Sound effect recommendation method, system and equipment based on sound reverberation suppression and white noise

Abstract

The invention relates to the technical field of signal processing, in particular to a sound effect recommendation method, system and device based on sound reverberation suppression and white noise, and the method comprises the steps: carrying out the preprocessing of an in-vehicle sound signal collected in real time; performing spectral analysis on the preprocessed sound signals, judging sound sources and types, and extracting sound features; collecting user operation data through a user interaction interface, and constructing a white noise sound effect preference model; according to the sound features and a pre-constructed preference model, sound effects meeting constraint conditions are screened from a user-defined sound effect database to serve as recommended white noise sound effects; and mixing the recommended white noise sound effect with the original audio signal in the vehicle, dynamically adjusting the sound mixing proportion, and playing through a loudspeaker. According to the scheme, the in-vehicle sound signals are collected in real time, reverberation suppression processing is carried out, the adaptive white noise sound effect is accurately recommended by combining personalized preferences of the user, and the in-vehicle audio experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a method, system and device for recommending sound effects based on sound reverberation suppression and white noise. Background Art

[0002] While driving, the interior of a vehicle is subject to various noise disturbances, including engine noise, tire noise, and wind noise. These noises not only affect the auditory comfort of passengers but also interfere with the audio playback quality of the vehicle's multimedia system. For example, when driving on the highway, strong wind and engine noise can make the music in the car unclear, seriously affecting the passengers' listening enjoyment.

[0003] Reverberation is the continuous reverberation of sound after multiple reflections within a closed or semi-enclosed space before the original sound fades away. In a car, reverberation can muddy the sound, reducing clarity and spatial perception. This effect is particularly pronounced in relatively confined car spaces, further exacerbating the interference of in-car noise with audio playback.

[0004] While some sound effect recommendation systems currently exist, most lack the ability to perceive and analyze the actual in-car acoustic environment in real time, making it impossible to dynamically adjust sound effect recommendation strategies based on the specific noise levels inside the vehicle. Furthermore, existing systems rarely consider individual user preferences, and the recommended sound effects often fail to meet the diverse needs of different users. Summary of the Invention

[0005] The purpose of the present invention is to provide a sound effect recommendation method, system and device based on sound reverberation suppression and white noise. By real-time acquisition of in-car sound signals, reverberation suppression processing is performed, and the user's personalized preferences are combined to accurately recommend adapted white noise sound effects, thereby effectively shielding the noise in the car, improving the clarity and comfort of in-car audio playback, and meeting the personalized needs of different users.

[0006] The purpose of the present invention is achieved by adopting the following technical solutions:

[0007] According to one embodiment of the present invention, a method for recommending sound effects based on sound reverberation suppression and white noise is provided, comprising:

[0008] Pre-process the real-time collected in-car sound signals;

[0009] Perform spectrum analysis on the pre-processed sound signal to determine the sound source and type and extract sound features;

[0010] Collect user operation data through the user interaction interface and build a white noise sound effect preference model;

[0011] Based on the sound characteristics and the pre-built preference model, the sound effects that meet the constraints are selected from the custom sound effect database as the recommended white noise sound effects;

[0012] The recommended white noise sound effect is mixed with the original audio signal in the car, and the mixing ratio is dynamically adjusted before playing through the speakers.

[0013] In an exemplary embodiment, the pre-processing of the real-time collected in-vehicle sound signal includes:

[0014] Microphone arrays distributed on the vehicle doors and roof are used to collect sound signals inside the vehicle;

[0015] The in-vehicle sound signal is pre-amplified and subjected to anti-aliasing filtering processing.

[0016] In an exemplary embodiment, performing spectrum analysis on the pre-processed sound signal, determining the sound source and type, and extracting sound features includes:

[0017] Using a short-time Fourier transform algorithm, the time-domain signal is converted into a frequency-domain signal, and the specific noise source and type are obtained by matching it with known noise patterns in a sound feature database; and the noise source and type are defined as sound features;

[0018] The sound effect database is used to store a variety of different types of white noise sound effects, each of which has specific frequency characteristics and noise reduction effects.

[0019] In an exemplary embodiment, the construction of the above-mentioned white noise sound effect preference model includes: collecting the user's operation data on the white noise sound effect through a user interaction interface, analyzing the user's operation data on the white noise sound effect using a neural network algorithm, determining the user's preference weights for different sound features, and constructing a white noise sound effect preference model.

