Audio processing method, device, equipment and medium based on parameter equalizer

Abstract

The embodiment of the present invention discloses an audio processing method, device, equipment and medium based on a parametric equalizer, which relates to the field of audio processing technology. The method includes: smoothing the output loudness of the acquired audio to be processed to find out the segment row with higher than the average loudness as the first background sound segment; Fourier transforming the audio to be processed to obtain time-frequency audio, and processing the time-frequency audio by a similarity method to obtain a second background sound segment; taking the intersection and expansion of the first background sound segment and the second background sound segment to obtain a chorus time segment; scanning and monitoring the human voice frequency and background sound frequency in the audio to be processed to obtain the frequency width and center frequency; equalizing the audio to be processed by a parametric equalizer according to the frequency width, center frequency and chorus time segment. The embodiment of the present application solves the problem of mutual masking of human voice and background sound in the audio, thereby improving the sound quality of the audio.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of audio processing technology, and in particular to an audio processing method, device, equipment and medium based on a parametric equalizer. Background Art

[0002] Multi-track music processing often occurs in the process of mastering. Different from the two-channel audio we see in daily life, multi-track music has richer instrumental accompaniment and vocal a cappella tracks. Different audio effects can be produced by processing each track separately. The existing technology mainly uses the vocal improvement method based on the fixed-band equalizer to improve the frequency energy level of a fixed interval, thereby changing the pitch of the vocals and improving the overall sound quality. The method based on the fixed-band equalizer has the following disadvantages: 1. The non-adjustability of the fixed frequency makes the frequency that the vocals can modify relatively fixed. Even if the fixed frequency band is continuously subdivided, it is impossible to cover the full range of audio frequency bands; 2. It is easy to cause the optimized vocals and background sounds to mask each other's frequencies, affecting the overall sound quality. Summary of the invention

[0003] The embodiments of the present invention provide an audio processing method, device, equipment and medium based on a parametric equalizer, aiming to solve the problem of poor sound quality caused by mutual masking between human voice and background sound in existing audio.

[0004] In a first aspect, an embodiment of the present invention provides an audio processing method based on a parametric equalizer, comprising: obtaining an audio to be processed, and smoothing the output loudness of the audio to be processed to find a segment row with a higher loudness than an average loudness as a first background sound segment; performing Fourier transform on the audio to be processed to obtain a time-frequency audio, and processing the time-frequency audio by a similarity method to obtain a second background sound segment; taking the intersection and expansion of the first background sound segment and the second background sound segment to obtain a chorus time segment; scanning and monitoring the human voice frequency and the background sound frequency in the audio to be processed to obtain a frequency width and a center frequency; and performing equalization processing on the audio to be processed by a parametric equalizer according to the frequency width, the center frequency and the chorus time segment.

[0005] Furthermore, the audio to be processed is calculated using a loudness calculation formula to obtain an output loudness; the output loudness is smoothed based on a moving median method to obtain a target output loudness; an average loudness of the target output loudness is calculated, and a segment of the target output loudness that is greater than the average loudness is used as a first background sound segment.

[0006] Furthermore, starting from the starting position in the time-frequency audio, audio segments of a preset length are sequentially obtained as the first segment; the audio segments in the time-frequency audio except the first segment are taken as the remaining segments, and audio segments of the same length as the first segment are sequentially obtained from the remaining segments as the second segment; the similarity between the first segment and the second segment is calculated by the Pearson coefficient to construct a self-similarity matrix; and the self-similarity matrix is ​​subjected to line detection by image processing to obtain the second background sound segment.

[0007] Furthermore, the first background sound segment and the second background sound segment are merged and their intersection is taken to obtain an initial chorus segment; the initial chorus segment is expanded by a long rise method and a long fall method to obtain a chorus time segment.

[0008] Furthermore, the human voice frequency and the background sound frequency in the audio to be processed are obtained, and the difference between the human voice frequency and the background sound frequency is calculated to obtain a frequency difference; if the frequency difference is less than a preset frequency difference, the sampling frequency and sampling time point corresponding to the frequency difference are saved, and the center frequency and frequency width are determined according to the sampling frequency and the sampling time point.

