Information processing method, device, electronic device and storage medium
By collecting and analyzing environmental audio information, the system identifies target noise scenes, solving the problem of misjudgment in the judgment of external noise by electronic devices, enabling more accurate adjustment of audio and video parameters, and improving the user experience.
Patent Information
- Application Number
- CN202110455789.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-04-26
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2041-04-26
AI Technical Summary
In the existing technology, electronic devices cannot accurately judge the external environmental noise when playing audio and video, resulting in misjudgment of volume adjustment, especially in the case of mobile phone calls or ringtones, where it is impossible to distinguish whether the volume needs to be increased.
By collecting environmental audio information and performing noise detection, it is determined whether the target noise scene is characterized. This includes residual echo information processing, frequency band range analysis, noise energy detection, and correlation calculation, ensuring that audio and video parameters are adjusted under the target noise scene.
It improves the accuracy of electronic devices in judging external environmental noise, reduces the misadjustment of audio and video parameters in non-target noise scenarios, and enhances the accuracy of volume adjustment and user experience.
Smart Images

Figure CN113190207B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of electronic technology, and in particular to information processing methods, devices, electronic devices and storage media. Background Art
[0002] In the related art, electronic devices will automatically adjust the parameters of audio and video according to the noise conditions of the external environment during the audio and video playback process. However, this adjustment method often increases the playback volume when the noise volume of the external environment is greater than the preset volume. Obviously, this method is too general and there are many misjudgment scenarios. For example, when the noise of the external environment is a mobile phone call or a mobile phone ringtone, it is often unnecessary to increase the playback volume of the electronic device. Based on this, how to accurately automatically adjust the audio and video parameters of the electronic device based on the noise of the external environment has become a technical problem that needs to be solved urgently. Summary of the invention
[0003] In order to overcome the problems existing in the related art, the present disclosure provides an audio signal adjustment method, device, electronic device and storage medium, and the technical solution is as follows:
[0004] According to a first aspect of an embodiment of the present disclosure, there is provided an information processing method for an electronic device, comprising:
[0005] During the process of playing audio and video by the electronic device, collecting ambient audio information;
[0006] Performing noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene;
[0007] In a case where the environmental audio information represents the target noise scene, parameters of the audio and video played by the electronic device are processed.
[0008] In some embodiments, the performing noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene includes:
[0009] Determine first ambient noise information according to the ambient audio information;
[0010] In a case where the first environmental noise information includes residual echo information, determining a first frequency band range corresponding to the residual echo information;
[0011] Processing the first environmental noise information according to the first frequency band of the residual echo information to obtain second environmental noise information;
[0012] It is determined, according to the second environmental noise information, whether the environmental audio information represents the target noise scene.
[0013] In some embodiments, determining, according to the second environmental noise information, whether the environmental audio information represents the target noise scene includes:
[0014] determining first noise energy of the second environmental noise information according to the second environmental noise information;
[0015] When the first noise energy is greater than an energy threshold, and a duration during which the first noise energy is greater than the energy threshold exceeds a preset period, it is determined that the ambient audio information represents the target noise scene.
[0016] In some embodiments, the preset period includes: a first preset sub-period and a second preset sub-period that are of the same duration and adjacent to each other;
[0017] The determining that the ambient audio information represents the target noise scene when the first noise energy is greater than an energy threshold and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period includes:
[0018] When the first noise energy is greater than an energy threshold, and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period, determining a correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period;
[0019] When the correlation is greater than or equal to a correlation threshold, it is determined that the environmental audio information represents the target noise scene.
[0020] In some embodiments, the method further comprises:
[0021] In a case where the second environmental noise information includes sound information of a specific scene, determining a second frequency band range of the sound information of the specific scene;
[0022] Processing the second environmental noise information according to the second frequency band of the sound information of the specific scene to obtain third environmental noise information;
[0023] The determining the correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period includes:
[0024] Determine the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period.
[0025] In some embodiments, the first preset sub-period and the second preset sub-period each include: a preset number of frame periods;
[0026] The determining the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period includes:
[0027] Determine the first noise sub-energy of each frame period in the third environmental noise information of the first preset sub-period; determine the energy distribution of the first noise sub-energy of the third environmental noise information of the first preset sub-period according to the first noise sub-energy of each frame period;
[0028] Determine the second noise sub-energy of each frame period in the third environmental noise information of the second preset sub-period; determine the energy distribution of the second noise sub-energy of the third environmental noise information of the second preset sub-period according to the second noise sub-energy of each frame period;
[0029] The correlation between the third noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is determined according to the energy distribution of the first noise sub-energy and the energy distribution of the second noise sub-energy.
[0030] In some embodiments, the method further comprises:
[0031] Determine a third noise sub-energy in each frame period of the second noise energy of the first environmental noise in the second preset sub-period;
[0032] In the case where the correlation is greater than or equal to the correlation threshold, determining whether the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets a preset condition;
[0033] When the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, it is determined that the ambient audio information represents the target noise scene, wherein the preset condition is that the frequency spectrum fluctuation represented by the energy ratio exceeds the preset fluctuation.
[0034] In some embodiments, the electronic device includes a plurality of speakers;
[0035] The determining the first environmental noise information according to the environmental audio information comprises:
[0036] According to the environmental audio information collected by the multiple speakers, echo cancellation processing is performed on the environmental audio information to determine the first environmental noise information.
[0037] According to a second aspect of an embodiment of the present disclosure, there is provided an information processing device, which is applied to an electronic device, including:
[0038] A collection module, used to collect ambient audio information during the process of playing audio and video by the electronic device;
[0039] A first determination module, configured to perform noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene;
[0040] The first processing module is used to process parameters of the audio and video played by the electronic device when the environmental audio information represents the target noise scene.
