A method and device for detecting audio dropouts

Abstract

A method and device for detecting audio dropouts. Among them, the method for detecting audio dropouts includes: obtaining a first signal sequence and a second signal sequence, where the first signal sequence is the signal sequence obtained by the audio system collecting the input audio signal using the target sampling rate; obtaining the amplitudes of the first signal sequence and the second signal sequence to obtain a first amplitude sequence and a second amplitude sequence respectively; performing a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; performing a linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; obtaining the amplitude of the third signal sequence to obtain a second target amplitude sequence; and obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude and the second target amplitude sequence. By adopting the technical solution of the present application, it is possible to determine the dropout situation of the audio according to the similarity of two amplitude measurement values.

Description

Technical Field

[0001] This application relates to the field of audio data processing, and in particular, to a method and device for detecting audio dropouts. Background Art

[0002] When an audio system samples, the acquired sample data may experience dropout situations. Dropout situations are an important indicator for measuring the quality of an audio system. For example, when dropout occurs in the acquired sample data, it may affect the subjective listening experience of the audio system or cause some audio algorithms in the audio system to fail. Therefore, it is necessary to detect the audio dropout situation of the audio system.

[0003] However, currently, professional audio detection equipment is used to detect the audio dropout situation of the audio system, resulting in high detection costs.

[0004] Therefore, how to reduce the cost of detecting the audio dropout situation of the audio system has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method and device for detecting audio dropouts, which can reduce the cost of detecting the audio dropout situation of the audio system.

[0006] In a first aspect, an embodiment of this application provides a method for detecting audio dropouts, including: obtaining a first signal sequence, where the first signal sequence is a signal sequence obtained by the audio system collecting an input audio signal using a target sampling rate; obtaining a second signal sequence; obtaining the amplitudes of the first signal sequence and the second signal sequence, respectively obtaining a first amplitude sequence and a second amplitude sequence; performing a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; performing the linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; obtaining the amplitude of the third signal sequence to obtain a second target amplitude sequence; and obtaining the audio dropout situation of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0007] In this embodiment, the first signal sequence refers to a signal sequence obtained after the audio system samples the input audio signal using the target sampling rate. Among them, the input audio signal may be a sine digital audio signal or a sine analog audio signal. The target sampling rate refers to the sampling frequency used by the audio system to sample the input audio signal. It should be noted here that when the input audio signal in this embodiment is a sine digital audio signal, the sampling frequency of the sine digital audio signal is the target sampling frequency.

[0008] In this embodiment, the second signal sequence refers to the signal sequence corresponding to the input audio signal when the input audio signal is collected at the target sampling rate before entering the input audio system.

[0009] For example, when the input audio signal is a sinusoidal digital audio signal with a sampling frequency equal to the target sampling frequency, the second signal sequence is the sinusoidal digital audio signal.

[0010] For example, when the input audio signal is a sinusoidal analog audio signal, the second signal sequence refers to the signal sequence obtained by sampling the sinusoidal analog audio with the target sampling rate using a preset audio system, where the preset audio system is an audio system that does not have dropout situations.

[0011] It should be understood that in this embodiment, the lengths of the first signal sequence and the second signal sequence can be the same. Exemplarily, this length can be marked as n, which is used to identify that the first signal sequence and the second signal sequence respectively contain n sampling signals.

[0012] In this embodiment, the first target amplitude sequence can be considered as the target amplitude sequence obtained after linear transformation of the first amplitude sequence and the second amplitude sequence. For example, the first target amplitude sequence is the amplitude sequence obtained by summing the first amplitude sequence and the second amplitude sequence.

[0013] In this embodiment, the third signal sequence refers to the signal sequence obtained after linear transformation of the first signal sequence and the second signal sequence. Among them, this linear transformation is the same as the linear transformation required to obtain the target amplitude sequence from the first amplitude sequence and the second amplitude sequence.

[0014] For example, if the first target amplitude sequence is the amplitude sequence obtained by summing the first amplitude sequence and the second amplitude sequence, then the third signal sequence refers to the signal sequence obtained after summing the first signal sequence and the second signal sequence.

[0015] It should be understood that in this embodiment, the length of the third signal sequence can be the same as that of the first signal sequence and the second signal sequence. Exemplarily, this length can be marked as n, which is used to identify that when the first signal sequence and the second signal sequence respectively contain n sampling signals, the third signal sequence also includes n sampling signals.

[0016] It should be understood that when there is no dropout in the audio of the audio system, the above first target amplitude sequence and the second target amplitude sequence will basically coincide. Therefore, in this embodiment, after obtaining the first target amplitude sequence and the second target amplitude sequence, the dropout situation of the audio of the audio system can be obtained through the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0017] In combination with the first aspect, in a possible implementation manner, the obtaining the amplitudes of the first signal sequence and the second signal sequence includes: performing a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and performing a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence; obtaining an amplitude sequence of the first analytic signal sequence to obtain the first amplitude sequence; obtaining an amplitude sequence of the second analytic signal sequence to obtain the second amplitude sequence; correspondingly, the obtaining the amplitude of the third signal sequence to obtain a second target amplitude sequence includes: performing a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence; obtaining an amplitude sequence of the third analytic signal sequence to obtain the second target amplitude sequence.

[0018] In this embodiment, the first analytic signal sequence refers to the signal sequence obtained after the first signal sequence undergoes a Hilbert transform, and the second analytic signal sequence refers to the signal sequence obtained after the second signal sequence undergoes a Hilbert transform.

[0019] It should be understood that after a certain signal undergoes a Hilbert transform to obtain a corresponding analytic signal, the amplitude and phase of the analytic signal can be obtained.

[0020] Therefore, in this embodiment, after the first signal sequence undergoes a Hilbert transform to obtain the first analytic signal sequence, an amplitude sequence corresponding to the first signal sequence can be obtained, and this amplitude sequence is called the first amplitude sequence; and after the second signal sequence undergoes a Hilbert transform to obtain the second analytic signal sequence, an amplitude sequence corresponding to the second signal sequence can be obtained, and this amplitude sequence is called the second amplitude sequence.

[0021] In this embodiment, the third analytic signal sequence refers to the signal sequence obtained after the third signal sequence undergoes a Hilbert transform. Similarly, after the third signal sequence undergoes a Hilbert transform to obtain the third analytic signal sequence, an amplitude sequence corresponding to the third signal sequence can be obtained, and this amplitude sequence is called the second target amplitude sequence.

[0022] It should be understood that in this embodiment, when the third signal sequence includes n sampling signals, the third analytic signal sequence will include n analytic signals. Among them, these n analytic signals correspond one-to-one to the n sampling signals in the third signal sequence, and each analytic signal is obtained by performing a Hilbert transform on the corresponding sampling signal.