[0009] Furthermore, the background sound loudness gain in the audio to be processed is adjusted according to the chorus time segment to obtain a target loudness gain; a background sound target frequency response value is obtained by a frequency response value calculation formula corresponding to a parameter equalizer according to the frequency width, the center frequency and the target loudness gain, and the audio to be processed is equalized according to the background sound target frequency response value.

[0010] Furthermore, whether the background sound in the audio to be processed is a chorus segment is determined according to the chorus start time corresponding to the chorus time segment; if the background sound is the chorus segment, the background sound loudness gain in the audio to be processed is lowered; if the background sound is not the chorus segment, the background sound loudness gain is increased.

[0011] In a second aspect, an embodiment of the present invention further provides an audio processing device based on a parametric equalizer, comprising: a search unit, used to obtain an audio to be processed, and to smooth the output loudness of the audio to be processed to find a segment row with a higher loudness than the average loudness as a first background sound segment; a processing unit, used to perform Fourier transform on the audio to be processed to obtain a time-frequency audio, and to process the time-frequency audio by a similarity method to obtain a second background sound segment; an expansion unit, used to take the intersection and expand the first background sound segment and the second background sound segment to obtain a chorus time segment; a monitoring unit, used to scan and monitor the human voice frequency and the background sound frequency in the audio to be processed to obtain a frequency width and a center frequency; and an equalizing unit, used to equalize the audio to be processed by a parametric equalizer according to the frequency width, the center frequency and the chorus time segment.

[0012] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program can implement the above method when executed by a processor.

[0014] The embodiment of the present invention provides an audio processing method, device, equipment and medium based on a parametric equalizer. The method includes: obtaining the audio to be processed, and smoothing the output loudness of the audio to be processed to find out the segment row with higher than the average loudness as the first background sound segment; performing Fourier transform on the audio to be processed to obtain time-frequency audio, and processing the time-frequency audio by a similarity method to obtain a second background sound segment; taking the intersection and expansion of the first background sound segment and the second background sound segment to obtain a chorus time segment; scanning and monitoring the human voice frequency and background sound frequency in the audio to be processed to obtain the frequency width and center frequency; equalizing the audio to be processed by a parametric equalizer according to the frequency width, the center frequency and the chorus time segment. The technical solution of the embodiment of the present invention first performs a series of processing on the processed audio to obtain the chorus time segment, then scans and monitors the human voice frequency and background sound frequency in the processed audio to obtain the frequency width and center frequency, and finally performs equalization processing on the processed audio through a parameter equalizer according to the chorus time segment, frequency width and center frequency, thereby solving the problem of mutual masking of human voice and background sound in the audio, thereby improving the sound quality effect of the audio. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0016] Figure 1 A schematic diagram of a flow chart of an audio processing method based on a parametric equalizer provided in an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of a sub-flow diagram of an audio processing method based on a parameter equalizer provided by an embodiment of the present invention;

[0018] Figure 3 A schematic diagram of a sub-flow diagram of an audio processing method based on a parameter equalizer provided by an embodiment of the present invention;

[0019] Figure 4 A schematic diagram of a sub-flow diagram of an audio processing method based on a parameter equalizer provided by an embodiment of the present invention;

[0020] Figure 5 A schematic block diagram of an audio processing device based on a parametric equalizer provided by an embodiment of the present invention; and

[0021] Figure 6 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0024] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0025] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0027] See also Figure 1 , Figure 1 1 is a flow chart of an audio processing method based on a parameter equalizer provided by an embodiment of the present invention. The audio processing method based on a parameter equalizer is described in detail below. Figure 1 As shown, the method includes the following steps S100-S140.

[0028] S100: Acquire audio to be processed, and perform smoothing processing on the output loudness of the audio to be processed to find out a segment row with a loudness higher than an average loudness as a first background sound segment.

[0029] In an embodiment of the present invention, a user uploads the audio to be processed to the audio and video editing software. After the upload is completed, the audio and video editing software will obtain the audio to be processed, and smooth the output loudness of the audio to be processed to find a segment row with a loudness higher than the average as the first background sound segment. It should be noted that in this embodiment, the audio to be processed includes background sound and human voice, wherein the background sound includes chorus, prelude and ending, etc. Understandably, the chorus part is the main component of a song. This part often requires the human voice and chorus to reach the highest loudness at the same time. The chorus part can be found in the long audio according to the similarity of frequency and loudness.

