Audio signal processing method, apparatus and device, and storage medium
By acquiring the characteristic parameters of the audio signal and the electroacoustic transducer, calculating the distortion value, and suppressing the noise signal based on the amplitude and distortion value, the problem of low sound playback quality in the existing technology is solved, and higher quality audio signal playback is achieved.
Patent Information
- Application Number
- PCT/CN2024/083536
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-31
- Filing Date
- 2024-03-25
- Publication Date
- 2024-12-05
AI Technical Summary
Existing technologies cannot effectively suppress noise signals in audio signals, resulting in low sound playback quality.
By acquiring the characteristic parameters of the audio signal and the electroacoustic transducer, the distortion value is calculated, and the noise signal is suppressed based on the amplitude and distortion value.
It effectively suppresses noise signals in audio signals and improves sound playback quality.
Smart Images

Figure CN2024083536_05122024_PF_FP_ABST
Abstract
Description
Audio signal processing method, device, equipment and storage medium Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to an audio signal processing method, apparatus, device and storage medium. Background Art
[0002] Small speakers are prone to noise when used in various scenarios in the terminal market. For example, in scenarios where the diaphragm speed is fast or the vibration amount is large, and the airflow in the small speaker cavity will also cause airflow noise when rubbing the sound outlet. Therefore, how to effectively suppress the noise signal in the audio signal is a problem that needs to be solved urgently. At present, the commonly used suppression method is dynamic suppression, but the above method only identifies and suppresses the input audio signal, and does not consider the real cause of the noise, resulting in the loss of audio signal quality and listening experience during the suppression process. In addition, the suppression degree of the above method is relatively small, and it cannot effectively suppress the noise signal in the audio signal, which ultimately results in low sound playback quality.
[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art.
[0004] Summary of the Invention
[0005] The main purpose of the present invention is to provide an audio signal processing method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology cannot effectively suppress the noise signal in the audio signal, resulting in low sound playback quality.
[0006] To achieve the above object, the present invention provides an audio signal processing method, which includes the following steps:
[0007] Acquiring an audio signal to be processed and characteristic parameters of an electroacoustic transducer device that inputs the audio signal to be processed;
[0008] When it is determined that the type of the audio signal to be processed is a preset signal type, calculating a distortion value of the electroacoustic transducer device according to the characteristic parameter;
[0009] Acquiring the amplitude of the audio signal to be processed;
[0010] The noise signal in the audio signal to be processed is suppressed according to the amplitude and the distortion level value.
[0011] Optionally, the obtaining of the audio signal to be processed and characteristic parameters of an electroacoustic transducer device that inputs the audio signal to be processed includes:
[0012] Obtaining the audio signal to be processed;
[0013] Determining an electroacoustic transducer device that inputs the audio signal to be processed, and obtaining basic attribute parameters of the electroacoustic transducer device;
[0014] The basic attribute parameters are identified to obtain characteristic parameters of the electroacoustic transducer device.
[0015] Optionally, when determining that the type of the audio signal to be processed is a preset signal type, before calculating the distortion value of the electroacoustic transducer device according to the characteristic parameter, the method further includes:
[0016] Extracting features of the audio signal to be processed to obtain target audio signal features;
[0017] Identifying the target audio signal features using a target distortion recognition model to obtain a relative position between the audio signal to be processed and the target interval hyperplane;
[0018] When the relative position is that the audio signal to be processed is located above the target interval hyperplane, it is determined that the type of the audio signal to be processed is a preset signal type.
[0019] Optionally, before identifying the target audio signal feature by using the target distortion recognition model to obtain the relative position of the audio signal to be processed and the target interval hyperplane, the method further includes:
[0020] Acquire a number of audio signals of a preset signal type;
[0021] Extracting distortion features from the plurality of audio signals of the preset signal types to obtain a plurality of distortion features;
[0022] Determining relative positions of the plurality of audio signals of the preset signal types and the target interval hyperplane according to the plurality of distortion features;
[0023] A target distortion recognition model is trained by a preset deep learning algorithm according to the relative positions of the audio signals of the plurality of preset signal types and the target interval hyperplane.