[0023] In combination with the first aspect, in one implementable manner, obtaining the dropout condition of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: obtaining the average value of the amplitudes in the first target amplitude sequence to obtain a first average value; obtaining the average value of the amplitudes in the second target amplitude sequence to obtain a second average value; obtaining the difference between the first average value and the second average value to obtain an average difference; determining that the audio of the audio system has a dropout when the average difference is greater than or equal to a first preset value; and determining that the audio of the audio system does not have a dropout when the average difference is less than the first preset value.

[0024] In this implementable manner, when determining the dropout condition of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined by comparing the magnitude relationship between the difference between the average value of the amplitudes in the first target amplitude sequence and the average value of the amplitudes in the second target amplitude sequence and the first preset value.

[0025] In combination with the first aspect, in one implementable manner, obtaining the dropout condition of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: obtaining the variance of the amplitudes in the first target amplitude sequence to obtain a first variance; obtaining the variance of the amplitudes in the second target amplitude sequence to obtain a second variance; obtaining the difference between the first variance and the second variance to obtain a variance difference; determining that the audio of the audio system has a dropout when the variance difference is greater than or equal to a second preset value; and determining that the audio of the audio system does not have a dropout when the variance difference is less than the second preset value.

[0026] In this implementable manner, when determining the dropout condition of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined by comparing the magnitude relationship between the difference between the variance of the amplitudes in the first target amplitude sequence and the variance of the amplitudes in the second target amplitude sequence and the second preset value.

[0027] Combined with the first aspect, in one implementable manner, obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: obtaining the standard deviation of the amplitudes in the first target amplitude sequence to obtain a first standard deviation; obtaining the standard deviation of the amplitudes in the second target amplitude sequence to obtain a second standard deviation; obtaining the difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference; determining that there is a dropout in the audio of the audio system when the standard deviation difference is greater than or equal to a third preset value; and determining that there is no dropout in the audio of the audio system when the standard deviation difference is less than the third preset value.

[0028] In this implementable manner, when determining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined whether there is a dropout in the audio of the audio system by comparing the magnitude relationship between the difference between the standard deviation of the amplitudes in the first target amplitude sequence and the standard deviation of the amplitudes in the second target amplitude sequence and the third preset value.

[0029] Combined with the first aspect, in one implementable manner, obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: obtaining the similarity between the first target amplitude sequence and the second target amplitude sequence according to a preset relational expression to obtain a first similarity, the preset relational expression: b = log 10 min(X 1,i / X 2,i ), where i is an integer and takes values from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; determining that there is a dropout in the audio of the audio system when the first similarity is greater than or equal to a fourth preset value; and determining that there is no dropout in the audio of the audio system when the first similarity is less than the fourth preset value.

[0030] In this implementable manner, when determining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined whether there is a dropout in the audio of the audio system by the magnitude relationship between the similarity between the first target amplitude sequence and the second target amplitude sequence obtained according to the preset relational expression and the fourth preset value.

[0031] In a second aspect, the present application provides a device for detecting audio dropouts, including: an acquisition module, configured to acquire a first signal sequence, where the first signal sequence is a signal sequence obtained by the audio system collecting an input audio signal using a target sampling rate; the acquisition module is further configured to acquire a second signal sequence; the acquisition module is further configured to acquire the amplitudes of the first signal sequence and the second signal sequence, respectively obtaining a first amplitude sequence and a second amplitude sequence; a processing module, configured to perform a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; the processing module is further configured to perform the linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; the acquisition module is further configured to acquire the amplitude of the third signal sequence to obtain a second target amplitude sequence; the processing module is further configured to obtain the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0032] In combination with the second aspect, in a possible implementation, the acquisition module is further configured to: perform a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and perform a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence; acquire the amplitude sequence of the first analytic signal sequence to obtain the first amplitude sequence; acquire the amplitude sequence of the second analytic signal sequence to obtain the second amplitude sequence; correspondingly, the acquisition module is further configured to: perform a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence; acquire the amplitude sequence of the third analytic signal sequence to obtain the second target amplitude sequence.

[0033] In combination with the second aspect, in a possible implementation, the input audio signal is a sine digital audio signal or a sine analog audio signal, and the sampling frequency of the sine digital audio signal is the target sampling rate; when the input audio signal is the sine digital audio signal, the second signal sequence is the sine digital audio signal sequence, and when the input audio signal is the sine analog audio signal, the second signal sequence is the signal sequence obtained by sampling the sine analog audio with the target sampling rate by a preset audio system. In combination with the second aspect, in a possible implementation, the processing module is specifically configured to: obtain the average value of the amplitudes in the first target amplitude sequence to obtain a first average value; obtain the average value of the amplitudes in the second target amplitude sequence to obtain a second average value; obtain the difference between the first average value and the second average value to obtain an average difference value; determine that there is a dropout in the audio of the audio system when the average difference value is greater than or equal to a first preset value; and determine that there is no dropout in the audio of the audio system when the average difference value is less than the first preset value.

[0034] In combination with the second aspect, in a possible implementation, the processing module is specifically configured to: obtain the variance of the amplitudes in the first target amplitude sequence to obtain a first variance; obtain the variance of the amplitudes in the second target amplitude sequence to obtain a second variance; obtain the difference between the first variance and the second variance to obtain a variance difference value; determine that there is a dropout in the audio of the audio system when the variance difference value is greater than or equal to a second preset value; and determine that there is no dropout in the audio of the audio system when the variance difference value is less than the second preset value.

[0035] In combination with the second aspect, in a possible implementation, the processing module is specifically configured to: obtain the standard deviation of the amplitudes in the first target amplitude sequence to obtain a first standard deviation; obtain the standard deviation of the amplitudes in the second target amplitude sequence to obtain a second standard deviation; obtain the difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference value; determine that there is a dropout in the audio of the audio system when the standard deviation difference value is greater than or equal to a third preset value; and determine that there is no dropout in the audio of the audio system when the standard deviation difference value is less than the third preset value.

[0036] In combination with the second aspect, in a possible implementation, the processing module is specifically configured to: obtain the similarity between the first target amplitude sequence and the second target amplitude sequence according to a preset relational expression to obtain a first similarity, and the preset relational expression: b = log 10 min(X 1,i / X 2,i), where i is an integer ranging from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; when the first similarity is greater than or equal to the fourth preset value, it is determined that there is a dropout in the audio of the audio system; when the first similarity is less than the fourth preset value, it is determined that there is no dropout in the audio of the audio system.