[0030] In some embodiments, such as the present embodiment, Figure 2 As shown, the step S100 may include steps S101-S103.

[0031] S101, calculating the output loudness of the audio to be processed using a loudness calculation formula;

[0032] S102, smoothing the output loudness based on a moving median method to obtain a target output loudness;

[0033] S103: Calculate an average loudness of the target output loudness, and use a segment of the target output loudness that is greater than the average loudness as a first background sound segment.

[0034] In the embodiment of the present invention, the output loudness is obtained by calculating the audio to be processed using a loudness calculation formula, wherein the loudness calculation formula is shown in formula (1). In formula (1), data is the audio to be processed, X is db is the output loudness of the audio to be processed; it is understandable that in this embodiment, the number of input sampling points of the audio to be processed is the same as the number of output sampling points; the output loudness is smoothed based on the moving median method to obtain the target output loudness; the average loudness of the target output loudness is calculated, and the segments of the target output loudness that are greater than the average loudness are recorded as the first background sound segment. It should be noted that in this embodiment, the moving median method is used to smooth the output loudness because if the traditional median takes the median value of 5 numbers, the 5 numbers will be covered as one number, while the moving median will increase the information usage rate of the point in each movement, making the data result smoother. For example, the traditional median of 12345 is 3, 3, 3, 3, 3, while the moving median of 12345 is 2, 2.5, 3.

[0035] X db =20*log10(abs(data)) (1)

[0036] S110, performing Fourier transform on the audio to be processed to obtain time-frequency audio, and processing the time-frequency audio by a similarity method to obtain a second background sound segment.

[0037] In an embodiment of the present invention, after obtaining the first background sound segment, the audio to be processed is subjected to Fourier transform to obtain time-frequency audio, wherein the audio signal to be processed is a one-dimensional signal, and the time-frequency audio is a two-dimensional matrix of time-frequency analysis; the time-frequency audio is processed by a similarity method to obtain a second background sound segment, wherein the similarity method is to calculate the similarity between an audio segment of a preset length in the time-frequency audio and an audio segment of equal length in the remaining segments by using the Pearson coefficient. It should be noted that, in this embodiment, the amplitude value of the background sound in the audio to be processed is calculated by Fourier transform because the amplitude value represents the energy information of the audio to be processed in the frequency domain. It can be understood that the total audio sampling points are the time length multiplied by the sampling rate, and the sampling rate represents how many sampling points there are in one second of audio, and the sampling points contain the audio time domain information.

[0038] In some embodiments, such as the present embodiment, Figure 3 As shown, the step S110 may include steps S111-S114.

[0039] S111, starting from the starting position in the time-frequency audio, sequentially acquiring audio segments of a preset length as the first segment;

[0040] S112: removing the audio segments other than the first segment from the time-frequency audio as remaining segments, and sequentially acquiring audio segments of the same length as the first segment from the remaining segments as second segments;

[0041] S113, calculating the similarity between the first segment and the second segment by using the Pearson coefficient to construct a self-similarity matrix;

[0042] S114, performing line detection on the self-similar matrix by using image processing to obtain a second background sound segment.