[0041] In some embodiments, the first determining module further includes:
[0042] A first determining submodule, configured to determine first ambient noise information according to the ambient audio information;
[0043] A second determining submodule, configured to determine a first frequency band range corresponding to the residual echo information when the first environmental noise information includes residual echo information;
[0044] a processing submodule, configured to process the first environmental noise information according to the first frequency band of the residual echo information to obtain second environmental noise information;
[0045] The third determination submodule is configured to determine, based on the second environmental noise information, whether the environmental audio information represents the target noise scene.
[0046] In some embodiments, the third determining submodule is further used to:
[0047] determining, according to the second environmental noise information, a first noise energy of the second environmental noise information;
[0048] When the first noise energy is greater than an energy threshold, and a duration during which the first noise energy is greater than the energy threshold exceeds a preset period, it is determined that the ambient audio information represents the target noise scene.
[0049] In some embodiments, the preset period includes: a first preset sub-period and a second preset sub-period that are of the same duration and adjacent to each other;
[0050] The third determining submodule is further used for:
[0051] When the first noise energy is greater than an energy threshold, and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period, determining a correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period;
[0052] When the correlation is greater than or equal to a correlation threshold, it is determined that the environmental audio information represents the target noise scene.
[0053] In some embodiments, the apparatus further comprises:
[0054] A second determining module, configured to determine a second frequency band range of the sound information of a specific scene when the second environmental noise information includes sound information of a specific scene;
[0055] A second processing module, configured to process the second environmental noise information according to the second frequency band of the sound information of a specific scene to obtain third environmental noise information;
[0056] The third determining submodule is further used for:
[0057] Determine the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period.
[0058] In some embodiments, the first preset sub-period and the second preset sub-period each include: a preset number of frame periods;
[0059] The third determining submodule is specifically used for:
[0060] Determine the first noise sub-energy of each frame period in the third environmental noise information of the first preset sub-period; determine the energy distribution of the first noise sub-energy of the third environmental noise information of the first preset sub-period according to the first noise sub-energy of each frame period;
[0061] Determine the second noise sub-energy of each frame period in the third environmental noise information of the second preset sub-period; determine the energy distribution of the second noise sub-energy of the third environmental noise information of the second preset sub-period according to the second noise sub-energy of each frame period;
[0062] The correlation between the third noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is determined according to the energy distribution of the first noise sub-energy and the energy distribution of the second noise sub-energy.
[0063] In some embodiments, the apparatus further comprises:
[0064] A third determination module, configured to determine a third noise sub-energy in each frame period of the second noise energy of the first environmental noise information in the second preset sub-period;
[0065] The third determining submodule is further specifically used for:
[0066] In a case where the correlation is greater than or equal to the correlation threshold, determining whether an energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets a preset condition;
[0067] When the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, it is determined that the ambient audio information represents the target noise scene, wherein the preset condition is that the frequency spectrum fluctuation represented by the energy ratio exceeds the preset fluctuation.
[0068] In some embodiments, the electronic device includes a plurality of speakers;
[0069] The first determining submodule is further used for:
[0070] According to the environmental audio information collected by the multiple speakers, echo cancellation processing is performed on the environmental audio information to determine the first environmental noise information.
[0071] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:
[0072] processor;
[0073] a memory for storing processor-executable instructions;
[0074] Wherein, the processor is configured to: implement any of the above-mentioned information processing methods when executed.
[0075] According to a fourth aspect of the embodiments of the present disclosure, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can perform the steps of implementing any of the above-described information processing methods.
[0076] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:
[0077] In the disclosed embodiments, during the process of playing audio and video by the electronic device, environmental audio information can be collected, and noise detection can be performed on the collected audio information to determine whether the environmental audio information represents a target noise scene. Only when the environmental noise information represents the target noise scene will the parameters of the audio and video played by the electronic device be processed. This makes the electronic device's judgment on the external environmental noise no longer just a judgment on the volume. Instead, the parameters of the audio and video played by the electronic device will be processed only when it is determined that the collected environmental audio information represents the target noise scene. This improves the accuracy of automatic volume adjustment of the electronic device for external environmental noise, reduces the phenomenon of erroneous adjustment of audio and video parameters that are not in the target noise scene, and makes the solution of automatically adjusting the volume of the electronic device based on environmental noise more accurate.
[0078] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0079] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0080] Figure 1 is a flow chart of an information processing method according to an exemplary embodiment;
[0081] Figure 2 is another flow chart of an information processing method according to an exemplary embodiment;
[0082] Figure 3 is another flow chart of an information processing method according to an exemplary embodiment;
[0083] Figure 4 is an energy distribution curve of noise sub-energy of the third environmental noise according to an exemplary embodiment;
[0084] Figure 5 is another energy distribution curve of noise sub-energy of the third environmental noise according to an exemplary embodiment;
[0085] Figure 6 It is a schematic diagram of a scenario of automatically adjusting the volume based on environmental noise in the related art;
[0086] Figure 7 is a schematic diagram of a scenario of automatically adjusting the volume based on environmental noise according to a specific embodiment;
[0087] Figure 8 is a block diagram of an information processing device according to an exemplary embodiment;
[0088] Fig. 9 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0089] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.
[0090] The present disclosure optimizes a scheme for automatically adjusting audio and video parameters based on environmental noise, aiming to achieve a scheme for automatically adjusting audio and video parameters with higher accuracy. Based on this, in order to achieve a scheme for automatically adjusting audio and video parameters with higher accuracy, the present disclosure provides an information processing method.
[0091] The method is applied to electronic devices, which may be mobile terminals, desktop computers, smart home devices, etc. The mobile terminals may be mobile phones, tablet computers, and laptop computers; the smart home devices may be smart TVs or smart speakers, etc. It is understandable that the method may be applied to any electronic device with an audio module, such as an electronic device with a microphone and a speaker.