[0037] In a third aspect, an audio system is provided, including the device as described in the second aspect or any one of the second aspects. In a fourth aspect, a detection device for audio dropout is provided, including a processor, which is used to call a computer program from a memory. When the computer program is executed, the processor is used to execute the method in the first aspect or any possible implementation manner in the first aspect.

[0038] In a fifth aspect, a computer-readable storage medium is provided for storing a computer program, which includes code for executing the method described in the first aspect or any possible implementation manner in the first aspect. Description of the Drawings

[0039] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation to the present application. In the drawings:

[0040] Figure 1 is a structural schematic diagram of an audio system according to an embodiment of the present application;

[0041] Figure 2 is a flowchart schematic diagram of a dropout detection system according to an embodiment of the present application;

[0042] Figure 3 is a flowchart schematic diagram of a method for detecting audio dropout according to an embodiment of the present application;

[0043] Figure 4 is a structural schematic diagram of a first amplitude sequence and a second amplitude sequence according to an embodiment of the present application;

[0044] Figure 5 is a flowchart schematic diagram of a method for detecting audio dropout according to another embodiment of the present application;

[0045] Figure 6 is a structural schematic diagram of a detection device for audio dropout according to an embodiment of the present application;

[0046] Figure 7It is a schematic structural diagram of a missing point detection device according to an embodiment of the present application; Detailed implementation manners

[0047] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0048] For the convenience of understanding, several terms involved in the embodiments of the present application are first introduced.

[0049] 1. Hilbert transform

[0050] In digital signal processing, the Hilbert transform is to convolve the signal s(t) with 1 / (πt) to obtain the analytic signal s'(t). After the signal undergoes the Hilbert transform, the amplitude of each frequency component in the frequency domain remains unchanged, but the phase will have a 90-degree phase shift, that is, leading π / 2 for positive frequencies and leading π / 2 for negative frequencies. It should be noted that after the signal is transformed into an analytic signal by the Hilbert transform, the amplitude and phase of the analytic signal can be obtained.

[0051] 2. Audio signal

[0052] Audio signals are signals representing mechanical waves and are information carriers for the wavelength and intensity changes of mechanical waves. According to the characteristics of mechanical waves, they can be divided into regular signals and irregular signals.

[0053] Currently, with the rapid development of the audio-visual field, various audio systems are widely used in life. Exemplarily, Figure 1 is a schematic structural diagram of an audio system provided by an embodiment of the present application. As Figure 1 shown, when the input audio signal is input to the audio system 101, the audio system 101 can process the input audio signal to obtain the target audio signal and output the target audio signal. More specifically, before processing the input audio signal, the audio system 101 will first sample the input audio signal to obtain a signal sequence corresponding to the input audio signal, and then process the signal sequence.

[0054] It should be noted here that the audio system 101 in this application can be, for example, a smart speaker, a smart pickup, or an audio-video integrated machine, which does not constitute a limitation to this application. It is also noted here that the specific structure of the audio system 101 in this embodiment is not limited. For example, the audio system 101 may include an input source, a processor, an output source, etc., which does not constitute a limitation to this application.

[0055] However, for Figure 1 the audio system shown, when the audio system 101 samples, the sampled data obtained may have dropout situations. The dropout situation is an important indicator for measuring the quality of the audio system. For example, when the sampled data has a dropout situation, it may affect the subjective listening experience of the audio system or may cause some audio algorithms in the audio system to fail. Therefore, it is necessary to detect the audio dropout situation of the audio system.

[0056] However, currently, the audio dropout situation of the audio system is detected by professional audio detection equipment, resulting in high detection costs. Therefore, how to reduce the cost when detecting the audio dropout situation of the audio system has become a technical problem to be solved urgently.

[0057] In view of this, this application provides a method and device for detecting audio dropout. In the method for detecting audio dropout proposed in this application, first, the input audio signal of the audio system and the signal sequence obtained by sampling the input audio signal using the target sampling rate are respectively obtained, and then the corresponding amplitude measurement value is obtained by performing a linear operation on the amplitudes of the two signals; in addition, another amplitude measurement value is also obtained by using the amplitude of the signal sequence obtained by first performing a linear operation on the input audio signal and the signal sequence obtained by sampling the input audio signal using the target sampling rate. It should be understood that if there is no dropout in the audio system, then these two amplitude measurement values will basically coincide and be equal. Therefore, in the technical solution provided in this application, the audio dropout situation of the audio system can be determined by the similarity of these two amplitude measurement values.

[0058] Exemplarily, Figure 2 is a structural schematic diagram of a dropout detection system provided in an embodiment of this application. As Figure 2 shown, the dropout detection system includes an audio system 201 and a detection device 202. In this dropout detection system, the input audio signal will obtain an output audio signal after passing through the audio system 201. Then, by inputting the output audio signal and the input audio signal into the detection device 202, the detection device 202 is used to determine the dropout situation of the audio system 201 according to the input signal and the output signal.

[0059] The following uses specific embodiments to elaborate in detail on the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0060] Figure 3 is a schematic flowchart of a method for detecting audio dropouts in an embodiment of the present application. As Figure 3 shown, the method of this embodiment may include S301, S302, S303, S304, S305, S306, and S307. Among them, the method for detecting audio dropouts in this embodiment may be executed by Figure 2 the detection device 202 in the dropout detection system shown.

[0061] S301, obtain a first signal sequence, where the first signal sequence is a signal sequence obtained by the audio system collecting an input audio signal using a target sampling rate.

[0062] In this embodiment, the first signal sequence (also denoted as S1 in the embodiments of the present application) refers to the signal sequence obtained after the audio system samples the input audio signal using the target sampling rate. Among them, the target sampling rate refers to the sampling frequency used by the audio system when sampling the input audio signal. For example, the target sampling rate used by the audio system is 48 kHz.

[0063] For ease of understanding, the dropout detection system shown in Figure 2 is used as an example for illustration. As Figure 2 shown, the first signal sequence S1 is the Figure 2 output audio signal in.

[0064] It should be understood that the input audio signal may be a sine digital audio signal or a sine analog audio signal.

[0065] In this embodiment, when the input audio signal is a sine digital audio signal, the sampling frequency of the sine digital audio signal is the target sampling frequency.

[0066] When the input audio signal is a sine digital audio signal, the present application embodiment does not limit the frequency corresponding to the input audio signal. For example, when the target sampling rate used by the audio system is 48 kHz, the frequency of the input audio signal can be selected as 11 kHz, 17 kHz, 20 kHz, etc., which does not constitute a limitation to the present application.

[0067] S302, obtain a second signal sequence.

[0068] In this embodiment, the second signal sequence (in the embodiments of the present application, the first sequence is also denoted as S2) refers to the signal sequence corresponding to the input audio signal when the input audio signal is collected using the target sampling rate before entering the input audio system.