[0043] In an embodiment of the present invention, starting from the starting position in the time-frequency audio, audio segments of a preset length are sequentially obtained as the first segment, wherein the preset length is 3-5s; the audio segments in the time-frequency audio except the first segment are taken as the remaining segments, and audio segments of the same length as the first segment are sequentially obtained from the remaining segments as the second segment; the similarity between the first segment and the second segment is calculated by the Pearson coefficient to construct a self-similarity matrix; and the convolution operation in image processing is used to perform line detection on the self-similarity matrix to obtain the second background sound segment. For ease of understanding, it is assumed that the time-frequency audio is an audio of 20s in length. When the first segment is obtained for the first time, it is obtained from the starting position of the time-frequency audio, that is, the first segment is an audio segment from 0-4s, that is, an audio segment of 4s in length. It can be understood that the audio segment from 4s to 20s is the remaining segment, and an audio segment of the same length as the first segment is obtained from the remaining segment as the second segment. For example, an audio segment of 4s-8s is obtained as the second segment. The similarity value between the first segment and the second segment is calculated by the Pearson coefficient as SIM11. After that, an audio segment of 8s-12s is obtained as the second segment, and the similarity value calculated by the Pearson coefficient is performed. The similarity between the first segment and the second segment is obtained by the step of similarity to obtain the similarity value SIM12, and so on, SIM13 and SIM14 can be obtained; when the first segment is obtained for the second time, it starts from the end position of the first acquisition of the first segment, that is, the second acquisition of the first segment is an audio segment of 4-8s, and the remaining segments are audio segments of 0-4s and 8-20s, and then the audio segments of 0-4s, 8-12s, 12-16s and 16-20s are used as the second segments in turn, and the similarity is calculated with the first segment in turn to obtain SIM21, SIM22, SIM23 and SIM24, and so on, and a self-similarity matrix can be constructed. It should be noted that in other embodiments, for the same first segment, the selection of the second segment is logically overlapped. For example, when the second segment corresponding to SIM11 is an audio segment of 4-8s, the second segment corresponding to SIM12 can be an audio segment of 7s-11s, that is, an audio segment overlapped by 1s. It should also be noted that, in this embodiment, the closer the SIM value is to 1, the higher the similarity is, indicating that the spectra of the two audio segments have the same meaning and are considered to belong to the same part in the background sound, such as other song components such as the chorus, prelude or ending.

[0044] S120, taking the intersection and expanding the first background sound segment and the second background sound segment to obtain a chorus time segment.

[0045] In an embodiment of the present invention, the first background sound segment and the second background sound segment are merged and the intersection is taken to obtain an initial chorus segment; the initial chorus segment is expanded by a long rise method and a long fall method to obtain a chorus time segment. It should be noted that in this embodiment, the reason why the long rise method and the long fall method are used to expand the initial chorus segment is that the beginning of a conventional audio chorus segment is accompanied by a loudness increase process, and this part is often also considered to be the content of the chorus. A smooth curve is used to filter the short loudness amplitude to find the first loudness point of the audio chorus segment. In a period of time thereafter, the loudness value continues to rise with the sampling point. Similarly, the logic of the long fall is the same. The lowest loudness point at the end of the chorus is found to obtain the chorus part of the audio to be processed.

[0046] S130, scanning and monitoring the human voice frequency and the background sound frequency in the audio to be processed to obtain the frequency width and the center frequency.

[0047] In an embodiment of the present invention, the human voice frequency and the background sound frequency in the audio to be processed are obtained, and the difference between the human voice frequency and the background sound frequency is calculated to obtain a frequency difference; it is determined whether the frequency difference is less than a preset frequency difference. If the frequency difference is less than the preset frequency difference, it indicates that the human voice frequency is close to the background sound frequency, and the sampling frequency and sampling time point corresponding to the frequency difference are saved, and the center frequency and frequency width are determined according to the sampling frequency and the sampling time point. It can be understood that the frequency width is the frequency width between the last saved sampling time point and the first saved sampling point, and the center frequency is the frequency corresponding to the midpoint of the frequency width. It should be noted that in this embodiment, the reason for scanning and monitoring the human voice frequency and the background sound frequency is to find out whether there is masking between the background sound and the human voice. When there is masking, it will cause the user to hear the sound lag, reducing the user's experience.

[0048] S140, performing equalization processing on the audio to be processed by a parameter equalizer according to the frequency width, the center frequency and the chorus time segment.

[0049] In an embodiment of the present invention, the background sound loudness gain in the audio to be processed is adjusted according to the chorus time segment to obtain the target loudness gain, and then the audio to be processed is equalized by a parametric equalizer according to the frequency width, the center frequency and the target loudness gain. It should be noted that the difference between the parametric equalizer and the graphic equalizer is that the audio and band that can be adjusted by the graphic equalizer are fixed, while the parametric equalizer can arbitrarily determine the audio to be adjusted (i.e., the central frequency point) in the full range, and can also determine the bandwidth of the adjustment. The core of the parametric equalizer is a second-order filter group, which is mainly composed of the center frequency f0, the frequency width Q and the loudness factor dbgain, etc., wherein Q is the frequency band width that needs to be gained or attenuated, that is, the influence range of the gain at this frequency point. The larger the set Q value, the narrower the frequency band; conversely, the smaller the Q value, the wider the frequency band.