[0024] Optionally, when determining that the type of the audio signal to be processed is a preset signal type, calculating the distortion value of the electroacoustic transducer device according to the characteristic parameter includes:
[0025] Establishing a target linear equation system for calculating the distortion degree value;
[0026] When it is determined that the type of the audio signal to be processed is a preset signal type, the distortion degree value of the electroacoustic transducer device is calculated according to the characteristic parameters using the target linear equation group.
[0027] Optionally, establishing a target linear equation group for calculating the distortion degree value includes:
[0028] Obtain characteristic parameters of several types of electroacoustic transducer devices;
[0029] determining a constant solution set according to characteristic parameters of the several types of electroacoustic transducer devices;
[0030] Solving the initial linear equation group for calculating the distortion degree value according to the constant solution set to obtain linear equation constants;
[0031] A target linear equation group for calculating a distortion degree value is established based on the linear equation constants and the initial linear equation group.
[0032] Optionally, the suppressing the noise signal in the audio signal to be processed according to the amplitude and the distortion degree value includes:
[0033] Mapping the distortion degree value according to a target mapping strategy to obtain a distortion control degree value;
[0034] The noise signal in the audio signal to be processed is suppressed according to the amplitude and the distortion control degree value.
[0035] In addition, to achieve the above-mentioned object, the present invention further provides an audio signal processing device, the audio signal processing device comprising:
[0036] An acquisition module, configured to acquire characteristic parameters of an audio signal to be processed and an electroacoustic transducer device that inputs the audio signal to be processed;
[0037] a calculation module, configured to calculate a distortion value of the electroacoustic transducer device according to the characteristic parameter when determining that the type of the audio signal to be processed is a preset signal type;
[0038] The acquisition module is further configured to determine the signal amplitude of the audio signal to be processed;
[0039] A suppression module is used to suppress the noise signal in the audio signal to be processed according to the amplitude and the distortion level value.
[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes an audio signal processing device, which includes: a memory, a processor, and an audio signal processing program stored in the memory and executable on the processor, wherein the audio signal processing program is configured to implement the audio signal processing method described above.
[0041] In addition, to achieve the above-mentioned object, the present invention further proposes a storage medium, on which an audio signal processing program is stored. When the audio signal processing program is executed by a processor, the audio signal processing method described above is implemented.
[0042] The audio signal processing method proposed in the present invention obtains characteristic parameters of an audio signal to be processed and an electroacoustic transducer device that inputs the audio signal to be processed; when it is determined that the type of the audio signal to be processed is a preset signal type, calculates the distortion value of the electroacoustic transducer device according to the characteristic parameters; obtains the amplitude of the audio signal to be processed; and suppresses the noise signal in the audio signal to be processed according to the amplitude and the distortion value; through the above method, after obtaining the audio signal to be processed, it is determined whether the type of the audio signal to be processed is the preset signal type, and if so, the distortion value of the electroacoustic transducer device is calculated, and then the noise signal in the audio signal to be processed is suppressed in combination with the amplitude, thereby effectively suppressing the noise signal in the audio signal, thereby improving the sound playback quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] 1 is a schematic structural diagram of an audio signal processing device in a hardware operating environment according to an embodiment of the present invention;
[0044] FIG2 is a flow chart of a first embodiment of an audio signal processing method according to the present invention;
[0045] FIG3 is a schematic diagram showing the principle of an SVM support vector machine classifier algorithm according to an embodiment of an audio signal processing method of the present invention;
[0046] FIG4 is a schematic flow chart of a second embodiment of an audio signal processing method according to the present invention;
[0047] FIG5 is a schematic diagram of functional modules of the first embodiment of the audio signal processing device of the present invention.
[0048] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION
[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0050] 1 , which is a schematic diagram illustrating the structure of an audio signal processing device in a hardware operating environment according to an embodiment of the present invention.
