Sound effect generation method and device, television and computer readable storage medium

Abstract

The invention provides a sound effect generation method and device, a television and a computer readable storage medium. The method comprises the following steps: acquiring current environment information; determining target sound field distribution information according to the current environment information; and generating target sound effect information according to the target sound field distribution information. According to the sound effect generation method provided by the invention, the current environment information can be firstly obtained, the target sound field distribution information corresponding to the current environment information is determined according to the current environment information, and the target sound effect information is obtained according to the target sound field distribution information, so that the equipment can adjust the sound effect of the equipment according to the target sound effect information; automatic sound effect adjustment is achieved, the sound effect better fits the current environment, and the adaptation degree of the sound effect and the environment is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of audio processing, in particular to an audio effect generation method and device, a television and a computer readable storage medium. BACKGROUND

[0002] In the prior art, scene audio effect generation mainly faces the following problems: audio effect mode is static, environmental perception is disconnected from personalized audio effects, and user interaction is inconvenient. These problems result in a lack of personalization and adaptability in audio experience, and users need to manually adjust audio effect parameters, which cannot achieve intelligent and automated audio effect optimization. SUMMARY

[0003] The present application provides an audio effect generation method that can automatically optimize audio effects.

[0004] In a first aspect, the present application provides an audio effect generation method, comprising:

[0005] obtaining current environmental information;

[0006] determining target sound field distribution information according to the current environmental information;

[0007] generating target audio effect information according to the target sound field distribution information.

[0008] In some embodiments of the present application, the current environmental information includes spatial area information, the number of environmental sound sources, and sound source propagation distance.

[0009] The determination of sound field distribution information according to the current environmental information comprises:

[0010] determining the sound field distribution information corresponding to each environmental sound source according to the spatial area information and the sound source propagation distance of each environmental sound source;

[0011] determining the target sound field distribution information according to the number of environmental sound sources and the sound field distribution information corresponding to each environmental sound source.

[0012] In some embodiments of the present application, the generation of target audio effect information according to the target sound field distribution information comprises:

[0013] obtaining historical audio playback information;

[0014] generating target audio effect information according to the historical audio playback information and the target sound field distribution information.

[0015] In some embodiments of the present application, the generation of target audio effect information according to the historical audio playback information and the target sound field distribution information comprises:

[0016] According to the historical audio playing information, initial sound effect information is predicted;

[0017] According to the target sound field distribution information, the initial sound effect information is adjusted to obtain the target sound effect information.

[0018] In some embodiments of the present application, the adjusting of the initial sound effect information according to the target sound field distribution information to obtain the target sound effect information comprises:

[0019] According to the current environment information, sound intensity information is determined;

[0020] According to the target sound field distribution information, the initial sound effect information is adjusted to obtain sound field adjustment sound effect information;

[0021] According to the sound intensity information, the sound field adjustment sound effect information is compensated to obtain the target sound effect information.

[0022] In some embodiments of the present application, the compensating of the sound field adjustment sound effect information according to the sound intensity information to obtain the target sound effect information comprises:

[0023] According to the sound intensity information, the sound field adjustment sound effect information is compensated to obtain initial target sound effect information;

[0024] According to the historical audio playing information, initial equalizer configuration information is predicted;

[0025] Current equalizer configuration information is obtained;

[0026] According to the current equalizer configuration information, the initial equalizer configuration information is adjusted to obtain target equalizer configuration information;

[0027] According to the target equalizer configuration information and the initial target sound effect information, the target sound effect information is obtained.

[0028] In some embodiments of the present application, the current environment information comprises space area information;

[0029] The obtaining of the current environment information comprises:

[0030] Space light information and space image information are obtained;

[0031] According to the space light information and the space image information, space area information is determined.

[0032] In some embodiments of the present application, after the generating of the target sound effect information according to the target sound field distribution information, the method further comprises:

[0033] obtaining a sampling time interval and current sound effect deviation information;

[0034] optimizing the target sound effect information according to the current sound effect deviation information and the sampling time interval.

[0035] In some embodiments of the present application, the step of optimizing the target sound effect information according to the current sound effect deviation information comprises:

[0036] if the current sound effect deviation information is less than a first deviation threshold, maintaining the target sound effect information;

[0037] if the current sound effect deviation information is greater than or equal to the first deviation threshold and less than a second deviation threshold, adjusting volume information and / or frequency information in the target sound effect information;

[0038] if the current sound effect deviation information is greater than or equal to the second deviation threshold, enhancing a target frequency band in the target sound effect information.

[0039] In a second aspect, the present application further provides an audio effect generation device, which comprises:

[0040] an obtaining module configured to obtain current environment information;

[0041] a determining module configured to determine target sound field distribution information according to the current environment information;

[0042] a generating module configured to generate target sound effect information according to the target sound field distribution information.

[0043] In a third aspect, the present application further provides a television, which comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the audio effect generation methods.

[0044] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program executable by a processor to implement the steps of any of the audio effect generation methods.