[0069] Specifically, taking Figure 2 the drop point detection system shown as an example for illustration. As Figure 2 shown, in implementation, when the input audio signal is a sine digital audio signal and the sampling frequency of the sine digital audio signal is the target sampling rate of the audio system 201, the second signal sequence is the sine digital audio signal sequence. When the input audio signal is a sine analog audio signal, the second signal sequence in this embodiment refers to the signal sequence obtained by sampling the sine analog audio using the target sampling rate by a preset audio system. Wherein, the preset audio system refers to an audio system without drop point conditions.

[0070] It should be understood that in this embodiment, the lengths of the first signal sequence and the second signal sequence may be the same. Exemplarily, this length can be marked as n, which is used to identify that the first signal sequence and the second signal sequence respectively contain n sampling signals.

[0071] S303, obtain the amplitudes of the first signal sequence and the second signal sequence respectively to obtain the first amplitude sequence and the second amplitude sequence.

[0072] For example, in a possible implementation manner, the method for obtaining the first amplitude sequence and the second amplitude sequence is as follows: perform Hilbert transform on the first signal sequence to obtain the first analytical signal sequence of the first signal sequence, obtain the amplitude sequence of the first analytical signal sequence to obtain the first amplitude sequence; perform Hilbert transform on the second signal sequence to obtain the second analytical signal sequence of the second signal sequence, obtain the amplitude sequence of the second analytical signal sequence to obtain the second amplitude sequence.

[0073] In this implementation manner, after the first signal sequence S1 is obtained, Hilbert transform is performed on the first signal sequence S1, that is, through the formula: A1 = HilbertTransform(S1), to obtain the corresponding analysis signal A1 (also referred to as the first analytical signal sequence A1 in this embodiment). It can be understood that the first analytical signal sequence A1 and the first signal sequence S1 have the same time sequence length, and the difference is that the first analytical signal sequence A1 is a complex signal.

[0074] It should be understood that in this implementation manner, when the first signal sequence includes n sampling signals, the first analytical signal sequence will include n analytical signals. Among them, these n analytical signals correspond one-to-one with the n sampling signals in the first signal sequence, and each analytical signal is obtained by performing Hilbert transform on the corresponding sampling signal.

[0075] In this implementation, after the second signal sequence S2 is obtained, the Hilbert transform is performed on the second signal sequence S2, that is, through the formula: A2 = HilbertTransform(S2), and the corresponding analytical signal A2 (also referred to as the second analytical signal sequence A2) is obtained. It can be understood that the second analytical signal sequence A2 has the same time series length as the second signal sequence S2, and the difference is that the second analytical signal sequence A2 is a complex signal.

[0076] It should be understood that in this embodiment, when the second signal sequence includes n sampling signals, the second analytical signal sequence will include n analytical signals. Among them, these n analytical signals correspond one-to-one with the n sampling signals in the second signal sequence, and each analytical signal is obtained by performing the Hilbert transform on the corresponding sampling signal.

[0077] It should be understood that after a certain signal undergoes the Hilbert transform to obtain the corresponding analytical signal, the amplitude and phase of the analytical signal can be obtained.

[0078] Therefore, in this implementation, after the first signal sequence S1 undergoes the Hilbert transform to obtain the first analytical signal sequence A1, the amplitude sequence corresponding to the first analytical signal sequence A1 (i.e., the first amplitude sequence) can be obtained, and after the second signal sequence S2 undergoes the Hilbert transform to obtain the second analytical signal sequence A2, the amplitude sequence corresponding to the second analytical signal sequence A2 (i.e., the second amplitude sequence) can also be obtained.

[0079] Exemplarily, in an implementable manner, the first amplitude sequence of the first analytical signal sequence A1 can be obtained through the formula: ||A1|| 2 where ||A1|| 2 represents taking the L2 norm of the first analytical signal sequence A1. It should be noted here that the concept of the L2 norm and its detailed explanation can be referred to the description in the related art, and will not be elaborated here.

[0080] Exemplarily, in an implementable manner, the second amplitude sequence of the second analytical signal sequence A2 can be obtained through the formula: ||A2|| 2 where ||A2|| 2 represents taking the L2 norm of the second analytical signal sequence A2.

[0081] It should be understood that in this embodiment, when the second signal sequence includes n sampling signals, the second analytical signal sequence will include n analytical signals, and further, n amplitudes will be obtained. Among them, these n amplitudes correspond one-to-one with the n sampling signals in the second signal sequence or with the n analytical signals in the second analytical signal sequence.

[0082] S304. Perform a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence.

[0083] It should be understood that the first amplitude sequence includes multiple amplitudes, and the second amplitude sequence includes multiple amplitudes. Therefore, in a specific implementation, the amplitudes at the same position in the first amplitude sequence and the second amplitude sequence can be added to obtain the amplitude at the corresponding position in the first target amplitude sequence (in the embodiments of the present application, the first target amplitude sequence is also denoted as X1).

[0084] Exemplarily, assume that the first amplitude sequence and the second amplitude sequence are as Figure 4 shown. Now assume that Figure 4 the length of the line segment at each position in represents the amplitude at that position. Then, when obtaining the first target amplitude sequence from the first amplitude sequence shown in Figure 4 and the second amplitude sequence shown in Figure 4 , the amplitudes at the same position in the first amplitude sequence and the second amplitude sequence can be added to obtain the amplitude at the corresponding position in the first target amplitude sequence. For example, add the amplitudes at position 1 in the first amplitude sequence and the second amplitude sequence to obtain the amplitude at the corresponding position in the first target amplitude sequence.

[0085] It should be understood that in this embodiment, the first target amplitude sequence may include n amplitudes, where these n amplitudes correspond one-to-one to the n sampling signals in the first signal sequence or the n analytical signals in the second analytical signal sequence.

[0086] S305. Perform a linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence.

[0087] For example, in one possible implementation, the first signal sequence and the second signal sequence can be summed to obtain the third signal sequence.

[0088] It should be understood that in this embodiment, the length of the third signal sequence may be the same as that of the first signal sequence and the second signal sequence. Exemplarily, this length can be marked as n, which is used to indicate that when the first signal sequence and the second signal sequence each include n sampling signals, the third signal sequence also includes n sampling signals.

[0089] S306. Obtain the amplitude of the third signal sequence to obtain a second target amplitude sequence.

[0090] In one possible implementation, the method for obtaining the second target amplitude sequence is as follows: perform a Hilbert transform on the third signal sequence to obtain a third analytical signal sequence of the third signal sequence; obtain the amplitude sequence of the third analytical signal sequence to obtain the second target amplitude sequence.

