Intelligent sound effect optimization system based on dynamic frequency gain adjustment

Abstract

The invention relates to the technical field of audio, in particular to an intelligent sound effect optimization system based on dynamic frequency gain adjustment, which comprises an audio signal processing module, an environmental noise suppression module, a dynamic frequency gain adjustment module, a user interaction interface module and an intelligent learning module, through cooperation of an audio signal processing module, an environmental noise suppression module, a dynamic frequency gain adjustment module, a user interaction interface module and an intelligent learning module, the audio signal processing module is used for receiving an original audio signal and performing preliminary processing and analysis; the environmental noise suppression module is used for monitoring the environmental noise level in real time and correspondingly adjusting the audio signal so as to eliminate or reduce the influence of the noise; real-time adjustment can be carried out according to different acoustic environments and audio signal characteristics through dynamic frequency gain adjustment, it is ensured that the best sound effect experience can be provided in any environment, and the sound effect optimization effect in the complex environment is improved.

Description

Technical Field

[0001] The present invention belongs to the field of audio technology, and in particular relates to an intelligent sound effect optimization system based on dynamic frequency gain adjustment Background Art

[0002] The intelligent sound optimization system integrates sound processing, sound design and artificial intelligence technology to not only enhance the user's auditory experience, but also opens up new possibilities for the development of future audio technology.

[0003] At present, the intelligent sound optimization system is mainly composed of smart speakers and acceleration sensor units. The smart speaker uses independently controlled sound signal sending units and receiving units to send the original tuning signal and receive the reflected tuning feedback signal to obtain the spatial position parameters, thereby performing sound compensation. The spatial position parameters include angle parameters and amplitude parameters. This method can be adaptively adjusted according to different room boundaries to ensure the best sound quality. The acceleration sensor unit can detect the movement of the device. After the device moves, the system will re-obtain the sound compensation parameters based on the real-time measured acceleration force and adaptively adjust the sound effect. This dynamic adjustment capability makes sound optimization more flexible and accurate.

[0004] However, although the above-mentioned sound effect adjustment method can perform well in a general home environment, its performance may be limited in a complex acoustic environment (such as a large auditorium or outdoor venue), thereby affecting the effect of sound effect optimization in a complex environment. Therefore, we need to propose an intelligent sound effect optimization system based on dynamic frequency gain adjustment to solve the above-mentioned problems, so that it can be adjusted in real time according to different acoustic environments and audio signal characteristics, ensuring the best sound effect experience in any environment. Summary of the invention

[0005] In view of the above problems, the present invention provides an intelligent sound effect optimization system based on dynamic frequency gain adjustment, comprising: an audio signal processing module, the audio signal processing module is used to receive the original audio signal and perform preliminary processing and analysis; An environmental noise suppression module, which is used to monitor the environmental noise level in real time and adjust the audio signal accordingly to eliminate or reduce the impact of the noise; A dynamic frequency gain adjustment module, which automatically adjusts the gain values ​​of different frequency bands by analyzing the frequency distribution of the audio signal to ensure the balance and clarity of the sound quality; A user interaction interface module, wherein the user interaction interface module provides a user interaction platform, allowing the user to adjust the sound effect settings according to personal preferences; An intelligent learning module collects the user's listening data, analyzes the user's preferences and behavior patterns, continuously optimizes the sound effect parameters, and realizes intelligent sound effect adjustment; The audio signal processing module is connected to the environmental noise suppression module, the environmental noise suppression module is connected to the dynamic frequency gain adjustment module, the dynamic frequency gain adjustment module is respectively connected to the user interaction interface module and the intelligent learning module, and the user interaction interface module is connected to the intelligent learning module.

[0006] Furthermore, the audio signal processing module includes an analog-to-digital converter, a digital signal processor and an encoder, the analog-to-digital converter is used to convert the continuous analog original audio signal into a digital signal, the digital signal processor is used to extract features from the converted digital signal, and the encoder is used to encode the extracted features so that the encoded data format is suitable for the processing format of the environmental noise suppression module.