[0051] As shown in Figure 1, the audio signal processing device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) memory or a stable non-volatile memory (NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0052] Those skilled in the art will appreciate that the structure shown in FIG1 does not limit the audio signal processing device, and may include more or fewer components than shown, or combine certain components, or arrange components differently.
[0053] As shown in FIG. 1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an audio signal processing program.
[0054] In the audio signal processing device shown in Figure 1, the network interface 1004 is primarily used for data communication with a network integration platform workstation; the user interface 1003 is primarily used for data interaction with a user; the processor 1001 and memory 1005 in the audio signal processing device of the present invention can be provided in the audio signal processing device. The audio signal processing device calls the audio signal processing program stored in the memory 1005 via the processor 1001 and executes the audio signal processing method provided in an embodiment of the present invention.
[0055] Based on the above hardware structure, an embodiment of an audio signal processing method of the present invention is proposed.
[0056] 2 , which is a flowchart of a first embodiment of an audio signal processing method according to the present invention.
[0057] In a first embodiment, the audio signal processing method includes the following steps:
[0058] Step S10: Acquire the audio signal to be processed and characteristic parameters of the electroacoustic transducer device that inputs the audio signal to be processed.
[0059] It should be noted that the executor of this embodiment is an audio signal processing device, and it can also be other devices that can achieve the same or similar functions, such as a signal processing controller, etc. This embodiment does not limit this. In this embodiment, the signal processing controller is used as an example for explanation.
[0060] It should be understood that the electric energy environmental energy device refers to a device used to input the audio signal to be processed. The electroacoustic environmental energy device can be a small speaker. The electroacoustic environmental energy device can be suitable for AR devices, VR devices, smart audio glasses, neck-hanging speakers, open headphones, audio equipment, televisions, mobile phones, tablets and other products. The characteristic parameters refer to the parameters used to calculate the distortion value of the electroacoustic transducer device. The characteristic parameters include but are not limited to impedance, power, frequency, resonant frequency and equivalent mass.
[0061] Furthermore, step S10 includes: obtaining an audio signal to be processed; determining an electroacoustic transducer device that inputs the audio signal to be processed, and obtaining basic attribute parameters of the electroacoustic transducer device; identifying the basic attribute parameters to obtain characteristic parameters of the electroacoustic transducer device.
[0062] It can be understood that the basic attribute parameters refer to the parameters of the basic attributes of the electroacoustic transducer device, which can be detected by the Klippel tool. The basic attribute parameters include characteristic parameters and non-characteristic parameters. After obtaining the audio signal to be processed, the electroacoustic transducer device that inputs the audio signal to be processed is determined, and then the characteristic parameters of the electroacoustic transducer device are identified from the basic attribute parameters.
[0063] Step S20 : When it is determined that the type of the audio signal to be processed is a preset signal type, a distortion value of the electroacoustic transducer device is calculated according to the characteristic parameter.
[0064] It can be understood that the preset signal type can be a distorted signal type, and the distortion degree value refers to the numerical value of the distortion degree of the electroacoustic transducer device. After obtaining the audio to be processed, it is determined whether the type of the audio signal to be processed is the preset signal type. If so, it indicates that the audio signal to be processed is a distorted signal. At this time, the distortion degree value of the electroacoustic transducer device is calculated based on the characteristic parameters.
[0065] Furthermore, before step S20, it also includes: extracting features of the audio signal to be processed to obtain target audio signal features; identifying the target audio signal features through a target distortion recognition model to obtain the relative position of the audio signal to be processed and the target interval hyperplane; when the relative position is that the audio signal to be processed is above the target interval hyperplane, determining that the type of the audio signal to be processed is a preset signal type.