[0092] Figure 1 is a flowchart of an information processing method according to an exemplary embodiment. Figure 1 As shown, the method may include the following steps:
[0093] Step 11: collecting ambient audio information during the process of the electronic device playing audio and video;
[0094] Step 12: performing noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene;
[0095] Step 13: When the environmental audio information represents the target noise scene, process parameters of the audio and video played by the electronic device.
[0096] The ambient audio information here refers to all audio information in the environment. Exemplarily, the ambient audio information may include, but is not limited to: audio information emitted by the electronic device itself, audio information emitted by other sound sources other than the electronic device, and audio information reflected by a target object, such as a wall.
[0097] The target noise scene here refers to a pre-set related scene that requires audio and video parameter adjustment. For example, the household noise scene of household appliances such as a hair dryer can be the target noise scene described in this embodiment. Of course, in other embodiments, the user can also set other noise scenes as target noise scenes, such as traffic noise on outdoor roads.
[0098] Here, the parameters of the audio and video played by the electronic device may be the volume of the audio and video played by the electronic device. In some embodiments, the processing of the parameters of the audio and video played by the electronic device may include:
[0099] The volume of the audio and video played by the electronic device is increased.
[0100] In some embodiments, the step of increasing the volume of the audio or video played by the electronic device may further include:
[0101] The volume of the audio and video played by the electronic device is increased according to the preset first adjustment amount, for example, by five volume levels. In this way, when the ambient audio information represents the target noise scene, the volume is increased according to the fixed preset first adjustment amount, so that the audio and video played by the electronic device in the target noise scene can be more clearly recognized by the user, and the electronic device does not need to calculate the volume adjustment amount, thereby reducing the computing resources of the electronic device.
[0102] In order to ensure that the audio and video played by the electronic device in the target noise scene can be recognized by the user, in other embodiments, the volume of the audio and video played by the electronic device can be increased, and the volume of the audio and video played by the electronic device can also be increased.
[0103] Determining a second adjustment amount according to the volume in the ambient audio information;
[0104] According to the second adjustment amount, the volume of the audio and video played by the electronic device is increased.
[0105] It is understandable that the volume of the ambient audio information is proportional to the second adjustment amount. In this way, it can be ensured that when the volume of the ambient volume information increases, the adjustment amount is also increased to ensure that the audio and video played by the electronic device in the target noise scene can be recognized by the user.
[0106] Of course, the parameters of the audio and video played by the electronic device may also be the playback speed of the audio and video played by the electronic device. In some embodiments, the processing of the parameters of the audio and video played by the electronic device may include:
[0107] The playing speed of the audio and video played by the electronic device is slowed down.
[0108] In this way, when the ambient audio information represents a target noise scene, by slowing down the playback speed of the audio and video played by the electronic device, the electronic device can slow down the playback in the target noise scene, thereby reducing the amount of audio and video playback that interferes with the audio and video that the user is watching or listening to due to the noise in the target noise scene.
[0109] In the embodiment of the present disclosure, the parameters of the audio and video played by the electronic device are processed only when the environmental audio information represents the target noise scene. Compared with the related art, in which the automatic volume is adjusted only by the noise volume of the external environment, the embodiment of the present disclosure can collect environmental audio information during the process of the electronic device playing audio and video, and perform noise detection on the collected audio information to determine whether the environmental audio information represents the target noise scene, and only when the environmental noise information represents the target noise scene, the parameters of the audio and video played by the electronic device are processed, so that the electronic device's judgment on the external environmental noise is no longer just a judgment on the volume, but the parameters of the audio and video played by the electronic device are processed only when it is determined that the collected environmental audio information represents the target noise scene, thereby improving the accuracy of the electronic device's automatic volume adjustment for the noise of the external environment and reducing the phenomenon of erroneous adjustment of audio and video parameters that are not in the target noise scene.
[0110] In other embodiments, in order to improve the accuracy of determining whether the ambient audio information represents the target noise scene, Figure 2 is another flow chart of an information processing method according to an exemplary embodiment. Figure 2 As shown, the step 12, i.e., performing noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene, may include:
[0111] Step 121: determining first environmental noise information according to the environmental audio information;
[0112] Step 122: when the first environmental noise information includes residual echo information, determining a first frequency band range corresponding to the residual echo information;
[0113] Step 123: Processing the first environmental noise information according to the first frequency band of the residual echo information to obtain second environmental noise information;
[0114] Step 124: Determine, based on the second environmental noise information, whether the environmental audio information represents the target noise scene.
[0115] It is understandable that when an electronic device has multiple speakers, the sounds emitted by the multiple speakers affect each other, so that the electronic device cannot accurately obtain the echo information generated in the environment, so that part of the echo information is left, generating residual echo information. The residual echo information here refers to the part of the echo information that is not eliminated after the echo cancellation processing of the ambient audio information.
[0116] In some embodiments, the electronic device includes a plurality of speakers; the step 121, i.e., determining the first ambient noise information according to the ambient audio information, may include:
[0117] According to the environmental audio information collected by the multiple speakers, echo cancellation processing is performed on the environmental audio information to determine the first environmental noise information.
[0118] Here, the environmental audio information can be collected by a microphone.
[0119] Exemplarily, performing echo cancellation processing on the ambient audio information according to the ambient audio information collected by multiple speakers to determine the first ambient noise information may include:
[0120] Directly perform echo cancellation processing on the environmental audio information collected by multiple speakers to determine the first environmental noise information.
