TENS Signal Generation Method, System, Device and Medium Based on Multi-Band Fusion

Abstract

The present invention relates to the technical field of multimodal signal fusion, and its purpose is to provide a TENS signal generation method, system, device and medium based on multi-band fusion. The method includes: receiving an audio signal and obtaining the Mel spectrum of the audio signal; dividing the Mel spectrum into multiple frequency bands, obtaining the energy value of each frequency band respectively; merging the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum; establishing a one-to-one mapping relationship between the frequencies in the frequency band energy set and the specified vibration electrical signal frequencies, and using the energy values corresponding to the frequency band energy set as amplitude values to generate a series of square wave signals with single frequencies; performing synthesis processing on all the square wave signals to obtain a TENS signal. The present invention can achieve the fusion effect of touch and hearing.

Description

Technical Field

[0001] The present invention relates to the technical field of multimodal signal fusion, and particularly to a method, system, device and medium for generating TENS signals based on multi-band fusion. Background Art

[0002] Multimodal signal fusion is one of the bases of virtual reality enhancement technology. Currently, there are many technologies based on visual and auditory signal processing and enhancement, but the fusion of tactile signals is still in the research stage. On the one hand, introducing tactile signals can greatly improve human perception and significantly enhance the experience of various virtual reality enhancement technologies. For example, mainstream game consoles (such as X-box, Sony PlayStation and Nintendo Switch) will add gamepads with vibration functions to improve the gaming experience of players; video websites (such as Bilibili) use mechanical vibrations to cooperate with videos with strong rhythms to improve the viewing experience. On the other hand, touch has unique applications in the medical and health care fields. For example, massaging with a massager can relieve pain.

[0003] Currently, for the stimulation of touch, traditional mechanisms such as vibration motors can be used to simulate tactile stimulation by vibration, and electrical signals can also be used to simulate tactile stimulation, that is, the transcutaneous electrical nerve stimulation (TENS) mechanism is adopted. Among them, SKG (a brand of wearable massagers) has also launched a massage chair product that stimulates through TENS. However, in the process of using the existing technology, the inventor found that there are at least the following problems in the existing technology:

[0004] 1) The electrical signals generated by current TENS-based products are simple periodic signals, and the experience is single;

[0005] 2) The signals generated by current TENS-based products cannot be automatically fused with other sensory signals (such as hearing). Summary of the Invention

[0006] The present invention aims to solve the above technical problems at least to a certain extent, and provides a method, system, device and medium for generating TENS signals based on multi-band fusion.

[0007] The technical solution adopted by the present invention is:

[0008] In the first aspect, the present invention provides a method for generating TENS signals based on multi-band fusion, including:

[0009] Receiving an audio signal and obtaining the Mel spectrum of the audio signal;

[0010] Divide the Mel spectrum into frequency bands to obtain multiple frequency bands, and respectively obtain the energy values of each frequency band. Then, merge the energy values corresponding to the Mel scales in the same frequency band of the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum; establish a one-to-one mapping relationship between the frequencies in the frequency band energy set and the specified vibration electrical signal frequency, and use the energy value corresponding to the frequency band energy set as the amplitude value to generate a series of square wave signals with a single frequency;

[0011] Perform a synthesis process on all the square wave signals to obtain a TENS signal.

[0012] The TENS signal obtained by the present invention has good coordination with the audio signal, which is convenient for improving the user experience. Specifically, in the implementation process of the present invention, first obtain the Mel spectrum of the audio signal, then respectively obtain the energy values of each frequency band in the Mel spectrum, and then use the energy value as the amplitude value and the specified vibration electrical signal frequency as the frequency value to obtain the square wave signals corresponding to each frequency band in the Mel spectrum, and finally obtain the TENS signal. In this process, the present invention obtains the TENS signal by fusing each frequency band corresponding to the audio signal with the specified vibration electrical signal frequency respectively, so that the TENS signal can adapt to each signal segment of the audio signal in turn, and the TENS signal can change with the change of the energy value corresponding to each segment of the audio signal, thereby realizing the technical effect of combining the TENS signal with the audio data heard by the user, thus realizing the fusion of touch and hearing and making the user experience better.