[0066] It should be understood that the target distortion recognition model refers to a model for identifying whether the type of an audio signal is a preset signal type, and the relative position refers to the position between the audio signal to be processed and the target interval hyperplane. After obtaining the audio signal to be processed, the target audio signal feature of the audio signal to be processed is extracted, and then the target distortion recognition model is used to identify the relative position of the audio signal to be processed and the target interval hyperplane based on the target audio signal feature. When the relative position is that the audio signal to be processed is above the target interval hyperplane, that is, f(x) is greater than 0, it indicates that the type of the audio signal to be processed is the preset signal type. The larger the f(x), the farther the position of the audio signal to be processed is from the target interval hyperplane, and the greater the probability that the type of the audio signal to be processed is determined to be the preset signal type. Conversely, when the relative position is that the audio signal to be processed is below the target interval hyperplane, that is, f(x) is less than 0, the larger the f(x), the farther the position of the audio signal to be processed is from the target interval hyperplane, and the lower the probability that the type of the audio signal to be processed is determined to be the preset signal type, that is, the greater the probability that the audio signal to be processed is determined to be a non-distorted signal type.
[0067] Furthermore, before the target audio signal features are identified by the target distortion recognition model and the relative position of the audio signal to be processed and the target interval hyperplane is obtained, it also includes: obtaining a number of audio signals of preset signal types; extracting distortion features of the audio signals of the preset signal types to obtain a number of distortion features; determining the relative positions of the audio signals of the preset signal types and the target interval hyperplane based on the distortion features; and training a target distortion recognition model based on the relative positions of the audio signals of the preset signal types and the target interval hyperplane based on a preset deep learning algorithm.
[0068] It can be understood that the preset deep learning algorithm refers to an algorithm used to train a target distortion recognition model. The preset deep learning algorithm includes but is not limited to a threshold algorithm, a threshold algorithm, a support vector machine classifier algorithm (SVM), a decision tree algorithm, and a hidden Markov algorithm. After determining the relative positions of a number of audio signals of preset signal types and the target interval hyperplane, the target distortion recognition model is trained according to the relative positions of a number of audio signals of preset signal types and the target interval hyperplane through the preset deep learning algorithm. For example, the preset deep learning algorithm is an SVM support vector machine classifier algorithm. Referring to Figure 3, Figure 3 is a schematic diagram of the principle of the SVM support vector machine classifier algorithm, specifically: the target interval hyperplane is represented by γ,
[0069] Wherein, w represents a hyperplane parameter, ||w|| represents the norm of the hyperplane parameter, and the entire area is divided into two parts by the target interval hyperplane, namely, an area above the target interval hyperplane and an area below the target interval hyperplane. The area above the target interval hyperplane represents an area for determining that the type of the audio signal to be processed is a distorted signal type, and the area below the target interval hyperplane represents an area for determining that the type of the audio signal to be processed is a non-distorted signal type.
[0070] Step S30: Acquire the amplitude of the audio signal to be processed.
[0071] Step S40: Suppressing noise signals in the audio signal to be processed according to the amplitude and the distortion level value.
[0072] It is understandable that after determining the distortion level of the electroacoustic transducer, the noise signal in the audio signal to be processed is suppressed in combination with the amplitude of the audio signal to be processed, thereby improving the quality of sound playback.
[0073] Furthermore, step S40 includes: mapping the distortion degree value according to a target mapping strategy to obtain a distortion control degree value; and suppressing a noise signal in the audio signal to be processed according to the amplitude and the distortion control degree value.
[0074] It should be understood that the target mapping strategy refers to a strategy for mapping the distortion degree value. The target mapping strategy can be a linear mapping strategy or an exponential mapping strategy. The distortion control degree value refers to the degree value of suppressing the noise signal in the audio signal to be processed. The distortion control degree value is obtained by mapping the distortion degree value using the target mapping strategy. Specifically, after obtaining the distortion degree value of the sound transducer device, the target mapping strategy is used to map the distortion degree value to the interval [0,1] to obtain the distortion control degree value K. The larger the value of the distortion control degree value K, the deeper the noise signal in the audio signal to be processed that needs to be suppressed, and the more distortion processing.