[0045] The audio effect generation method provided by the present application can first obtain current environment information, determine target sound field distribution information corresponding to the current environment information according to the current environment information, and obtain target sound effect information according to the target sound field distribution information, so that the device can adjust its own sound effect according to the target sound effect information, realize automatic sound effect adjustment, and make the sound effect more suitable for the current environment, thereby improving the adaptation degree of the sound effect and the environment. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0047] Figure 1 is a scene schematic diagram of the sound effect generation system provided in the embodiments of the present application;

[0048] Figure 2 is a flowchart of one embodiment of the sound effect generation method in the embodiments of the present application;

[0049] Figure 3 is a functional module schematic diagram of the sound effect generation device in the embodiments of the present application;

[0050] Figure 4 is a structural schematic diagram of the television in the embodiments of the present application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0052] In the description of the present application, it should be understood that the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0053] In the present application, the word "exemplary" is used to mean "serving as an example, instance, or illustration". Any embodiment described as "exemplary" in the present application is not necessarily to be construed as preferred or advantageous over other embodiments. It should also be understood that, in the specific embodiments of the present application, the data related to user information, user data, etc. When the above embodiments of the present application are applied to specific products or technologies, the user's permission or consent needs to be obtained, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of the country and region.

[0054] The following description is presented to enable any person skilled in the art to practice the application as claimed. Details are set forth in the following description for purpose of explanation. It should be appreciated that one of ordinary skill in the art will realize the application can be practiced without the use of these specific details. In other instances, well-known structures and processes have not been described in detail in order to avoid obscuring the description of the application. Therefore, it will be appreciated that the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features presented herein.

[0055] The application provides an audio effect generation method and device, equipment and storage medium, which are described in detail below.

[0056] Please refer to Figure 1 , Figure 1 The scene schematic diagram of the audio effect generation system provided by the embodiments of the application can include a television 100. As shown in Figure 1 The television 100 in the application can acquire current environment information to execute the audio effect generation method in the application.

[0057] In the embodiments of the application, the television 100 can be, but is not limited to, a liquid crystal display (LCD) television, a light-emitting diode (LED) television, an organic light-emitting diode (OLED) television, and the like.

[0058] In addition, in the embodiments of the application, the television 100 can also be connected to a sound equipment, including a wireless sound equipment or a wired sound equipment, and the like. If the television 100 is connected to the sound equipment, the sound equipment can output the audio when the television 100 plays the audio.

[0059] In the embodiments of the application, if the television 100 is connected to the sound equipment, any communication mode can be used to realize the communication, including but not limited to Bluetooth, computer network communication based on a TCP / IP protocol suite (TCP / IP), a user datagram protocol (UDP), a wired connection, and the like. The specific embodiments of the application are not limited.

[0060] It should be noted that Figure 1The scene schematic diagram of the sound effect generation system shown is only an example, and the sound effect generation system and the scene described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of the sound effect generation system and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0061] As shown in Figure 2 Figure 2 is an embodiment flow schematic diagram of the sound effect generation method in the embodiments of the present application. The sound effect generation method can include the following steps 201-203.

[0062] 201, obtaining current environment information.

[0063] In the embodiments of the present application, the current environment information can include non-device played environmental sound of the space where the device is located, such as noise, etc. The way to obtain the current environment information can be through installing an audio sensor on the device, and obtaining the environmental volume of the space where the device is located through the audio sensor. For example, the environmental volume of a conference room, a living room, a bedroom, etc.

[0064] The audio sensor can be arranged on the device, and the audio sensor can also be arranged at each position in the space. By arranging the audio sensor in the environment, the current environment information can be better obtained. After the audio sensor arranged in the space obtains the current environment information, the current environment information can be sent to the device through wireless network transmission, so that the device obtains the current environment information. It should be emphasized that the embodiments of the present application are not specifically limited.

[0065] 202, determining target sound field distribution information according to the current environment information.

[0066] In the embodiments of the present application, the sound field refers to the sound distribution area formed by the sound wave emitted by the sound source when propagating in space. In simple terms, it is the distribution of sound in a certain space, including the intensity, direction and wave characteristics of sound waves. Specifically, the sound field includes sound wave propagation: sound waves are emitted from a sound source and propagate in air or other media to form a three-dimensional sound wave distribution area. Sound pressure and sound intensity: different positions in the sound field have different sound pressure (sound pressure) and sound intensity (sound energy transmission rate), which describe the changes of sound waves in space. Therefore, the sound field distribution information includes the sound distribution area formed when propagating in space.

[0067] ​Based on this, in the embodiments of the present application, according to the obtained current environment information, the relevant parameters of the sound distribution area formed by the propagation of the environmental volume in space, such as intensity, direction, fluctuation characteristics, sound pressure, sound intensity, transmission efficiency, etc., can be effectively analyzed, and then it is determined whether the current space is conducive to the propagation of sound waves. These parameters can be regarded as parameters in the target sound field distribution information.

[0068] 203. Generating target sound effect information according to the target sound field distribution information.

[0069] When the target sound field distribution information of the environmental volume in the current environment information in the current space is determined, by analyzing the target sound field distribution information, it can be determined which sound effect the device currently adopts can best match the current space.

[0070] Specifically, assuming that according to the intensity, direction, fluctuation characteristics, sound pressure, sound intensity, and transmission efficiency in the target sound field distribution information, it is determined that the current space is not conducive to the propagation of sound, the environmental noise is large, etc., then the volume during the audio playback of the device can be increased, reverberation can be used to increase the depth of sound, the spatial stereo sound can be enhanced, etc., so that the sound effect is more prominent, and the user's listening experience is improved. Or, according to the target sound field distribution information, it is determined that the sound information in the current environment information is conducive to the propagation of sound, the environmental noise is small, etc., then it can be determined that the audio sound effect played by the device is played with the sound effect setting selected by the user, or the proportion of bass can be appropriately increased.