[0013] In a possible design, after obtaining the Mel spectrum of the audio signal, the method further includes:

[0014] Set the minimum specified frequency threshold and the maximum specified frequency threshold corresponding to each frequency band;

[0015] Correspondingly, merging the energy values corresponding to the Mel scales in the same frequency band of the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum includes:

[0016] According to the minimum specified frequency threshold and the maximum specified frequency threshold, merge the energy values corresponding to the Mel scales in the same frequency band to obtain a frequency band energy set corresponding to the Mel spectrum; where the i-th frequency band in the frequency band energy set is:

[0017]

[0018] where f min represents the minimum specified frequency threshold; f max represents the maximum specified frequency threshold; M j represents the frequency corresponding to the j-th Mel scale in the Mel spectrum; M j(low) represents the lowest Mel scale with a frequency greater than f in the Mel spectrum; min M j (high) represents the highest Mel scale with a frequency less than f in the Mel spectrum. max

[0019] In a possible design, the energy of each frequency band is concentrated, and the energy value of any frequency band is the average of the energies of the n frames of frequency bands before and after that frequency band; where the energy value of the i-th frequency band at the k-th frame in the concentration of frequency band energy is:

[0020]

[0021] where n represents the specified number of frames of frequency bands before or after the k-th frame frequency band in the Mel spectrum; B j (i) represents the frequency of the j-th frame frequency band, and j ∈ [k - n, k + n].

[0022] In a possible design, after obtaining the energy values of each frequency band respectively, the method further includes:

[0023] performing amplitude modulation processing on the energy values of each frequency band respectively to obtain the modulated energy values of each frequency band;

[0024] performing discretization processing on the modulated energy values of each frequency band to obtain the discretized energy values, so as to perform merging processing on the discretized energy values corresponding to the Mel scales of the same frequency band in the Mel spectrum to obtain the frequency band energy set corresponding to the Mel spectrum.

[0025] In a possible design, the modulated energy value of the k-th frame frequency band in the Mel spectrum is:

[0026]

[0027] where represents the energy value of the k-th frame frequency band in the Mel spectrum; represents the minimum value among the energy values of the frequency bands in the Mel spectrum; represents the maximum value among the energy values of the frequency bands in the Mel spectrum; represents the modulation coefficient of the k-th frame frequency band.

[0028] In a possible design, based on the number of frequency bands divided when dividing the Mel spectrum, there are preset vibration electrical signal frequencies with the same number as the number of frequency bands; the square wave signal value corresponding to the k-th frame frequency band in the Mel spectrum is:

[0029] ​

[0030] wherein, represents the energy value of the k-th frame band in the Mel spectrum; SquareWave(f) represents a square wave generation function, which is used to generate a square wave with a time length corresponding to the frame length of the k-th frame band in the Mel spectrum according to the input frequency f; represents a preset vibration electrical signal frequency corresponding to the frequency set B(i) in the Mel spectrum.

[0031] In a possible design, after synthesizing all the square wave signals, the method further includes:

[0032] Normalizing the synthesized square wave signal to obtain a TENS signal; the value of the TENS signal corresponding to the k-th frame band in the Mel spectrum is:

[0033]

[0034] where W k represents the synthesized square wave signal, and represents the square wave signal corresponding to the k-th frame band in the Mel spectrum; W min represents the minimum value of the square wave signal corresponding to the band in the Mel spectrum; W max represents the maximum value of the square wave signal corresponding to the band in the Mel spectrum.

[0035] In a second aspect, the present invention provides a TENS signal generation system based on multi-band fusion for implementing the method as described in any one of the above; the system includes:

[0036] A spectrum generation module, configured to receive an audio signal and obtain the Mel spectrum of the audio signal;

[0037] A band division module, communicatively connected to the spectrum generation module, configured to divide the Mel spectrum into multiple bands;

[0038] A band energy set generation module, communicatively connected to the band division module, configured to respectively obtain the energy values of each band, and then perform a merging process on the energy values corresponding to the Mel scale of the same band in the Mel spectrum to obtain a band energy set corresponding to the Mel spectrum;

[0039] A square wave signal generation module, communicatively connected to the band energy set module, configured to establish a one-to-one mapping relationship between the frequencies in the band energy set and a specified vibration electrical signal frequency, and use the energy value corresponding to the band energy set as the amplitude value to generate a series of single-frequency square wave signals;

[0040] The TENS signal generation module is communicatively connected to the square wave signal generation module and is configured to synthesize all the square wave signals to obtain a TENS signal.

