Media data playing loudness processing method and device, equipment and storage medium

Abstract

The invention relates to the technical field of computer processing, and discloses a media data playing loudness processing method and device, equipment and a storage medium, and the method comprises the steps: obtaining to-be-played media data and audio features of the to-be-played media data; obtaining loudness demand information, wherein the loudness demand information comprises attributes of a current playing environment and / or playing equipment; determining loudness processing information of the to-be-played media data based on the audio features and the loudness demand information; and processing the to-be-played media data based on the loudness processing information to obtain target media data for playing.

Description

Technical Field

[0001] The present disclosure relates to the field of computer processing technology, and in particular to a method, device, equipment and storage medium for processing playback loudness of media data. Background Art

[0002] When media data is played on the terminal, different media data is created with different published loudness. In order to ensure balanced playback loudness when playing on the terminal side, that is, the loudness of all media data is unified, usually the volume gain and forced limiter are used to pull the media data with different loudness to the same playback loudness. Summary of the invention

[0003] In view of this, the present disclosure provides a method, apparatus, device and storage medium for processing playback loudness of media data to solve the problem of playback loudness balance.

[0004] In a first aspect, the present disclosure provides a method for processing playback loudness of media data, the method comprising:

[0005] Acquire the media data to be played and the audio features of the media data to be played;

[0006] Acquiring loudness requirement information, where the loudness requirement information includes properties of a current playback environment and / or a playback device;

[0007] Determining loudness processing information of the to-be-played media data based on the audio feature and the loudness requirement information;

[0008] The to-be-played media data is processed based on the loudness processing information to obtain target media data for playing.

[0009] In a second aspect, the present disclosure provides a device for processing playback loudness of media data, the device comprising:

[0010] A data acquisition module, used to acquire the media data to be played and the audio features of the media data to be played;

[0011] A demand information acquisition module, used to acquire loudness demand information, wherein the loudness demand information includes properties of a current playback environment and / or a playback device;

[0012] A processing information determination module, configured to determine loudness processing information of the to-be-played media data based on the audio feature and the loudness requirement information;

[0013] The audio processing module is used to process the to-be-played media data based on the loudness processing information to obtain target media data for playing.

[0014] In a third aspect, the present disclosure provides a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for processing playback loudness of media data of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0015] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for processing playback loudness of media data of the first aspect or any corresponding embodiment thereof.

[0016] The method for processing the playback loudness of media data provided by the embodiments of the present disclosure performs loudness processing on the playback side for the media data to be played. Since the properties of the current playback environment or the playback device will affect the playback of the media data, even if the same media data is played in different environments or on different playback devices, there may be differences in the listening experience. Based on this, when the playback side processes the media data, based on the audio features, combined with the loudness requirement information such as the properties of the current playback environment and / or the playback device, the obtained loudness processing information can not only meet the requirements of the audio itself, but also meet the requirements of the environment or the hardware device, thereby realizing adaptive adjustment of the playback loudness of the media data to be played, and improving the playback effect of the media data to be played. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a flow chart of a method for processing playback loudness of media data according to an embodiment of the present disclosure;

[0019] Figure 2 is a flow chart of another method for processing playback loudness of media data according to an embodiment of the present disclosure;

[0020] Figure 3 is a flowchart of a method for calculating loudness gain according to an embodiment of the present disclosure;

[0021] Figure 4 is a flow chart of a method for calculating a dynamic range control parameter according to an embodiment of the present disclosure;

[0022] Figure 5is a flowchart of a method for calculating a loudness compensation gain according to an embodiment of the present disclosure;

[0023] Figure 6 is a flowchart of a method for processing media data to be played according to an embodiment of the present disclosure;

[0024] Figure 7 is a structural block diagram of a device for playing loudness of media data according to an embodiment of the present disclosure;

[0025] Figure 8 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0027] In the related art, the loudness processing of the playback end is done in a one-size-fits-all manner, for example, by multiplying the volume gain, etc., to pull most of the audio with inconsistent loudness to the same loudness. However, this processing does not take into account the impact of different phonemes on the audio loudness experience when different users play videos. For example, the maximum sound pressure that the playback device can reach, the ambient sound, the user's preferences, and the audio content, etc. Specifically, the device used by the user when playing, whether it is a mobile phone speaker or headphones, the playback device can reach the maximum sound pressure without distortion; what environment the user is in when playing, whether it is a noisy environment or a quiet environment; when the user plays, is it more preferred to hear audio with a larger dynamic range, even if some loudness regularity is lost, or is it more preferred to unify the loudness, so that a greater degree of dynamic range compression can be applied; whether the current audio is pure voice or pure music or a mixture of the two, or other content such as news, movies, etc., for different content, such as content with different voice proportions, the target loudness should be fine-tuned from the listening sense to ensure that the loudness heard by the user is consistent.

[0028] In some application scenarios, due to the different published loudness of different media data to be played, or the different capabilities of the device on the playback end, etc., the loudness of different short videos played on the same playback end may vary significantly, that is, some short videos have a louder volume, while some short videos have a smaller volume, requiring users to manually adjust the volume to adapt to different short videos.

[0029] Based on this, the present disclosure proposes a method for processing the playback loudness of media data to solve the problem that users have different audio loudness experiences when playing media data, so that users can get a loudness suitable for the current scene in any usage scenario, and avoid the following situations to the greatest extent, for example, the device volume is not enough when it is turned up to the maximum, the device volume is still too loud when it is turned up to one level, the user needs to adjust the volume in the same video, the user needs to adjust the volume between different videos, the audio with excessive loudness but insufficient dynamics is played at a low volume on a high-end speaker, and the weaker volume part of the video cannot be heard clearly at the normal volume on the low-end speaker.

[0030] At the playback end, the video cloud service provider sends the transcoded media data to be played and the audio features of the media data to be played to the playback end. After being processed by the playback limit processing method of the playback end, the target media data for playback is obtained for playback.

[0031] According to an embodiment of the present disclosure, an embodiment of a method for processing playback loudness of media data is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical sequence is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] In this embodiment, a method for processing the playback loudness of media data is provided, which can be used in the above-mentioned computer devices, such as computers, mobile phones, tablet computers, etc. Figure 1 is a flowchart of a method for processing playback loudness of media data according to an embodiment of the present disclosure. Figure 1 As shown, the process includes the following steps:

[0033] Step S101: Acquire the media data to be played and the audio features of the media data to be played.

