[0135] A computer program product, comprising a computer program, which, when executed by a processor, implements the following steps of a voice control method:

[0136] When a voice wake-up word is detected, the ambient noise parameters of the current environment are obtained; based on the ambient noise parameters, the voice recognition sensitivity adapted to the current environment and the voice reply volume adapted to the current environment are determined; the voice action instructions are recognized based on the voice recognition sensitivity; in response to the recognition result of the voice action instructions, a reply signal is output at the voice reply volume.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing a matching analysis based on environmental noise parameters and a preset sensitivity database to determine a speech recognition sensitivity adapted to the current environment; performing a matching analysis based on environmental noise parameters and a preset volume database to determine a speech response volume adapted to the current environment.

[0138] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a first energy parameter of the voice wake-up word and a second energy parameter of the ambient noise; and determining the ambient signal-to-noise ratio based on the first energy parameter and the second energy parameter.

[0139] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the environmental signal-to-noise ratio is within a first threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the first sensitivity, and the speech reply volume adapted to the current environment is the first reply volume; when the environmental signal-to-noise ratio is within a second threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the second sensitivity, and the speech reply volume adapted to the current environment is the second reply volume; when the environmental signal-to-noise ratio is within a third threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the third sensitivity, and the speech reply volume adapted to the current environment is the third reply volume.

[0140] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the first voiceprint feature parameter of the voice wake-up word and timing it with a preset time length; when a voice action instruction is received within the preset time length, identifying the voice action instruction according to the first voiceprint feature parameter and the voice recognition sensitivity.

[0141] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when no voice action instruction is received within a preset time period, a feedback signal of not receiving the instruction is replied with a voice reply volume.

[0142] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when a voice action instruction is received within a preset time length, a second voiceprint feature parameter of the voice action instruction is obtained; when the first voiceprint feature parameter matches the second voiceprint feature parameter, the voice action instruction is identified according to the voice recognition sensitivity.

[0143] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the first voiceprint feature parameter does not match the second voiceprint feature parameter, ending the voice control; or, when the first voiceprint feature parameter does not match the second voiceprint feature parameter, waiting to receive the voice action instruction again.

[0144] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0145] The above-mentioned storage medium and computer program product, when detecting that the user sends a voice wake-up word, first obtain the environmental noise parameters of the current environment, and then adapt the voice recognition sensitivity and voice reply volume for the current environment in combination with the environmental noise parameters, and finally perform the relevant actions of voice control with the adapted voice recognition sensitivity and voice reply volume, that is, recognize the voice action instructions, and feedback the reply signal to the user based on the voice action instructions. Through this scheme, the voice recognition sensitivity can be adaptively adjusted in combination with the noise conditions in the current environment, which can avoid the situation where the voice recognition sensitivity is too low and the voice action instructions cannot be recognized, and the situation where the voice recognition sensitivity is too high and the trigger is false can be avoided. At the same time, by adaptively adjusting the voice reply volume, it is ensured that the reply signal is accurately transmitted to the user, and the output of subsequent voice control instructions is guaranteed. In this way, the voice action instructions issued by the user can be accurately identified, and the reply signal can be transmitted to the user with sufficient volume, effectively reducing the possibility of voice control failure.

[0146] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A voice control method, characterized in that: include: When a voice wake-up word is detected, obtain the ambient noise parameters of the current environment; Determining, according to the environmental noise parameter, a speech recognition sensitivity adapted to the current environment and a speech reply volume adapted to the current environment; recognizing a voice action instruction according to the voice recognition sensitivity; In response to the recognition result of the voice action instruction, a reply signal is output at the voice reply volume.

2. The voice control method according to claim 1, characterized in that: The step of determining the speech recognition sensitivity adapted to the current environment and the speech reply volume adapted to the current environment according to the environmental noise parameter includes: Perform matching analysis according to the environmental noise parameters and a preset sensitivity database to determine the speech recognition sensitivity adapted to the current environment; the sensitivity database stores speech recognition sensitivities corresponding to different environmental noise parameters; A matching analysis is performed according to the environmental noise parameters and a preset volume database to determine a voice reply volume adapted to the current environment; the volume database stores voice reply volumes corresponding to different environmental noise parameters.