[0071] It should be noted that in the embodiments of the present application, the current environment information is actually obtained, and if the current environment changes, the real-time obtained current environment information will also change. For example, the environmental volume in the current environment information may change, at this time the target sound field distribution information will also change with the change of the current environment information, and then the target sound effect information will also change.

[0072] Based on this, the sound effect generation method provided by the present application can first obtain the current environment information, and determine the target sound field distribution information corresponding to the current environment information according to the current environment information, and obtain the target sound effect information according to the target sound field distribution information, so that the device can adjust its own sound effect according to the target sound effect information, realize automatic sound effect adjustment, and make the sound effect more suitable for the current environment, and improve the adaptation degree of the sound effect and the environment.

[0073] In order to better realize the embodiments of the present application, in one embodiment of the present application, the current environment information includes space area information, the number of environmental sound sources of the environmental sound source, and the sound source propagation distance; according to the current environment information, the sound field distribution information is determined, including:

[0074] According to the space area information and the sound source propagation distance of each environmental sound source, sound field distribution information corresponding to each environmental sound source is determined; and according to the number of environmental sound sources and the sound field distribution information corresponding to each environmental sound source, target sound field distribution information is determined.

[0075] In the above embodiment, a scheme for determining target sound field distribution information according to current environmental information is provided. In order to further improve the adaptation degree of subsequent target sound effect information to the environment, the present embodiment also provides a scheme for determining target sound field distribution information according to current environmental information.

[0076] It should be noted that, on the basis of the above embodiment, the present embodiment further limits a case where the current environmental information includes space area information, environmental sound source quantity and sound source propagation distance information. At the same time, the environmental sound source quantity can include not only environmental sound but also sound propagated in the environment after the device plays audio. The reason for counting the device audio as the environmental sound source quantity is that the device audio will be integrated with the environmental audio, which will also cause the change of the sound field. Therefore, considering the device audio and the environmental audio at the same time can simulate the sound actually heard by the user as much as possible. The space area information can be obtained by the image sensor installed on the device to obtain a space image, so as to calculate the space area.

[0077] Specifically, in actual cases, the space can include multiple sources of sound, and each source of sound corresponds to a different sound. The presence of multiple sounds will cause different sounds in the space to interact with each other, resulting in different effects. Based on this, the present embodiment provides a scheme for calculating target sound field distribution information according to the space area information, the environmental sound source quantity and the sound source propagation distance included in the current environmental information, as shown in formula (1):

[0078]

[0079] In formula (1), S(x, y) represents the complex sound pressure (sound field intensity) at the coordinates (x, y), which is the sound field distribution result calculated by the "room sound field optimization". S(x, y) describes the sound field (sound pressure, sound intensity) distribution under the joint action of multiple sound sources (including the sound source of device audio) at a certain point in space. The system will optimize and adjust the parameters of the sound source of device audio using S(x, y) to achieve a suitable immersive sound field. In formula (1), -jkr i is a phase delay term in physics, which represents the phase delay of the sound source to the target point wave, and is the sound field synthesis. j is the imaginary unit in physics, k is the wave number, and r i is the distance from the i-th sound source to the coordinates (x, y), i.e. the sound source propagation distance, A iis the amplitude of the ith sound source. N is the number of environmental sound sources. As can be seen, the summation part in formula (1) is to determine the target sound field distribution information according to the number of environmental sound sources and the sound field distribution information corresponding to each environmental sound source. The remaining part is to determine the sound field distribution information corresponding to each environmental sound source according to the sound source propagation distance of each environmental sound source. After the specific spatial area information is obtained, some parameters in the formula need to be adjusted according to the actual situation. For example:

[0080] ① Small room (room area ≤ 30 square meters), sound source number N = 4, (surround sound with static sound field distribution), adjust sound source amplitude A i , such as strengthening the mid-frequency reflected sound effect, sound source distance r i belongs to the range of 1 meter to 5 meters, adjust the target sound field distribution information.

[0081] ② Medium room (30 square meters < room area ≤ 60 square meters), sound source number N ∈ [6, 8] (dynamic simulation of sound field changes with user position), adjust sound source amplitude A i , such as strengthening the low frequency part, and strengthening the immersion, sound source distance r i belongs to the range of 3 meters to 10 meters, dynamically adjust the target sound field distribution information.

[0082] ③ Large room (room area > 60 square meters), sound source number N ≥ 10, adjust sound source amplitude A i , such as expanding the dynamic range, strengthening both low frequency and high frequency sound effects to maintain uniform coverage, sound source distance r i belongs to the range of 5 meters to 15 meters, dynamically adjust.

[0083] It should be noted that in addition to the above real-time method, other parameter adjustment schemes can also be included, which are not limited by the embodiments of the application, including: if N < 4, the sound source number is too small to form an effective surround or spatial immersive sound field, which has no practical application value, N = 9, which is a critical value between a medium room and a large room, generally can not be processed, can be merged into a medium room scene or a large room scene. When the specific target sound field distribution information is determined, the subsequent method of adjusting the target sound effect information according to the target sound field distribution information is the same as the above embodiment, which will not be described here.