[0034] The media data to be played is the media data to be played received by the playback end, including but not limited to video or audio. The form of the media data to be played is not limited here, and is set according to actual needs. For example, the playback end is installed with a short video playback application. When the user uses the short video playback application to play a short video, the corresponding video, i.e., the media data to be played, is pulled from the server of the short video playback application.

[0035] The audio features of the media data to be played can be obtained at the media data creation end and sent to the playback end together with the media data to be played; or the audio features of the media data to be played can be obtained by the playback end after performing feature analysis on the audio data of the media data to be played according to needs after obtaining the media data to be played; or part of the audio features can be obtained at the creation end, and the other part can be obtained after performing feature analysis on the playback end according to needs, etc. Of course, the method of obtaining audio features is not limited to the above, and can also be obtained by other methods, which are not limited here.

[0036] Audio features include, but are not limited to, source loudness, voice ratio, dynamic range, loudness peak, and audio content, etc. The specific features included are determined based on actual needs.

[0037] Step S102: obtaining loudness requirement information.

[0038] The loudness requirement information includes properties of the current playback environment and / or playback device.

[0039] The loudness requirement information is the requirement of the current playback scene of the playback end, such as the playback environment, the properties of the playback device or user preferences, etc. Among them, the current playback environment refers to the noise level and loudness requirement of the user's current environment, such as indoors, outdoors or on the road, etc., which can generally be obtained through variables such as location positioning, noise collection microphones and timestamps, combined with user usage habits analysis. The properties of the playback device include the playback capability of the playback device, the sensitivity of the playback device, the maximum sound pressure level, etc. Generally, the higher the power of the playback device, the lower the required loudness. User preference refers to the current user's demand for loudness, which can be determined by interacting with the terminal using the interaction method provided by the terminal.

[0040] Step S103: determining loudness processing information of the to-be-played media data based on the audio features and the loudness requirement information.

[0041] The loudness processing information of the media data to be played is related to the way of processing the media data to be played. If the media data to be played is processed in a dynamic range control (DRC) manner, the loudness processing information includes the parameters of the DRC curve. DRC refers to mapping the dynamic range of the input audio signal to a specified dynamic range, which can make the sound sound softer or louder, that is, a signal amplitude adjustment method. Usually the dynamic range after mapping is smaller than the dynamic range before mapping, so it is called dynamic range compression. The audio signal can be subjected to overall dynamic range control, or it can be divided into several sub-bands for dynamic range control separately.

[0042] If loudness gain processing is performed on the media data to be played, the loudness processing information includes a specific size of the gain, which is obtained by the difference between the source loudness and the target loudness in the media data to be played. If the processing of the media data to be played also includes gain smoothing processing, it is also necessary to determine the attack time, release time, and hold time, so as to reduce the sharp change of the gain by using the gain smoothing processing, and avoid artifacts and less natural sound.

[0043] The loudness processing information is determined based on the audio features and the loudness requirement information. For example, a network model can be trained in advance, and the input of the network model is the audio features and the loudness requirement information, and the output is the corresponding loudness processing information. The network model is obtained after training with a large amount of sample data, and its specific network structure is set according to actual needs, and is not limited here.

[0044] The loudness processing information may also be obtained by performing digital signal processing based on the audio features and the loudness requirement information. For example, the parameters of the DRC curve include a slope, and the slope may be calculated based on the source loudness in the audio features and the properties of the playback device in the loudness requirement information.

[0045] Step S104: Process the media data to be played based on the loudness processing information to obtain target media data for playing.

[0046] As described above, the loudness processing information is related to the method of processing the media data to be played. Therefore, after obtaining the loudness processing information, the media data to be played is processed according to the corresponding processing method and using the loudness processing information, that is, the target media data is obtained. Among them, the target media data is the media data played on the playback end.

[0047] The playback loudness processing method for media data provided in this embodiment performs loudness processing on the playback side for the media data to be played. Since the properties of the current playback environment or the playback device will affect the playback of the media data, even if the same media data is played in different environments or on different playback devices, there may be differences in the listening experience. Based on this, when the playback side processes the media data, based on the audio features, combined with the loudness requirement information such as the properties of the current playback environment and / or the playback device, the obtained loudness processing information can not only meet the requirements of the audio itself, but also meet the requirements of the environment or the hardware device, thereby realizing adaptive adjustment of the playback loudness of the media data to be played, and improving the playback effect of the media data to be played.

[0048] In this embodiment, a method for processing the playback loudness of media data is provided, which can be used in the above-mentioned computer devices, such as computers, mobile phones, tablet computers, etc. Figure 2 is a flowchart of a method for processing playback loudness of media data according to an embodiment of the present disclosure. Figure 2 As shown, the process includes the following steps:

[0049] Step S201: Acquire the media data to be played and the audio features of the media data to be played. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0050] Step S202: obtaining loudness requirement information.

[0051] The loudness requirement information includes the properties of the current playback environment and / or playback device. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0052] Step S203: determining loudness processing information of the to-be-played media data based on the audio features and the loudness requirement information.

[0053] Specifically, the above step S203 includes:

[0054] Step S2031: Determine the target loudness of the media data to be played based on the loudness requirement information.

[0055] The loudness requirement information includes the current playback environment. The noisier the current playback environment is, the higher the target loudness will be. When determining the target loudness, the noise level of the current playback environment or the playback capability of the playback device may be considered.

[0056] In some optional implementations, the attributes of the playback device include playback capabilities. Based on this, the above step S2031 includes:

[0057] Step a1: determining an initial target loudness based on playback capabilities.

[0058] Step a2: adjusting the initial target loudness based on the audio features to obtain the target loudness.

[0059] The properties of the playback device can be obtained from the property interface of the playback device. After the playback capability is obtained, the playback capability can be mapped to the loudness according to a preset mapping relationship to obtain the initial target loudness. Alternatively, the playback capability can be graded, and different grades correspond to different initial loudnesses. After the playback capability of the playback device is obtained, the corresponding grade is determined to obtain the corresponding initial target loudness.