3. The voice control method according to claim 1, characterized in that: The noisier the current environment represented by the environmental noise parameter is, the lower the adapted speech recognition sensitivity is; And / or, the noisier the current environment represented by the environmental noise parameter is, the higher the adapted voice reply volume is.

4. The voice control method according to claim 1, characterized in that: The environmental noise parameter is an environmental signal-to-noise ratio, and obtaining the environmental noise parameter of the current environment includes: Acquire a first energy parameter of the voice wake-up word and a second energy parameter of the ambient noise; The environmental signal-to-noise ratio is determined according to the first energy parameter and the second energy parameter.

5. The voice control method according to claim 4, characterized in that: The step of determining the speech recognition sensitivity adapted to the current environment and the speech reply volume adapted to the current environment according to the environmental noise parameter includes: When the environmental signal-to-noise ratio is within a first threshold range, determining that the speech recognition sensitivity adapted to the current environment is the first sensitivity, and the speech reply volume adapted to the current environment is the first reply volume; When the environmental signal-to-noise ratio is within a second threshold range, determining that the voice recognition sensitivity adapted to the current environment is the second sensitivity, and the voice reply volume adapted to the current environment is the second reply volume; wherein the upper limit value of the first threshold range is less than or equal to the lower limit value of the second threshold range, the first sensitivity is less than the second sensitivity, and the first reply volume is greater than the second reply volume; When the environmental signal-to-noise ratio is within the third threshold range, the speech recognition sensitivity adapted to the current environment is determined to be the third sensitivity, and the speech reply volume adapted to the current environment is determined to be the third reply volume; wherein the upper limit value of the second threshold range is less than or equal to the lower limit value of the third threshold range, the second sensitivity is less than the third sensitivity, and the second reply volume is greater than the third reply volume.

6. The voice control method according to any one of claims 1 to 5, characterized in that: The step of recognizing the voice action instruction according to the voice recognition sensitivity includes: Obtaining a first voiceprint feature parameter of the voice wake-up word and timing it according to a preset time length; When a voice action instruction is received within the preset time period, the voice action instruction is identified according to the first voiceprint feature parameter and the voice recognition sensitivity.

7. The voice control method according to claim 6, characterized in that: After obtaining the first voiceprint feature parameter of the voice wake-up word and timing by a preset time, the method further includes: When no voice action instruction is received within the preset time period, a feedback signal of not receiving the instruction is replied with the voice reply volume.

8. The voice control method according to claim 6, characterized in that: When the voice action instruction is received within the preset time period, identifying the voice action instruction according to the first voiceprint feature parameter and the voice recognition sensitivity includes: When a voice action instruction is received within the preset time period, obtaining a second voiceprint feature parameter of the voice action instruction; When the first voiceprint feature parameter matches the second voiceprint feature parameter, the voice action instruction is recognized according to the voice recognition sensitivity.

9. The voice control method according to claim 8, characterized in that: In the case where a voice action instruction is received within the preset time period, after obtaining the second voiceprint feature parameter of the voice action instruction, the method further includes: If the first voiceprint feature parameter does not match the second voiceprint feature parameter, ending the voice control; or, When the first voiceprint feature parameter does not match the second voiceprint feature parameter, wait for receiving the voice action instruction again.

10. A voice control device, characterized in that: include: A noise detection module is used to obtain the ambient noise parameters of the current environment when a voice wake-up word is detected; Running a matching module to determine, according to the environmental noise parameter, a speech recognition sensitivity adapted to the current environment and a speech reply volume adapted to the current environment; A command recognition module, used for recognizing voice action commands according to the voice recognition sensitivity; The command response module is used to respond to the recognition result of the voice action command and output a reply signal at the voice reply volume.

11. A voice control system, characterized in that: It comprises a sound receiving component, a processor and a broadcasting component, wherein the sound receiving component and the broadcasting component are respectively connected to the processor, and the processor is used to execute the steps of the voice control method according to any one of claims 1 to 9.

12. A household appliance, characterized in that: Includes the voice control system as claimed in claim 11.

13. The household appliance according to claim 12, characterized in that: The household electrical appliance includes any one of a clothes dryer, an intelligent clothes drying rack, a refrigerator, a washing machine and an air conditioner.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the voice control method according to any one of claims 1 to 9 are implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the voice control method according to any one of claims 1 to 9 are implemented.

Images