[0084] In order to better implement the embodiments of the application, in an embodiment of the application, the target sound effect information is generated according to the target sound field distribution information, comprising:

[0085] Obtain historical audio playback information; generate target sound effect information according to historical audio playback information and target sound field distribution information.

[0086] The above embodiments provide a scheme of determining the final target sound effect information directly according to the current environment information. However, the scheme does not combine the user's own preference. Therefore, in order to make the generated target sound effect information parameters more match the user's preference, the embodiments of the present application further provide a scheme of generating target sound effect information on the basis of the user's preference.

[0087] Specifically, the historical audio playback information of the user can be acquired, for example, the historical audio playback information of the user after the last time the device is turned off, to obtain the user's setting information for audio playback as the user's preferred sound effect setting or basic sound effect setting. For example: according to the recorded user operation history (such as sound effect mode selection, volume adjustment, etc.). Analyze the audio playback history (such as playback frequency, playback time length, etc.). Then data preprocessing is performed, the collected raw data is filtered, noise reduced, etc. to improve the data quality. After the target sound field distribution information is determined, taking the volume parameter as an example, assuming that the volume setting determined according to the target sound field distribution information is less than the user's historical preference volume, the volume in the target sound effect parameter can be set to the historical preference volume; if it is assumed that the volume setting determined according to the target sound field distribution information is greater than the user's historical preference volume, the volume can be appropriately increased on the basis of the user's historical preference volume, for example, 10%, 20%, etc. to ensure that it is close to the user's preference on the basis, and more consistent with the current target sound field distribution information. Similarly, for other sound effect parameters, such as reverberation parameters, stereo surround, frequency, etc., the mode is similar to the volume mode, which will not be repeated here.

[0088] As can be seen, the target sound effect information determined according to the user's preference can better meet the user's needs.

[0089] In order to better implement the embodiments of the present application, in one embodiment of the present application, the target sound effect information is generated according to the historical audio playback information and the target sound field distribution information, comprising:

[0090] According to the historical audio playback information, the initial sound effect information is predicted; and the initial sound effect information is adjusted according to the target sound field distribution information to obtain the target sound effect information.

[0091] In the above embodiments, a scheme is provided for directly generating subsequent target sound effect information according to the user's historical audio playback information on the device as the user's preference data. However, in actual situations, the user may have different sound effect setting schemes for different application scenarios. For example, watching movies, watching sports matches, watching concerts, and the like. Different videos may correspond to different sound requirements of the user. Assuming that the user watches a movie and then watches a sports match in a single use of the device, the user may use different sound effect settings. If the user turns off the device after watching the sports match, the next time the target sound effect information is generated, the sound effect of the sports match may be taken as the user's preference. If the user uses the device to watch other video types other than sports matches the next time, it may also lead to a situation that does not meet the user's requirements.

[0092] Based on this, the embodiments of the present application provide a scheme for predicting a user based on historical audio playback information to obtain a reference initial sound effect information. Specifically, the historical audio playback information in a certain time period in the device can be obtained, such as one month, three months, and the like, so as to obtain the probability of the user watching different video types in a specific time, for example, watching sports matches regularly on Friday night, and preferring to watch movies on Saturday afternoon, and the like, so as to analyze the user's video watching rule, and then predict the highest possibility of watching which video under the current situation based on the historical audio playback information, and then select the sound effect setting of the corresponding type as the initial sound effect information. Wherein, the user is predicted to obtain the corresponding initial sound effect information, which can be predicted by a neural network. The neural network can use any neural network model, and the embodiments of the present application do not limit it. After the initial sound effect information is obtained by predicting based on the neural network, the initial sound effect information can be adjusted based on the target sound field distribution information to obtain the target sound effect information in the manner of the above embodiments, and the embodiments of the present application will not be described again.

[0093] As can be seen, the embodiments can better determine the user's preference setting for sound effect, so that the subsequently determined target sound effect information can better meet the user's requirements.

[0094] In order to better implement the embodiments of the present application, in an embodiment of the present application, the initial sound effect information is adjusted based on the target sound field distribution information to obtain the target sound effect information, which includes:

[0095] The sound intensity information is determined according to the current environment information; the initial sound effect information is adjusted based on the target sound field distribution information to obtain the sound field adjustment sound effect information; and the sound field adjustment sound effect information is compensated based on the sound intensity information to obtain the target sound effect information.

[0096] In the above embodiments, a scheme is provided for determining target sound effect information according to target sound field distribution information. However, in order to make the determined target sound effect information have better effect, an embodiment is further provided in the present application.

[0097] Specifically, the initial sound effect information is adjusted according to the target sound field distribution information to obtain sound field adjustment sound effect information, which can refer to the scheme of adjusting the initial sound effect information according to the target sound field distribution information to obtain the target sound effect information in any of the above embodiments, which will not be described here. However, it should be noted that the target sound effect information obtained in any of the above embodiments is regarded as the sound field adjustment sound effect information.

[0098] In addition, since the current environment information includes sound information in the environment, the intensity of the volume of the sound can be determined according to the sound information in the current environment information, and the sound effect is further adjusted according to the volume intensity to realize sound effect compensation. Specifically, as shown in formula (2):

[0099] G adjusted =G base +α·(P noise -P threshold )……(2)

[0100] In formula (2), P noise is sound intensity information, P threshold is a noise threshold, G base is a basic compensation, and a is a compensation coefficient.

