Multi-window spectrum parameter extraction algorithm and system for voiceprint information

Abstract

The invention relates to a multi-window spectrum parameter extraction algorithm and system for voiceprint information. The algorithm comprises the steps that feedback signals at position points are collected on a signal collection window; multiplying the plurality of window spectrums by the feedback signal to obtain a first feedback signal; performing fast Fourier transform on the plurality of first feedback signals and then synthesizing the first feedback signals to obtain second feedback signals; background environment data in the background environment sound library is used for creating background environment data screening waves, the background environment data screening waves are used for screening the second feedback signals, suspected loose signals are obtained and decomposed, and an alarm is given when harmonic waves exist in the suspected loose signals. According to the multi-window spectrum parameter extraction algorithm and system of the voiceprint information disclosed by the invention, the range detection is carried out on the loosening condition of the bolt on the iron tower by using the excitation signal, so that the potential loosened bolt can be found, and a more accurate detection result can be obtained while the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a multi-window spectrum parameter extraction algorithm and system for voiceprint information. Background Art

[0002] Transmission line towers are widely used in transmission lines as supports for overhead conductors. The safety of the towers is directly related to the safe and stable operation of the transmission lines. Transmission lines swing in strong winds, and even conductors may dance when certain meteorological conditions such as icing are met. In this case, the stress on the tower increases, causing the bolts of the tower to loosen. If not handled in time, defects such as bolts falling off may occur, and even tower collapse and line break accidents may occur. Due to the large number of bolts on the towers, there has been no efficient method for detecting loose bolts on transmission towers.

[0003] The methods currently used include manual detection and single-point sensor detection.

[0004] During manual inspection, for the bolts on the bottom of the tower, the bottom tower material is knocked on and the sound is used to identify the tightness of the bolts on the bottom of the tower. For the bolts in the middle and upper parts of the tower, high-altitude workers climb the tower to conduct random inspections to roughly determine the looseness of the bolts.

[0005] Single-point sensor detection is to install sensors on the bolts of the tower. This method can only detect the bolts at the installation position. The detection position is very limited, and it is restricted by cost (deployment, maintenance), quantity, etc., so its scope of use is very limited. Summary of the invention

[0006] The present invention provides a multi-window spectrum parameter extraction algorithm and system for voiceprint information, which uses an excitation signal to perform range detection on the looseness of bolts on an iron tower. This method can detect potential loose bolts, reduce costs and obtain more accurate detection results.

[0007] The above object of the present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a multi-window spectrum parameter extraction algorithm for voiceprint information, comprising: Establishing a signal acquisition window matching the generation time period of the excitation signal in the time series and acquiring the feedback signal at the position point in the signal acquisition window; Multiplying the feedback signal by multiple window spectra to obtain a first feedback signal, where the number of the first feedback signals is multiple; Performing fast Fourier transform on the multiple first feedback signals respectively and then synthesizing them to obtain a second feedback signal; Using background environment data in a background environment sound library to create a background environment data screening wave, and using the background environment data screening wave to screen the second feedback signal to obtain a suspected loose signal; The suspected loose signal is decomposed to determine whether there are harmonics in the suspected loose signal, and an alarm is issued when harmonics exist in the suspected loose signal.

[0008] In a possible implementation manner of the first aspect, using the background environment data in the background environment sound library to create a background environment data screening wave and using the background environment data screening wave to screen the second feedback signal includes: Obtaining environmental parameters and using the environmental parameters to calculate an adjustment factor, the environmental parameters including time, temperature and humidity; Selecting background environmental data according to the obtained environmental parameters and correcting the background environmental data using an adjustment coefficient; The background environment data is transferred into the frequency domain for decomposition to obtain a background environment data curve group; The part of the second feedback signal that is identical or similar to the background environment data curve group is removed to obtain a suspected loose signal.

[0009] In a possible implementation manner of the first aspect, when the portion of the second feedback signal that is identical to or similar to the background environment data curve group is removed, the excitation signal in the second feedback signal is retained.