[0041] In a third aspect, the present invention provides an electronic device, including:

[0042] A memory for storing computer program instructions; and,

[0043] A processor for executing the computer program instructions to complete the operations of the method as described in any one of the above.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer-readable computer program instructions, and the computer program instructions are configured to perform the operations of the method as described in any one of the above when running. Description of the Drawings

[0045] Figure 1 is a flowchart of a method for generating a TENS signal based on multi-band fusion in the present invention;

[0046] Figure 2 is a block diagram of a system for generating a TENS signal based on multi-band fusion in the present invention. Detailed Embodiments

[0047] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0048] It should be understood that attention should also be paid to the fact that in some alternative embodiments, the functions / operations may appear in a different order from that shown in the drawings. For example, depending on the functions / operations involved, they may actually be executed substantially concurrently, or sometimes the two continuously shown figures may be executed in the reverse order.

[0049] Embodiment 1:

[0050] In the first aspect of this embodiment, a method for generating a TENS signal based on multi-band fusion is provided, which can be, but is not limited to, executed by a computer device or virtual machine with certain computing resources, such as an electronic device such as a personal computer, a smart phone, a personal digital assistant, or a wearable device, or executed by a virtual machine, so as to achieve the fusion of touch and hearing, thereby enhancing the user experience.

[0051] As Figure 1 shown, a method for generating a TENS signal based on multi-band fusion may, but is not limited to, include the following steps:

[0052] S1. Receive an audio signal and obtain the Mel spectrum of the audio signal. It should be understood that the characteristic information of the audio signal, such as the frequency range and cut-off frequency of the audio signal, can be conveniently obtained according to the Mel spectrum.

[0053] In this embodiment, obtaining the Mel spectrum of the audio signal includes:

[0054] Based on time-frequency transformation, convert the audio signal from the time domain to the frequency domain to obtain the transformed audio signal;

[0055] Convert the transformed audio signal into a Mel spectrum.

[0056] Among them, the time-frequency transformation can be through Fourier transform. When converting the audio signal from the time domain to the frequency domain, Fourier transform can be performed on each frame of the audio signal to convert the audio signal from the time domain to the frequency domain, obtaining the transformed audio signal in the frequency domain for further spectral analysis of the transformed audio signal.

[0057] Since the spectrum of the obtained transformed audio signal is a linear spectrum, which is not sufficient to reflect the characteristics of human ear auditory perception, the linear spectrum can be further input into a Mel filter to output a non-linear Mel spectrum, so as to be able to simulate the processing process of the human ear for auditory perception, and can further improve the accuracy of audio scene recognition.

[0058] In the implementation process, the Mel filter can be used to output a Mel non-linear spectrum that can simulate human ear auditory perception. Through the filtering effect of the Mel filter, the frequency components that do not match human ear auditory perception are filtered out, and the frequency components that match human ear auditory perception are allowed to pass through, thereby outputting a Mel non-linear spectrum. Among them, matching human ear auditory perception means having a linear relationship with the perception degree of the human ear.

[0059] S2. Divide the Mel spectrum into frequency bands to obtain multiple frequency bands, and respectively obtain the energy values of each frequency band;

[0060] S3. Set the minimum specified frequency threshold and the maximum specified frequency threshold corresponding to each frequency band.

[0061] S4. Perform a merging process on the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum.

[0062] Specifically, step S4 includes: performing a merging process on the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum according to the minimum specified frequency threshold and the maximum specified frequency threshold, so as to obtain a frequency band energy set corresponding to the Mel spectrum; where the i-th frequency band in the frequency band energy set is:

[0063]

[0064] Among them, f min represents the minimum specified frequency threshold; f max represents the maximum specified frequency threshold; M j represents the frequency corresponding to the j-th Mel scale in the Mel spectrum; M j (low) represents the lowest Mel scale in the Mel spectrum where the frequency is greater than f min ; M j (high) represents the highest Mel scale in the Mel spectrum where the frequency is less than f max .

