Signal correction method, device, equipment, storage medium and computer program product

Abstract

Embodiments of the present application provide a signal correction method, device, equipment, storage medium and computer program product. The method comprises: obtaining a to-be-corrected signal, the to-be-corrected signal being a signal with a correlation coefficient less than a first preset threshold with respect to a reference signal; performing polynomial fitting on the to-be-corrected signal to obtain a polynomial fitting function; performing sampling processing on the polynomial fitting function to obtain a signal after sampling processing; and determining the signal after sampling processing as a corrected signal when the correlation coefficient of the signal after sampling processing with respect to the reference signal is greater than a second preset threshold. The present application corrects the to-be-corrected signal by the method of polynomial fitting, can correct the signal whose correlation coefficient does not meet the condition, and avoids the problem of inaccurate results when filtering by using the correlation coefficient.

Description

Technical Field

[0001] The present application belongs to the field of signal processing technology, and in particular relates to a signal correction method, apparatus, device, storage medium and computer program product. Background Art

[0002] Currently, when using voice interaction devices to collect voice signals, since they are capturing the same segment of voice signal, theoretically the correlation between the signals collected by any two microphones is strong. However, in reality, due to factors such as the quality and differences of the microphones used in voice interaction devices, the actual correlation of the calculated results is not high, that is, the two calculated correlation coefficients have a certain error. In this case, when using the correlation coefficient to analyze and process the signal, there will be a certain amount of error. For example, when using the correlation coefficient to filter the signal, the filtering results obtained are poor and the accuracy is low. Summary of the Invention

[0003] The embodiments of the present application provide a signal correction method, apparatus, device, storage medium, and computer program product, which can correct signals, and the corrected signals have a strong correlation, thereby obtaining more accurate analysis and processing results.

[0004] In a first aspect, an embodiment of the present application provides a signal correction method, comprising:

[0005] Acquire a signal to be corrected, where the signal to be corrected has a correlation coefficient with the reference signal that is less than a first preset threshold;

[0006] Perform polynomial fitting on the signal to be corrected to obtain a polynomial fitting function;

[0007] Perform sampling processing on the polynomial fitting function to obtain a sampled signal;

[0008] When the correlation coefficient between the sampled signal and the reference signal is greater than a second preset threshold, the sampled signal is determined to be a corrected signal.

[0009] In a second aspect, an embodiment of the present application provides a signal correction device, comprising:

[0010] An acquisition module, configured to acquire a signal to be corrected, the signal to be corrected being a signal whose correlation coefficient with the reference signal is less than a first preset threshold;

[0011] A fitting module is used to perform polynomial fitting on the signal to be corrected to obtain a polynomial fitting function;

[0012] A sampling module is used to perform sampling processing on the polynomial fitting function to obtain a sampled signal;

[0013] The determining module is further configured to determine that the sample-processed signal is the corrected signal when the correlation coefficient between the sample-processed signal and the reference signal is greater than a second preset threshold.

[0014] In a third aspect, an embodiment of the present application provides a signal correction device, comprising:

[0015] a processor, and a memory storing computer program instructions;

[0016] The processor reads and executes the computer program instructions to implement the signal correction method in the first aspect.

[0017] In a fourth aspect, an embodiment of the present application provides a computer storage medium, and the computer storage medium stores computer program instructions. When the computer program instructions are executed by a processor, the signal correction method in the first aspect is implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, and instructions in the computer program product are executed by a processor of an electronic device, so that the electronic device executes the signal correction method in the first aspect.

[0019] The signal correction method, the device, the equipment, the storage medium and the computer program product provided in the embodiments of the present application can determine the to-be-corrected signal that does not satisfy the correlation coefficient condition according to the correlation coefficient between signals, and correct the to-be-corrected signal by using the polynomial fitting method, so that the corrected signal satisfies the corresponding correlation coefficient condition, and the problem of inaccurate filtering result when subsequent filtering is performed by using the correlation coefficient is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. For those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0021] Figure 1 is a flow diagram of a signal correction method provided by an embodiment of the present application;

[0022] Figure 2 is a structural diagram of a signal correction device provided by an embodiment of the present application;

[0023] Figure 3 is a structural diagram of a signal correction device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0025] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0026] Currently, when using at least two microphones in a voice interaction device to collect voice data, in theory, the microphones have a strong correlation. However, due to factors such as microphone quality, there is a large error between the correlation coefficient of the microphone signal actually calculated and the theoretical value. When the correlation coefficient is subsequently used for filtering, the filtering result is poor.