[0010] In a possible implementation manner of the first aspect, removing a portion of the second feedback signal that is identical to or similar to the background environment data curve group to obtain the suspected loose signal includes: Obtain a first frequency distribution curve of the background environment data curve group, wherein a point in the first frequency distribution curve has both a start time and an end time; After transferring the second feedback signal into the time domain and the frequency domain for processing, a second feedback signal curve group is obtained; generating a second frequency distribution curve using a curve in the second feedback signal curve group; removing a portion of the second frequency distribution curve that is identical to or similar to the first frequency distribution curve; The remaining curves in the second feedback signal curve group are used to form a suspected loose signal.

[0011] In a possible implementation manner of the first aspect, retaining the excitation signal in the second feedback signal includes: After transferring the excitation signal into the time domain and frequency domain for processing, a group of excitation signal curves is obtained; Matching the excitation signal curve group and the second feedback signal curve group according to the start time, the end time, the frequency and the amplitude; The curves that appear in both the excitation signal curve group and the second feedback signal curve group are copied to the remaining curves in the second feedback signal curve group.

[0012] In a possible implementation manner of the first aspect, determining whether there are harmonics in the suspected loose signal includes: The waveforms constituting the suspected loose signal are grouped according to the start time and the end time to obtain a time group; The time groups are regrouped according to the frequency and amplitude to obtain harmonic groups. During the regrouping, the groups with only one data are discarded.

[0013] In a possible implementation manner of the first aspect, the ratio of the frequency of the excitation signal to the natural frequency is adjusted and the above process is repeated to determine whether there is data in the secondary grouping having the same ratio as the frequency of the excitation signal to the natural frequency; Wherein, when the ratio of the frequency of the excitation signal to the natural frequency is adjusted in each group, the ratio is different.

[0014] In a second aspect, the present invention provides a multi-window spectrum parameter extraction device for voiceprint information, comprising: A first signal processing unit is used to establish a signal acquisition window matching the generation time period of the excitation signal in the time series and to acquire the feedback signal at the position point in the signal acquisition window; A second signal processing unit is used to multiply the feedback signal by using multiple window spectra to obtain a first feedback signal, where the number of the first feedback signals is multiple; A third signal processing unit, configured to perform fast Fourier transform on the plurality of first feedback signals respectively and then synthesize them to obtain a second feedback signal; A signal screening unit, configured to create a background environment data screening wave using background environment data in a background environment sound library and screen the second feedback signal using the background environment data screening wave to obtain a suspected loose signal; The result output unit is used to decompose the suspected loose signal, determine whether there is harmonic in the suspected loose signal, and issue an alarm when harmonic exists in the suspected loose signal.

[0015] In a third aspect, the present invention provides a multi-window spectrum parameter extraction system for voiceprint information, the system comprising: one or more memories for storing instructions; and One or more processors, used to call and run the instructions from the memory to execute the algorithm as described in the first aspect and any possible implementation of the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium, the computer-readable storage medium comprising: The program, when the program is executed by a processor, the algorithm described in the first aspect and any possible implementation of the first aspect is executed.

[0017] In a fifth aspect, the present invention provides a computer program product, comprising program instructions, and when the program instructions are executed by a computing device, the algorithm described in the first aspect and any possible implementation of the first aspect is executed.

[0018] In a sixth aspect, the present invention provides a chip system comprising a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0019] The chip system may be composed of chips, or may include chips and other discrete devices.

[0020] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device.

[0021] The beneficial effects of adopting the above technical solution are: The multi-window spectrum parameter extraction algorithm and system of voiceprint information provided by the present invention use an excitation signal to perform range detection on the looseness of bolts on the iron tower. When the excitation signal reaches the bolt, a signal carrying the bolt information is generated. The signal carrying the bolt information is collected and analyzed, and whether the bolt is loose is determined by the presence of harmonics. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The present invention provides a schematic flowchart of the steps of a multi-window spectrum parameter extraction algorithm.