[0050] In some embodiments, such as the present embodiment, Figure 4 As shown, the step S140 may include steps S141-S144.

[0051] S141, judging whether the background sound in the to-be-processed audio is a chorus segment according to the chorus start time corresponding to the chorus time segment, if the background sound is the chorus segment, executing step S142, otherwise executing step S143;

[0052] S142, lowering the background sound loudness gain in the audio to be processed;

[0053] S143, increasing the background sound loudness gain;

[0054] S144: Obtain a background sound target frequency response value according to the frequency width, the center frequency, and the target loudness gain through a frequency response value calculation formula corresponding to a parameter equalizer, and perform equalization processing on the audio to be processed according to the background sound target frequency response value.

[0055] In an embodiment of the present invention, whether the background sound in the audio to be processed is a chorus segment is determined according to the chorus start time corresponding to the chorus time segment, wherein the chorus start time includes the chorus start time and the chorus end time; specifically, if the time corresponding to the background sound in the audio to be processed is between the chorus start time and the chorus end time, then the background sound is determined to be the chorus segment; conversely, if the time corresponding to the background sound in the audio to be processed is not between the chorus start time and the chorus end time, then the background sound is determined not to be the chorus segment; if the background sound is the chorus segment, the background sound loudness gain in the audio to be processed is lowered to highlight the human voice; if the background sound is not the chorus segment, for example, it is a prelude or At the end, the background sound loudness gain is increased to highlight the background sound. The target frequency response value of the background sound is obtained according to the frequency width, the center frequency and the target loudness gain through the frequency response value calculation formula corresponding to the parameter equalizer, and the audio to be processed is equalized according to the target frequency response value of the background sound. The frequency response value calculation formula is shown in formula (2). In formula (2), H(z) is the target frequency response value of the background sound, a0, a1, a2, b0, b1, and b2 are coefficients of the second-order filter, Q is the frequency width, dbgain is the loudness gain factor, f0 is the center frequency of the audio, Fs is the sampling frequency of the audio, A is the loudness gain, w0 is the rotation direction in the audio frequency domain, which is physically called angular velocity, and S is the shelf slope used to balance dBgain to change the frequency domain capacity distribution near the specified center frequency point, so as to achieve the purpose of not masking the human voice and the background sound.

[0056] in,

[0057] b0=sin(w0) / 2=Q*alpha

[0058] b1=0

[0059] b2=-sin(w0) / 2=-Q*alpha

[0060] a0=1+alpha

[0061] a1=-2*cos(w0)

[0062] a2=1-alpha

[0063] A=sqrt(10^(dBgain / 20))=10^(dBgain / 40)

[0064] (for peaking and shelving EQ filters only)

[0065] w0=2*pi*f0 / Fs

[0066] alpha=sin(w0) / 2*sqrt((A+1 / A)*(1 / S-1)+2)

[0067] Figure 5 is a schematic block diagram of an audio processing device 200 based on a parameter equalizer provided by an embodiment of the present invention. Figure 5 As shown, corresponding to the above audio processing method based on parameter equalizer, the present invention also provides an audio processing device 200 based on parameter equalizer. The audio processing device 200 based on parameter equalizer includes a unit for executing the above audio processing method based on parameter equalizer. Figure 5 The audio processing device 200 based on parameter equalizer includes a search unit 201, a processing unit 202, an expansion unit 203, a monitoring unit 204 and an equalization unit 205.

[0068] Among them, the search unit 201 is used to obtain the audio to be processed, and smooth the output loudness of the audio to be processed to find out the segment row with higher than the average loudness as the first background sound segment; the processing unit 202 is used to perform Fourier transform on the audio to be processed to obtain time-frequency audio, and process the time-frequency audio through a similarity method to obtain a second background sound segment; the expansion unit 203 is used to take the intersection and expand the first background sound segment and the second background sound segment to obtain a chorus time segment; the monitoring unit 204 is used to scan and monitor the human voice frequency and the background sound frequency in the audio to be processed to obtain the frequency width and the center frequency; the equalization unit 205 is used to equalize the audio to be processed through a parameter equalizer according to the frequency width, the center frequency and the chorus time segment.

[0069] In some embodiments, such as this embodiment, the search unit 201 includes a first calculation unit, a smoothing processing unit, and a second calculation unit.