[0065] It should be understood that each frequency band occupies a constant proportion of the Mel spectrum, and multiple frequency bands constitute the Mel spectrum. In this embodiment, the Mel spectrum uses 128 Mel frequency scales, that is, frequency analysis is performed in frames in time, and the Mel spectrum is divided into 128 standard frequency bands in frequency.

[0066] It should be noted that since the perceptual resolution of human touch is lower than that of hearing, in this embodiment, by removing the frequency bands corresponding to the frequencies that have little influence on human touch perception in the Mel spectrum of the audio signal and only retaining the specified frequency bands, the subsequent amount of frequency band processing can be reduced.

[0067] The energy of the frequency bands in this embodiment is concentrated. The energy value of any frequency band is the average of the energies of the n frames of frequency bands before and after that frequency band; among them, the energy value of the i-th frequency band at the k-th frame in the frequency band energy concentration is:

[0068]

[0069] Among them, n represents the specified number of frames of the frequency bands before or after the k-th frame frequency band in the Mel spectrum; B j (i) represents the frequency of the j-th frame frequency band, and j ∈ [k - n, k + n].

[0070] In this embodiment, after obtaining the energy values of each frequency band respectively, the method further includes:

[0071] Performing amplitude modulation processing on the energy values of each frequency band respectively to obtain the modulated energy values of each frequency band.

[0072] The modulated energy value of the k-th frame frequency band in the Mel spectrum is:

[0073]

[0074] Among them, Represents the energy value of the k-th frame band in the said Mel spectrum; Represents the minimum value among the energy values of the bands in the said Mel spectrum; Represents the maximum value among the energy values of the bands in the said Mel spectrum; Represents the modulation coefficient of the k-th frame band.

[0075] Perform discretization processing on the modulated energy values of each band to obtain the discretized energy values, so as to perform merging processing on the discretized energy values corresponding to the Mel scale of the same band in the said Mel spectrum, and obtain a band energy set corresponding to the said Mel spectrum. It should be noted that after the discretization processing, the subsequent processing efficiency of the energy value data in the band energy set can be further improved, and the operation rate is higher.

[0076] S5. Establish a one-to-one mapping relationship between the frequencies in the said band energy set and the specified vibration electrical signal frequencies, and use the energy values corresponding to the band energy set as amplitude values to generate a series of single-frequency square wave signals.

[0077] Specifically, based on the number of bands divided when dividing the Mel spectrum into bands, there are preset vibration electrical signal frequencies equal to the number of bands; the square wave signal value corresponding to the k-th frame band in the said Mel spectrum is:

[0078]

[0079] Wherein, Represents the energy value of the k-th frame band in the said Mel spectrum; SquareWave(f) represents a square wave generation function, which is used to generate a square wave with a time length corresponding to the frame length of the k-th frame band in the said Mel spectrum according to the input frequency f; Represents the preset vibration electrical signal frequency corresponding to the frequency set B(i) in the said Mel spectrum.

[0080] It should be noted that the number of finally obtained vibration electrical signals corresponds one-to-one with the number of bands in the Mel spectrum, and their forms are all square waves; the specified vibration electrical signals corresponding to any band can be the same or different, depending on the energy value of the band, that is, the specified vibration electrical signals corresponding to bands with the same energy value are the same, otherwise different; in this embodiment, the form of the said specified vibration electrical signal is also a square wave, and its time length is the same as the frame length of the band in the said Mel spectrum.

[0081] S8. Perform synthesis processing on all the square wave signals. Specifically, in this embodiment, the synthesis processing of all the square wave signals is realized by means of weighted summation.

[0082] S9. Normalize the synthesized square wave signal to obtain the TENS signal; the value of the TENS signal corresponding to the k-th frame frequency band in the Mel spectrum is:

[0083]

[0084] where W k represents the synthesized square wave signal, which is the sum of the square wave signals corresponding to all frequency bands in the Mel spectrum, and represents the square wave signal corresponding to the k-th frame frequency band in the Mel spectrum; W min represents the minimum value of the square wave signals corresponding to the frequency bands in the Mel spectrum; W max represents the maximum value of the square wave signals corresponding to the frequency bands in the Mel spectrum.