[0091] In this implementation manner, after obtaining the third signal sequence, a Hilbert transform is performed on the third signal sequence.

[0092] Exemplarily, it is assumed that the third signal sequence is obtained by summing the first signal sequence and the second signal sequence, that is, the third signal sequence is equal to S1 + S2. Then, the corresponding analytical signal Asum (also referred to as the third analytical signal sequence Asum in the embodiments of the present application) can be obtained through the formula: Asum = HilbertTransform(S1 + S2).

[0093] It should be understood that in this embodiment, when the third signal sequence includes n sampling signals, the third analytical signal sequence will include n analytical signals. Among them, these n analytical signals correspond one-to-one to the n sampling signals in the third signal sequence, and each analytical signal is obtained by performing a Hilbert transform on the corresponding sampling signal.

[0094] Exemplarily, in an implementable manner, the formula: ||Asum|| 2 can be used to obtain the amplitude sequence of the third analytical signal sequence Asum (i.e., the second target amplitude sequence). Among them, ||Asum|| 2 represents taking the L2 norm of the third analytical signal sequence Asum.

[0095] It should be noted here that in the embodiments of the present application, the second target amplitude sequence is also denoted as X2.

[0096] It should be understood that in this embodiment, the second target amplitude sequence may include n amplitudes, where these n amplitudes correspond one-to-one to the n sampling signals in the third signal sequence or to the n analytical signals in the third analytical signal sequence.

[0097] S307, obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0098] Generally, if there is no phase difference in the hardware system, then X1 and X2 basically coincide and are equal, that is, D(n) = X1 - X2 = 0. Where n belongs to any moment. However, due to the fact that in actual measurement, D will not be exactly equal to 0, but is a very small time series, therefore, in the embodiments of the present application, in specific implementation, a threshold can be set, and then after calculating the similarity between the first target amplitude sequence and the second target amplitude sequence, the dropout situation of the audio of the audio system can be determined by the magnitude relationship between the similarity value and the set threshold.

[0099] Exemplarily, in a possible implementation, S307 includes: obtaining the average value of the amplitudes in the first target amplitude sequence X1 to obtain a first average value; obtaining the average value of the amplitudes in the second target amplitude sequence X2 to obtain a second average value; obtaining the difference between the first average value and the second average value to obtain an average difference; determining that there is a dropout in the audio of the audio system when the average difference is greater than or equal to a first preset value; and determining that there is no dropout in the audio of the audio system when the average difference is less than the first preset value.

[0100] In this implementation, when determining the dropout of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined whether there is a dropout in the audio of the audio system by comparing the magnitude relationship between the difference between the average value of the amplitudes in the first target amplitude sequence and the average value of the amplitudes in the second target amplitude sequence and the first preset value.

[0101] Exemplarily, in a possible implementation, S307 includes: obtaining the variance of the amplitudes in the first target amplitude sequence X1 to obtain a first variance; obtaining the variance of the amplitudes in the second target amplitude sequence X2 to obtain a second variance; obtaining the difference between the first variance and the second variance to obtain a variance difference; determining that there is a dropout in the audio of the audio system when the variance difference is greater than or equal to a second preset value; and determining that there is no dropout in the audio of the audio system when the variance difference is less than the second preset value.

[0102] In this implementation, when determining the dropout of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined whether there is a dropout in the audio of the audio system by comparing the magnitude relationship between the difference between the variance of the amplitudes in the first target amplitude sequence and the variance of the amplitudes in the second target amplitude sequence and the second preset value.

[0103] Exemplarily, in a possible implementation, S307 includes: obtaining the standard deviation of the amplitudes in the first target amplitude sequence X1 to obtain a first standard deviation; obtaining the standard deviation of the amplitudes in the second target amplitude sequence X2 to obtain a second standard deviation; obtaining the difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference; determining that there is a dropout in the audio of the audio system when the standard deviation difference is greater than or equal to a third preset value; and determining that there is no dropout in the audio of the audio system when the standard deviation difference is less than the third preset value.

[0104] In this implementation manner, when determining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined whether there is a dropout in the audio of the audio system by comparing the difference between the standard deviation of the amplitudes in the first target amplitude sequence and the standard deviation of the amplitudes in the second target amplitude sequence with a third preset value.

[0105] Exemplarily, in a possible implementation manner, S307 includes: obtaining the similarity between the first target amplitude sequence X1 and the second target amplitude sequence X2 according to a preset relational expression to obtain a first similarity, where the preset relational expression is: b = log 10 min(X 1,i / X 2,i ), where i is an integer and takes values from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; in the case where the first similarity is greater than or equal to a fourth preset value, it is determined that there is a dropout in the audio of the audio system; in the case where the first similarity is less than the fourth preset value, it is determined that there is no dropout in the audio of the audio system.

[0106] In this implementation manner, when determining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence, it is determined whether there is a dropout in the audio of the audio system by the magnitude relationship between the similarity between the first target amplitude sequence and the second target amplitude sequence obtained through a preset relational expression and a fourth preset value.

[0107] Exemplarily, the detection device can also combine at least two of the above-mentioned magnitude relationships between the mean difference and the first preset value, the variance difference and the second preset value, the standard deviation difference and the third preset value, and the first similarity and the fourth preset value to determine whether there is a dropout in the audio of the audio system. For example, in the case where the mean difference is greater than or equal to the first preset value and the standard deviation difference is greater than or equal to the third preset value, it is determined that there is a dropout in the audio of the audio system; or, in the case where the first similarity is greater than or equal to the fourth preset value and the variance difference is greater than or equal to the second preset value, it is determined that there is a dropout in the audio of the audio system.

[0108] It should be noted here that Figure 3In the illustrated embodiment, when determining the first amplitude sequence corresponding to the first signal sequence, the second amplitude sequence corresponding to the second signal sequence, and the second target amplitude sequence corresponding to the third signal sequence, obtaining the corresponding amplitude sequences through Hilbert transform is only one possible implementation. For example, it can also be other variations that have the same properties as the Hilbert transform and can obtain amplitude sequences, which do not constitute a limitation of this application.