[0027] In order to solve the problems of the prior art, the embodiments of the present application provide a signal correction method, apparatus, device, storage medium and computer program product. The method provided in the embodiments of the present application can correct the acquired signal by polynomial fitting, and the corrected signal can satisfy strong correlation and obtain accurate results in subsequent filtering processing. The above method is specifically applied to the collection of voice signals, and the corresponding signal is obtained by collecting voice data through the microphone in the voice interaction device. For example, when using the voice interaction function of a mobile phone, the user's voice data is collected by the built-in microphone array of the mobile phone to obtain multiple voice signals.

[0028] The following first introduces the signal correction method provided in the embodiment of the present application.

[0029] Figure 1 FIG. 1 is a flow chart of a signal correction method provided by an embodiment of the present application. Figure 1 As shown, the signal correction method may include the following steps:

[0030] S110 , obtaining a signal to be corrected, where the signal to be corrected is a signal whose correlation coefficient with the reference signal is less than a first preset threshold.

[0031] A signal to be corrected is obtained, where the signal to be corrected does not meet a correlation coefficient condition. Specifically, the correlation coefficient between the signal to be corrected and a reference signal is less than a first preset threshold. The reference signal is a normal signal that meets the correlation coefficient condition. The first preset threshold is configurable and is not limited thereto.

[0032] In some embodiments, the reference signal is a signal collected by an audio collection device in a normal voice interaction device or a preset signal; the signal to be corrected is a signal collected by a problematic voice interaction device, or a signal whose correlation coefficient does not meet a preset condition. The audio collection device may be a microphone.

[0033] S120 , performing polynomial fitting on the signal to be corrected to obtain a polynomial fitting function.

[0034] A polynomial fit is performed on the signal to be corrected, using a first predetermined order of the polynomial. The polynomial is expanded to fit the signal at each point containing the signal to be corrected, and the expansion coefficients are determined using least squares fitting to obtain a polynomial fitting function. The first predetermined order can be set and is not limited thereto.

[0035] In an example, the first preset order may be set to first order, and a linear polynomial is used to fit the signal to be corrected to obtain a linear polynomial fitting function.

[0036] S130 , performing sampling processing on the polynomial fitting function to obtain a sampled signal.

[0037] The obtained polynomial fitting function is sampled according to a preset sampling frequency, and the obtained discrete signal is used as the sampled signal. The preset sampling frequency can be set and is not limited to this.

[0038] S140: When the correlation coefficient between the sampled signal and the reference signal is greater than a second preset threshold, determine that the sampled signal is a corrected signal.

[0039] The sampled signal is a signal obtained by sampling the polynomial fitting function. A correlation coefficient between the sampled signal and the reference signal is calculated. When the correlation coefficient is greater than a second preset threshold, the sampled signal is determined to be a corrected signal. The second preset threshold can be set and is not limited thereto. It should be understood that the second preset threshold should be greater than or equal to the first preset threshold.

[0040] The signal correction method provided in the embodiment of the present application can determine the signal to be corrected that does not meet the correlation condition based on the correlation coefficient, and correct the signal to be corrected using a polynomial fitting method so that the corrected signal meets the condition of strong correlation, which can avoid poor filtering results and low accuracy when filtering using the correlation coefficient.

[0041] In some embodiments, obtaining the signal to be corrected includes: obtaining signals of the same voice data respectively collected by at least two audio collection devices in the voice interaction device; calculating the correlation coefficient of the signals collected by the two audio collection devices; when the correlation coefficient includes a correlation coefficient less than or equal to a second preset threshold, determining that the voice interaction device is the first voice interaction device; respectively calculating the correlation coefficient of the signal collected by each audio collection device in the first voice interaction device and the reference signal; when the correlation coefficient of the signal collected by the audio collection device in the first voice interaction device and the reference signal is less than the first preset threshold, determining that the signal collected by the audio collection device in the first voice interaction device is the signal to be corrected.

[0042] Acquire multiple discrete signals obtained by at least two audio acquisition devices in each of the multiple voice interaction devices for the same voice data. For each voice interaction device, calculate the correlation coefficients between the signals collected by the audio acquisition devices in the voice interaction device, wherein the method for calculating the correlation coefficient is a prior art and will not be described in detail here. Based on the calculated correlation coefficients, determine that the device with the correlation coefficient between the signals collected by the audio acquisition devices is less than or equal to a first preset threshold value is the first voice interaction device, that is, the problem device. Calculate the correlation coefficient between the signal collected by each audio acquisition device of the first voice interaction device and the reference signal. When the calculated correlation coefficient is less than the first preset threshold value, determine that the signal is a signal to be corrected.