[0020] In an exemplary embodiment, the user interaction interface is a touch screen or button of an in-vehicle multimedia system, which is used to collect user operation data and display recommended white noise sound effect information.

[0021] In an exemplary embodiment, the above constraint condition includes: with respect to the current sound condition of the vehicle, preferentially selecting from high-energy low-frequency white noise for masking low-frequency sounds and high-frequency-emphasized white noise for masking high-frequency sounds.

[0022] In an exemplary embodiment, the above-mentioned mixing of the recommended white noise sound effect with the original audio signal in the car, dynamically adjusting the mixing ratio and then playing it through the speaker includes: determining the mixing ratio according to the noise intensity and the noise reduction effect of the white noise sound effect, continuously monitoring the noise and audio output in the car during the playback process, and if the noise intensity or frequency changes, dynamically adjusting the volume and frequency characteristics of the white noise sound effect, and optimizing the mixing ratio again before playing it through the speaker.

[0023] According to one embodiment of the present invention, a sound effect recommendation system based on sound reverberation suppression and white noise is provided, comprising:

[0024] The real-time sound acquisition module is used to pre-process the real-time collected in-vehicle sound signals;

[0025] The sound feature analysis module is used to perform spectrum analysis on the pre-processed sound signal, determine the source and type of the sound, and extract the sound features;

[0026] User preference data collection and modeling module, used to collect user operation data through the user interaction interface and build a white noise sound effect preference model;

[0027] The sound effect matching recommendation module is used to filter sound effects that meet the constraints from the custom sound effect database based on sound characteristics and a pre-built preference model, and use them as recommended white noise sound effects;

[0028] The audio mixing and playback module is used to mix the recommended white noise sound effect with the original audio signal in the car, dynamically adjust the mixing ratio, and then play it through the speaker.

[0029] According to another embodiment of the present invention, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps of any one of the above method embodiments.

[0030] According to another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0031] Through the present invention, users can collect in-car sound signals in real time, perform reverberation suppression processing, and accurately recommend adaptive white noise sound effects based on user personalized preferences. This can not only improve the in-car audio experience, but also improve the clarity and comfort of in-car audio playback, meeting the personalized needs of different users.

[0032] In terms of precise noise reduction, the present invention can accurately analyze the sound characteristics inside the car in real time, and recommend the most effective white noise sound effect for shielding sounds of different types and frequencies. Compared with traditional noise reduction methods, the noise reduction effect is more accurate and comprehensive. In terms of personalized experience, by learning the user's preferences for white noise sound effects, each user is provided with sound effect recommendations that meet their personal preferences, meeting the diverse needs of users and improving their comfort and satisfaction in the car. In terms of audio compatibility, while effectively shielding noise, the system can reasonably handle the mixing of white noise sound effects with other audio signals in the car, ensuring that users can normally enjoy audio services such as music and navigation without affecting the integrity of the in-car audio experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0034] Figure 1 This is a flow chart of a sound effect recommendation method based on sound reverberation suppression and white noise according to an embodiment of the present invention;

[0035] Figure 2 This is a structural block diagram of a sound effect recommendation system based on sound reverberation suppression and white noise according to an embodiment of the present invention;

[0036] Figure 3 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0038] The sound effect recommendation method based on sound reverberation suppression and white noise provided in the embodiment of the present application can be applied to various types of automotive application environments. By real-time acquisition of in-car sound signals, reverberation suppression processing can be performed, and adaptive white noise sound effects can be accurately recommended, which can effectively shield common in-car noises such as engine noise, tire noise, and wind noise, and improve the clarity of in-car audio playback. The sound effects are recommended in combination with the user's personalized preferences, so that the recommended white noise sound effects can not only effectively shield noise, but also meet the user's auditory preferences, providing a more comfortable and personalized audio experience for passengers in the car. In particular, during the playback process, the in-car noise and audio output can be continuously monitored, the volume and frequency characteristics of the white noise sound effects can be dynamically adjusted, and the mixing ratio can be optimized to ensure that good noise reduction effects and audio playback quality can be maintained in different driving environments.

[0039] Furthermore, the method can be applied to automotive terminal devices, servers, or systems comprising terminals and servers, and implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, tablet computers, and the like.

[0040] (1) Hardware composition:

[0041] Microphone arrays, installed on vehicle doors, roofs, and other locations, collect sound signals from within the vehicle. They use highly sensitive, low-noise microphones to ensure high-quality sound signals.