[0121] Exemplarily, directly performing echo cancellation processing on the ambient audio information collected by multiple speakers to determine the first ambient noise information includes:
[0122] When performing echo cancellation on the ambient audio information and speaker information collected by multiple speakers, the same Fourier transform function is reused to calculate and obtain the first ambient noise information.
[0123] Here, the speaker information refers to the parameters of the speaker, such as the factory parameters of the speaker.
[0124] Compared with the prior art, in which the ambient audio information collected by multiple speakers is first Fourier transformed, and then the data obtained after the inverse Fourier transform and the speaker information used in echo elimination are Fourier transformed again to calculate the first ambient noise information, in this embodiment, the same Fourier transform function is reused when echo elimination is performed on the ambient audio information collected by multiple speakers and the speaker information to calculate the first ambient noise information, which can reduce the amount of calculation of multiple Fourier transforms and inverse transforms on the ambient audio information collected by multiple speakers, and at the same time reduce the inaccurate echo elimination caused by data omissions in the process of performing multiple Fourier transforms and inverse transforms on the ambient audio collected by multiple speakers.
[0125] Here, before performing echo cancellation on the ambient audio information and speaker information collected by multiple speakers, the method further includes: preprocessing the ambient audio information and the speaker information.
[0126] The preprocessing of the ambient audio information and the speaker information may include: performing frame-by-frame windowing processing on the ambient audio information and the speaker information.
[0127] For example, the ambient audio information s(n) and the speaker information y(n) are framed and windowed, taking the sampling rate as 16000, and the window function is w(n), the frame length is 16ms and the shift is 8ms, and the window function can be any one of the common Hanning window or Hamming window. After framed and windowed, s(n,m) and y(n,m) are obtained, where m represents the index of the frame number. For details of framed and windowed, please refer to expressions (1) and (2):
[0128] s(n,m)=s((m-1)*inc+n)*w(n),1≤n≤L (1)
[0129] y(n,m)=y((m-1)*inc+n)*w(n),1≤n≤L (2)
[0130] Among them, m represents the index of the frame number, L represents the frame length, taking 256 as an example, inc represents the frame shift, taking 128 as an example, the input of echo cancellation is s(n,m) and y(n,m), and the output is the first environmental noise information with the echo information removed, such as the spectrum information S(k,m) of the ambient audio, where k represents the index of the spectrum information after Fourier transform.
[0131] Ideally, S(k,m) does not contain any echo information of the microphone, but in practical applications, existing algorithms will retain a lot of echo information under multi-channel playback devices.
[0132] To reduce the interference of the residual echo information, in step 122 of the embodiment of the present disclosure, when the first environmental noise information includes the residual echo information, a first frequency band range corresponding to the residual echo information is determined.
[0133] Here, the first frequency band range of the residual echo information may be pre-set in the electronic device. Exemplarily, the step 122, i.e., the determining of the first frequency band range corresponding to the residual echo information, may include: reading the first frequency band range of the residual echo information pre-set in the electronic device. It is understandable that the first frequency band range of the residual echo information may be detected by an external instrument or by an experiment. Here, by means of experimental detection, for example, the noise information detected in the playback scene and the non-playback scene may be compared under the same noise environment provided, and the frequency band range of the echo information may be determined, and the frequency band range of the echo information may be used as the first frequency band range of the residual echo information. In other embodiments, the first frequency band range of the residual echo information may also be read from a cloud server.
[0134] Exemplarily, the first frequency range of the residual echo information may be less than or equal to the range of the 1200 Hz frequency range.
[0135] It is understandable that, since the first environmental noise information contains residual echo information, that is, the first environmental noise information cannot represent the real environmental noise information, in the related art, since the residual echo information is not removed, the first environmental noise information is used as the real environmental noise information, which obviously makes the judgment result inaccurate. Here, step 123, that is, according to the first frequency band range of the residual echo information, the first environmental noise information is processed to obtain the second environmental noise information. Exemplarily, the first environmental noise information is processed according to the first frequency band range of the residual echo information to obtain the second environmental noise information, which may include: selecting the first environmental noise information of the frequency band outside the first frequency band range from the first environmental noise information to obtain the second environmental noise information. In this way, using the second environmental noise information as the real environmental noise information can improve the accuracy of judging whether the environmental noise information is the target noise information, and at the same time, since the first frequency band range is removed during the calculation, the amount of calculation can also be reduced.
[0136] In some other embodiments, see Figure 3 ,like Figure 3 As shown, determining whether the ambient sound information represents a target noise scene according to the second ambient noise information may include:
[0137] Step 1241: determining first noise energy of the second environmental noise information according to the second environmental noise information;
[0138] Step 1242: When the first noise energy is greater than an energy threshold, and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period, determine that the ambient audio information represents the target noise scene.
[0139] Here, here, the first noise energy may be the energy of the second noise information in a predetermined time period. Exemplarily, the first noise energy may be the sliding energy of the second noise information in a predetermined time period.
[0140] The energy threshold here may be the lowest energy of the actual ambient noise in the noise scene corresponding to the target noise information within a preset time period.
[0141] It should be supplemented that, in some embodiments, the preset duration may include multiple frame durations, wherein the multiple frame durations may be integrated into multiple segment data, wherein one segment data may include multiple frames.
[0142] When calculating the first noise energy, the noise energy of each frame of the second environmental noise is first calculated. Exemplarily, the noise energy Se(m) of each frame is calculated using expression (3);
[0143]
[0144] m represents the index of the frame number, N represents the length of the Fourier transform, generally N=L; r represents the lowest frequency point when calculating the second environmental noise of a frame. Here, taking the frequency band range of the residual echo information as less than 1200Hz as an example, r here can be 20. In this embodiment, dividing by N when calculating the noise energy of each frame can prevent the numerical overflow problem when calculating the noise energy.