[0023] Figure 2 It is a schematic diagram of the principle of obtaining a feedback signal provided by the present invention.

[0024] Figure 3 It is a schematic diagram of performing regional analysis on an iron tower provided by the present invention.

[0025] Figure 4 It is a schematic diagram of establishing a signal acquisition window provided by the present invention. DETAILED DESCRIPTION

[0026] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0027] The present invention discloses a multi-window spectrum parameter extraction algorithm for voiceprint information, please refer to Figure 1 In some examples, the multi-window spectrum parameter extraction algorithm of voiceprint information disclosed in the present invention includes the following steps: S101, establishing a signal acquisition window matching the generation time period of the excitation signal in the time series and acquiring the feedback signal at the position point in the signal acquisition window; S102, multiplying a feedback signal by a plurality of window spectra to obtain a first feedback signal, wherein the number of the first feedback signals is a plurality; S103, performing fast Fourier transform on the multiple first feedback signals respectively and synthesizing them to obtain a second feedback signal; S104, using the background environment data in the background environment sound library to create a background environment data screening wave, and using the background environment data screening wave to screen the second feedback signal, and obtain a suspected loose signal; S105, decomposing the suspected loose signal to determine whether there is harmonic in the suspected loose signal, and issuing an alarm when harmonic exists in the suspected loose signal.

[0028] In general, the multi-window spectrum parameter extraction algorithm for voiceprint information provided by the present invention directly deploys the excitation signal generator and collector on the tower. The function of the excitation signal generator is to generate an excitation signal. After the excitation signal is transmitted to the bolt, it drives the bolt to vibrate, and the bolt generates a bolt vibration signal. Please refer to Figure 2 and Figure 3 , Figure 2 The dashed area in Figure 3 The dotted area in is an area.

[0029] The excitation signal and bolt vibration signal are collected by the collector and analyzed. The collector also collects the background signal synchronously, which is generated by the surrounding environment and the tower.

[0030] The deployment locations of the excitation signal generator and collector need to be targeted, generally for a certain area ( Figure 2 The dashed area in Figure 3 The dotted area in the figure is controlled at 20-30 square meters. Because the transmission distance of the bolt vibration signal needs to be considered, the bolt vibration signal includes harmonics, and the transmission distance of the harmonics is limited. Long-distance collection will cause harmonic loss.

[0031] The purpose of windowing is to reduce spectrum leakage and fence effect, because it is difficult to ensure that each frame is completely periodic when framing. After the non-periodic signal is truncated, after Fourier transform FFT, there will be frequencies that are not in the original signal, that is, redundant frequency components. This phenomenon is called spectrum leakage. By adding a suitable window, these components can be suppressed, making the result smoother.

[0032] When performing FFT on a signal, a series of discrete spectral lines are obtained. If the frequency components in the signal are located between the spectral lines rather than on the spectral lines, it will cause deviations in amplitude and phase. This is the fence effect.

[0033] The windows used include rectangular window, Hamming window, Hanning window, etc.

[0034] See also Figure 4 In step S101, a signal acquisition window matching the generation time period of the excitation signal is first established in the time series, because the generation time and cut-off time of the excitation signal are both known quantities. After determining the signal acquisition window, the feedback signal at the position point on the signal acquisition window is collected. At this time, the feedback signal includes the excitation signal, the bolt vibration signal and the environmental background signal.

[0035] In step S102, a plurality of window spectra are used to multiply the feedback signal to obtain a first feedback signal, and the number of the first feedback signals is multiple. Then, in step S103, the multiple first feedback signals are respectively subjected to fast Fourier transformation and synthesized to obtain a second feedback signal.

[0036] The contents in step S102 and step S103 are basic processing of the feedback signal after extraction. The windows used here include rectangular window, Hamming window, Hanning window and the like.