[0060] The initial target loudness is determined based on the playback capability of the playback device, and then fine-tuned based on the audio characteristics to improve the accuracy of the target loudness.

[0061] In some optional implementations, the above step a1 includes:

[0062] Step a11, obtaining a first correspondence between the playback capability of the playback device and the initial loudness.

[0063] Step a12: based on the playback capability of the playback device in the loudness requirement information, query the first corresponding relationship to obtain an initial target loudness.

[0064] The first correspondence relationship represents the correspondence between the playback capability of the playback device and the initial loudness. For example, if the playback capability level is small, the initial loudness is -16LU; if the playback capability level is medium, the initial loudness is -24LU; if the playback capability level is large, the initial loudness is -31LU. For the currently used playback device, after obtaining the playback capability of the playback device, the first correspondence relationship is queried to obtain the corresponding initial target loudness.

[0065] By maintaining the first correspondence between the playback capability of the playback device and the initial loudness, in actual processing, the initial target loudness can be determined directly by querying the first correspondence, thereby improving the efficiency of determining the initial target loudness.

[0066] In some optional implementations, the above step a2 includes:

[0067] Step a21, determining a target loudness increment based on audio features, where the audio features include the type of audio content or the proportion of speech.

[0068] Step a22: adjusting the initial target loudness based on the target loudness increment to obtain the target loudness.

[0069] Audio features include but are not limited to the type of audio content or the proportion of speech. Different audio features correspond to different target loudness increments. For example, if the audio feature includes the type of audio content, and the type is speech, the target loudness increment is -2LU; if the audio feature includes the speech proportion speech_ratio, the target loudness increment = -1*speech_ratio*2.

[0070] Of course, other methods may be used to determine the target loudness increment, which is not limited here. After the target loudness increment is determined, the initial target loudness is adjusted using the target loudness increment to obtain the target loudness. Further, the target loudness has a certain loudness range, such as (-50, -5). After adjusting the initial target loudness, if the target loudness obtained exceeds the range, it needs to be processed to ensure that the target loudness used subsequently is within the loudness range. It should be noted that the above loudness range (-50, -5) is only an example and does not limit the protection scope of the present disclosure.

[0071] Different audio features have different effects on hearing. Based on this, the corresponding target loudness increment is obtained based on the audio features, and the initial target loudness is fine-tuned, further improving the accuracy of the target loudness.

[0072] Step S2032: determine a loudness gain based on a difference between the source loudness and the target loudness in the audio feature.

[0073] The audio features include active loudness, and the loudness gain is obtained by calculating the difference between the target loudness and the source loudness, that is, loudness gain = target loudness - source loudness.

[0074] For example, Figure 3 The processing flow of loudness gain is shown. Specifically, the target feature of dynamic range adjustment is determined using the loudness requirement information. If the target feature is that compression is not required, the loudness gain gain = 0; otherwise, the initial target loudness is determined based on the playback capability of the playback device, and then the initial target loudness is fine-tuned based on the audio features to determine the target loudness. Due to the set target loudness range, it is determined whether the target loudness obtained above is within the target loudness range (-50, -5). If it is within the target loudness range, the loudness gain gain = target loudness - source loudness, and gain <= 24dB.

[0075] Step S2033: Determine the dynamic range control parameters of the media data to be played based on the audio features and the loudness requirement information.

[0076] The dynamic range control parameters include slope ratio, threshold value of static characteristics, and knee width kneeWidth. The dynamic range control parameters are the parameters of the DRC curve. In this embodiment, the DRC curve includes two sections. The first section corresponds to the static characteristics. The threshold value of the first section of the curve is the threshold value of the static characteristics, and there is a knee width setting at the knee point. The slope ratio refers to the slope of the second section.

[0077] In some optional implementations, the above step S2033 includes:

[0078] Step b1, obtaining a second corresponding relationship between loudness requirement and a characteristic of dynamic range control.

[0079] Step b2: querying the second corresponding relationship based on the loudness requirement information to determine the target characteristic of the dynamic range control.

[0080] Step b3: if the target characteristic is that compression is required, the slope of the dynamic range control curve is determined based on the audio characteristics and the target loudness, and the dynamic range control parameters include the slope.

[0081] The characteristics of dynamic range control include needing compression and not needing compression (off). The characteristics of needing compression can be further divided into light compression (light) and heavy compression (noisy) according to the degree of compression. The characteristics of dynamic range control are related to loudness requirements, and the loudness requirements here correspond to the loudness requirement information mentioned above. Among them, the loudness requirements include but are not limited to user preferences, the playback capabilities of the playback device, and the current playback environment, etc. In actual processing, the acquired loudness requirement information includes one or more of the above-mentioned loudness requirements. Due to the different contents included in the loudness requirement information, the second corresponding relationship to be queried is also different. For example, the second corresponding relationship includes the corresponding relationship between user preferences and the characteristics of dynamic range control, the corresponding relationship between the playback capabilities of the playback device and the characteristics of dynamic range control, the corresponding relationship between the playback environment and the characteristics of dynamic range control, the corresponding relationship between user preferences and the playback capabilities of the playback device and the characteristics of dynamic range control, and the corresponding relationship between the user preferences and the playback capabilities of the playback device and the characteristics of dynamic range control, etc. That is, the second corresponding relationship includes the corresponding relationship between the combination of one or more loudness requirements in the loudness requirement and the characteristics of dynamic range control.

[0082] For example, if the loudness requirement includes the playback environment and the playback capability of the playback device, the corresponding correspondence is shown in the following table:

[0083]

[0084] Among them, the playback environment includes an ideal environment (ideal), a noisy environment (noisy) and an empty playback environment (n / a); the playback capabilities include high (L), medium (M), low (S) and empty (n / a); the DRC characteristics that require compression include general compression (general), heavy compression (noisy) and extreme compression (limited).

[0085] If the loudness requirement includes user preference, playback capability of the playback device, and playback environment, the corresponding correspondence is shown in the following table:

[0086] Among them, user preferences include maximum DRC (Max DRC), smaller DRC (Light DRC) and turn off DRC (DRC off); playback capabilities include all (all), high (L), medium (M), low (S) and empty (n / a); playback environments include all (all), ideal (ideal) and empty (n / a); DRC characteristics include heavy compression (noisy), light compression (light) and off (off).