[0145] For example, 4 frames of data are used as 1 segment of data, and the energy of 1 segment of data is calculated as the comprehensive energy of 4 frames of data. Expression (4) is used to calculate the comprehensive energy of 4 frames of data:
[0146]
[0147] Among them, a is the index of the segment data.
[0148] For example, 10 segments of data are used to calculate the comprehensive energy of the 10 segments of data using expression (5):
[0149]
[0150] In this way, by calculating multiple segment data as a first noise energy, compared with the related art in which the audio parameters are adjusted as long as the noise energy is greater than the energy threshold, this embodiment determines that the ambient audio information represents the target noise scene when the first noise energy is greater than the energy threshold and the duration of the first noise energy being greater than the energy threshold exceeds the preset period, so that the audio parameters are adjusted based on the target noise scene with higher accuracy, reducing the phenomenon of misadjustment in short-term non-target noise scenes.
[0151] In order to further improve the accuracy of determining the target environment noise information, as another optional embodiment, the preset period includes: a first preset sub-period and a second preset sub-period that are of the same duration and adjacent to each other;
[0152] The determining that the ambient audio information represents the target noise scene when the first noise energy is greater than an energy threshold and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period includes:
[0153] When the first noise energy is greater than an energy threshold, and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period, determining a correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period;
[0154] When the correlation is greater than or equal to a correlation threshold, it is determined that the environmental audio information represents the target noise scene.
[0155] It should be noted that the preset period includes a first preset sub-period and a second preset sub-period of the same duration and adjacent to each other, which means that the first preset sub-period and the second preset sub-period are both within the preset period, but the sum of the first preset sub-period and the second preset sub-period may not be the preset period. For example, if the preset period is 2.5 seconds, then the first preset sub-period may be a period from 0.5 seconds to 1.5 seconds, and the second preset sub-period may be a period from 1.5 seconds to 2.5 seconds.
[0156] In some embodiments, the first preset sub-period may be a period after the third preset sub-period, where the third preset sub-period may be the same as the first preset sub-period or may be different from the first preset sub-period. In this embodiment, after detecting that the first noise energy of the second environmental noise information is greater than the energy threshold in the third preset sub-period, the correlation between the first preset sub-period and the second preset sub-period of the second environmental noise information is calculated, that is, the correlation calculation is performed after the noise information tends to be stable, which can improve the accuracy of the judgment and reduce the unnecessary calculation caused by unstable noise information or short-term noise information.
[0157] Here, the correlation between the second environmental noise information of the first preset sub-period and the environmental noise information of the second preset sub-period may include: a difference between the noise energy of the second environmental noise information of the first preset sub-period and the noise energy of the environmental noise information of the second preset sub-period.
[0158] Of course, in order to accurately judge the correlation, the correlation between the second environmental noise information of the first preset sub-period and the environmental noise information of the second preset sub-period may also include: the overlap between the energy distribution curve of the noise energy of the second environmental noise information of the first preset sub-period and the energy distribution curve of the noise energy of the environmental noise information of the second preset sub-period. In short, the more the second environmental noise information of the first preset sub-period is correlated with the environmental noise information of the second preset sub-period, the more stable the noise information is, that is, the greater the possibility that the second environmental noise information is the target noise information.
[0159] In this embodiment, by judging the correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period, when the correlation is greater than or equal to a correlation threshold, the second environmental noise information is determined to be target noise information, thereby improving the accuracy of judging whether it is target noise information.
[0160] In order to simplify the calculation, as another optional embodiment, the method further includes:
[0161] In a case where the second environmental noise information includes sound information of a specific scene, determining a second frequency band range of the sound information of the specific scene;
[0162] Processing the second environmental noise information according to the second frequency band of the sound information of the specific scene to obtain third environmental noise information;
[0163] The determining of the correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period may include:
[0164] Determine the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period.
[0165] Here, the sound of a specific scene can be, for example, a mobile phone ringtone, a person's voice, etc. Since these sounds are not target noise information, the frequency band where these sounds are located can be directly eliminated, and only the second environmental noise information outside the second frequency band can be calculated. In this way, the amount of calculation can be reduced and the calculation efficiency can be improved. At the same time, since the instability of the sound of a person's voice is strong, the interference when comparing the noise energy within the preset time period is relatively large, so the accuracy of comparing the correlation between the second environmental noise in the first preset time period and the second preset time period can also be improved.
[0166] In order to further improve the accuracy of correlation comparison, as another optional embodiment, the first preset sub-period and the second preset sub-period both include: a preset number of frame periods;
[0167] The determining of the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period may include:
[0168] Determine the first noise sub-energy of each frame period in the third environmental noise information of the first preset sub-period; determine the energy distribution of the first noise sub-energy of the third environmental noise information of the first preset sub-period according to the first noise sub-energy of each frame period;
[0169] Determine the second noise sub-energy of each frame period in the third environmental noise information of the second preset sub-period; determine the energy distribution of the second noise sub-energy of the third environmental noise information of the second preset sub-period according to the second noise sub-energy of each frame period;
[0170] The correlation between the third noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is determined according to the energy distribution of the first noise sub-energy and the energy distribution of the second noise sub-energy.
[0171] For example, see Figure 4 ,like Figure 4 As shown, the energy distribution curve 41 of the first noise sub-energy in each frame period of the third environmental noise information of the first preset sub-period and the energy distribution curve 42 of the second noise sub-energy in each frame period of the third environmental noise information of the second preset sub-period have a degree of overlap that is greater than the overlap threshold, that is, the correlation between the third noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is greater than the correlation threshold.
[0172] In some other embodiments, see Figure 5 ,like Figure 5 As shown, the energy distribution curve 51 of the first noise sub-energy in each frame period in the third environmental noise information of the first preset sub-period and the energy distribution curve 52 of the second noise sub-energy in each frame period in the third environmental noise information of the second preset sub-period have a degree of overlap that is less than the overlap threshold, that is, the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is less than the correlation threshold.