[0101] In addition, compensating the sound field adjustment sound effect information according to the sound intensity information to obtain the target sound effect information can include:

[0102] If it is a low-noise environment (P noise ≤P threshold ), G adjusted =G base , the system does not perform gain compensation, and the sound field adjustment sound effect information is taken as the target sound effect information;

[0103] If it is a medium-noise environment (P threshold <P noise ≤P threshold +10), the gain fine tuning (G adjusted =G base +α·(P noise -P threshold )) is enhanced to enhance the detail audio (such as the clarity of dialogue) on the basis of the sound field adjustment sound effect information, for example, the frequency band range: 200Hz-2kHz, to obtain the target sound effect information;

[0104] If it is a high-noise environment (P noise >Pthreshold +10), on the basis of sound field adjustment sound effect information, a substantial gain compensation (G adjusted = G base +1.5a·(P noise -P threshold )), reduce low frequency noise interference, frequency range focus weakening 100Hz~300Hz, enhance the high frequency sound effect, such as frequency range 800Hz~4kHz, so as to obtain the target sound effect information.

[0105] Wherein, P noise The acquisition method can identify noise type and intensity by fast Fourier transform (FFT) and spectrum analysis, as follows formula (3) and (4):

[0106]

[0107] P noise = max(X(k)) …… (4)

[0108] In formula (3), x(n) is a time domain signal, X(k) is a frequency domain signal, and N is the number of sampling points.

[0109] Therefore, the embodiments of the present application can further adjust the sound effect according to the sound intensity information of the current environment information, so that the sound effect is more in line with the current environment.

[0110] In order to better realize the embodiments of the present application, in one embodiment of the present application, the sound field adjustment sound effect information is compensated according to the sound intensity information, and the target sound effect information is obtained, comprising:

[0111] According to the sound intensity information, the sound field adjustment sound effect information is compensated to obtain the initial target sound effect information; according to the historical audio playing information, the initial equalizer configuration information is predicted; the current equalizer configuration information is obtained; according to the current equalizer configuration information, the initial equalizer configuration information is adjusted to obtain the target equalizer configuration information; according to the target equalizer configuration information and the initial target sound effect information, the target sound effect information is obtained.

[0112] In the embodiments of the present application, on the basis of the above sound compensation, an additional equalizer adjustment scheme is also provided, which can further improve the effect of sound effect adjustment.

[0113] Specifically, according to the sound intensity information, the sound field adjustment sound effect information is compensated to obtain the initial target sound effect information, which can be regarded as the above compensation scheme according to the sound intensity information, and the embodiments will not be described again.

[0114] In the historical audio playback information, not only the sound effect parameters in the historical device use process of the user can be included, but also the specific equalizer setting parameters for the sound effect can be included. Therefore, in actual situations, for different application scenarios, different equalizer parameter settings can exist on the basis of different sound effect setting schemes. For example, different equalizer settings can be used for watching movies, watching sports matches, and watching concerts. Assuming that the user watches a movie and then watches a sports match in a single device use, the equalizer settings can also be different.

[0115] Based on this, an embodiment of the present application provides a kind of according to historical audio playback information, further to user, to obtain a benchmark initial equalizer setting parameter of prediction.For specific, can obtain the historical audio playback information in a certain period of time in device, such as a month, three months etc., to obtain the probability that user watches different video types in specific time, for example, regularly watch sports match on Friday night, prefer to watch movie on Saturday afternoon etc., to analyze the video watching rule of user, and then according to historical audio playback information, predict the highest possibility of watching that video under current situation, and then select the equalizer setting of corresponding type as initial equalizer configuration information. Wherein, to user, to obtain corresponding initial equalizer configuration information by prediction can also be carried out by the way of neural network, the neural network can adopt any neural network model, and the embodiment of the present application does not limit it. After that, if initial equalizer configuration information is obtained according to neural network to complete prediction, then initial equalizer configuration information can be adjusted to obtain target sound effect information. Specific, as shown in formula (5):

[0116]

[0117] In formula (3), Z is a transformation variable, represents frequency domain, delay operation, digital filter / signal processing standard symbol. L is a summation subscript, indicates delay step number, corresponds to different order of filter. M is the highest order of molecule, order of filter molecule, controls filter complexity and model capability. The formula is IIR filter description, for realizing the dynamic optimization of sound effect parameter (such as different frequency band gain) to audio output. The result H (z) of calculation is the mathematical expression of gain characteristic or frequency response of system (such as equalizer, filter). H (z) completely determines the amplification (gain) or weakening (attenuation) of sound effect system / equalizer to signal in different frequency band.

[0118] For example, the movie mode: strengthen the low frequency band (gain 10%), frequency range 20Hz~150Hz, weaken the high frequency sharp sound (gain-5%) frequency range 8kHz~12kHz; music mode: balance low, medium and high sound gain: frequency band gain +5%, +10%, +10%, respectively, optimize the voice frequency band (gain +15%): frequency range 200Hz-2kHz; game mode: enhance the positioning sound effect (gain +20%): frequency range 800Hz-6kHz, reduce the background noise: high frequency band (frequency range 12kHz-20kHz gain-10%) and the like.