[0037] In step S104, the background environment data in the background environment sound library is used to create a background environment data filtering wave, and the background environment data filtering wave is used to filter the second feedback signal to obtain a suspected loose signal. At this time, the suspected loose signal includes an excitation signal, harmonics associated with the excitation signal (may exist), a bolt vibration signal, and harmonics associated with the bolt vibration signal (may exist).

[0038] Finally, in step S105, the suspected loose signal is decomposed to determine whether there are harmonics in the suspected loose signal. When there are harmonics in the suspected loose signal, an alarm is issued, which means that there are loose bolts in the area recorded in the above content. It should be noted that the present invention can predict whether there are loose bolts in an area, but it cannot accurately determine which bolts are loose. After determining the area, the bolts in the area need to be checked.

[0039] In some examples, the specific method of creating a background environment data filtering wave using the background environment data in the background environment sound library and filtering the second feedback signal using the background environment data filtering wave is: S201, obtaining environmental parameters and using the environmental parameters to calculate an adjustment coefficient, the environmental parameters including time, temperature and humidity; S202, selecting background environment data according to the obtained environmental parameters and correcting the background environment data using an adjustment coefficient; S203, transferring the background environment data into the frequency domain for decomposition to obtain a background environment data curve group; S204, removing the portion of the second feedback signal that is identical or similar to the background environment data curve group to obtain a suspected loose signal.

[0040] In step S201 to step S204, an environmental parameter is first determined, and then a background environment data filtering wave is selected from a background environment sound library using the environmental parameter and the background environment data filtering wave is adjusted.

[0041] The parameters specified in the present invention are time, temperature and humidity. The propagation speed of sound is proportional to the temperature. The increase in humidity will increase the water vapor content in the air, and the water vapor molecules will absorb the energy of the sound, thereby causing the sound to decay faster.

[0042] When the time parameter is used, when selecting background environment data in the background environment sound library, the background environment data obtained in a similar time period will be used.

[0043] The background environment data in the background environment sound library is based on the data obtained when collecting sound generated by the iron tower. It should be noted here that the sound collection involved in the present invention is the sound collected in close contact with the iron tower, that is, the sound is mainly or only transmitted by the iron tower, not by the air. This method is also to shield some low-frequency and low-energy sounds in the environment around the iron tower.

[0044] Then, the background environment data is selected according to the obtained environmental parameters and the adjustment coefficient is used to correct the background environment data. There are two ways to correct the background environment data using the adjustment coefficient: enhancement and weakening. For example, when the temperature and wind speed increase, it needs to be enhanced, and when the humidity increases, it needs to be weakened.

[0045] The parameters related to enhancement and weakening need to be determined based on experiments and are not limited here.

[0046] In step S203, the background environment data is transferred to the frequency domain for decomposition to obtain a background environment data curve group, and then in step S204, the parts of the second feedback signal that are the same as or similar to the background environment data curve group are removed to obtain a suspected loose signal.

[0047] However, at this time, when the curve removes the same and similar parts of the second feedback signal as the background environment data curve group, the excitation signal in the second feedback signal is removed at the same time. In this case, the excitation signal in the second feedback signal needs to be retained.

[0048] In some examples, the specific steps of removing the portion of the second feedback signal that is identical or similar to the background environment data curve group to obtain the suspected loose signal are as follows: S301, obtaining a first frequency distribution curve of the background environment data curve group, wherein a point in the first frequency distribution curve has both a start time and an end time; S302, transferring the second feedback signal into the time domain and the frequency domain for processing to obtain a second feedback signal curve group; S303, generating a second frequency distribution curve using a curve in the second feedback signal curve group; S304, removing the portion of the second frequency distribution curve that is identical or similar to the first frequency distribution curve; S305: Use the remaining curves in the second feedback signal curve group to form a suspected loose signal.