[0042] The preamplifier and anti-aliasing filter are connected to the microphone array to perform pre-amplification and anti-aliasing filtering on the collected sound signals. The preamplifier uses a low-noise, high-gain operational amplifier, and the anti-aliasing filter uses a high-quality filter chip.

[0043] The audio processing chip is responsible for processing algorithms such as sound feature analysis, sound effect matching, and recommendation. With powerful computing capabilities and a rich set of interfaces, the audio processing chip can process large amounts of sound data in real time.

[0044] The user interaction interface can be a touch screen, buttons, etc. of the in-car multimedia system, which is used to collect user operation data and display recommended white noise sound effects and other information.

[0045] The speaker is used to play the mixed audio signal. The speaker uses a high-quality audio unit to ensure that the sound played has good sound quality.

[0046] (2) Software Process:

[0047] In this embodiment, a sound effect recommendation method based on sound reverberation suppression and white noise is provided. Figure 1 As shown, the process includes the following steps:

[0048] Step S101, pre-processing the real-time collected in-vehicle sound signal;

[0049] Step S102, performing spectrum analysis on the pre-processed sound signal to determine the sound source and type and extract sound features;

[0050] Step S103, collecting user operation data through the user interaction interface and constructing a white noise sound effect preference model;

[0051] Step S104, based on the sound characteristics and the pre-built preference model, filter the sound effects that meet the constraint conditions from the custom sound effect database as the recommended white noise sound effects;

[0052] In step S105 , the recommended white noise sound effect is mixed with the original audio signal in the car, and the mixing ratio is dynamically adjusted before playing through the speaker.

[0053] In step S101 of the above embodiment, preprocessing the real-time collected in-vehicle sound signal includes:

[0054] Microphone arrays distributed on the vehicle doors and roof are used to collect sound signals inside the vehicle;

[0055] The in-vehicle sound signal is pre-amplified and subjected to anti-aliasing filtering processing.

[0056] In the above embodiment, the microphone array is distributed in various locations within the vehicle, such as the doors and roof, to ensure comprehensive acquisition of sound signals from all directions within the vehicle. The preamplifier amplifies the weak electrical signal to an appropriate amplitude for subsequent processing. The anti-aliasing filter removes high-frequency interference signals above half the sampling frequency, ensuring the collected noise signal is pure and accurate.

[0057] In step S102 of the above embodiment, the spectral analysis of the preprocessed sound signal, the determination of the sound source and type, and the extraction of sound features include: using a short-time Fourier transform algorithm to convert the time domain signal into a frequency domain signal, and obtaining the specific noise source and type by matching it with known noise patterns in a sound feature database; and defining the noise source and type as sound features; providing accurate noise feature information for subsequent sound effect recommendations.

[0058] The sound effect database is used to store a variety of different types of white noise sound effects, each of which has specific frequency characteristics and noise reduction effects.

[0059] In step S103 of the above embodiment, the construction of the white noise sound effect preference model includes: collecting user operation data on the white noise sound effect through the user interaction interface, analyzing the user operation data on the white noise sound effect using a neural network algorithm, determining the user's preference weights for different sound characteristics (such as frequency range, volume, sound effect enhancement type, etc.), and constructing the white noise sound effect preference model. For example, based on the provided sound characteristics, the noise frequency band to be blocked is determined, and then the most suitable white noise sound effect is selected based on the user's preferences for sound effects such as pink noise and low-frequency enhancement.

[0060] In step S103 of the above embodiment, the user interaction interface is a touch screen or button of the in-vehicle multimedia system, which is used to collect user operation data and display recommended white noise sound effect information.

[0061] In step S104 of the above embodiment, the constraint condition includes: according to the current vehicle sound condition, preferentially selecting from high-energy low-frequency white noise for shielding low-frequency sounds and high-frequency-emphasized white noise for shielding high-frequency sounds.

[0062] In step S105 of the above embodiment, mixing the recommended white noise sound effect with the original audio signal in the car, and dynamically adjusting the mixing ratio before playing through the speaker includes: determining the mixing ratio based on the noise intensity and the noise reduction effect of the white noise sound effect; continuously monitoring the noise and audio output in the car during playback; if the noise intensity or frequency changes, dynamically adjusting the volume and frequency characteristics of the white noise sound effect; and re-optimizing the mixing ratio before playing through the speaker to ensure that good noise reduction effect and audio playback quality are always maintained.