[0075] This embodiment obtains characteristic parameters of an audio signal to be processed and an electroacoustic transducer device that inputs the audio signal to be processed; when it is determined that the type of the audio signal to be processed is a preset signal type, calculates the distortion value of the electroacoustic transducer device according to the characteristic parameters; obtains the amplitude of the audio signal to be processed; and suppresses the noise signal in the audio signal to be processed according to the amplitude and the distortion value; through the above method, after obtaining the audio signal to be processed, it is determined whether the type of the audio signal to be processed is the preset signal type, and if so, the distortion value of the electroacoustic transducer device is calculated, and then the noise signal in the audio signal to be processed is suppressed in combination with the amplitude, thereby effectively suppressing the noise signal in the audio signal, thereby improving the sound playback quality.
[0076] In one embodiment, as shown in FIG. 4 , a second embodiment of the audio signal processing method of the present invention is proposed based on the first embodiment, wherein step S20 includes:
[0077] Step S201: establishing a target linear equation group for calculating the distortion level value.
[0078] It should be understood that the target linear equation refers to an equation for calculating the distortion value of the electroacoustic transducer device, and all parameters in the equation group except the characteristic parameters of the acoustic transducer device are known.
[0079] Furthermore, step S201 includes: obtaining characteristic parameters of several types of electroacoustic transducer devices; determining a constant solution set based on the characteristic parameters of the several types of electroacoustic transducer devices; solving an initial linear equation group for calculating the distortion degree value based on the constant solution set to obtain linear equation constants; and establishing a target linear equation group for calculating the distortion degree value based on the linear equation constants and the initial linear equation group.
[0080] It can be understood that the constant solution set refers to a set of constants used to solve the initial linear equations for calculating the distortion value. The constant solution set is determined based on the characteristic parameters of several types of electroacoustic transducer devices. After solving the linear equation constants, the linear equation constants are substituted into the initial linear equations. At this time, in addition to the characteristic parameters and the distortion value, all other parameters in the initial linear equations are known, that is, a target linear equation for calculating the distortion value is established, specifically:
[0081] Where u(t) represents the transient input voltage signal, i(t) represents the current flowing through the voice coil, t represents the time, L represents the inductance, R represents the resistance, Bl represents the force factor, m represents the equivalent mass of the vibration system, r represents the equivalent resistance of the vibration system, k represents the equivalent elastic coefficient of the vibration system, and x(t) represents the current of the quasi-inductor.
[0082] Step S202 : When it is determined that the type of the audio signal to be processed is a preset signal type, the distortion value of the electroacoustic transducer device is calculated according to the characteristic parameters by using the target linear equation group.
[0083] It can be understood that when the type of the audio signal to be processed is determined to be a preset signal type, the transient input voltage signal is calculated through the target linear equation group, specifically: the characteristic parameters of the electroacoustic transducer device are substituted into the target linear equation group to solve the transient input voltage signal, and then the distortion degree value of the electroacoustic transducer device is calculated based on the transient input voltage signal.
[0084] This embodiment establishes a target linear equation group for calculating the distortion degree value; when it is determined that the type of the audio signal to be processed is a preset signal type, the distortion degree value of the electroacoustic transducer device is calculated according to the characteristic parameters by using the target linear equation group; in the above manner, after the target linear equation group for calculating the distortion degree value is established, it is determined whether the type of the audio signal to be processed is the preset signal type, and if so, the distortion degree value of the electroacoustic transducer device is calculated according to the characteristic parameters using the target linear equation group, thereby effectively improving the accuracy of the distortion degree value obtained for the electroacoustic transducer device.
[0085] In addition, an embodiment of the present invention further provides a storage medium, on which an audio signal processing program is stored. When the audio signal processing program is executed by a processor, the steps of the audio signal processing method described above are implemented.
[0086] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.
[0087] In addition, referring to FIG5 , an embodiment of the present invention further provides an audio signal processing device, the audio signal processing device comprising:
[0088] The acquisition module 10 is used to acquire the audio signal to be processed and characteristic parameters of the electroacoustic transducer device that inputs the audio signal to be processed.
[0089] The calculation module 20 is configured to calculate the distortion value of the electroacoustic transducer device according to the characteristic parameter when it is determined that the type of the audio signal to be processed is a preset signal type.