[0049] In step S301 to step S304, the background environment data curve group will be transferred to the time domain and frequency domain for processing, such as using wavelet decomposition. The curve obtained at this time has time characteristics and frequency characteristics. The irregular sounds in the background environment data curve group are discarded here. Irregular sounds refer to sounds that appear discontinuously or have uncertain appearance times.

[0050] The second feedback signal is processed in the same manner, that is, the second feedback signal is transferred into the time domain and the frequency domain for processing to obtain a second feedback signal curve group.

[0051] Finally, the part of the second frequency distribution curve that is the same or similar to the first frequency distribution curve is removed. Similar means that the frequency is the same but the amplitude difference is within the allowable range. The allowable range here is generally set at 0.5%-1%.

[0052] The specific method of retaining the excitation signal in the second feedback signal is as follows: S401, transferring the excitation signal into the time domain and frequency domain for processing to obtain an excitation signal curve group; S402, matching the excitation signal curve group and the second feedback signal curve group according to the start time, the end time, the frequency and the amplitude; S403: copy the curves that appear simultaneously in the excitation signal curve group and the second feedback signal curve group to the remaining curves in the second feedback signal curve group.

[0053] In the above steps, screening is mainly performed through time. In some possible implementations, the signal acquisition window needs to be appropriately lengthened, for example, a blank area is added before the signal acquisition window. The blank area can improve the resolution of the start time.

[0054] In some examples, the steps to determine if harmonics are present in a suspected loose signal are as follows: S501, grouping the waveforms constituting the suspected loose signal according to the start time and the end time to obtain a time group; S502, performing secondary grouping on the time group according to the frequency and amplitude to obtain harmonic groups. During the secondary grouping, discarding the group with only one data.

[0055] First, the waveforms that constitute the suspected loose signal are grouped according to the start time and end time. At this time, the start time and end time of the waveforms obtained are the same. Then, the time group is grouped again according to the frequency and amplitude to obtain the harmonic group. At this time, the group with only one data is discarded.

[0056] When frequency and amplitude are used as the basis for secondary grouping, the main frequency and main amplitude are determined first. The frequencies of other waveforms in the harmonic group are multiples (integer multiples) or sub-multiples (one-half, three-half, one-quarter) of the main frequency. The amplitude of the waveform with a multiple relationship is smaller than the main amplitude, and the amplitude of the waveform with a sub-multiple relationship is greater than or less than the main amplitude.

[0057] In some possible implementations, the ratio of the frequency of the excitation signal to the natural frequency is adjusted and the above process is repeated to determine whether there is data in the secondary grouping having the same ratio as the frequency of the excitation signal to the natural frequency; Wherein, when the ratio of the frequency of the excitation signal to the natural frequency is adjusted in each group, the ratio is different.

[0058] Because when adjusting the ratio of the frequency of the excitation signal to the natural frequency, it is easier to generate harmonics and subharmonics, the ratio is selected as a multiple, for example, the ratio of the frequency of the excitation signal to the natural frequency is one-half, three-half and one-quarter, etc.

[0059] The present invention also provides a multi-window spectrum parameter extraction device for voiceprint information, comprising: A first signal processing unit is used to establish a signal acquisition window matching the generation time period of the excitation signal in the time series and to acquire the feedback signal at the position point in the signal acquisition window; A second signal processing unit is used to multiply the feedback signal by using multiple window spectra to obtain a first feedback signal, where the number of the first feedback signals is multiple; A third signal processing unit, configured to perform fast Fourier transform on the plurality of first feedback signals respectively and then synthesize them to obtain a second feedback signal; A signal screening unit, configured to create a background environment data screening wave using background environment data in a background environment sound library and screen the second feedback signal using the background environment data screening wave to obtain a suspected loose signal; The result output unit is used to decompose the suspected loose signal, determine whether there is harmonic in the suspected loose signal, and issue an alarm when harmonic exists in the suspected loose signal.