[0087] Of course, the correspondences represented by the above two tables are merely examples and do not limit the protection scope of the present disclosure. The specific content included in the second correspondence is set according to actual needs.

[0088] The content included in the loudness requirement information is determined based on the loudness requirement information, and then the second corresponding relationship is queried using the included content to determine the target characteristic of the dynamic range control. If it is determined that the target characteristic requires compression, the slope of the DRC curve is determined based on the audio characteristics and the target loudness.

[0089] By maintaining a second correspondence between loudness requirements and characteristics of dynamic range control, during actual loudness processing, the target characteristics of dynamic range control can be obtained by directly querying the second correspondence, thereby improving the efficiency of determining the target characteristics. Furthermore, when the target characteristic requires compression, the slope of the DRC curve is obtained by combining the audio characteristics and the target loudness. Since the slope is obtained based on the audio characteristics, it can be better applied to the media data to be played.

[0090] In some optional implementations, the audio feature includes a loudness peak, and step b3 includes:

[0091] Step b31, performing peak normalization processing on the source loudness based on the loudness peak value and the preset loudness peak value to obtain processed loudness.

[0092] Step b32: determining an initial slope of a curve for dynamic range control based on a ratio of the processed loudness to the target loudness.

[0093] Step b33: if the loudness requirement information includes the current playback environment or user preference, obtain a preset slope corresponding to the target characteristic.

[0094] Step b34, determining the slope of the dynamic range control curve based on the preset slope and the maximum value of the initial slope.

[0095] The preset loudness peak is set according to actual needs, for example, 0dB. Compare the loudness peak in the audio feature with the preset loudness peak. If the loudness peak exceeds the preset loudness peak, the source loudness needs to be peak normalized to obtain the processed loudness. For example, if the loudness peak is 4dB, which exceeds the preset loudness peak by 4dB, the source loudness needs to be adjusted down by 4dB to obtain the processed loudness.

[0096] The ratio of the processed loudness to the target loudness is calculated and used as the initial slope of the DRC curve. Furthermore, if the loudness requirement information includes the current playback environment or user preference, it can be seen from the above correspondence that the loudness requirement information will affect the characteristics of the DRC, that is, if compression is required, it affects the degree of compression. Among them, there is also a corresponding relationship between the characteristics of the DRC and the slope, so the preset slope corresponding to the target characteristics can be determined using this corresponding relationship.

[0097] For example, when the DRC characteristic is off, the preset slope is 1; when the DRC characteristic is general compression, the preset slope is 1.25; when the DRC characteristic is heavy compression or extreme compression, the preset slope is 2.5. Based on this, the preset slope corresponding to the target characteristic is obtained.

[0098] After the processing of step b32, the initial slope is obtained, and the processing of step b33, the preset slope is obtained. It is necessary to select one of the two slopes as the slope of the DRC curve. Specifically, the two slopes are compared and the maximum slope is used as the slope of the DRC curve.

[0099] An initial slope is obtained using source loudness and target loudness. When the loudness requirement information includes the current playback environment or user preference, there is also a preset slope corresponding to the target characteristic. The slope is re-determined in combination with the initial slope and the preset slope, which further improves the accuracy of the obtained slope.

[0100] In some optional implementations, if the target characteristic requires compression, step S2033 further includes:

[0101] Step b4, determining a starting point of the dynamic range based on the dynamic range in the audio feature.

[0102] Step b5, determining the starting point of the dynamic range as the threshold of the static characteristic in the curve of the dynamic range control, and determining the inflection point width of the curve as a preset value greater than zero.

[0103] For the DRC curve, when the target characteristic is to be compressed, the parameters of the DRC curve also include the threshold of the static characteristic and the knee width. Among them, the audio feature includes a dynamic range, and the starting point of the dynamic range is determined as the threshold of the static characteristic, that is, the knee, and the knee width is set to a preset value greater than zero. For example, the threshold of the static characteristic is threshold = the starting value of the loudness range, and the knee width is 4.

[0104] The specific value of the preset value greater than zero is set according to actual needs, and no limitation is made to its specific value here.

[0105] The DRC curve includes two parts, one part corresponding to the static characteristic and the other part corresponding to the slope. By setting the starting point of the dynamic range as the threshold of the static characteristic, the obtained DRC curve can better process the media data to be played.

[0106] In some optional implementations, step S2033 further includes:

[0107] Step b6, determine whether the length of the media data to be played is greater than a preset length, if so, execute step b1, if less than the preset length, execute step b7.

[0108] Step b7, obtaining the maximum short-term loudness in the audio feature, and determining the loudness difference between the maximum short-term loudness and the target loudness.

[0109] Step b8: If the loudness difference is greater than the preset loudness difference, the slope of the dynamic range control curve is determined based on the loudness difference and the preset loudness difference.

[0110] Step b9: If the loudness difference is less than the preset loudness difference, determine that the target characteristic of the dynamic range control is that compression is not required.

[0111] The determination of the parameters of the DRC curve is also related to the length of the media data to be played. For the media data to be played with a shorter length, the slope of the corresponding DRC curve is determined by the maximum short-time loudness and the target loudness, so as to simplify the processing process and improve the processing efficiency. Specifically, the length of the media data to be played is compared with the preset length. If it is greater than the preset length, the above step b1 is executed, that is, the parameters of the DRC curve are determined in the manner described above; if it is less than the preset length, the maximum short-time loudness in the audio feature is obtained, and the loudness difference between the maximum short-time loudness and the target loudness is calculated. If the loudness difference is greater than the preset loudness difference, the slope of the DRC curve is determined based on the loudness difference and the preset loudness difference. Among them, the preset loudness difference can be 5LU or other values, which are set according to actual needs.

[0112] When the loudness difference is greater than the preset loudness difference, it indicates that compression is required, and the slope of the DRC curve is determined by using the loudness difference and the preset length difference; when the loudness difference is less than the preset loudness difference, it indicates that the target characteristic of the dynamic range control is that compression is not required.

[0113] In some optional implementations, the step b8 includes: determining the slope of the dynamic range control curve based on the ratio of the loudness difference to the preset loudness difference. Specifically, the slope of the DRC curve ratio = (maximum short-term loudness - target loudness) / preset loudness difference.