[0085] It should be noted that normalizing the synthesized square wave signal can limit the synthesized square wave signal within a certain range, thereby eliminating the adverse effects caused by singular sample data with too large a difference from other square wave signals.

[0086] The TENS signal obtained in this embodiment has good coordination with the audio signal, which is convenient for improving the user experience. Specifically, in the implementation process of this embodiment, first obtain the Mel spectrum of the audio signal, then respectively obtain the energy values of each frequency band in the Mel spectrum, and then use this energy value as the amplitude value, and use the specified vibration electrical signal frequency as the frequency value to obtain the square wave signal corresponding to each frequency band in the Mel spectrum, and finally obtain the TENS signal. In this process, this embodiment obtains the TENS signal by fusing each frequency band corresponding to the audio signal with the specified vibration electrical signal frequency respectively, so that the TENS signal can adapt to each signal segment of the audio signal in turn, and the TENS signal can change with the change of the energy value corresponding to each segment of the audio signal, thereby achieving the technical effect of combining the TENS signal with the audio data heard by the user, thus realizing the fusion of touch and hearing, and making the user experience better.

[0087] Embodiment 2:

[0088] This embodiment provides a TENS signal generation system based on multi-band fusion for implementing the method in Embodiment 1; as Figure 2 shown, the system includes:

[0089] A spectrum generation module, configured to receive an audio signal and obtain the Mel spectrum of the audio signal;

[0090] A frequency band division module, communicatively connected to the spectrum generation module, configured to divide the Mel spectrum into multiple frequency bands;

[0091] A band energy set generation module, communicatively connected to the band division module, is configured to obtain the energy values of each band respectively, and then perform a merging process on the energy values corresponding to the Mel scales in the same band of the Mel spectrum to obtain a band energy set corresponding to the Mel spectrum;

[0092] A square wave signal generation module, communicatively connected to the band energy set module, is configured to establish a one-to-one mapping relationship between the frequencies in the band energy set and a specified vibration electrical signal frequency, and use the energy value corresponding to the band energy set as the amplitude value to generate a series of single-frequency square wave signals;

[0093] A TENS signal generation module, communicatively connected to the square wave signal generation module, is configured to perform a synthesis process on all the square wave signals to obtain a TENS signal.

[0094] Embodiment 3:

[0095] Based on Embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like. The electronic device may be referred to as a terminal for use, a portable terminal, a desktop terminal, etc. The electronic device includes:

[0096] A memory, configured to store computer program instructions; and,

[0097] A processor, configured to execute the computer program instructions to complete the operations of any of the methods described in Embodiment 1.

[0098] Embodiment 4:

[0099] Based on any one of Embodiments 1 to 3, this embodiment discloses a computer-readable storage medium, configured to store computer-readable computer program instructions, and the computer program instructions are configured to perform the operations of the method described in Embodiment 1 when running.

[0100] It should be noted that if the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, optical disks, and other media that can store program codes.

[0101] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to be implemented. In this way, the present invention is not limited to any specific combination of hardware and software.

[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for generating TENS signals based on multi-band fusion, characterized in that: Including: Receiving an audio signal and obtaining the Mel spectrum of the audio signal; Dividing the Mel spectrum into frequency bands to obtain a plurality of frequency bands; Respectively obtaining the energy values of each frequency band, and then performing a merging process on the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum; Establishing a one-to-one mapping relationship between the frequencies in the frequency band energy set and a specified vibration electrical signal frequency, and using the energy value corresponding to the frequency band energy set as the amplitude value to generate a series of square wave signals with a single frequency; Performing a synthesis process on all the square wave signals to obtain a TENS signal; After respectively obtaining the energy values of each frequency band, the method further includes: Performing amplitude modulation processing on the energy values of each frequency band respectively to obtain the modulated energy values of each frequency band; Performing discretization processing on the modulated energy values of each frequency band to obtain the discretized energy values, so as to perform a merging process on the discretized energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum; In the Mel spectrum, the modulated energy value of the k-th frame frequency band is: Among them, represents the energy value of the k-th frame frequency band in the said Mel spectrum; represents the minimum value among the energy values of the frequency bands in the said Mel spectrum; represents the maximum value among the energy values of the frequency bands in the said Mel spectrum; α B(i) represents the modulation coefficient of the k-th frame frequency band.