[0043] In some embodiments, the signal correction method also includes: when the correlation coefficients are all greater than a second preset threshold, determining that the voice interaction device is a second voice interaction device; determining the maximum value of the correlation coefficients of the signals collected by the pairwise audio collection devices in the second voice interaction device as the target correlation coefficient; and determining any one of the two signals corresponding to the target correlation coefficient as the reference signal.

[0044] Exemplarily, based on the calculated correlation coefficients, a voice interaction device whose correlation coefficients are all greater than a second preset threshold is determined to be a second voice interaction device, i.e., a normal device. Based on the calculated correlation coefficients of the signals collected by the pairwise audio collection devices within the second voice interaction device, the maximum correlation coefficient is determined to be the target correlation coefficient, and any one of the two signals corresponding to the target correlation coefficient is further determined to be the reference signal.

[0045] In one example, the relationship between the correlation coefficient Y and the signal correlation is: when Y < 0.5, the two signals are weakly correlated; when 0.5 ≤ Y ≤ 0.8, the two signals are correlated; when 0.8 ≤ Y ≤ 1, the two signals are strongly correlated. The first preset threshold is 0.8, and the second preset threshold is set to 0.8.

[0046] In some embodiments, the signal correction method further includes: when the correlation coefficient between the sampled signal and the reference signal is less than or equal to a second preset threshold, performing a polynomial fitting on the signal to be corrected according to a preset fitting iteration condition to obtain a polynomial fitting function, and then performing sampling processing on the polynomial fitting function to obtain a sampled signal, until the correlation coefficient between the sampled signal and the reference signal is greater than the second preset threshold. When the correlation coefficient between the sampled signal and the reference signal is still less than or equal to the second preset threshold, repeatedly performing a polynomial fitting on the signal to be corrected according to an iteration condition with increasing polynomial order until the sampled signal obtained by the polynomial fitting function satisfies a condition, which is that the correlation coefficient between the sampled signal and the reference signal is greater than the second preset threshold.

[0047] In one example, a first-order polynomial fitting function is used to fit the signal to be corrected, and the obtained polynomial fitting function is sampled according to a preset sampling frequency to obtain a sampled signal. When the correlation coefficient between the signal and the reference signal is greater than a second preset threshold, the sampled signal is determined to be a corrected signal; when the correlation coefficient between the signal and the reference signal is less than or equal to the second preset threshold, a polynomial fitting is performed again on the signal to be corrected, and at this time the polynomial fitting is a second-order polynomial fitting. The polynomial fitting function obtained by the second-order polynomial fitting is sampled to obtain a new sampled signal, and the correlation coefficient value between the signal and the reference signal is judged to determine whether a third-order polynomial fitting is required for the signal to be corrected.

[0048] In some embodiments, before calculating the correlation coefficient between the signal collected by each audio collection device in the first voice interaction device and the reference signal, the signal correction method further includes: determining the noise signal based on the difference between each pair of signals in the signal collected by the second voice interaction device; and performing noise removal processing on the signal collected by the second voice interaction device based on the noise signal.

[0049] In one example, the noise signal is calculated as the average of the differences between any two signals in the signal collected by the second voice interaction device. For example, a sequence of absolute values ​​of the algebraic differences between any two signals in the signal collected by the second voice interaction device is calculated, and the average of all such absolute value sequences is taken as the noise sequence. The noise sequence is then subtracted from all signals collected by the second voice interaction device to obtain the noise-removed signal.

[0050] In some embodiments, the signal correction method further includes: performing noise removal on the signal collected by the first voice interaction device according to the noise signal, and subtracting the noise sequence from the signal collected by the first voice interaction device according to the calculated noise sequence to obtain a noise-removed signal.

[0051] In some embodiments, the above steps of calculating the correlation coefficient between signals, performing polynomial fitting, and sampling the polynomial fitting function are performed using the signal after noise removal.

[0052] The signal correction method provided in the embodiment of the present application can obtain a noise sequence based on the algebraic difference of the acquired signal, and perform noise removal on the acquired signal, and then use the calculated signal correlation coefficient to determine the signal to be corrected, and correct the signal to be corrected by polynomial fitting so that the corrected signal meets the correlation requirements, thereby avoiding inaccurate results when the correlation coefficient is used for subsequent filtering.

[0053] Figure 2 Schematic diagram of a signal correction device 200 provided in an embodiment of the present application. Figure 2 As shown, the apparatus may include an acquisition module 210 , a fitting module 220 , a sampling module 230 and a determination module 240 .