[0063] The above specific embodiments can effectively shield the noise inside the car, improve the audio experience, and meet the personalized needs of users. Taking a car traveling on a highway as an example, the specific implementation process of the present invention is described.

[0064] Example 1: While a vehicle is in motion, the microphone array continuously collects sound signals from within the vehicle. Microphones located on the doors and roof pick up strong wind noise, as well as noise from the engine and tires. These signals are amplified by a preamplifier and filtered by an anti-aliasing filter before being transmitted to the audio processing chip.

[0065] The audio processing chip performs spectral analysis on the pre-processed sound signal and finds that the sound is primarily concentrated in the low-frequency range of 20Hz-200Hz (engine and tire noise) and the mid- and high-frequency range of 1000Hz-5000Hz (wind noise). By matching this with known noise patterns in a sound signature database, the specific source and type of noise are determined.

[0066] Over the past week, users have selected pink noise multiple times through the in-car multimedia system's user interface, often adjusting the volume to a moderate to high setting. They also frequently prefer low-frequency enhancement. The audio processing chip uses a neural network algorithm to analyze this data, constructing a white noise preference model and determining the user's preference for pink noise, medium-to-high volume, and low-frequency enhancement.

[0067] The audio processing chip selects recommended sound effects from a sound effects database based on sound characteristics and a white noise sound effect preference model. Based on the current vehicle's acoustic conditions, it prioritizes high-energy, low-frequency white noise for blocking low-frequency sounds and high-frequency white noise for blocking high-frequency sounds. Taking into account the user's preference for pink noise and low-frequency enhancement, a pink white noise sound effect with low-frequency enhancement is selected. This sound effect boosts energy in the 20Hz-200Hz band to block engine and tire noise, and adjusts the amplitude in the 1000Hz-5000Hz band to match the frequency characteristics of wind noise.

[0068] The audio processing chip mixes the recommended white noise effect with the music currently playing in the car. The mixing ratio is determined based on the noise intensity and the noise reduction effect of the white noise effect, for example, setting the white noise effect volume to 40% of the music volume. The mixed audio signal is amplified by the power amplifier and played through the car's speakers. During playback, if stronger crosswinds increase wind noise, the audio processing chip dynamically adjusts the volume and frequency characteristics of the white noise effect based on this feedback, further optimizing the mixing ratio to ensure consistent noise reduction and audio playback quality.

[0069] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0070] Example 2: This example provides a sound effect recommendation method based on sound reverberation suppression and white noise. This method uses an in-car microphone array to collect ambient noise in real time and dynamically adjusts the white noise effect based on user preferences, achieving intelligent noise reduction and a personalized audio experience. The specific steps are as follows:

[0071] First, the architecture design is performed on the local system. The system corresponding to this embodiment includes the following functions:

[0072] 1. Hardware: 4-channel microphone array, preamplifier, anti-aliasing filter.

[0073] Function: Collect vehicle interior noise in real time and output digital signals to the analysis module.

[0074] 2. Sound feature analysis;

[0075] Algorithms: STFT spectrum analysis, noise pattern matching.

[0076] Output: noise type, source direction, eigenvector.

[0077] Interactive interface: 10-inch touch screen, supports sound effect rating, switching, and collection.

[0078] 3. Model: An LSTM preference model based on user operation data outputs a preference weight matrix.

[0079] Database: Custom sound effect library (including frequency band labels and noise reduction effect ratings).

[0080] Logic: Filter the top 3 recommended sound effects based on noise characteristics and preference models.

[0081] 4. Audio mixing and playback;

[0082] Dynamic adjustment: Based on real-time noise monitoring data, the mixing ratio is updated every 500ms.

[0083] Output: Optimized audio signal played through a 6-speaker system.

[0084] The specific implementation plan is as follows:

[0085] A 4-channel microphone array is deployed on the vehicle doors and roof to collect in-vehicle noise signals (such as engine roar, tire noise, wind noise, etc.) in real time.

[0086] The signal is boosted by a preamplifier, and high-frequency interference is eliminated by an anti-aliasing filter (cut-off frequency 20kHz). The analog signal is then output to the ADC module for conversion into a digital signal.

[0087] Short-time Fourier transform (STFT) is used to convert the time domain signal into the frequency domain signal. The frame length is set to 256ms and the frame shift is 50% to generate the spectrum diagram.