[0060] Furthermore, it also includes: An adjustment coefficient calculation unit, used to obtain environmental parameters and use the environmental parameters to calculate the adjustment coefficient, the environmental parameters including time, temperature and humidity; A correction unit, used for selecting background environment data according to the obtained environmental parameters and correcting the background environment data using an adjustment coefficient; The first processing unit is used to transfer the background environment data into the frequency domain for decomposition to obtain a background environment data curve group; The first removal unit is used to remove the part of the second feedback signal that is the same as or similar to the background environment data curve group to obtain a suspected loose signal.

[0061] Further, when the parts of the second feedback signal that are identical or similar to the background environment data curve group are removed, the excitation signal in the second feedback signal is retained.

[0062] Furthermore, it also includes: A second processing unit is used to obtain a first frequency distribution curve of the background environment data curve group, wherein the points in the first frequency distribution curve have both a start time and an end time; A third processing unit, configured to transfer the second feedback signal into the time domain and the frequency domain for processing to obtain a second feedback signal curve group; A curve generating unit, configured to generate a second frequency distribution curve using a curve in the second feedback signal curve group; A second removing unit, used to remove a portion of the second frequency distribution curve that is identical or similar to the first frequency distribution curve; The intermediate result output unit is used to form a suspected loose signal using the remaining curves in the second feedback signal curve group.

[0063] Furthermore, it also includes: A fourth processing unit, used for transferring the excitation signal into the time domain and the frequency domain for processing to obtain an excitation signal curve group; A matching unit, used for matching the excitation signal curve group and the second feedback signal curve group according to the start time, the end time, the frequency and the amplitude; The copying unit is used to copy the curves that appear simultaneously in the excitation signal curve group and the second feedback signal curve group to the remaining curves in the second feedback signal curve group.

[0064] Furthermore, it also includes: A primary grouping unit, used for grouping the waveforms constituting the suspected loose signal according to the start time and the end time to obtain a time group; The secondary grouping unit is used to perform secondary grouping on the time group according to the frequency and amplitude to obtain the harmonic group. During the secondary grouping, the group with only one data is discarded.

[0065] Further, the ratio of the frequency of the excitation signal to the natural frequency is adjusted and the above process is repeated to determine whether there is data in the secondary grouping having the same ratio of the frequency of the excitation signal to the natural frequency; Wherein, when the ratio of the frequency of the excitation signal to the natural frequency is adjusted in each group, the ratio is different.

[0066] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0067] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0068] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in the present invention are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in the present invention should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0070] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0071] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0073] It should also be understood that in various embodiments of the present invention, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present invention.

[0074] It should also be understood that in the various embodiments of the present invention, unless otherwise specified or there is any logical conflict, the terms and / or descriptions between the different embodiments are consistent and can be referenced to each other, and the technical features in the different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a computer-readable storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0076] The present invention also provides a multi-window spectrum parameter extraction system for voiceprint information, the system comprising: one or more memories for storing instructions; and One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0077] The present invention also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0078] The present invention also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0079] The chip system may be composed of chips, or may include chips and other discrete devices.

[0080] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0081] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0082] Optionally, the computer instructions are stored in a memory.

[0083] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0084] It can be understood that the memory in the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0085] The nonvolatile memory may be ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), or flash memory.

[0086] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0087] The embodiments of this specific implementation method are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-window spectrum parameter extraction algorithm for voiceprint information, characterized in that: include: Establishing a signal acquisition window matching the generation time period of the excitation signal in the time series and acquiring the feedback signal at the position point in the signal acquisition window; Multiplying the feedback signal by multiple window spectra to obtain a first feedback signal, where the number of the first feedback signals is multiple; Performing fast Fourier transform on the multiple first feedback signals respectively and then synthesizing them to obtain a second feedback signal; Using background environment data in a background environment sound library to create a background environment data screening wave, and using the background environment data screening wave to screen the second feedback signal to obtain a suspected loose signal; The suspected loose signal is decomposed to determine whether there are harmonics in the suspected loose signal, and an alarm is issued when harmonics exist in the suspected loose signal.