[0070] The first calculation unit is used to calculate the output loudness of the audio to be processed by a loudness calculation formula; the smoothing unit is used to smooth the output loudness based on a moving median method to obtain a target output loudness; the second calculation unit is used to calculate an average loudness of the target output loudness, and use a segment of the target output loudness that is greater than the average loudness as a first background sound segment.

[0071] In some embodiments, such as this embodiment, the processing unit 202 includes a first acquisition unit, a second acquisition unit, a third calculation unit, and a detection unit.

[0072] Among them, the first acquisition unit is used to start from the starting position in the time-frequency audio and sequentially acquire audio segments of a preset length as the first segment; the second acquisition unit is used to remove the audio segments other than the first segment from the time-frequency audio as the remaining segments, and sequentially acquire audio segments of the same length as the first segment from the remaining segments as the second segment; the third calculation unit is used to calculate the similarity between the first segment and the second segment through the Pearson coefficient to construct a self-similarity matrix; the detection unit is used to perform line detection on the self-similarity matrix using image processing to obtain the second background sound segment.

[0073] In some embodiments, such as this embodiment, the expansion unit 203 includes a merging unit and an expansion sub-unit.

[0074] Among them, the merging unit is used to merge the first background sound segment and the second background sound segment to obtain the intersection to obtain an initial chorus segment; the expansion subunit is used to expand the initial chorus segment through a long rise method and a long fall method to obtain a chorus time segment.

[0075] In some embodiments, such as this embodiment, the monitoring unit 204 includes a fourth calculation unit and a storage determination unit.

[0076] Among them, the fourth calculation unit is used to obtain the human voice frequency and the background sound frequency in the audio to be processed, and calculate the difference between the human voice frequency and the background sound frequency to obtain the frequency difference; the saving and determination unit is used to save the sampling frequency and sampling time point corresponding to the frequency difference if the frequency difference is less than the preset frequency difference, and determine the center frequency and frequency width according to the sampling frequency and the sampling time point.

[0077] In some embodiments, such as this embodiment, the balancing unit 205 includes an adjustment unit and a balancing sub-unit.

[0078] The adjustment unit is used to adjust the background sound loudness gain in the audio to be processed according to the chorus time segment to obtain a target loudness gain; the equalization subunit is used to obtain a background sound target frequency response value according to the frequency width, the center frequency and the target loudness gain through a frequency response value calculation formula corresponding to a parametric equalizer, and perform equalization processing on the audio to be processed according to the background sound target frequency response value.

[0079] In some embodiments, such as this embodiment, the adjustment unit includes a determination unit, a first adjustment subunit, and a second adjustment subunit.

[0080] Among them, the judgment unit is used to judge whether the background sound in the audio to be processed is a chorus segment according to the chorus start time corresponding to the chorus time segment; the first adjustment subunit is used to lower the background sound loudness gain in the audio to be processed if the background sound is the chorus segment; the second adjustment subunit is used to increase the background sound loudness gain if the background sound is not the chorus segment.

[0081] The specific implementation of the audio processing device 200 based on the parameter equalizer in the embodiment of the present invention corresponds to the above-mentioned audio processing method based on the parameter equalizer, which will not be described in detail here.

[0082] The above-mentioned audio processing device based on parameter equalizer can be implemented in the form of a computer program. The computer program can be used in Figure 6 Runs on the computer device shown.

[0083] See also Figure 6 , Figure 6 300 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 300 is a terminal, which can be an electronic device with communication function such as a smart phone, a desktop computer, a laptop, a tablet computer, etc.

[0084] See also Figure 6 The computer device 300 includes a processor 302 , a memory and a network interface 305 connected via a system bus 301 , wherein the memory may include a storage medium 303 and an internal memory 304 .

[0085] The storage medium 303 may store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, the processor 302 may execute an audio processing method based on a parametric equalizer.

[0086] The processor 302 is used to provide computing and control capabilities to support the operation of the entire computer device 300 .

[0087] The internal memory 304 provides an environment for the operation of the computer program 3032 in the storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute an audio processing method based on a parameter equalizer.