[0088] The spectrum is matched with a preset sound feature database to identify the noise type (such as low-frequency road noise, high-frequency wind noise) and source direction (such as the driver's side / passenger side).

[0089] Extract key characteristic parameters: center frequency, bandwidth, energy distribution, etc. to form a sound feature vector.

[0090] Through the interactive interface provided by the in-car multimedia touch screen, users can rate (1-5 stars) or switch recommended white noise sound effects (such as rain, waves, and forest wind).

[0091] Collect user operation data (such as number of clicks, playback time, and rating records), use neural network algorithms (such as LSTM) to analyze users' preference weights for noise in different frequency bands, and build a personalized preference model.

[0092] The custom sound effect database stores 100+ white noise sound effects, classified by frequency band characteristics:

[0093] Low-frequency sound shielding effect: center frequency 50-200Hz, suitable for engine noise;

[0094] High-frequency sound effects: center frequency 2-8kHz, suitable for wind noise or tire noise.

[0095] Based on the current noise characteristics (such as the proportion of low-frequency energy > 60%) and the user preference model, matching sound effects are selected (for example, if the user prefers high-frequency white noise, "ocean wave sound" is recommended first).

[0096] Initial mixing ratio setting: white noise sound effect volume = noise intensity × 1.2 (to ensure complete coverage), frequency band energy complementarity (such as low-frequency noise matches high-frequency white noise).

[0097] During playback, the microphone monitors the noise changes in the car in real time. If the low-frequency noise intensity increases by 10%, the high-frequency white noise volume will be dynamically increased by 5%, and the frequency band equalizer parameters will be fine-tuned.

[0098] After the mixed signal is processed by the DSP chip, it is played through the speakers in the car to ensure uniform coverage of the sound field.

[0099] The test results of the above embodiments show that in terms of noise reduction effect, through actual measurement on a highway (120 km / h), low-frequency noise (50-200 Hz) is reduced by 12 dB, and high-frequency noise (2-8 kHz) is reduced by 8 dB.

[0100] In terms of user satisfaction: 90% of users reported that the recommended sound effects and noise were highly matched, and the accuracy rate of personalized recommendations reached 85%.

[0101] In terms of system response: the delay from noise collection to sound effect recommendation is <200ms, meeting real-time requirements.

[0102] Based on the same inventive concept, embodiments of the present application also provide a sound effect recommendation system based on sound reverberation suppression and white noise for implementing the aforementioned sound effect recommendation method based on sound reverberation suppression and white noise. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the sound effect recommendation system based on sound reverberation suppression and white noise provided below can be found in the above-mentioned limitations of the sound effect recommendation method based on sound reverberation suppression and white noise, and will not be repeated here.

[0103] In one embodiment, Figure 3 As shown, a sound effect recommendation system based on sound reverberation suppression and white noise is provided, comprising: a real-time sound acquisition module 210, a sound feature analysis module 220, a user preference data collection and modeling module 230, a sound effect matching recommendation module 240, and an audio mixing and playing module 250, wherein:

[0104] The real-time sound acquisition module 210 is used to pre-process the real-time acquired in-vehicle sound signals;

[0105] The sound feature analysis module 220 is used to perform spectrum analysis on the pre-processed sound signal, determine the source and type of the sound, and extract the sound features;

[0106] User preference data collection and modeling module 230, for collecting user operation data through the user interaction interface and building a white noise sound effect preference model;

[0107] The sound effect matching recommendation module 240 is used to filter the sound effects that meet the constraint conditions from the custom sound effect database based on the sound characteristics and the pre-built preference model as the recommended white noise sound effect;

[0108] The audio mixing and playing module 250 is used to mix the recommended white noise sound effect with the original audio signal in the car, dynamically adjust the mixing ratio, and then play it through the speaker.

[0109] The real-time sound collection module 210 includes:

[0110] A collection unit, configured to collect in-vehicle sound signals using microphone arrays distributed on the vehicle doors and roof;

[0111] The processing unit is used to perform pre-amplification and anti-aliasing filtering on the in-vehicle sound signal.

[0112] The sound feature analysis module 220 includes:

[0113] A signal matching and conversion unit is used to convert the time domain signal into the frequency domain signal using a short-time Fourier transform algorithm, and obtain the specific noise source and type by matching it with known noise patterns in the sound feature database;

[0114] A definition unit is used to define the noise source and type as sound features.