[0114] When the loudness difference is greater than the preset loudness difference, the slope is determined using the ratio of the two, which simplifies the slope determination method and improves processing efficiency.

[0115] When determining the dynamic range control parameters, the length of the media data to be played is combined. When the length is less than the preset length, the slope is determined by the difference between the maximum short-time loudness and the target loudness, so as to compress the dynamic range within the preset loudness difference, so as to balance the complexity of the algorithm and the effect of loudness equalization. When the loudness difference is less than the preset loudness difference, there is no need to perform dynamic range processing, which simplifies the dynamic range processing process and improves efficiency.

[0116] For example, Figure 4 The process of determining the parameters of the DRC curve is shown. Specifically, first determine whether it is necessary to skip the DRC. If it is necessary to skip the DRC, it means that no compression is required. At this time, the slope ratio of the DRC curve is 1, the threshold threshold of the static curve is the target loudness, and the knee width is kneeWidth=0. If it is not necessary to skip the DRC, continue to determine whether the length duration of the media data to be played is less than the length threshold (i.e., 30s). If it is less than, the parameters of the DRC curve are determined based on the maximum short-term loudness and the target loudness. For specific processing methods, please refer to the relevant descriptions of steps b7 to b9 above. Otherwise, by querying the corresponding corresponding relationship, the target characteristics of the dynamic range control are determined. If the target characteristic is that no compression is required, the slope ratio of the DRC curve is 1, the threshold threshold of the static curve is the target loudness, and the knee width is kneeWidth=0. If the target characteristic is that compression is required, the parameters of the DRC curve are determined based on the description of step b3 above.

[0117] Step S2034: obtaining loudness compensation gain.

[0118] The loudness compensation gain is obtained based on the loudness offset, and the loudness processing information includes the loudness gain, the dynamic range control parameter and the loudness compensation gain.

[0119] The loudness compensation gain may be determined by scanning the loudness of the media data to be played twice to obtain the loudness offset, or by determining the loudness offset through a large amount of data analysis, etc. For example, if a large amount of data analysis is performed, the loudness offset at the start and end points of a specific dynamic range is obtained by pulling the data and combining the linear regression method to obtain the loudness offset, and the loudness offset is determined as the loudness compensation gain.

[0120] In some optional implementations, if the loudness is determined by scanning twice, step S2034 includes:

[0121] Step c1: determining a loudness offset based on audio features and target loudness.

[0122] Step c2: determining a loudness compensation gain based on the loudness offset.

[0123] The audio features include the starting point of the dynamic range or the maximum short-term loudness, on which the loudness offset is obtained in combination with the target loudness. After the loudness offset is obtained, the loudness offset can be determined as the loudness compensation gain, or the loudness compensation gain can be obtained based on the loudness offset in combination with a preset value.

[0124] The loudness offset is calculated using the audio features and the target loudness, and the loudness compensation gain is determined on this basis. Since the audio features represent the situation of the audio itself, the loudness offset is determined in combination with the target loudness, which improves the accuracy of the loudness offset and thus improves the accuracy of the determined loudness compensation gain.

[0125] When determining the loudness compensation gain, different methods are used according to the length of the media data to be played. If the length is greater than the preset length, loudness estimation is required first, and then the loudness offset is determined on this basis; if the length is less than the preset length, the loudness offset is determined using the maximum short-term loudness.

[0126] In some optional implementations, if the length of the media data to be played is greater than a preset length, the step c1 includes:

[0127] Step c11, obtaining the slope in the dynamic range control parameter and the starting point of the dynamic range in the audio feature.

[0128] Step c12: performing loudness estimation based on the target loudness, the slope and the starting point to determine the estimated loudness.

[0129] Step c13: determining a loudness offset based on a difference between the target loudness and the estimated loudness.

[0130] When the length of the media data to be played is greater than the preset length, the slope of the DRC curve obtained through the above steps is obtained, and the starting point of the dynamic range is obtained from the audio features. Loudness estimation is performed based on the target loudness, the slope, and the starting point, that is, estimated loudness = (target loudness - starting point of dynamic range) / slope + starting point of dynamic range.

[0131] After the estimated loudness is obtained, the difference between the target loudness and the estimated loudness is calculated to determine the loudness offset.

[0132] When the length of the media data to be played is greater than the preset length, since the loudness gain and dynamic range are processed before loudness compensation, the loudness estimation is performed here in combination with the starting point and slope of the dynamic range, which can ensure the accuracy of the obtained loudness estimation.

[0133] Accordingly, if the length of the to-be-played media data is greater than the preset length, the above step c2 includes: obtaining a loudness compensation gain based on the sum of the loudness offset and the first compensation value. The first compensation value may be set based on an empirical value, or may be obtained by analyzing a large amount of data. For example, the first compensation value is 1, and accordingly, the loudness compensation gain = target loudness - estimated loudness + 1.

[0134] The loudness compensation gain is obtained based on the loudness offset and combined with the first compensation value, thereby further improving the accuracy of the loudness compensation gain.

[0135] In some optional implementations, if the length of the to-be-played media data is less than a preset length, the above step c1 includes:

[0136] Step c14, obtaining the maximum short-term loudness in the audio features.

[0137] Step c15: determining a loudness offset based on a difference between the maximum short-term loudness and the target loudness.

[0138] When the length of the media data to be played is less than the preset length, the difference between the maximum short-term loudness and the target loudness is calculated, and the difference can be directly determined as the loudness offset. The loudness offset can be determined by combining the size of the difference with other parameters.

[0139] When the length of the media data to be played is less than the preset length, the processing of the loudness offset is simplified, and the loudness offset is directly determined by using the difference between the maximum short-time limit and the target loudness, thereby improving the processing efficiency.

[0140] Correspondingly, if the length of the media data to be played is less than the preset length, the above step c2 includes:

[0141] Step c21: if the loudness offset is greater than the preset loudness difference value, a loudness compensation gain is obtained based on the difference between the loudness offset and the second compensation value.

[0142] Step c22: if the loudness offset is less than the preset loudness difference, determine that the loudness compensation gain is zero.