2. The multi-window spectrum parameter extraction algorithm of voiceprint information according to claim 1 is characterized in that: Using the background environment data in the background environment sound library to create a background environment data filtering wave and using the background environment data filtering wave to filter the second feedback signal includes: Obtaining environmental parameters and using the environmental parameters to calculate an adjustment factor, the environmental parameters including time, temperature and humidity; Selecting background environmental data according to the obtained environmental parameters and correcting the background environmental data using an adjustment coefficient; The background environment data is transferred into the frequency domain for decomposition to obtain a background environment data curve group; The part of the second feedback signal that is identical or similar to the background environment data curve group is removed to obtain a suspected loose signal.

3. The multi-window spectrum parameter extraction algorithm of voiceprint information according to claim 2 is characterized in that: When the parts of the second feedback signal that are identical or similar to the background environment data curve group are removed, the excitation signal in the second feedback signal is retained.

4. The multi-window spectrum parameter extraction algorithm for voiceprint information according to claim 2 or 3, characterized in that: The parts of the second feedback signal that are identical or similar to the background environment data curve group are removed, and the suspected loose signals obtained include: Obtain a first frequency distribution curve of the background environment data curve group, wherein a point in the first frequency distribution curve has both a start time and an end time; After transferring the second feedback signal into the time domain and the frequency domain for processing, a second feedback signal curve group is obtained; generating a second frequency distribution curve using a curve in the second feedback signal curve group; removing a portion of the second frequency distribution curve that is identical to or similar to the first frequency distribution curve; The remaining curves in the second feedback signal curve group are used to form a suspected loose signal.

5. The multi-window spectrum parameter extraction algorithm of voiceprint information according to claim 4 is characterized in that: Retaining the excitation signal in the second feedback signal comprises: After transferring the excitation signal into the time domain and frequency domain for processing, a group of excitation signal curves is obtained; Matching the excitation signal curve group and the second feedback signal curve group according to the start time, the end time, the frequency and the amplitude; The curves that appear in both the excitation signal curve group and the second feedback signal curve group are copied to the remaining curves in the second feedback signal curve group.

6. The multi-window spectrum parameter extraction algorithm of voiceprint information according to claim 1 is characterized in that: Determining whether harmonics are present in a suspected loosening signal involves: The waveforms constituting the suspected loose signal are grouped according to the start time and the end time to obtain a time group; The time groups are regrouped according to the frequency and amplitude to obtain harmonic groups. During the regrouping, the groups with only one data are discarded.

7. The multi-window spectrum parameter extraction algorithm of voiceprint information according to claim 6 is characterized in that: Adjust the ratio of the frequency of the excitation signal to the natural frequency and repeat the above process to determine whether there is data in the secondary grouping with the same ratio of the frequency of the excitation signal to the natural frequency; Wherein, when the ratio of the frequency of the excitation signal to the natural frequency is adjusted in each group, the ratio is different.

8. A multi-window spectrum parameter extraction device for voiceprint information, characterized in that: include: A first signal processing unit is used to establish a signal acquisition window matching the generation time period of the excitation signal in the time series and to acquire the feedback signal at the position point in the signal acquisition window; A second signal processing unit is used to multiply the feedback signal by multiple window spectra to obtain a first feedback signal, where the number of the first feedback signals is multiple; A third signal processing unit, configured to perform fast Fourier transform on the plurality of first feedback signals respectively and then synthesize them to obtain a second feedback signal; A signal screening unit, configured to create a background environment data screening wave using background environment data in a background environment sound library and screen the second feedback signal using the background environment data screening wave to obtain a suspected loose signal; The result output unit is used to decompose the suspected loose signal, determine whether there is harmonic in the suspected loose signal, and issue an alarm when harmonic exists in the suspected loose signal.

9. A multi-window spectrum parameter extraction system for voiceprint information, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to execute the algorithm as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the algorithm as claimed in any one of claims 1 to 7 is executed.

Images