[0090] The acquisition module 10 is further configured to determine the signal amplitude of the audio signal to be processed.
[0091] The suppression module 30 is configured to suppress the noise signal in the audio signal to be processed according to the amplitude and the distortion level value.
[0092] This embodiment obtains characteristic parameters of an audio signal to be processed and an electroacoustic transducer device that inputs the audio signal to be processed; when it is determined that the type of the audio signal to be processed is a preset signal type, calculates the distortion value of the electroacoustic transducer device according to the characteristic parameters; obtains the amplitude of the audio signal to be processed; and suppresses the noise signal in the audio signal to be processed according to the amplitude and the distortion value; through the above method, after obtaining the audio signal to be processed, it is determined whether the type of the audio signal to be processed is the preset signal type, and if so, the distortion value of the electroacoustic transducer device is calculated, and then the noise signal in the audio signal to be processed is suppressed in combination with the amplitude, thereby effectively suppressing the noise signal in the audio signal, thereby improving the sound playback quality.
[0093] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.
[0094] In addition, for technical details not fully described in this embodiment, reference can be made to the audio signal processing method provided in any embodiment of the present invention, and will not be repeated here.
[0095] In one embodiment, the acquisition module 10 is further used to obtain the audio signal to be processed; determine the electroacoustic transducer device that inputs the audio signal to be processed, and obtain basic attribute parameters of the electroacoustic transducer device; identify the basic attribute parameters to obtain characteristic parameters of the electroacoustic transducer device.
[0096] In one embodiment, the calculation module 20 is further used to extract features of the audio signal to be processed to obtain target audio signal features; identify the target audio signal features through a target distortion recognition model to obtain the relative position of the audio signal to be processed and the target interval hyperplane; when the relative position is that the audio signal to be processed is above the target interval hyperplane, determine that the type of the audio signal to be processed is a preset signal type.
[0097] In one embodiment, the calculation module 20 is also used to obtain a number of audio signals of preset signal types; perform distortion feature extraction on the number of audio signals of preset signal types to obtain a number of distortion features; determine the relative positions of the number of audio signals of preset signal types and the target interval hyperplane based on the number of distortion features; and train a target distortion recognition model based on the relative positions of the number of audio signals of preset signal types and the target interval hyperplane through a preset deep learning algorithm.
[0098] In one embodiment, the calculation module 20 is further used to establish a target linear equation group for calculating the distortion degree value; when it is determined that the type of the audio signal to be processed is a preset signal type, the distortion degree value of the electroacoustic transducer device is calculated according to the characteristic parameters through the target linear equation group.
[0099] In one embodiment, the calculation module 20 is also used to obtain characteristic parameters of several types of electroacoustic transducer devices; determine a constant solution set based on the characteristic parameters of the several types of electroacoustic transducer devices; solve the initial linear equation group used to calculate the distortion degree value based on the constant solution set to obtain linear equation constants; and establish a target linear equation group for calculating the distortion degree value based on the linear equation constants and the initial linear equation group.
[0100] In one embodiment, the suppression module 30 is further configured to map the distortion level value according to a target mapping strategy to obtain a distortion control level value; and suppress the noise signal in the audio signal to be processed according to the amplitude and the distortion control level value.
[0101] Other embodiments or implementation methods of the audio signal processing device of the present invention can refer to the above-mentioned method embodiments, which are not repeated here.
[0102] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system 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 system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.
[0103] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.
[0104] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, an integrated platform workstation, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0105] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. An audio signal processing method, characterized in that: The audio signal processing method comprises the following steps: Acquiring a to-be-processed audio signal and characteristic parameters of an electroacoustic transducer device that inputs the to-be-processed audio signal; When it is determined that the type of the audio signal to be processed is a preset signal type, calculating the distortion degree value of the electroacoustic transducer device according to the characteristic parameter; Acquiring the amplitude of the audio signal to be processed; The noise signal in the audio signal to be processed is suppressed according to the amplitude and the distortion degree value.