[0007] Furthermore, the digital signal processor is set as a DSP processor, and the process of feature extraction by the digital signal processor is as follows: A1. Cut the long-time series audio signals in the converted digital signal into short-frame audio signals. Each short-frame audio signal contains hundreds to thousands of sample points. There will be overlaps between two adjacent short-frame audio signals. A2. Perform windowing processing on each short-frame audio signal, and select a suitable window function according to the signal characteristics and analysis requirements. The window functions include Hamming window and Hanning window. A3. Determine the window length according to the selected window function; A4, applying the selected window function to each frame signal, multiplying the window function with the original signal, thereby changing the shape of the signal; A5. Perform fast Fourier transform on the windowed signal to obtain frequency domain representation; A6. Extract the required features or parameters from the spectrum graph, including peak value and bandwidth; A7. Adjust the parameters of the window function according to the analysis results.

[0008] Furthermore, the process of the environmental noise suppression module monitoring the environmental noise level is as follows: B1. Perform time domain and frequency domain analysis on the collected noise samples to identify the noise type, intensity and frequency distribution. The noise categories include white noise and colored noise. B2. Use Fourier transform to convert the time domain signal to the frequency domain, then calculate the energy of each frequency component and estimate the power spectral density; B3. Determine the noise level based on the power spectrum density estimation result; B4. Dynamically adjust audio processing parameters based on the results of noise level assessment; B5. Continuously monitor changes in environmental noise and update noise models and processing strategies accordingly; B6. Establish a noise suppression feedback system to continuously adjust the noise suppression strategy based on the quality of the processed signal; B7, outputting the signal after noise suppression processing to the dynamic frequency gain adjustment module for processing; B8. Regularly evaluate the performance of the ambient noise suppression module; B9. Continuously optimize the noise suppression algorithm and parameter settings based on the results of the performance evaluation.

[0009] Furthermore, the process of the dynamic frequency gain adjustment module automatically adjusting the gain values ​​of different frequency bands is as follows: C1. Perform Fourier transform on the input signal to obtain the frequency domain representation of the signal, i.e., the spectrum diagram; C2. Calculate the gain values ​​of different frequency bands according to the spectrum analysis results; C3, applying the calculated gain value to the corresponding frequency band, and then converting the signal back to the time domain through inverse Fourier transform to obtain the processed audio signal; C4, continuously monitor the frequency distribution changes of the audio signal and update the gain value as needed to keep the gain value at the target level; C5. Establish a gain feedback system to continuously adjust the gain strategy based on the quality of the processed signal; C6. Regularly evaluate the performance of the dynamic frequency gain adjustment module to ensure that it can effectively optimize the frequency response of the audio signal in different environments; C7. Based on the results of performance evaluation, continuously optimize the gain adjustment algorithm and parameter settings.

[0010] Furthermore, in step C1, the process of Fourier transform is as follows: C11, set the time domain signal to , the number of sampling points is N; C12. For each frequency k, calculate the corresponding frequency domain signal X(k), the calculation formula is: ,in, is the kth frequency component of the frequency domain signal, is the time domain signal samples, N is the number of sampling points, k is the frequency index, e is the base of the natural logarithm, and j is the imaginary unit used to represent complex numbers; C13. Convert the time domain signal into a frequency domain signal to obtain a spectrum diagram.

[0011] Furthermore, in step C2, the calculation process of the gain value is as follows: C21, use spectrum analysis to measure the current signal level Dn; C22, set a target level Dm according to the application scenario and requirements; C23. Use the gain calculation formula to calculate the gain value G. The gain calculation formula is as follows: , where Dm is the target level, is the average value of the current signal level; C24. If the current level Dn is lower than the target level Dm, the gain value is positive and the gain is amplified; if the current level Dn is higher than the target level Dm, the gain value is negative and the gain is attenuated.

[0012] Furthermore, the user interaction interface module includes an input unit responsible for receiving user input, an event processing unit that encapsulates user input into an event object, a UI component that performs corresponding operations based on the received event, a parameter adjustment unit that allows the user to select preset or adjust parameters, and a sound effect processing unit that adjusts the audio signal based on the user-set parameters.