[0173] It should be added that, in some embodiments, the noise energy of a predetermined number of frame periods is first counted so as to draw an energy distribution curve. Here, the predetermined number is smaller than the preset number.
[0174] For example, 4 frames of data are still used as 1 segment of data, and the energy of 1 segment of data is calculated as the comprehensive energy of 4 frames of data. Expression (4) is used to calculate the comprehensive energy of 4 frames of data:
[0175]
[0176] Among them, a is the index of the segment data.
[0177] In order to draw the energy curve more smoothly, a set number of segments can be used to draw the energy distribution curve. For example, 10 segments of data are used to calculate the comprehensive energy of the 10 segments of data using expression (5):
[0178]
[0179] Based on this, a smoother energy distribution curve can be drawn, so that the overlap of the correlation can be determined and then the correlation of the third environmental noise information in the first preset time period and the second preset time period can be accurately determined.
[0180] When performing correlation calculation, taking the first preset time period of 0.5s to 1.5s and the second preset time period of 1.5s to 2.5s as an example, the noise energy is stored starting from 0.5s when the first noise energy is greater than the energy threshold, and each segment Sblock(a) is calculated using the splicing method of 4 frames of sub-energy using expression (6).
[0181]
[0182] Here, r is 40, which means that only the spectrum information of the frequency band greater than 2400 Hz is used, which reduces the interference of residual echo and sound of specific scenes on the correlation calculation and reduces the amount of calculation.
[0183] According to expression (7), the noise energy means from 0.5 seconds to 1.5 seconds and 2.5 seconds are determined respectively.
[0184]
[0185] Here, the value of c is 31, so the average value of the noise energy of 1 s is approximately selected.
[0186] Here, when calculating the correlation, the correlation between Sblockmean(0.5) and Sblockmean(1.5) can be calculated using the Pearson correlation coefficient.
[0187] In some embodiments, the correlation threshold may be 0.85. Of course, in other embodiments, the correlation threshold may also take other values. The value of the correlation threshold may be determined according to the noise type corresponding to the noise scene, etc. It is understandable that different noise types correspond to different noise stability, wherein the stability of the noise is positively correlated with the noise threshold. For example, in a home noise scene, the correlation threshold may be 0.85.
[0188] In order to further improve the accuracy of determining the target noise information, as another optional embodiment, the method further includes:
[0189] In a case where the correlation is greater than or equal to the correlation threshold, determining whether an energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets a preset condition;
[0190] When the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, it is determined that the ambient audio information represents the target noise scene, wherein the preset condition is that the frequency spectrum fluctuation represented by the energy ratio exceeds the preset fluctuation.
[0191] In some embodiments, the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, which may include: determining the mean of the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period; if the mean is greater than the mean threshold, determining that the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition.
[0192] In other embodiments, the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, which may include: determining the standard deviation of the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period; if the standard deviation is less than the standard deviation threshold, determining that the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition.
[0193] It can be understood that if the mean of the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period is greater than the mean threshold, or the standard deviation of the second noise sub-energy to the third noise sub-energy in each frame period is less than the standard deviation threshold, it indicates that the spectrum information distribution of the second ambient noise is relatively uniform and the spectrum fluctuation is small, and it can be identified as target noise information.
[0194] In some embodiments, when the standard deviation of the energy ratio is lower than 0.1 and the energy mean is higher than 0.012, it indicates that target noise information is detected.
[0195] In this way, by further determining whether the second environmental noise information is the target noise information based on the mean and standard deviation of the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period, the accuracy of the determination can be improved.
[0196] As another optional embodiment, the method further includes:
[0197] If the correlation is less than the correlation threshold, it is determined that the ambient audio information does not represent the target noise scene.
[0198] In this way, the phenomenon of misadjustment of the audio and video parameters of the electronic device when the electronic device is not in the target noise scene can be reduced.
[0199] Furthermore, the present disclosure also provides a specific embodiment to further understand the information processing method provided by the embodiment of the present disclosure.
[0200] The method described in this embodiment is specifically applied to electronic devices, especially to smart TVs; the audio module described in this embodiment includes a speaker of the smart TV and a microphone of the smart TV. The noise scene in this embodiment takes a home noise scene as an example. For example, home noises are noises from a sweeping robot, a hair dryer, a smoke extractor, or a wall breaker. When a user is watching a TV program, if there are these noises, the volume of the TV needs to be turned up.
[0201] See also Figure 6 , Figure 6 is a schematic diagram of a scene in which the volume is automatically adjusted based on ambient noise in the related art, such as Figure 6 As shown, when the microphone of the smart TV collects household noise, it will perform noise detection and adjust the volume based on the detection result of the noise detection. In the related art, the accuracy of noise detection is low, and usually only the noise volume is judged, and it is impossible to judge in combination with the scene. For example, when the user makes a phone call, the noise volume will increase. If the volume is also increased at this time, it is obviously not in line with the current scene. In addition, the judgment of the noise scene often requires the use of more complex neural network algorithms, etc., which is obviously more complicated to implement.
[0202] Based on this, how to achieve an automatic volume adjustment solution with higher accuracy and simpler calculation has become a technical problem that needs to be solved urgently.
[0203] See also Figure 7 , Figure 7 FIG. 1 is a schematic diagram of a scenario in which the volume is automatically adjusted based on ambient noise according to a specific embodiment. Figure 7 As shown, in this embodiment, noise detection and analysis are optimized. Exemplarily, in the process of using ambient sound detection information and speaker information to perform echo cancellation, due to the presence of residual echo information, the first frequency band of the residual echo information is removed in the step of noise energy detection, and the ambient noise information of the frequency bands other than the first frequency band is calculated, that is, the second ambient noise information described in the above embodiment. In this way, not only the amount of calculation can be reduced, but also the residual echo information can be removed, thereby improving the accuracy of the analysis object of the noise analysis.