[0119] When the final target equalizer configuration information is determined, the target sound effect information can be obtained by adjusting the equalizer based on the initial target sound effect information.

[0120] In order to better implement the embodiments of the present application, in an embodiment of the present application, the current environment information includes space area information; obtaining the current environment information includes:

[0121] Obtaining the space light information and the space image information; determining the space area information according to the space light information and the space image information.

[0122] The above embodiment provides a scheme for determining the space area according to the image information of the space. In order to improve the accuracy of the space area calculation, the embodiments of the present application also provide a scheme combined with light calculation.

[0123] Specifically, the space light information can be collected by a light sensor. At the same time, the space image information can still be obtained by an image sensor or an infrared sensor. After obtaining the space light information, the average light intensity can be calculated as formula (6), which is shown as follows:

[0124]

[0125] In formula (6), L i is the light intensity collected for the i-th time, w i is a weight coefficient, L avg is the average brightness, and n is the number of collection times. Then, the light and the image can be combined by an image processing algorithm to identify the room size.

[0126] In order to better implement the embodiments of the present application, in an embodiment of the present application, after generating the target sound effect information according to the target sound field distribution information, the method further includes:

[0127] Obtaining the sampling time interval and the current sound effect deviation information; optimizing the target sound effect information according to the current sound effect deviation information and the sampling time interval.

[0128] The above embodiments provide various schemes for generating target sound effect information. In order to further improve the adjustment of sound effect according to the target sound effect information, the embodiments of the present application also provide a scheme for continuously optimizing the target sound effect information in real time. Specifically, as shown in formula (7):

[0129]

[0130] In formula (7), t is a sampling time interval, and e(t) is a current sound effect deviation, which is an error between a current actual output sound effect parameter of the system and a target / desired sound effect parameter. For example, it can be a difference between an actually output frequency band gain value and an ideal gain value, or a difference between an actual listening feeling after environmental self-adaptive adjustment and a target value set by an intelligent algorithm. The specific source can be: a deviation between collected environmental data and a model expectation, a difference between a user preference prediction value and a current sound effect parameter, and an error between an actual sound output and an expected value in a certain evaluation index (such as overall loudness, frequency band gain).

[0131] e(τ) is a value of e(t) at a certain past time τ. It represents a deviation of the system at a certain time τ in history. Specifically, e(τ) refers to a real-time error between the sound effect parameter of the system and the target value at time τ. For example, if the volume detected by the system 9 seconds ago deviates from the target volume by 2 dB, then at τ = t-9 seconds, e(τ) = 2 dB. τ: is a time variable between 0 and t, representing a historical time point, used for integral statistical process. If e(t) represents the difference between the current real volume and the ideal volume (such as 2 decibels), the system calculates u(t) = 1.2 dB through PID, and then the “sound effect system will actually increase 1.2 dB” to approach the target value. If the frequency band gain is adjusted, e(t) is the difference between the theoretical gain of the frequency band and the actual gain, and u(t) is the new adjustment amplitude of the frequency band.

[0132] And K p , K i , K d are respectively the first coefficient, the second coefficient and the third coefficient of integration and differentiation. By adjusting the first coefficient, the second coefficient and the third coefficient, u(t) is adjusted. Therefore, according to the current sound effect deviation information and the sampling time interval, the optimization of the target sound effect information can include optimizing the target sound effect information according to the current sound effect deviation information, the sampling time interval, the first coefficient, the second coefficient and the third coefficient

[0133] In order to better realize the embodiments of the present application, in an embodiment of the present application, the optimization of the target sound effect information according to the current sound effect deviation information includes:

[0134] If the current sound effect deviation information is less than the first deviation threshold, the target sound effect information is maintained; if the current sound effect deviation information is greater than or equal to the first deviation threshold and less than the second deviation threshold, the volume information and / or the frequency information in the target sound effect information are adjusted; and if the current sound effect deviation information is greater than or equal to the second deviation threshold, the target frequency band in the target sound effect information is enhanced.

[0135] The above embodiments provide a scheme for optimizing the target audio information according to the current sound effect deviation information and the sampling time interval. The embodiments of the present application also provide a more specific optimization method to improve the optimization effect.

[0136] For example: sound dynamic deviation < 5% (environment is stable): keep the existing sound effect configuration, and no real-time adjustment is needed. Sound dynamic deviation 5%-15% (environment changes moderately): small amplitude adjustment gain, according to the proportional coefficient K p Adjust the volume or frequency band intensity; smooth dynamic change, and moderately adjust the integral coefficient K i Reduce the volume fluctuation. Sound dynamic deviation > 15% (environment changes dramatically): quickly respond to dynamic changes, and amplify the differential coefficient K d Reduce sound effect distortion in time; and enhance the highlight effect of the key frequency band (such as human voice or action scene audio).

[0137] Of course, it also needs to be explained that after the generation of the target sound effect information and the sound effect adjustment according to the target sound effect information are completed, the user can also perform manual adjustment. For example, the user can perform voice instructions, such as "increase the volume": adjust the overall gain G adjusted ; or "switch to music mode", execute the equalizer adjustment algorithm, and strengthen the music frequency band. The user can also perform gesture instructions: according to the user's mobile phone, adjust the volume by moving up and down, and switch the mode by moving left and right. The user can also perform touch instructions, including adjusting the equalizer slider by touching (remote control or hand sliding), gradually adjusting the gain of each frequency band, and updating the sound effect parameters in real time. Specifically, the embodiments of the present application do not limit this.