[0088] The network interface 305 is used to communicate with other devices over the network. Figure 6The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 300 to which the solution of the present application is applied. The specific computer device 300 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0089] The processor 302 is used to run a computer program 3032 stored in a memory to implement the following steps: obtaining an audio to be processed, and smoothing the output loudness of the audio to be processed to find a segment row with a higher loudness than the average loudness as a first background sound segment; performing Fourier transform on the audio to be processed to obtain a time-frequency audio, and processing the time-frequency audio by a similarity method to obtain a second background sound segment; taking the intersection and expansion of the first background sound segment and the second background sound segment to obtain a chorus time segment; scanning and monitoring the human voice frequency and the background sound frequency in the audio to be processed to obtain a frequency width and a center frequency; and performing equalization processing on the audio to be processed by a parameter equalizer according to the frequency width, the center frequency and the chorus time segment.

[0090] In some embodiments, such as the present embodiment, when the processor 302 implements the step of smoothing the output loudness of the audio to be processed to find out a segment row with a higher loudness than the average loudness as the first background sound segment, the processor 302 specifically implements the following steps: calculating the output loudness of the audio to be processed by a loudness calculation formula; smoothing the output loudness based on a moving median method to obtain a target output loudness; calculating the average loudness of the target output loudness, and taking the segment of the target output loudness greater than the average loudness as the first background sound segment.

[0091] In certain embodiments, such as the present embodiment, when the processor 302 implements the step of processing the time-frequency audio by a similarity method to obtain a second background sound segment, the processor 302 specifically implements the following steps: starting from the starting position in the time-frequency audio, sequentially obtaining audio segments of a preset length as the first segment; removing the audio segments other than the first segment from the time-frequency audio as the remaining segments, and sequentially obtaining audio segments of the same length as the first segment from the remaining segments as the second segment; calculating the similarity between the first segment and the second segment by the Pearson coefficient to construct a self-similarity matrix; and performing line detection on the self-similarity matrix by image processing to obtain the second background sound segment.

[0092] In certain embodiments, such as the present embodiment, when the processor 302 implements the step of intersecting and expanding the first background sound segment and the second background sound segment to obtain a chorus time segment, the processor 302 specifically implements the following steps: merging the first background sound segment and the second background sound segment to obtain an initial chorus segment; and expanding the initial chorus segment by a long rise method and a long fall method to obtain a chorus time segment.

[0093] In certain embodiments, such as the present embodiment, when the processor 302 implements the step of scanning and monitoring the human voice frequency and the background sound frequency in the audio to be processed to obtain the frequency width and the center frequency, it specifically implements the following steps: obtaining the human voice frequency and the background sound frequency in the audio to be processed, and calculating the difference between the human voice frequency and the background sound frequency to obtain a frequency difference; if the frequency difference is less than a preset frequency difference, saving the sampling frequency and the sampling time point corresponding to the frequency difference, and determining the center frequency and the frequency width according to the sampling frequency and the sampling time point.

[0094] In some embodiments, such as the present embodiment, when the processor 302 implements the step of performing equalization processing on the audio to be processed by a parametric equalizer according to the frequency width, the center frequency and the chorus time segment, the processor 302 specifically implements the following steps: judging whether the background sound in the audio to be processed is a chorus segment according to the chorus start time corresponding to the chorus time segment; if the background sound is the chorus segment, lowering the background sound loudness gain in the audio to be processed; if the background sound is not the chorus segment, raising the background sound loudness gain; obtaining a target frequency response value of the background sound according to the frequency width, the center frequency and the target loudness gain through a frequency response value calculation formula corresponding to the parametric equalizer, and performing equalization processing on the audio to be processed according to the target frequency response value of the background sound.

[0095] It should be understood that in the embodiment of the present application, the processor 302 may be a central processing unit (CPU), and the processor 302 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0096] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0097] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above-mentioned audio processing method based on the parameter equalizer.

[0098] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0099] Those of ordinary skill 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, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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.

[0100] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0101] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0103] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0104] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0105] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An audio processing method based on a parametric equalizer, characterized in that: include: Acquire the audio to be processed, and perform smoothing processing on the output loudness of the audio to be processed to find out a segment row with a loudness higher than the average loudness as the first background sound segment; Performing Fourier transform on the audio to be processed to obtain time-frequency audio, and processing the time-frequency audio by a similarity method to obtain a second background sound segment; Intersecting and expanding the first background sound segment and the second background sound segment to obtain a chorus time segment; Scanning and monitoring the human voice frequency and background sound frequency in the audio to be processed to obtain the frequency width and center frequency; The audio to be processed is equalized by a parameter equalizer according to the frequency width, the center frequency and the chorus time segment.