[0143] If the loudness offset is greater than the preset loudness difference, the loudness compensation gain = maximum short-term loudness - target loudness - second compensation value; if the loudness offset is less than the preset loudness difference, the loudness compensation gain = 0. The specific value of the second compensation value is set according to actual needs, for example, the second compensation value = 5, and its specific value is not limited to it here.

[0144] According to the magnitude relationship between the loudness offset and the preset loudness difference, different methods are used to determine the loudness compensation gain, thereby further improving the accuracy of the loudness compensation gain.

[0145] For example, Figure 5The method for determining the loudness compensation gain is shown. Specifically, if the target characteristic is that compression is not required, the loudness compensation gain make_up_gain=0. If the target characteristic is that compression is required, it is necessary to determine again whether the length of the to-be-played media data is greater than the preset length. If it is greater than the preset length, the loudness compensation gain is determined according to the description of steps c11 to c13 above; if it is less than the preset length, the loudness compensation gain is determined according to the description of steps c14 to c15 above.

[0146] It should be noted that when performing size comparison, the processing of the equal situation can be the same as the processing of the greater than situation, or the same as the processing of the less than situation. The specific setting is based on actual needs and is not limited here.

[0147] Step S204: Process the media data to be played based on the loudness processing information to obtain target media data for playing.

[0148] Specifically, the above step S204 includes:

[0149] Step S2041: loudness processing is performed on the media data to be played based on the loudness gain to obtain first media data.

[0150] Step S2042: Perform dynamic range processing on the first media data based on the dynamic range control parameter to obtain second media data.

[0151] Step S2043: loudness compensation is performed on the second media data based on the loudness compensation gain to obtain third media data.

[0152] Step S2044: perform peak value limitation on the third media data to obtain target media data.

[0153] The loudness processing information includes loudness gain, parameters of the DRC curve, and loudness compensation gain. Based on this, the media data to be played is processed based on the loudness gain to obtain first media data; the DRC curve is obtained based on the parameters of the DRC curve, and the dynamic range of the first media data is processed using the DRC curve to obtain second media data; the second media data is loudness compensated based on the loudness compensation gain to obtain third media data. Finally, the third media data is peak-limited in combination with a preset peak value to obtain target media data for playback.

[0154] For example, Figure 6The processing flow of the media data to be played is shown, and the whole process may include a parameter preparation stage and a streaming processing stage. The preparation stage includes determining a loudness gain, determining parameters of a DRC curve, and determining a loudness compensation gain. The streaming processing stage includes using the loudness gain to perform loudness gain processing on the media data to be played to obtain first media data; using the parameters of the DRC curve to obtain a DRC curve, and then using the DRC curve to perform dynamic range control processing on the first media data to obtain second media data; combining the loudness compensation gain to perform loudness compensation on the second media data to obtain third media data; finally, peak limiting the third media data to obtain target media data.

[0155] In the method for processing the playback loudness of media data provided in this embodiment, the target loudness is determined based on the loudness requirement information, that is, the loudness is set according to the requirement, which ensures the matching of the target loudness with the playback environment and the playback device; the dynamic range control parameter is obtained based on the audio features combined with the loudness requirement information, which is not only related to the audio features themselves, but also combined with the characteristics of the playback environment and the playback hardware, ensuring the adaptability of the dynamic range control parameter; the loudness processing information also includes the loudness compensation gain, which further ensures the accuracy of the loudness processing information. Loudness processing, dynamic range processing and loudness compensation are performed on the media data to be played in turn, and the loudness processing is performed on the media data to be played from the perspective of loudness and dynamic range. Since the loudness peak may be affected in this process, peak limitation is also performed to reduce the popping sound of the target media data obtained.

[0156] As a specific application embodiment of the disclosed embodiment, a short video playback application is installed on a mobile phone, and the user plays the short video by interacting with the short video playback application. Among them, an interactive interface is also provided in the short video playback application for the user to input corresponding preference data and obtain loudness requirement information. Specifically, the short video to be played is pulled from the server of the short video playback application. After the short video to be played is obtained, the loudness equalization processing is performed on each short video to be played through the above-mentioned media data playback loudness processing method, thereby ensuring adaptive adjustment of the loudness.

[0157] In this embodiment, a device for processing the playback loudness of media data is also provided. The device is used to implement the above embodiments and preferred implementations. The descriptions that have been made are not repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0158] This embodiment provides a device for processing the playback loudness of media data. Figure 7 As shown, including:

[0159] The data acquisition module 701 is used to acquire the media data to be played and the audio features of the media data to be played.

[0160] The demand information acquisition module 702 is used to acquire loudness demand information, where the loudness demand information includes properties of the current playback environment and / or playback device.

[0161] The processing information determining module 703 is configured to determine the loudness processing information of the to-be-played media data based on the audio feature and the loudness requirement information.

[0162] The audio processing module 704 is used to process the to-be-played media data based on the loudness processing information to obtain target media data for playing.

[0163] In some optional implementations, the processing information determination module 703 includes:

[0164] The target loudness determination unit is used to determine the target loudness of the to-be-played media data based on the loudness requirement information.

[0165] The loudness gain determination unit is used to determine the loudness gain based on the difference between the source loudness and the target loudness in the audio feature.

[0166] The parameter determination unit is used to determine the dynamic range control parameters of the media data to be played based on the audio characteristics and the loudness requirement information.

[0167] The compensation gain acquisition unit is used to acquire a loudness compensation gain, where the loudness compensation gain is obtained based on a loudness offset, and the loudness processing information includes the loudness gain, a dynamic range control parameter, and the loudness compensation gain.

[0168] In some optional implementations, the attribute of the playback device includes playback capability, and the target loudness determination unit includes:

[0169] The initial target loudness determination subunit is used to determine the initial target loudness based on the playback capability.

[0170] The loudness adjustment subunit is used to adjust the initial target loudness based on the audio feature to obtain the target loudness.

[0171] In some optional implementations, the initial target loudness determination subunit includes:

[0172] The first correspondence obtaining subunit is used to obtain a first correspondence between the playback capability of the playback device and the initial loudness.

[0173] The first query subunit is used to query the first corresponding relationship based on the playback capability of the playback device in the loudness requirement information to obtain an initial target loudness.