[0115] The user preference data collection and modeling module 230 includes: an analysis unit for collecting user operation data on the white noise sound effect through a user interaction interface, and analyzing the user operation data on the white noise sound effect using a neural network algorithm;

[0116] The model building unit is used to determine the user's preference weights for different sound features and build a white noise sound effect preference model.

[0117] The audio mixing and playback module 250 includes: a mixing optimization unit, which is used to determine the mixing ratio based on the noise intensity and the noise reduction effect of the white noise sound effect. During the playback process, it continuously monitors the noise and audio output in the car. If the noise intensity or frequency changes, the volume and frequency characteristics of the white noise sound effect are dynamically adjusted, and the mixing ratio is optimized again before playing through the speaker.

[0118] In addition, in one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of any one of the above steps S101 to S105 when executing the computer program.

[0119] The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. The wireless communication method can be achieved through Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements any step of a sound effect recommendation method based on sound reverberation suppression and white noise. The display screen of the computer device can be a liquid crystal display or an electronic ink display. The input device of the computer device can be a touch layer covering the display screen, or keys, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0120] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0121] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0122] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0123] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0124] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0125] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A sound effect recommendation method based on sound reverberation suppression and white noise, characterized in that: include: Pre-process the real-time collected in-car sound signals; Perform spectrum analysis on the pre-processed sound signal to determine the sound source and type and extract sound features; Collect user operation data through the user interaction interface and build a white noise sound effect preference model; Based on the sound characteristics and the pre-built preference model, the sound effects that meet the constraints are selected from the custom sound effect database as the recommended white noise sound effects; The recommended white noise sound effect is mixed with the original audio signal in the car, and the mixing ratio is dynamically adjusted before playing through the speakers.

2. The method according to claim 1, wherein The preprocessing of the real-time collected in-vehicle sound signal includes: Microphone arrays distributed on the vehicle doors and roof are used to collect sound signals inside the vehicle; The in-vehicle sound signal is pre-amplified and subjected to anti-aliasing filtering processing.

3. The method according to claim 1, wherein The performing of spectrum analysis on the pre-processed sound signal, determining the sound source and type, and extracting sound features comprises: Using a short-time Fourier transform algorithm, the time-domain signal is converted into a frequency-domain signal, and the specific noise source and type are obtained by matching it with known noise patterns in a sound feature database; and the noise source and type are defined as sound features; The sound effect database is used to store a variety of different types of white noise sound effects, each of which has specific frequency characteristics and noise reduction effects.

4. The system according to claim 1, wherein: The construction of the white noise sound effect preference model includes: collecting user operation data on the white noise sound effect through a user interaction interface, analyzing the user operation data on the white noise sound effect using a neural network algorithm, determining the user's preference weights for different sound features, and constructing the white noise sound effect preference model.

5. The system according to claim 4, characterized in that The user interaction interface is a touch screen or button of the in-vehicle multimedia system, which is used to collect user operation data and display recommended white noise sound effect information.

6. The system according to claim 4, characterized in that The constraint condition includes: according to the current sound condition of the vehicle, preferentially selecting from high-energy low-frequency white noise for shielding low-frequency sounds and high-frequency-emphasized white noise for shielding high-frequency sounds.

7. The system according to claim 1, characterized in that The mixing of the recommended white noise sound effect with the original audio signal in the car, and dynamically adjusting the mixing ratio before playing through the speakers includes: determining the mixing ratio based on the noise intensity and the noise reduction effect of the white noise sound effect; continuously monitoring the noise and audio output in the car during playback; if the noise intensity or frequency changes, dynamically adjusting the volume and frequency characteristics of the white noise sound effect; and optimizing the mixing ratio again before playing through the speakers.

8. A sound effect recommendation system based on sound reverberation suppression and white noise, characterized in that: include: The real-time sound acquisition module is used to pre-process the real-time collected in-vehicle sound signals; The sound feature analysis module is used to perform spectrum analysis on the pre-processed sound signal, determine the source and type of the sound, and extract the sound features; User preference data collection and modeling module, used to collect user operation data through the user interaction interface and build a white noise sound effect preference model; The sound effect matching recommendation module is used to filter sound effects that meet the constraints from the custom sound effect database based on sound characteristics and a pre-built preference model, and use them as recommended white noise sound effects; The audio mixing and playback module is used to mix the recommended white noise sound effect with the original audio signal in the car, dynamically adjust the mixing ratio, and then play it through the speaker.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images