2. The audio signal processing method according to claim 1, characterized in that: The step of obtaining the audio signal to be processed and the characteristic parameters of the electroacoustic transducer device that inputs the audio signal to be processed includes: Obtaining the audio signal to be processed; Determining an electroacoustic transducer device for inputting the audio signal to be processed, and obtaining basic attribute parameters of the electroacoustic transducer device; The basic attribute parameters are identified to obtain characteristic parameters of the electroacoustic transducer device.
3. The audio signal processing method according to claim 1, characterized in that: When determining that the type of the audio signal to be processed is a preset signal type, before calculating the distortion value of the electroacoustic transducer device according to the characteristic parameter, the method further includes: Extracting features of the audio signal to be processed to obtain target audio signal features; The target audio signal feature is identified by a target distortion identification model to obtain a relative position between the audio signal to be processed and the target interval hyperplane; When the relative position is that the audio signal to be processed is located above the target interval hyperplane, it is determined that the type of the audio signal to be processed is a preset signal type.
4. The audio signal processing method according to claim 3, characterized in that: Before the target audio signal feature is identified by the target distortion identification model to obtain the relative position of the audio signal to be processed and the target interval hyperplane, the method further includes: Acquire a number of audio signals of preset signal types; Extracting distortion features from the plurality of audio signals of the preset signal types to obtain a plurality of distortion features; Determining relative positions of the plurality of audio signals of the preset signal types and the target interval hyperplane respectively according to the plurality of distortion features; A target distortion recognition model is trained by a preset deep learning algorithm according to the relative positions of the audio signals of the several numbers of preset signal types and the target interval hyperplane.
5. The audio signal processing method according to claim 1, characterized in that: When determining that the type of the audio signal to be processed is a preset signal type, calculating the distortion value of the electroacoustic transducer device according to the characteristic parameter includes: Establishing a target linear equation system for calculating the distortion degree value; When it is determined that the type of the audio signal to be processed is a preset signal type, the distortion degree value of the electroacoustic transducer device is calculated according to the characteristic parameters by using the target linear equation group.
6. The audio signal processing method according to claim 5, characterized in that: The target linear equation group for calculating the distortion degree value is established, including: Obtain characteristic parameters of several types of electroacoustic transducer devices; Determining a constant solution set according to characteristic parameters of the several types of electroacoustic transducer devices; Solving the initial linear equation group for calculating the distortion degree value according to the constant solution set to obtain linear equation constants; A target linear equation group for calculating a distortion degree value is established based on the linear equation constants and the initial linear equation group.
7. The audio signal processing method according to claim 1, characterized in that: The suppressing the noise signal in the audio signal to be processed according to the amplitude and the distortion degree value includes: Mapping the distortion degree value according to the target mapping strategy to obtain a distortion control degree value; The noise signal in the audio signal to be processed is suppressed according to the amplitude and the distortion control degree value.
8. An audio signal processing device, characterized in that: The audio signal processing device comprises: An acquisition module, used to acquire characteristic parameters of an audio signal to be processed and an electroacoustic transducer device that inputs the audio signal to be processed; A calculation module, configured to calculate a distortion value of the electroacoustic transducer device according to the characteristic parameter when determining that the type of the audio signal to be processed is a preset signal type; The acquisition module is further used to determine the signal amplitude of the audio signal to be processed; A suppression module is used to suppress the noise signal in the audio signal to be processed according to the amplitude and the distortion degree value.
9. An audio signal processing device, characterized in that: The audio signal processing device comprises: a memory, a processor, and an audio signal processing program stored in the memory and executable on the processor, wherein the audio signal processing program is configured to implement the audio signal processing method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium stores an audio signal processing program, and when the audio signal processing program is executed by the processor, the audio signal processing method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Audio system
CN105530571A
Nonlinear compensation method, system and device for loudspeaker and storage medium
CN111741408A
Nonlinear compensation method of loudspeaker, loudspeaker equipment, device and storage medium
CN111741409A
Gesture action judgment method and device, electronic equipment and storage medium
CN111796792A
Loudspeaker simulation method and device, loudspeaker and electronic equipment
CN113286233A