[0109] It should be noted here that for Figure 3 in the illustrated embodiment, when performing a linear transformation on the first amplitude sequence and the second amplitude sequence, obtaining the amplitude at the corresponding position in the first target amplitude sequence by adding the amplitudes at the same position in the first amplitude sequence and the second amplitude sequence is only an example of the linear transformation. It can also include other linear transformations. For example, in another linear transformation method, the first amplitude sequence can be multiplied by a coefficient k1 to obtain a third amplitude sequence, the second amplitude sequence can be multiplied by a coefficient k2 to obtain a fourth amplitude sequence, and then the amplitudes at the same position in the third amplitude sequence and the fourth amplitude sequence are added to obtain the amplitude at the corresponding position in the first target amplitude sequence. However, it should be understood that the linear transformation performed on the first amplitude sequence and the second amplitude sequence should be the same as the linear transformation performed on the first signal sequence and the second signal sequence. Therefore, when the linear transformation performed on the first amplitude sequence and the second amplitude sequence is the above-mentioned another linear transformation method, the linear transformation performed on the first signal sequence and the second signal sequence should also be the above-mentioned another linear transformation method.

[0110] In addition, it should be noted here that in the embodiments of this application, the linear transformation can also be applied to the first signal sequence or the second signal sequence, which all fall within the concept of the embodiments of this application. For example, Figure 3 in the illustrated embodiment, a linear transformation can also be performed on the first signal sequence before performing the Hilbert transform on the first signal sequence. It should be understood that in this case, a linear transformation should also be performed on the first signal sequence before performing the linear transformation on the first signal sequence and the second signal sequence. Or, a linear transformation can also be performed on the second signal sequence before performing the Hilbert transform on the second signal sequence. It should be understood that in this case, a linear transformation should also be performed on the second signal sequence before performing the linear transformation on the first signal sequence and the second signal sequence.

[0111] In addition, it should be noted here that in the embodiments of this application, when performing a linear transformation, the number of times of the linear transformation is not limited, which all fall within the concept of the embodiments of this application.

[0112] For ease of understanding, Figure 5 FIG. 5 is a schematic flowchart of the audio dropout detection method provided in this application. As shown in FIG. 5, the dropout detection method includes:

[0113] S501 performs a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and performs a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence.

[0114] In specific implementation, as Figure 5 shown, S501 may include the following steps:

[0115] S5011 performs a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence.

[0116] S5012 performs a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence.

[0117] S502 obtains a first amplitude sequence of the first analytic signal sequence and a second amplitude sequence of the second analytic signal.

[0118] In specific implementation, as Figure 5 shown, S502 may include the following steps:

[0119] S5021 obtains a first amplitude sequence of the first analytic signal sequence.

[0120] S5022 obtains a second amplitude sequence of the second analytic signal sequence.

[0121] S503 performs a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence.

[0122] S504 performs a linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence.

[0123] S505 performs a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence.

[0124] S506 obtains the amplitude of the third analytic signal sequence to obtain a second target amplitude sequence.

[0125] S507 obtains the situation of audio dropouts of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0126] Among them, the concepts appearing in this embodiment can be referred to Figure 3 the description in the shown embodiment, and will not be described here again.

[0127] Figure 6 is a schematic structural diagram of a detection device 600 for audio dropouts according to an embodiment of the present application. As Figure 6 shown, the device 600 includes: an acquisition module 601 and a processing module 602.

[0128] Among them, an acquisition module 601 is configured to acquire a first signal sequence, where the first signal sequence is a signal sequence obtained by the audio system collecting an input audio signal using a target sampling rate; the acquisition module 601 is further configured to acquire a second signal sequence; the acquisition module 601 is further configured to acquire the amplitudes of the first signal sequence and the second signal sequence, respectively obtaining a first amplitude sequence and a second amplitude sequence; a processing module 602 is configured to perform a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; the processing module 602 is further configured to perform the linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; the acquisition module 601 is further configured to acquire the amplitude of the third signal sequence to obtain a second target amplitude sequence; the processing module 602 is further configured to obtain the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0129] In a possible implementation manner, the acquisition module 601 is further configured to: perform a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and perform a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence; acquire the amplitude sequence of the first analytic signal sequence to obtain the first amplitude sequence; acquire the amplitude sequence of the second analytic signal sequence to obtain the second amplitude sequence; correspondingly, the acquisition module 601 is further configured to: perform a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence; acquire the amplitude sequence of the third analytic signal sequence to obtain the second target amplitude sequence.

[0130] In a possible implementation manner, the input audio signal is a sine digital audio signal or a sine analog audio signal, and the sampling frequency of the sine digital audio signal is the target sampling rate; when the input audio signal is the sine digital audio signal, the second signal sequence is the sine digital audio signal sequence, and when the input audio signal is the sine analog audio signal, the second signal sequence is a signal sequence obtained by a preset audio system sampling the sine analog audio using the target sampling rate.

[0131] In a possible implementation, the processing module 602 is specifically configured to: obtain the average value of the amplitudes in the first target amplitude sequence to obtain a first average value; obtain the average value of the amplitudes in the second target amplitude sequence to obtain a second average value; obtain the difference between the first average value and the second average value to obtain an average difference value; determine that there is a dropout in the audio of the audio system when the average difference value is greater than or equal to a first preset value; and determine that there is no dropout in the audio of the audio system when the average difference value is less than the first preset value.

[0132] In a possible implementation, the processing module 602 is specifically configured to: obtain the variance of the amplitudes in the first target amplitude sequence to obtain a first variance; obtain the variance of the amplitudes in the second target amplitude sequence to obtain a second variance; obtain the difference between the first variance and the second variance to obtain a variance difference value; determine that there is a dropout in the audio of the audio system when the variance difference value is greater than or equal to a second preset value; and determine that there is no dropout in the audio of the audio system when the variance difference value is less than the second preset value.

[0133] In a possible implementation, the processing module 602 is specifically configured to: obtain the standard deviation of the amplitudes in the first target amplitude sequence to obtain a first standard deviation; obtain the standard deviation of the amplitudes in the second target amplitude sequence to obtain a second standard deviation; obtain the difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference value; determine that there is a dropout in the audio of the audio system when the standard deviation difference value is greater than or equal to a third preset value; and determine that there is no dropout in the audio of the audio system when the standard deviation difference value is less than the third preset value.

[0134] In a possible implementation, the processing module 602 is specifically configured to: obtain a first similarity between the first target amplitude sequence and the second target amplitude sequence according to a preset relational expression, where the preset relational expression is: b = log 10 min(X 1,i / X 2,i ), where i is an integer and ranges from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; determine that there is a dropout in the audio of the audio system when the first similarity is greater than or equal to a fourth preset value; and determine that there is no dropout in the audio of the audio system when the first similarity is less than the fourth preset value.

[0135] Figure 7 FIG. 700 is a schematic structural diagram of a missing point detection device 700 according to an embodiment of the present application. The missing point detection device 700 is used to execute the method performed by the detection device in the foregoing text.

[0136] The missing point detection device 700 includes a processor 710. The processor 710 is used to execute a computer program or instruction stored in the memory 720, or read data stored in the memory 720, so as to execute the methods in the foregoing method embodiments. Optionally, the processor 710 is one or more.