[0174] In some optional implementations, the loudness adjustment subunit includes:

[0175] The loudness increment determination subunit is used to determine a target loudness increment based on audio features, where the audio features include the type of audio content or the proportion of speech.

[0176] The adjusting subunit is used to adjust the initial target loudness based on the target loudness increment to obtain the target loudness.

[0177] In some optional implementations, the parameter determination unit includes:

[0178] The second correspondence relationship acquisition subunit is used to acquire a second correspondence relationship between the loudness requirement and the characteristic of the dynamic range control.

[0179] The target characteristic determination subunit is used to query the second corresponding relationship based on the loudness requirement information to determine the target characteristic of the dynamic range control.

[0180] The first slope determination subunit is used to determine the slope of the dynamic range control curve based on the audio characteristics and the target loudness if the target characteristic is that compression is required, and the dynamic range control parameters include the slope.

[0181] In some optional implementations, the audio feature includes a loudness peak, and the slope determination subunit includes:

[0182] The normalization subunit is used to perform peak normalization processing on the source loudness based on the loudness peak value and the preset loudness peak value to obtain the processed loudness.

[0183] The initial slope determination subunit is used to determine the initial slope of the dynamic range control curve based on the ratio of the processed loudness to the target loudness.

[0184] The preset slope acquisition subunit is used to acquire the preset slope corresponding to the target characteristic if the loudness requirement information includes the current playback environment or user preference.

[0185] The curve slope determination subunit is used to determine the slope of the curve of the dynamic range control based on the preset slope and the maximum value of the initial slope.

[0186] In some optional implementations, if the target characteristic requires compression, the parameter determination unit further includes:

[0187] The starting point determination subunit is used to determine the starting point of the dynamic range based on the dynamic range in the audio feature.

[0188] The threshold determination subunit is used to determine the starting point of the dynamic range as the threshold of the static characteristic in the curve of the dynamic range control, and determine the inflection point width of the curve as a preset value greater than zero.

[0189] In some optional implementations, the parameter determination unit further includes:

[0190] The execution subunit is used to execute the step of obtaining a second corresponding relationship between the loudness requirement and the characteristic of the dynamic range control if the length of the media data to be played is greater than the preset length.

[0191] The maximum short-term loudness acquisition subunit is used to acquire the maximum short-term loudness in the audio feature if the length is less than a preset length, and determine the loudness difference between the maximum short-term loudness and the target loudness.

[0192] The curve slope determination subunit is used to determine the slope of the dynamic range control curve based on the loudness difference value and the preset loudness difference value if the loudness difference value is greater than the preset loudness difference value.

[0193] In some optional embodiments, the curve slope determination subunit includes:

[0194] The second slope determination subunit is used to determine the slope of the dynamic range control curve based on the ratio of the loudness difference value to the preset loudness difference value.

[0195] In some optional implementations, the parameter determination unit further includes:

[0196] The compression-free determination subunit is used to determine that the target characteristic of the dynamic range control is compression-free if the loudness difference is less than a preset loudness difference.

[0197] In some optional implementations, the compensation gain acquisition unit includes:

[0198] The loudness shift subunit is used to determine the loudness shift based on the audio feature and the target loudness.

[0199] The loudness compensation gain determination subunit is used to determine the loudness compensation gain based on the loudness offset.

[0200] In some optional implementations, if the length of the media data to be played is greater than a preset length, the loudness shift subunit includes:

[0201] The starting point acquisition subunit is used to obtain the slope in the dynamic range control parameter and the starting point of the dynamic range in the audio feature.

[0202] The loudness estimation subunit is used to perform loudness estimation based on the target loudness, the slope and the starting point to determine the estimated loudness.

[0203] The offset determination subunit is configured to determine a loudness offset based on a difference between the target loudness and the estimated loudness.

[0204] In some optional implementations, the loudness compensation gain determination subunit includes:

[0205] The compensation gain determination subunit is used to obtain a loudness compensation gain based on the sum of the loudness offset and the first compensation value.

[0206] In some optional implementations, if the length of the to-be-played media data is less than a preset length, the loudness shift subunit includes:

[0207] The short-term loudness acquisition subunit is used to acquire the maximum short-term loudness in the audio feature.

[0208] The offset subunit is used to determine the loudness offset based on the difference between the maximum short-term loudness and the target loudness.

[0209] In some optional implementations, the loudness compensation gain determination subunit includes:

[0210] The first gain subunit is configured to obtain a loudness compensation gain based on a difference between the loudness offset and a second compensation value if the loudness offset is greater than a preset loudness difference value.

[0211] The second gain subunit is configured to determine that the loudness compensation gain is zero if the loudness offset is less than a preset loudness difference.

[0212] In some optional implementations, the audio processing module 704 includes:

[0213] The loudness processing unit is used to perform loudness processing on the media data to be played based on the loudness gain to obtain first media data.

[0214] The dynamic range processing unit is used to perform dynamic range processing on the first media data based on the dynamic range control parameter to obtain second media data.

[0215] The loudness compensation unit is configured to perform loudness compensation on the second media data based on the loudness compensation gain to obtain third media data.

[0216] The peak limiting unit is used to perform peak limiting on the third media data to obtain target media data.

[0217] The media data playback loudness processing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0218] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0219] The present disclosure also provides a computer device having the above Figure 7 The device for processing playback loudness of media data shown.

[0220] See also Figure 8 , Figure 8 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0221] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0222] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0223] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0224] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0225] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0226] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0227] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0228] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0229] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0230] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0231] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0232] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for processing the playback loudness of media data, characterized in that: The method comprises: Acquire the media data to be played and the audio features of the media data to be played; Acquiring loudness requirement information, where the loudness requirement information includes properties of a current playback environment and / or a playback device; Determining loudness processing information of the to-be-played media data based on the audio feature and the loudness requirement information; The to-be-played media data is processed based on the loudness processing information to obtain target media data for playing.

2. The method according to claim 1, characterized in that The determining, based on the audio feature and the loudness requirement information, the loudness processing information of the to-be-played media data includes: Determining a target loudness of the to-be-played media data based on the loudness requirement information; Determining a loudness gain based on a difference between a source loudness in the audio feature and the target loudness; Determining a dynamic range control parameter of the to-be-played media data based on the audio feature and the loudness requirement information; A loudness compensation gain is obtained, where the loudness compensation gain is obtained based on a loudness offset, and the loudness processing information includes the loudness gain, the dynamic range control parameter, and the loudness compensation gain.