2. The audio processing method based on parameter equalizer according to claim 1, characterized in that: The step of smoothing the output loudness of the audio to be processed to find out a segment row with a loudness higher than the average loudness as the first background sound segment comprises: Calculating the audio to be processed using a loudness calculation formula to obtain an output loudness; Smoothing the output loudness based on a moving median method to obtain a target output loudness; An average loudness of the target output loudness is calculated, and a segment of the target output loudness that is greater than the average loudness is used as a first background sound segment.

3. The audio processing method based on parameter equalizer according to claim 1, characterized in that: The step of processing the time-frequency audio by a similarity method to obtain a second background sound segment includes: Starting from the starting position in the time-frequency audio, sequentially obtaining audio segments of a preset length as the first segment; The audio segments except the first segment in the time-frequency audio are removed as remaining segments, and audio segments having the same length as the first segment are sequentially acquired from the remaining segments as second segments; Calculate the similarity between the first segment and the second segment by using the Pearson coefficient to construct a self-similarity matrix; The second background sound segment is obtained by performing line detection on the self-similar matrix using image processing.

4. The audio processing method based on parameter equalizer according to claim 1, characterized in that: The step of taking the intersection and expanding the first background sound segment and the second background sound segment to obtain the chorus time segment includes: Merge the first background sound segment and the second background sound segment and obtain the intersection thereof to obtain an initial chorus segment; The initial chorus segment is expanded by a long rise method and a long fall method to obtain a chorus time segment.

5. The audio processing method based on parameter equalizer according to claim 1, characterized in that: The step of scanning and monitoring the human voice frequency and the background sound frequency in the audio to be processed to obtain the frequency width and the center frequency comprises: Acquire the human voice frequency and the background sound frequency in the audio to be processed, and calculate the difference between the human voice frequency and the background sound frequency to obtain a frequency difference value; If the frequency difference is less than the preset frequency difference, the sampling frequency and the sampling time point corresponding to the frequency difference are saved, and the center frequency and the frequency width are determined according to the sampling frequency and the sampling time point.

6. The audio processing method based on parameter equalizer according to claim 1, characterized in that: The step of performing equalization processing on the audio to be processed by a parameter equalizer according to the frequency width, the center frequency and the chorus time segment comprises: Adjusting the background sound loudness gain in the audio to be processed according to the chorus time segment to obtain a target loudness gain; A background sound target frequency response value is obtained according to the frequency width, the center frequency and the target loudness gain through a frequency response value calculation formula corresponding to a parameter equalizer, and the audio to be processed is equalized according to the background sound target frequency response value.

7. The audio processing method based on parameter equalizer according to claim 6, characterized in that: The step of adjusting the background sound loudness gain in the audio to be processed according to the chorus time segment to obtain a target loudness gain includes: Determining whether the background sound in the audio to be processed is a chorus segment according to the chorus start time corresponding to the chorus time segment; If the background sound is the chorus segment, lowering the background sound loudness gain in the audio to be processed; If the background sound is not the chorus segment, the background sound loudness gain is increased.

8. An audio processing device based on a parametric equalizer, characterized in that: include: A search unit, configured to obtain the audio to be processed, and perform smoothing processing on the output loudness of the audio to be processed to search for a segment row with a loudness higher than an average loudness as a first background sound segment; A processing unit, configured to perform Fourier transform on the audio to be processed to obtain a time-frequency audio, and process the time-frequency audio by a similarity method to obtain a second background sound segment; An expansion unit, configured to obtain a chorus time segment by taking an intersection and expanding the first background sound segment and the second background sound segment; A monitoring unit, used for scanning and monitoring the human voice frequency and the background sound frequency in the audio to be processed to obtain the frequency width and the center frequency; An equalizing unit is used to perform equalization processing on the audio to be processed through a parameter equalizer according to the frequency width, the center frequency and the chorus time segment.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the audio processing method based on a parametric equalizer as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the audio processing method based on a parametric equalizer as described in any one of claims 1 to 7 can be implemented.

Images