[0204] During correlation detection, not only the second frequency band of the sound of a specific scene is removed, but also a smooth correlation comparison is performed frame by frame or segment by segment, that is, by comparing the energy distribution of the first noise sub-energy of the third environmental noise information of the first preset sub-time period described in the above embodiment with the overlap of the curve of the energy distribution of the second noise sub-energy of the third environmental noise information of the second preset sub-time period, the accuracy of the correlation comparison can be improved, thereby improving the accuracy of the noise analysis.
[0205] After the correlation is greater than the correlation threshold, spectrum fluctuation detection is performed, that is, only when the mean of the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period is greater than the mean threshold, and the standard deviation of the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period is less than the standard deviation threshold, the second environmental noise information is determined to be the target noise information. That is, only when the spectrum fluctuation of the third environmental noise information is small, that is, the noise is relatively stable, is it determined to be household noise, for example, continuous and stable noise such as a hair dryer.
[0206] In this way, after the triple detection of noise energy detection, correlation detection and spectrum fluctuation detection, it is determined whether the environmental noise is the target noise, which can obviously improve the accuracy of target noise detection. At the same time, since the first frequency band where the residual echo information is located is removed during the noise energy detection process, and the second frequency band of the sound of the specific scene is removed during the correlation detection process, the amount of calculation can also be reduced.
[0207] In the above-mentioned embodiment, the accuracy of target noise detection is ensured under low computational complexity, the solution of automatically adjusting the volume based on ambient noise in the related art is optimized, and the auditory experience of the electronic device is improved.
[0208] Figure 8 is an information processing device according to an exemplary embodiment, referring to Figure 8 , the device comprises:
[0209] A collection module 81 is used to collect ambient audio information during the process of playing audio and video by the electronic device;
[0210] A first determination module 82, configured to perform noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene;
[0211] The first processing module 83 is used to process the parameters of the audio and video played by the electronic device when the ambient audio information represents the target noise scene.
[0212] In some optional embodiments, the first determining module 82 further includes:
[0213] A first determining submodule, configured to determine first ambient noise information according to the ambient audio information;
[0214] A second determining submodule, configured to determine a first frequency band range corresponding to the residual echo information when the first environmental noise information includes residual echo information;
[0215] a processing submodule, configured to process the first environmental noise information according to the first frequency band of the residual echo information to obtain second environmental noise information;
[0216] The third determination submodule is configured to determine, based on the second environmental noise information, whether the environmental audio information represents the target noise scene.
[0217] In some optional embodiments, the third determining submodule is further used to:
[0218] determining first noise energy of the second environmental noise information according to the second environmental noise information;
[0219] When the first noise energy is greater than an energy threshold, and a duration during which the first noise energy is greater than the energy threshold exceeds a preset period, it is determined that the ambient audio information represents the target noise scene.
[0220] In some optional embodiments, the preset period includes: a first preset sub-period and a second preset sub-period that are of the same duration and adjacent to each other;
[0221] The third determining submodule is further used for:
[0222] When the first noise energy is greater than an energy threshold, and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period, determining a correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period;
[0223] When the correlation is greater than or equal to a correlation threshold, it is determined that the environmental audio information represents the target noise scene.
[0224] In some optional embodiments, the device further comprises:
[0225] A second determining module, configured to determine a second frequency band range of the sound information of a specific scene when the second environmental noise information includes sound information of a specific scene;
[0226] A second processing module, configured to process the second environmental noise information according to the second frequency band of the sound information of a specific scene to obtain third environmental noise information;
[0227] The third determining submodule is further used for:
[0228] Determine the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period.
[0229] In some optional embodiments, the first preset sub-period and the second preset sub-period both include: a preset number of frame periods;
[0230] The third determining submodule is specifically used for:
[0231] Determine the first noise sub-energy of each frame period in the third environmental noise information of the first preset sub-period; determine the energy distribution of the first noise sub-energy of the third environmental noise information of the first preset sub-period according to the first noise sub-energy of each frame period;
[0232] Determine the second noise sub-energy of each frame period in the third environmental noise information of the second preset sub-period; determine the energy distribution of the second noise sub-energy of the third environmental noise information of the second preset sub-period according to the second noise sub-energy of each frame period;
[0233] The correlation between the third noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is determined according to the energy distribution of the first noise sub-energy and the energy distribution of the second noise sub-energy.
[0234] In some optional embodiments, the device further comprises:
[0235] A third determination module, configured to determine a third noise sub-energy in each frame period of the second noise energy of the first environmental noise information in the second preset sub-period;
[0236] The third determining submodule is further specifically used for:
[0237] In a case where the correlation is greater than or equal to the correlation threshold, determining whether an energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets a preset condition;
[0238] When the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, it is determined that the ambient audio information represents the target noise scene, wherein the preset condition is that the frequency spectrum fluctuation represented by the energy ratio exceeds the preset fluctuation.
[0239] In some optional embodiments, the electronic device includes a plurality of speakers;
[0240] The first determining submodule is further used for:
[0241] According to the environmental audio information collected by the multiple speakers, echo cancellation processing is performed on the environmental audio information to determine the first environmental noise information.
[0242] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0243] Fig. 9 1 is a block diagram of an electronic device 900 according to an exemplary embodiment. For example, the electronic device 900 may be a mobile phone, a computer, a digital broadcast electronic device, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
[0244] Reference Fig. 9 , the electronic device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .
[0245] The processing component 902 generally controls the overall operation of the electronic device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.