2. The method according to claim 1, characterized in that: After obtaining the Mel spectrum of the audio signal, the method further includes: Setting a minimum specified frequency threshold and a maximum specified frequency threshold corresponding to each frequency band; Correspondingly, performing a merging process on the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum, including: Performing a merging process on the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum according to the minimum specified frequency threshold and the maximum specified frequency threshold, so as to obtain a frequency band energy set corresponding to the Mel spectrum; wherein, the i-th frequency band in the frequency band energy set is: where f min represents the minimum specified frequency threshold; f max represents the maximum specified frequency threshold; M j represents the frequency corresponding to the j-th Mel scale in the Mel spectrum; M j (low) represents the lowest Mel scale in the Mel spectrum with a frequency greater than f min ; M j (high) represents the highest Mel scale in the Mel spectrum with a frequency less than f max .

3. The method according to claim 1, wherein: In the frequency band energy set, the energy value of any frequency band is the average value of the energies of the n frames of frequency bands before and after that frequency band; wherein, the energy value of the i-th frequency band at the k-th frame in the frequency band energy set is: Among them, n represents the specified number of frames in the frequency band before or after the k-th frame frequency band in the Mel spectrum; B j (i) represents the frequency of the j-th frame frequency band, where j ∈ [k - n, k + n].

4. The method according to claim 1, wherein: Based on the number of frequency bands divided when dividing the Mel spectrum, there are preset vibration electrical signal frequencies equal to the number of frequency bands; the square wave signal value corresponding to the k-th frame frequency band in the Mel spectrum is: Among them, represents the energy value of the k-th frame band in the Mel spectrum; SquareWave(f) represents a square wave generation function, which is used to generate a square wave with a time length corresponding to the frame length of the k-th frame band in the Mel spectrum according to the input frequency f; represents the preset vibration electrical signal frequency corresponding to the frequency set B(i) in the Mel spectrum.

5. The method according to claim 1, characterized in that: After performing a synthesis process on all the square wave signals, the method further includes: Performing normalization processing on the synthesized square wave signal to obtain a TENS signal; the TENS signal value corresponding to the k-th frame frequency band in the Mel spectrum is: Among them, W k represents the synthesized processed square wave signal, and represents the square wave signal corresponding to the k-th frame band in the said Mel spectrum; W min represents the minimum value of the square wave signal corresponding to the band in the said Mel spectrum; W max represents the maximum value of the square wave signal corresponding to the band in the said Mel spectrum.

6. A TENS signal generation system based on multi-band fusion, characterized in that: For implementing the method according to any one of claims 1 to 5; the system includes: A spectrum generation module, configured to receive an audio signal and obtain the Mel spectrum of the audio signal; A frequency band division module, communicatively connected to the spectrum generation module, configured to divide the Mel spectrum into frequency bands to obtain a plurality of frequency bands; A frequency band energy set generation module, communicatively connected to the frequency band division module, configured to respectively obtain the energy values of each frequency band, and then perform a merging process on the energy values corresponding to the Mel scale of the same frequency band in the Mel spectrum to obtain a frequency band energy set corresponding to the Mel spectrum; A square wave signal generation module, communicatively connected to the band energy set module, is configured to establish a one-to-one mapping relationship between the frequencies in the band energy set and a specified vibration electrical signal frequency, and use the energy value corresponding to the band energy set as the amplitude value to generate a series of square wave signals with single frequencies; A TENS signal generation module, communicatively connected to the square wave signal generation module, is configured to perform a synthesis process on all the square wave signals to obtain a TENS signal.

7. An electronic device, characterized in that: Comprising: A memory for storing computer program instructions; And A processor for executing the computer program instructions to complete the operations of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium for storing computer-readable computer program instructions, characterized in that: The computer program instructions are configured to perform the operations of the method according to any one of claims 1 to 5 when running.

Images