[0138] In order to better implement the sound effect generation method in the embodiments of the present application, on the basis of the sound effect generation method, the embodiments of the present application also provide a sound effect generation device, as shown in Figure 3 The device 300 includes:

[0139] The acquisition module 301 is configured to acquire current environment information.

[0140] The determination module 302 is configured to determine target sound field distribution information according to the current environment information.

[0141] The generation module 303 is configured to generate target sound effect information according to the target sound field distribution information.

[0142] The sound effect generation apparatus provided in the present application can first acquire current environment information by the acquisition module 301, and according to the current environment information, the determination module 302 determines the target sound field distribution information corresponding thereto, and the generation module 303 obtains the target sound effect information according to the target sound field distribution information, so that the device can adjust its own sound effect according to the target sound effect information, realize automatic sound effect adjustment, and make the sound effect more suitable for the current environment, and improve the adaptation degree of the sound effect and the environment.

[0143] In some embodiments of the present application, the current environment information includes spatial area information, the number of environment sound sources of the environment sound source, and the sound source propagation distance, and the determination module 302 is specifically configured to:

[0144] determine the sound field distribution information corresponding to each environment sound source according to the spatial area information and the sound source propagation distance of each environment sound source;

[0145] determine the target sound field distribution information according to the number of environment sound sources and the sound field distribution information corresponding to each environment sound source.

[0146] In some embodiments of the present application, the generation module 303 is specifically configured to:

[0147] acquire historical audio playing information;

[0148] generate the target sound effect information according to the historical audio playing information and the target sound field distribution information.

[0149] In some embodiments of the present application, the generation module 303 is specifically further configured to:

[0150] predict initial sound effect information according to the historical audio playing information;

[0151] adjust the initial sound effect information according to the target sound field distribution information to obtain the target sound effect information.

[0152] In some embodiments of the present application, the generation module 303 is specifically further configured to:

[0153] determine sound intensity information according to the current environment information;

[0154] adjust the initial sound effect information according to the target sound field distribution information to obtain sound field adjustment sound effect information;

[0155] compensate the sound field adjustment sound effect information according to the sound intensity information to obtain the target sound effect information.

[0156] In some embodiments of the present application, the generation module 303 is specifically further configured to:

[0157] According to the sound intensity information, the sound field adjusts sound effect information to obtain initial target sound effect information;

[0158] According to historical audio playing information, initial equalizer configuration information is predicted;

[0159] Current equalizer configuration information is obtained;

[0160] According to the current equalizer configuration information, the initial equalizer configuration information is adjusted to obtain target equalizer configuration information;

[0161] According to the target equalizer configuration information and the initial target sound effect information, target sound effect information is obtained.

[0162] In some embodiments of the present application, the current environment information includes space area information, and the obtaining module 301 is specifically further used for:

[0163] Space light information and space image information are obtained;

[0164] According to the space light information and the space image information, the space area information is determined.

[0165] In some embodiments of the present application, after the target sound effect information is generated according to the target sound field distribution information, the generating module 303 is specifically further used for:

[0166] A sampling time interval and current sound effect deviation information are obtained;

[0167] According to the current sound effect deviation information and the sampling time interval, the target sound effect information is optimized.

[0168] In some embodiments of the present application, the generating module 303 is specifically further used for:

[0169] If the current sound effect deviation information is less than a first deviation threshold, the target sound effect information is maintained;

[0170] If the current sound effect deviation information is greater than or equal to the first deviation threshold and less than a second deviation threshold, volume information and / or frequency information in the target sound effect information are adjusted;

[0171] If the current sound effect deviation information is greater than or equal to the second deviation threshold, a target frequency band in the target sound effect information is enhanced.

[0172] Embodiments of the present application also provide a television, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps in the sound effect generation method of any one of the embodiments of the present application. Wherein, the television integrates any one of the sound effect generation methods provided by the embodiments of the present application, such as Figure 4As shown in FIG. 1, it shows a structural schematic diagram of a television related to the embodiments of the present application, in particular:

[0173] The television can include a processor 401 with one or more processing cores, a memory 402 with one or more computer readable storage media, a power supply 403, an input unit 404, and the like. Those skilled in the art can understand that, Figure 4 The television structure shown in FIG. 1 does not constitute a limitation on the television, and can include more or less components than those shown in the figure, or combine certain components, or different component arrangements. Among them:

[0174] The processor 401 is the control center of the television, which connects various parts of the television through various interfaces and lines, executes various functions of the television and processes data by running or executing software programs and / or modules stored in the memory 402 and calling data stored in the memory 402, thereby overall monitoring the television. Optionally, the processor 401 can include one or more processing cores; the processor 401 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like, and preferably, the processor 401 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 401.

[0175] The memory 402 can be used to store software programs and modules, and the processor 401 can execute various function applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the television, etc. In addition, the memory 402 can include a high-speed random access memory, and can also include a non-volatile memory, for example, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the memory 402 can also include a memory controller to provide the processor 401 with access to the memory 402.