[0246] The memory 904 is configured to store various types of data to support operations on the electronic device 900. Examples of such data include instructions for any application or method operating on the electronic device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0247] The power component 906 provides power to the various components of the electronic device 900. The power component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 900.
[0248] The multimedia component 908 includes a screen that provides an output interface between the electronic device 900 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and / or a rear camera. When the electronic device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
[0249] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the electronic device 900 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 904 or sent via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.
[0250] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.
[0251] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the electronic device 900. For example, the sensor assembly 914 can detect the open / closed state of the electronic device 900, the relative positioning of components, such as the display and keypad of the electronic device 900, and the sensor assembly 914 can also detect the position change of the electronic device 900 or a component of the electronic device 900, the presence or absence of contact between the user and the electronic device 900, the orientation or acceleration / deceleration of the electronic device 900, and the temperature change of the electronic device 300. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
[0252] The communication component 916 is configured to facilitate wired or wireless communication between the electronic device 900 and other devices. The electronic device 900 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 916 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 916 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0253] In an exemplary embodiment, the electronic device 900 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.
[0254] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the instructions can be executed by a processor 920 of an electronic device 900 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0255] A non-temporary computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the information processing methods described in the above embodiments.
[0256] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.
[0257] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. An information processing method, characterized in that: For use in electronic equipment, including: During the process of playing audio and video by the electronic device, collecting ambient audio information; Performing noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene; In a case where the environmental audio information represents the target noise scene, processing parameters of the audio and video played by the electronic device; The performing noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene includes: Determine first ambient noise information according to the ambient audio information; In a case where the first environmental noise information includes residual echo information, determining a first frequency band range corresponding to the residual echo information; Processing the first environmental noise information according to the first frequency band of the residual echo information to obtain second environmental noise information; It is determined, according to the second environmental noise information, whether the environmental audio information represents the target noise scene.
2. The method according to claim 1, characterized in that The determining, according to the second environmental noise information, whether the environmental audio information represents the target noise scene includes: determining, according to the second environmental noise information, a first noise energy of the second environmental noise information; When the first noise energy is greater than an energy threshold, and a duration during which the first noise energy is greater than the energy threshold exceeds a preset period, it is determined that the ambient audio information represents the target noise scene.
3. The method according to claim 2, characterized in that The preset time period includes: a first preset sub-period and a second preset sub-period that are of the same length and adjacent to each other; The determining that the ambient audio information represents the target noise scene when the first noise energy is greater than an energy threshold and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period includes: When the first noise energy is greater than an energy threshold, and the duration during which the first noise energy is greater than the energy threshold exceeds a preset period, determining a correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period; When the correlation is greater than or equal to a correlation threshold, it is determined that the environmental audio information represents the target noise scene.
4. The method according to claim 3, characterized in that The method further comprises: In a case where the second environmental noise information includes sound information of a specific scene, determining a second frequency band range of the sound information of the specific scene; Processing the second environmental noise information according to the second frequency band of the sound information of the specific scene to obtain third environmental noise information; The determining the correlation between the second environmental noise information of the first preset sub-period and the second environmental noise information of the second preset sub-period includes: Determine the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period.
5. The method according to claim 4, characterized in that The first preset sub-period and the second preset sub-period both include: a preset number of frame periods; The determining the correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period includes: Determine the first noise sub-energy of each frame period in the third environmental noise information of the first preset sub-period; determine the energy distribution of the first noise sub-energy of the third environmental noise information of the first preset sub-period according to the first noise sub-energy of each frame period; Determine the second noise sub-energy of each frame period in the third environmental noise information of the second preset sub-period; determine the energy distribution of the second noise sub-energy of the third environmental noise information of the second preset sub-period according to the second noise sub-energy of each frame period; The correlation between the third environmental noise information of the first preset sub-period and the third environmental noise information of the second preset sub-period is determined according to the energy distribution of the first noise sub-energy and the energy distribution of the second noise sub-energy.
6. The method according to claim 5, characterized in that The method further comprises: Determine a third noise sub-energy in each frame period of the second noise energy of the first environmental noise information in the second preset sub-period; When the correlation is greater than or equal to a correlation threshold, determining that the ambient audio information represents the target noise scene includes: In a case where the correlation is greater than or equal to the correlation threshold, determining whether an energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets a preset condition; When the energy ratio of the second noise sub-energy to the third noise sub-energy in each frame period meets the preset condition, it is determined that the ambient audio information represents the target noise scene, wherein the preset condition is that the frequency spectrum fluctuation represented by the energy ratio exceeds the preset fluctuation.
7. The method according to claim 1, characterized in that The electronic device includes a plurality of speakers; The determining the first environmental noise information according to the environmental audio information includes: According to the environmental audio information collected by the multiple speakers, echo cancellation processing is performed on the environmental audio information to determine the first environmental noise information.
8. An information processing device, characterized in that: For use in electronic equipment, including: A collection module, used to collect ambient audio information during the process of playing audio and video by the electronic device; A first determination module is used to perform noise detection on the ambient audio information to determine whether the ambient audio information represents a target noise scene; A first processing module, configured to process parameters of the audio and video played by the electronic device when the ambient audio information represents the target noise scene; The first determining module further includes: A first determining submodule, configured to determine first ambient noise information according to the ambient audio information; A second determining submodule, configured to determine a first frequency band range corresponding to the residual echo information when the first environmental noise information includes residual echo information; a processing submodule, configured to process the first environmental noise information according to the first frequency band of the residual echo information to obtain second environmental noise information; The third determination submodule is configured to determine, based on the second environmental noise information, whether the environmental audio information represents the target noise scene.
9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: implement the method described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement the method according to any one of claims 1 to 7.