3. The method according to claim 2, characterized in that The attribute of the playback device includes playback capability, and determining the target loudness of the to-be-played media data based on the loudness requirement information includes: Based on the playback capability, determining an initial target loudness; The initial target loudness is adjusted based on the audio feature to obtain the target loudness.

4. The method according to claim 3, characterized in that The determining of the initial target loudness based on the playback capability includes: Obtaining a first correspondence between a playback capability of a playback device and an initial loudness; Based on the playback capability of the playback device in the loudness requirement information, the first corresponding relationship is queried to obtain the initial target loudness.

5. The method according to claim 3, characterized in that: The adjusting the initial target loudness based on the audio feature to obtain the target loudness includes: Determine a target loudness increment based on the audio feature, where the audio feature includes a type of audio content or a voice ratio; The initial target loudness is adjusted based on the target loudness increment to obtain the target loudness.

6. The method according to claim 2, characterized in that The determining, based on the audio feature and the loudness requirement information, a dynamic range control parameter of the to-be-played media data includes: Obtaining a second correspondence between loudness requirements and characteristics of dynamic range control; querying the second corresponding relationship based on the loudness requirement information to determine a target characteristic of the dynamic range control; If the target characteristic is that compression is required, the slope of the curve of the dynamic range control is determined based on the audio feature and the target loudness, and the dynamic range control parameter includes the slope.

7. The method according to claim 6, characterized in that The audio feature includes a loudness peak, and determining the slope of the dynamic range control curve based on the audio feature and the target loudness includes: Based on the loudness peak value and a preset loudness peak value, performing peak normalization processing on the source loudness to obtain a processed loudness; determining an initial slope of a curve of the dynamic range control based on a ratio of the processed loudness to the target loudness; If the loudness requirement information includes the current playback environment or user preference, obtaining a preset slope corresponding to the target characteristic; The slope of the curve of the dynamic range control is determined based on the preset slope and the maximum value of the initial slope.

8. The method according to claim 6, characterized in that If the target characteristic is that compression is required, determining the dynamic range control parameter of the to-be-played media data based on the audio feature and the loudness requirement information further includes: Based on the dynamic range in the audio feature, determining a starting point of the dynamic range; The starting point of the dynamic range is determined as a threshold of a static characteristic in a curve of the dynamic range control, and the inflection point width of the curve is determined to be a preset value greater than zero.

9. The method according to claim 6, characterized in that The determining, based on the audio feature and the loudness requirement information, a dynamic range control parameter of the to-be-played media data further includes: If the length of the to-be-played media data is greater than a preset length, executing a step of obtaining a second correspondence between a loudness requirement and a characteristic of a dynamic range control; If the length is less than the preset length, obtaining the maximum short-term loudness in the audio feature, and determining a loudness difference between the maximum short-term loudness and the target loudness; If the loudness difference is greater than a preset loudness difference, a slope of the dynamic range control curve is determined based on the loudness difference and the preset loudness difference.

10. The method according to claim 9, characterized in that The determining the slope of the curve of the dynamic range control based on the loudness difference and the preset loudness difference includes: Based on the ratio of the loudness difference value to the preset loudness difference value, a slope of the dynamic range control curve is determined.

11. The method according to claim 9, characterized in that The determining, based on the audio feature and the loudness requirement information, a dynamic range control parameter of the to-be-played media data further includes: If the loudness difference is less than the preset loudness difference, it is determined that the target characteristic of the dynamic range control is that compression is not required.

12. The method according to claim 2, characterized in that: The obtaining of the loudness compensation gain comprises: Determining the loudness shift based on the audio feature and the target loudness; The loudness compensation gain is determined based on the loudness offset.

13. The method according to claim 2, characterized in that If the length of the to-be-played media data is greater than a preset length, determining the loudness offset based on the audio feature and the target loudness includes: Obtaining a slope in the dynamic range control parameter and a starting point of a dynamic range in the audio feature; Perform loudness estimation based on the target loudness, the slope, and the starting point to determine an estimated loudness; The loudness offset is determined based on a difference between the target loudness and the estimated loudness.

14. The method according to claim 13, characterized in that The determining the loudness compensation gain based on the loudness offset comprises: The loudness compensation gain is obtained based on the sum of the loudness offset and the first compensation value.

15. The method according to claim 2, characterized in that If the length of the to-be-played media data is less than a preset length, determining the loudness offset based on the audio feature and the target loudness includes: Obtaining the maximum short-term loudness in the audio feature; The loudness offset is determined based on a difference between the maximum short-term loudness and the target loudness.

16. The method according to claim 15, characterized in that The determining the loudness compensation gain based on the loudness offset comprises: If the loudness offset is greater than a preset loudness difference value, obtaining the loudness compensation gain based on a difference between the loudness offset and a second compensation value; If the loudness offset is less than the preset loudness difference, the loudness compensation gain is determined to be zero.

17. The method according to any one of claims 2 to 16, characterized in that The processing of the to-be-played media data based on the loudness processing information to obtain target media data for playing includes: Performing loudness processing on the to-be-played media data based on the loudness gain to obtain first media data; Performing dynamic range processing on the first media data based on the dynamic range control parameter to obtain second media data; Performing loudness compensation on the second media data based on the loudness compensation gain to obtain third media data; Peak value limitation is performed on the third media data to obtain the target media data.

18. A device for processing the playback loudness of media data, characterized in that: The device comprises: A data acquisition module, used to acquire the media data to be played and the audio features of the media data to be played; A demand information acquisition module, used to acquire loudness demand information, wherein the loudness demand information includes properties of a current playback environment and / or a playback device; A processing information determination module, configured to determine loudness processing information of the to-be-played media data based on the audio feature and the loudness requirement information; The audio processing module is used to process the to-be-played media data based on the loudness processing information to obtain target media data for playing.

19. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for processing the playback loudness of media data according to any one of claims 1 to 17 by executing the computer instructions.

20. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for processing playback loudness of media data according to any one of claims 1 to 17.

Images