[0137] Optionally, as Figure 7 shown, the missing point detection device 700 further includes a memory 720. The memory 720 is used to store computer programs or instructions and / or data. The memory 720 may be integrated with the processor 710, or may be separately provided. Optionally, the memory 720 is one or more.

[0138] Optionally, as Figure 7 shown, the missing point detection device 700 further includes a communication interface 730. The communication interface 730 is used for receiving and / or sending signals. For example, the processor 710 is used to control the communication interface 730 to receive and / or send signals.

[0139] Optionally, the missing point detection device 700 is used to implement the operations performed by the detection device in the foregoing method embodiments.

[0140] For example, the processor 710 is used to execute a computer program or instruction stored in the memory 720 to implement the related operations of the detection device in the foregoing method embodiments. For example, the processor 710 may be used to: obtain a first signal sequence, where the first signal sequence is a signal sequence obtained by the audio system collecting an input audio signal using a target sampling rate; obtain a second signal sequence; obtain the amplitudes of the first signal sequence and the second signal sequence, respectively obtaining a first amplitude sequence and a second amplitude sequence; perform a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; perform the linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; obtain the amplitude of the third signal sequence to obtain a second target amplitude sequence; and obtain the missing point condition of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

[0141] In a possible implementation, the obtaining the amplitudes of the first signal sequence and the second signal sequence includes: performing a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and performing a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence; obtaining an amplitude sequence of the first analytic signal sequence to obtain the first amplitude sequence; obtaining an amplitude sequence of the second analytic signal sequence to obtain the second amplitude sequence; correspondingly, the obtaining the amplitude of the third signal sequence to obtain a second target amplitude sequence includes: performing a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence; obtaining an amplitude sequence of the third analytic signal sequence to obtain the second target amplitude sequence.

[0142] In a possible implementation, the input audio signal is a sine digital audio signal or a sine analog audio signal, and the sampling frequency of the sine digital audio signal is the target sampling rate; when the input audio signal is the sine digital audio signal, the second signal sequence is the sine digital audio signal sequence, and when the input audio signal is the sine analog audio signal, the second signal sequence is a signal sequence obtained by sampling the sine analog audio using the target sampling rate by a preset audio system.

[0143] In some examples, the processor 710 is further configured to: obtain an average value of the amplitudes in the first target amplitude sequence to obtain a first average value; obtain an average value of the amplitudes in the second target amplitude sequence to obtain a second average value; obtain a difference between the first average value and the second average value to obtain an average difference; determine that there is a dropout in the audio of the audio system when the average difference is greater than or equal to a first preset value; determine that there is no dropout in the audio of the audio system when the average difference is less than the first preset value.

[0144] In some examples, the processor 710 is further configured to: obtain a variance of the amplitudes in the first target amplitude sequence to obtain a first variance; obtain a variance of the amplitudes in the second target amplitude sequence to obtain a second variance; obtain a difference between the first variance and the second variance to obtain a variance difference; determine that there is a dropout in the audio of the audio system when the variance difference is greater than or equal to a second preset value; determine that there is no dropout in the audio of the audio system when the variance difference is less than the second preset value.

[0145] In some examples, the processor 710 is further configured to: obtain the standard deviation of the amplitudes in the first target amplitude sequence to obtain a first standard deviation; obtain the standard deviation of the amplitudes in the second target amplitude sequence to obtain a second standard deviation; obtain the difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference; determine that there is a dropout in the audio of the audio system when the standard deviation difference is greater than or equal to a third preset value; and determine that there is no dropout in the audio of the audio system when the standard deviation difference is less than the third preset value.

[0146] In some examples, the processor 710 is further configured to: obtain a first similarity degree between the first target amplitude sequence and the second target amplitude sequence according to a preset relational expression, where the preset relational expression is: b = log 10 min(X 1,i / X 2,i ), where i is an integer and ranges from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity degree, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; determine that there is a dropout in the audio of the audio system when the first similarity degree is greater than or equal to a fourth preset value; and determine that there is no dropout in the audio of the audio system when the first similarity degree is less than the fourth preset value.

[0147] It should be noted that Figure 7 the dropout detection device 700 in

[0148] may be the detection device in the foregoing embodiments or a chip, which is not limited herein.

[0149] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method. For example: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0150] In addition, each unit in the above device can be integrated in whole or in part, or can be independently implemented. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SOC). The SOC can include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The types of the at least one processor can be different. For example, it includes CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0151] Correspondingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program / instructions are executed by a processor, the processor is caused to implement Figure 3 the steps in the method executed by the detection device in

[0152] Correspondingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program / instructions are executed by a processor, the processor is caused to implement Figure 3 the steps in the method executed by the detection device in

[0153] Correspondingly, an embodiment of the present application further provides a computer program product, including computer program / instructions. When the computer program / instructions are executed by a processor, the processor is caused to implement Figure 3 the steps in the method executed by the detection device in

[0154] Correspondingly, an embodiment of the present application further provides a computer program product, including computer program / instructions. When the computer program / instructions are executed by a processor, the processor is caused to implement Figure 3 the steps in the method executed by the detection device in

[0155] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0156] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0157] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0158] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0159] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0160] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0161] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0162] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0163] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for detecting audio dropouts, characterized in that, it includes: Obtain a first signal sequence, where the first signal sequence is a signal sequence obtained by an audio system collecting an input audio signal using a target sampling rate; Obtain a second signal sequence, where the second signal sequence is related to the input audio signal; Obtain the amplitudes of the first signal sequence and the second signal sequence, respectively obtaining a first amplitude sequence and a second amplitude sequence; Perform a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; Perform the linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; Obtain the amplitude of the third signal sequence to obtain a second target amplitude sequence; Obtain the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

2. The method according to claim 1, characterized in that, The obtaining the amplitudes of the first signal sequence and the second signal sequence, respectively obtaining a first amplitude sequence and a second amplitude sequence, includes: Perform a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and perform a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence; Obtain the amplitude sequence of the first analytic signal sequence to obtain the first amplitude sequence; Obtain the amplitude sequence of the second analytic signal sequence to obtain the second amplitude sequence; Correspondingly, the obtaining the amplitude of the third signal sequence to obtain a second target amplitude sequence includes: Perform a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence; Obtain the amplitude sequence of the third analytic signal sequence to obtain the second target amplitude sequence.

3. The method according to claim 1 or 2, characterized in that, The input audio signal is a sine digital audio signal or a sine analog audio signal, and the sampling frequency of the sine digital audio signal is the target sampling rate; When the input audio signal is the sine digital audio signal, the second signal sequence is a sine digital audio signal sequence, and when the input audio signal is the sine analog audio signal, the second signal sequence is a signal sequence obtained by a preset audio system sampling the sine analog audio signal using the target sampling rate.