[0176] The television also includes a power supply 403 for supplying power to various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so that the power management system can be used to manage charging, discharging, power consumption management, etc. The power supply 403 can also include one or more direct current or alternating current power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc.

[0177] The television can also include an input unit 404, which can be used to receive input digital or character information, and generate microphone, camera, optical or remote control device inputs related to user settings and function controls.

[0178] Although not shown, the television can also include a display unit, etc., which will not be described here. In particular, in the present embodiment, the processor 401 in the television can load executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and run the application programs stored in the memory 402 by the processor 401, so as to implement various functions, for example:

[0179] Obtaining current environmental information;

[0180] Determining target sound field distribution information according to the current environmental information;

[0181] Generating target sound effect information according to the target sound field distribution information.

[0182] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by related hardware controlled by the instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0183] To this end, an embodiment of the present application provides a computer readable storage medium, which can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. A computer program is stored on the storage medium, and the computer program is loaded by a processor to execute steps in any sound effect generation method provided by the embodiment of the present application. For example, the computer program loaded by the processor can execute the following steps:

[0184] obtaining current environment information;

[0185] determining target sound field distribution information according to the current environment information;

[0186] generating target sound effect information according to the target sound field distribution information.

[0187] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the detailed description of other embodiments above, which will not be repeated here.

[0188] In a specific implementation, each of the above units or structures can be implemented as an independent entity, or can be combined as the same or several entities, and the specific implementation of each unit or structure can be referred to the method embodiments above, which will not be repeated here.

[0189] The specific implementation of each operation can be referred to the embodiments above, which will not be repeated here.

[0190] The above describes in detail a sound effect generation method and device provided by the embodiment of the present application, and the principle and implementation manner of the present application are described by applying specific examples; the above embodiment is only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range can be changed, and the above description of the specification should not be understood as a limitation of the present application.

Claims

1. A sound effect generation method characterized by, The method comprises: obtaining current environment information; determining target sound field distribution information according to the current environment information; generating target sound effect information according to the target sound field distribution information.

2. The sound effect generation method of claim 1, wherein, The current environment information comprises spatial area information, the number of environmental sound sources, and sound source propagation distance; The determination of the sound field distribution information according to the current environment information comprises: determining the sound field distribution information corresponding to each environmental sound source according to the spatial area information and the sound source propagation distance of each environmental sound source; determining the target sound field distribution information according to the number of environmental sound sources and the sound field distribution information corresponding to each environmental sound source.

3. The sound effect generation method of claim 1, wherein, The generation of the target sound effect information according to the target sound field distribution information comprises: obtaining historical audio playback information; generating target sound effect information according to the historical audio playback information and the target sound field distribution information.

4. The sound effect generation method according to claim 3, wherein The generation of the target sound effect information according to the historical audio playback information and the target sound field distribution information comprises: predicting initial sound effect information according to the historical audio playback information; adjusting the initial sound effect information according to the target sound field distribution information to obtain the target sound effect information.

5. The sound effect generation method according to claim 4, wherein The adjustment of the initial sound effect information according to the target sound field distribution information to obtain the target sound effect information comprises: determining sound intensity information according to the current environment information; adjusting the initial sound effect information according to the target sound field distribution information to obtain sound field adjustment sound effect information; compensating the sound field adjustment sound effect information according to the sound intensity information to obtain the target sound effect information.

6. The sound effect generation method of claim 5, wherein, The compensation of the sound field adjustment sound effect information according to the sound intensity information to obtain the target sound effect information comprises: compensating the sound field adjustment sound effect information according to the sound intensity information to obtain initial target sound effect information; predicting initial equalizer configuration information according to the historical audio playback information; obtaining current equalizer configuration information; adjusting the initial equalizer configuration information according to the current equalizer configuration information to obtain target equalizer configuration information; obtaining the target sound effect information according to the target equalizer configuration information and the initial target sound effect information.

7. The sound effect generation method of claim 1, wherein, The current environment information comprises spatial area information; The obtaining of the current environment information comprises: obtaining spatial light information and spatial image information; determining spatial area information according to the spatial light information and the spatial image information.

8. The sound effect generation method according to any one of claims 1 to 7, characterized by, After the generation of the target sound effect information according to the target sound field distribution information, the method further comprises: obtaining a sampling time interval and current sound effect deviation information; optimizing the target sound effect information according to the current sound effect deviation information and the sampling time interval.

9. The sound effect generation method of claim 8, wherein, The optimization of the target sound effect information according to the current sound effect deviation information comprises: if the current sound effect deviation information is less than a first deviation threshold, maintaining the target sound effect information; if the current sound effect deviation information is greater than or equal to the first deviation threshold and less than a second deviation threshold, adjusting volume information and / or frequency information in the target sound effect information; if the current sound effect deviation information is greater than or equal to the second deviation threshold, enhancing a target frequency band in the target sound effect information.

10. A sound effect generating apparatus characterized by comprising: The device comprises: an acquisition module configured to acquire current environment information; a determination module configured to determine target sound field distribution information according to the current environment information; a generation module configured to generate target sound effect information according to the target sound field distribution information.

11. A television characterized by The television comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps in the sound effect generation method of any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium and is executed by the processor to implement the steps in the sound effect generation method of any one of claims 1 to 9.

Images