[0054] An acquisition module 210 is configured to acquire a signal to be corrected, where the signal to be corrected is a signal whose correlation coefficient with the reference signal is less than a first preset threshold;

[0055] A fitting module 220 is used to perform polynomial fitting on the signal to be corrected to obtain a polynomial fitting function;

[0056] The sampling module 230 is used to perform sampling processing on the polynomial fitting function to obtain a sampled signal;

[0057] The determination module 240 is further configured to determine that the sampled signal is a corrected signal when a correlation coefficient between the sampled signal and the reference signal is greater than a second preset threshold.

[0058] The signal correction device provided in the embodiment of the present application can determine the signal to be corrected that does not meet the correlation condition based on the correlation coefficient, and correct the signal to be corrected using a polynomial fitting method so that the corrected signal meets the condition of strong correlation, thereby avoiding the situation where poor filtering results occur when filtering using the correlation coefficient.

[0059] In some embodiments, the acquisition module 210 is used to obtain the signal to be corrected, including: the acquisition module 210 is used to obtain signals of the same voice data collected by at least two audio collection devices in each voice interaction device in the voice interaction device; the calculation module 250 is used to calculate the correlation coefficient of the signals collected by the two audio collection devices; the determination module 240 is used to determine that the voice interaction device is the first voice interaction device when the correlation coefficient includes a correlation coefficient less than or equal to a second preset threshold; the calculation module 250 is also used to calculate the correlation coefficient between the signal collected by each audio collection device in the first voice interaction device and the reference signal; the determination module 240 is also used to determine that the signal collected by the audio device in the first voice interaction device is the signal to be corrected when the correlation coefficient between the signal collected by the audio collection device in the first voice interaction device and the reference signal is less than the first preset threshold.

[0060] In some embodiments, the signal correction device also includes: a determination module 240 is used to determine that the voice interaction device is a second voice interaction device when the correlation coefficients are all greater than a second preset threshold; the determination module 240 is used to determine that the maximum value of the correlation coefficients of the signals collected by the pairwise audio collection devices in the second voice interaction device is the target correlation coefficient; the determination module 240 is also used to determine that any one of the two signals corresponding to the target correlation coefficient is a reference signal.

[0061] In some embodiments, the signal correction device also includes: an execution module 260, which is used to perform polynomial fitting on the signal to be corrected according to a preset fitting iteration condition to obtain a polynomial fitting function and sample the polynomial fitting function to obtain a sampled signal when the correlation coefficient between the sampled signal and the reference signal is less than or equal to a second preset threshold value, until the correlation coefficient between the sampled signal and the reference signal is greater than the second preset threshold value.

[0062] In some embodiments, the device also includes: a determination module 240, which is also used to determine the noise signal based on the difference between two signals in the signal collected by the second voice interaction device; a processing module 270, which is used to perform noise removal processing on the signal collected by the second voice interaction device based on the noise signal.

[0063] In some embodiments, the processing module 270 is further configured to perform noise removal on the signal collected by the first voice interaction device according to the noise signal.

[0064] The signal correction device provided in the embodiment of the present application can obtain a noise sequence based on the algebraic difference of the acquired signal, and perform noise removal on the acquired signal, and then use the calculated signal correlation coefficient to determine the signal to be corrected, and correct the signal to be corrected by polynomial fitting so that the corrected signal meets the correlation requirements, thereby avoiding inaccurate results when the correlation coefficient is used for subsequent filtering.

[0065] Figure 2 Each module / unit in the device shown has the function of realizing Figure 1 The functions of each step in the embodiment can achieve the corresponding technical effects, which will not be described in detail here for the sake of brevity.

[0066] Figure 3 A schematic diagram of the hardware structure of the signal correction provided in an embodiment of the present application is shown.

[0067] The signal correction device may include a processor 301 and a memory 302 storing computer program instructions.

[0068] Specifically, the processor 301 may include a central processing unit (CPU) or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0069] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In one example, the memory 302 may include a removable or non-removable (or fixed) medium, or the memory 302 may be a non-volatile solid-state memory. The memory 302 may be inside or outside the integrated gateway disaster recovery device.

[0070] In one example, the memory 302 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory 302 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present application.

[0071] The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement Figure 1 The method / steps S110 to S140 in the embodiment shown, and achieving Figure 1 The corresponding technical effects achieved by executing the methods / steps in the illustrated example will not be repeated here for the sake of brevity.