4. The method according to claim 3, characterized in that, The obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: Obtain the average value of the amplitudes in the first target amplitude sequence to obtain a first average value; Obtain the average value of the amplitudes in the second target amplitude sequence to obtain a second average value; Obtain the difference between the first average value and the second average value to obtain an average difference; When the average difference is greater than or equal to a first preset value, determine that the audio of the audio system has a dropout; When the mean difference is less than the first preset value, it is determined that there is no dropout in the audio of the audio system.

5. The method according to claim 3, wherein, obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: obtaining the variance of the amplitudes in the first target amplitude sequence to obtain a first variance; obtaining the variance of the amplitudes in the second target amplitude sequence to obtain a second variance; obtaining the difference between the first variance and the second variance to obtain a variance difference; when the variance difference is greater than or equal to a second preset value, it is determined that there is a dropout in the audio of the audio system; when the variance difference is less than the second preset value, it is determined that there is no dropout in the audio of the audio system.

6. The method according to claim 3, wherein, obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: obtaining the standard deviation of the amplitudes in the first target amplitude sequence to obtain a first standard deviation; obtaining the standard deviation of the amplitudes in the second target amplitude sequence to obtain a second standard deviation; obtaining the difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference; when the standard deviation difference is greater than or equal to a third preset value, it is determined that there is a dropout in the audio of the audio system; when the standard deviation difference is less than the third preset value, it is determined that there is no dropout in the audio of the audio system.

7. The method according to claim 3, wherein, obtaining the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence includes: Obtain the similarity between the first target amplitude sequence and the second target amplitude sequence according to a preset relational expression to obtain a first similarity, the preset relational expression: b = log 10 min(X 1,i / X 2,i ), where i is an integer and ranges from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; when the first similarity is greater than or equal to a fourth preset value, it is determined that there is a dropout in the audio of the audio system; when the first similarity is less than the fourth preset value, it is determined that there is no dropout in the audio of the audio system.

8. An audio dropout detection device, wherein, comprising: an acquisition module, configured to acquire a first signal sequence, where the first signal sequence is a signal sequence obtained by an audio system collecting an input audio signal using a target sampling rate; the acquisition module is further configured to acquire a second signal sequence, where the second signal sequence is related to the input audio signal; the acquisition module is further configured to acquire the amplitudes of the first signal sequence and the second signal sequence to obtain a first amplitude sequence and a second amplitude sequence respectively; a processing module, configured to perform a linear transformation on the first amplitude sequence and the second amplitude sequence to obtain a first target amplitude sequence; the processing module is further configured to perform the linear transformation on the first signal sequence and the second signal sequence to obtain a third signal sequence; the acquisition module is further configured to acquire the amplitudes of the third signal sequence to obtain a second target amplitude sequence; the processing module is further configured to obtain the dropout situation of the audio of the audio system based on the similarity between the first target amplitude sequence and the second target amplitude sequence.

9. The device according to claim 8, wherein, the obtaining module is further configured to: perform a Hilbert transform on the first signal sequence to obtain a first analytic signal sequence of the first signal sequence, and perform a Hilbert transform on the second signal sequence to obtain a second analytic signal sequence of the second signal sequence; obtain an amplitude sequence of the first analytic signal sequence to obtain the first amplitude sequence; obtain an amplitude sequence of the second analytic signal sequence to obtain the second amplitude sequence; correspondingly, the obtaining module is further configured to: perform a Hilbert transform on the third signal sequence to obtain a third analytic signal sequence of the third signal sequence; obtain an amplitude sequence of the third analytic signal sequence to obtain the second target amplitude sequence.

10. The device according to claim 8 or 9, wherein, the input audio signal is a sine digital audio signal or a sine analog audio signal, and the sampling frequency of the sine digital audio signal is the target sampling rate; when the input audio signal is the sine digital audio signal, the second signal sequence is a sine digital audio signal sequence, and when the input audio signal is the sine analog audio signal, the second signal sequence is a signal sequence obtained by sampling the sine analog audio signal using the target sampling rate by a preset audio system.

11. The device according to claim 10, wherein, the processing module is specifically configured to: obtain an average value of the amplitudes in the first target amplitude sequence to obtain a first average value; obtain an average value of the amplitudes in the second target amplitude sequence to obtain a second average value; obtain a difference between the first average value and the second average value to obtain an average difference; when the average difference is greater than or equal to a first preset value, determine that there is a dropout in the audio of the audio system; when the average difference is less than the first preset value, determine that there is no dropout in the audio of the audio system.

12. The device according to claim 10, wherein, the processing module is specifically configured to: obtain a variance of the amplitudes in the first target amplitude sequence to obtain a first variance; obtain a variance of the amplitudes in the second target amplitude sequence to obtain a second variance; obtain a difference between the first variance and the second variance to obtain a variance difference; when the variance difference is greater than or equal to a second preset value, determine that there is a dropout in the audio of the audio system; when the variance difference is less than the second preset value, determine that there is no dropout in the audio of the audio system.

13. The device according to claim 10, wherein, the processing module is specifically configured to: obtain a standard deviation of the amplitudes in the first target amplitude sequence to obtain a first standard deviation; obtain a standard deviation of the amplitudes in the second target amplitude sequence to obtain a second standard deviation; obtain a difference between the first standard deviation and the second standard deviation to obtain a standard deviation difference; when the standard deviation difference is greater than or equal to a third preset value, determine that there is a dropout in the audio of the audio system; When the difference in standard deviations is less than the third preset value, it is determined that there is no dropout in the audio of the audio system.

14. The apparatus according to claim 10, wherein, the processing module is specifically configured to: Obtain the similarity between the first target amplitude sequence and the second target amplitude sequence according to a preset relational expression, and obtain a first similarity. The preset relational expression: b = log 10 min(X 1,i / X 2,i ), where i is an integer and ranges from 1 to n, n represents the length of the first target amplitude sequence, b represents the similarity, min() represents finding the minimum value, X 1,i represents the i-th element in the first target amplitude sequence, and X 2,i represents the i-th element in the second target amplitude sequence; when the first similarity is greater than or equal to a fourth preset value, determine that there is a dropout in the audio of the audio system; when the first similarity is less than the fourth preset value, determine that there is no dropout in the audio of the audio system.

15. An audio system, wherein, it includes the apparatus according to any one of claims 8 to 14.

16. A computer-readable storage medium, wherein, the computer-readable storage medium stores instructions for computer execution, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

17. A computer program product, wherein, it includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images