[0072] In one example, the signal correction device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301 , the memory 302 , and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0073] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0074] Bus 310 includes hardware, software or both, and the parts of signal correction equipment are coupled to each other. For example, but not limitation, bus can include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 310 can include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0075] The signal correction device can perform the signal correction method in the embodiment of the present application based on the correlation coefficient between the signals, thereby achieving the combination of Figure 1 Describe the signal correction method.

[0076] In addition, in conjunction with the signal correction method in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the signal correction methods in the above embodiments is implemented.

[0077] An embodiment of the present application provides a computer program product, characterized in that when instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the above-mentioned signal correction method.

[0078] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0079] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0080] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0081] Aspects of the present application have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed via the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. This processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or the flowchart and the combination of the boxes in the block diagram and / or the flowchart can also be implemented by the dedicated hardware that performs the specified function or action, or can be implemented by the combination of dedicated hardware and computer instructions.

[0082] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A signal correction method, characterized in that: include: Acquire signals of the same voice data collected by at least two audio collection devices in the voice interaction device; Calculate the correlation coefficient of the signals collected by each audio collection device; When the correlation coefficients include a correlation coefficient that is less than or equal to a second preset threshold, determining that the voice interaction device is the first voice interaction device; Calculating correlation coefficients between the signals collected by each audio collection device in the first voice interaction device and the reference signal respectively; When a correlation coefficient between a signal collected by the audio collection device in the first voice interaction device and the reference signal is less than a first preset threshold, determining that the signal collected by the audio collection device in the first voice interaction device is a signal to be corrected; Performing polynomial fitting on the signal to be corrected to obtain a polynomial fitting function; Performing sampling processing on the polynomial fitting function to obtain a sampled signal; When the correlation coefficient between the sampled signal and the reference signal is greater than a second preset threshold, determining that the sampled signal is a corrected signal; When the correlation coefficient between the sampled signal and the reference signal is less than or equal to a second preset threshold, a polynomial fitting is performed on the signal to be corrected according to a preset fitting iteration condition to obtain a polynomial fitting function, and then sampling is performed on the polynomial fitting function to obtain the sampled signal, until the correlation coefficient between the sampled signal and the reference signal is greater than the second preset threshold.

2. The method according to claim 1, characterized in that The method further comprises: When the correlation coefficients are all greater than the second preset threshold, determining that the voice interaction device is a second voice interaction device; Determine a maximum value among correlation coefficients of signals collected by the pairwise audio collection devices in the second voice interaction device as a target correlation coefficient; Determine whether any one of the two signals corresponding to the target correlation coefficient is the reference signal.

3. The method according to claim 2, characterized in that Before calculating the correlation coefficient between the signal collected by each audio collection device in the first voice interaction device and the reference signal, the method further includes: Determining a noise signal based on the difference between any two signals in the signals collected by the second voice interaction device; According to the noise signal, noise removal processing is performed on the signal collected by the second voice interaction device.

4. The method according to claim 3, characterized in that The method further comprises: Perform noise removal processing on the signal collected by the first voice interaction device according to the noise signal.

5. A signal correction device, characterized in that: The device comprises: An acquisition module is configured to acquire signals of the same voice data respectively collected by at least two audio acquisition devices in a voice interaction device; calculate correlation coefficients of signals collected by two audio acquisition devices; determine that the voice interaction device is a first voice interaction device when the correlation coefficients include a correlation coefficient that is less than or equal to a second preset threshold; calculate correlation coefficients between the signals collected by each audio acquisition device in the first voice interaction device and a reference signal; and determine that the signal collected by the audio acquisition device in the first voice interaction device is a signal to be corrected when the correlation coefficient between the signal collected by the audio acquisition device in the first voice interaction device and the reference signal is less than a first preset threshold. A fitting module, configured to perform polynomial fitting on the signal to be corrected to obtain a polynomial fitting function; A sampling module, configured to perform sampling processing on the polynomial fitting function to obtain a sampled signal; The determination module is further used to determine that the sampled signal is a corrected signal when the correlation coefficient between the sampled signal and the reference signal is greater than a second preset threshold; when the correlation coefficient between the sampled signal and the reference signal is less than or equal to the second preset threshold, perform polynomial fitting on the signal to be corrected according to a preset fitting iteration condition to obtain a polynomial fitting function, and then sample the polynomial fitting function to obtain the sampled signal, until the correlation coefficient between the sampled signal and the reference signal is greater than the second preset threshold.

6. A signal correction device, characterized in that: The signal correction device includes: a processor, and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the signal correction method according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, which, when executed by a processor, implement the signal correction method according to any one of claims 1 to 4.

8. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the signal correction method according to any one of claims 1 to 4.

Images