[0013] Furthermore, the process of the intelligent learning module analyzing user preferences and behavior patterns is as follows: E1. Collecting the user's listening data from the user interaction interface module, the listening data including the user's playing history, music selection, volume adjustment and sound effect settings; E2. Conduct in-depth analysis of the collected data to identify user behavior patterns and preferences; E3. Based on the user's behavior data and preferences, the intelligent learning module provides users with personalized sound setting suggestions; E4. Analyze user feedback and comments to further understand users’ emotional responses; E5. Use deep learning and neural network technology to continuously learn and optimize its algorithms; E6. Continuously monitor the user's listening behavior and adjust the sound settings based on the user's real-time feedback; E7. Regularly evaluate the performance of the intelligent learning module and continuously optimize the gain adjustment algorithm and parameter settings based on the results of the performance evaluation.

[0014] Furthermore, in step E5, the specific operations of continuously learning and optimizing the algorithm using deep learning and neural network technology are as follows: E51. Collect and organize users’ listening data, clean and standardize the data; E52. Extract input features from the raw data, where the input features include music genre, artist, and album; E53. Select a suitable neural network architecture and design the network structure according to specific application scenarios and requirements. The network structure includes the number of layers, activation function and loss function. The neural network architecture is set to one of the following: convolutional neural network, recurrent neural network and long short-term memory network. E54. Use the collected data to train the neural network and adjust the network parameters through the back propagation algorithm to minimize the prediction error. During the training process, one of the following methods should be used for optimization: gradient descent, stochastic gradient descent, and Adam optimizer. E55. Evaluate the performance of the trained model on an independent test set. Based on the evaluation results, determine whether the model meets the requirements and decide whether further optimization is needed. E56. Adjust the hyperparameters of the neural network, including learning rate, batch size, and regularization coefficient; E57: Continuously monitor the performance of the system and make adjustments based on user feedback. If you find that the model's prediction results are not accurate enough or cannot meet user needs, you need to return to E51 and optimize again.

[0015] The beneficial effects of the present invention are: The present invention cooperates with an audio signal processing module, an environmental noise suppression module, a dynamic frequency gain adjustment module, a user interaction interface module and an intelligent learning module. The audio signal processing module is used to receive the original audio signal and perform preliminary processing and analysis; the environmental noise suppression module is used to monitor the environmental noise level in real time and adjust the audio signal accordingly to eliminate or reduce the impact of noise; the dynamic frequency gain adjustment can be used to perform real-time adjustment according to different acoustic environments and audio signal characteristics, ensuring that the best sound experience can be provided in any environment, thereby improving the effect of sound optimization in complex environments.

[0016] The present invention can effectively evaluate and optimize the signal-to-noise ratio in the signal processing system through the setting of the environmental noise suppression module, thereby improving the quality and reliability of the signal.

[0017] The present invention can effectively collect and analyze user listening data, understand user preferences and behavior patterns, and provide optimization suggestions to the dynamic frequency gain adjustment module through the setting of the intelligent learning module, thereby achieving a more personalized and high-quality sound experience.

[0018] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A system block diagram according to an embodiment of the present invention is shown; Figure 2 A flowchart of feature extraction performed by a digital signal processor according to an embodiment of the present invention is shown; Figure 3 A flowchart of monitoring the ambient noise level by an ambient noise suppression module according to an embodiment of the present invention is shown; Figure 4 A flowchart showing the automatic adjustment of gain values ​​of different frequency bands by a dynamic frequency gain adjustment module according to an embodiment of the present invention is shown; Figure 5 A flowchart of analyzing user preferences and behavior patterns by an intelligent learning module according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The embodiment of the present invention provides an intelligent sound effect optimization system based on dynamic frequency gain adjustment, such as Figure 1-5 As shown, it includes an audio signal processing module, an environmental noise suppression module, a dynamic frequency gain adjustment module, a user interaction interface module and an intelligent learning module, the audio signal processing module is connected to the environmental noise suppression module, the environmental noise suppression module is connected to the dynamic frequency gain adjustment module, the dynamic frequency gain adjustment module is respectively connected to the user interaction interface module and the intelligent learning module, and the user interaction interface module is connected to the intelligent learning module; The audio signal processing module is used to receive the original audio signal and perform preliminary processing and analysis; The audio signal processing module includes an analog-to-digital converter, a digital signal processor and an encoder. The analog-to-digital converter is used to convert a continuous analog original audio signal into a digital signal. The digital signal processor is used to extract features from the converted digital signal. The encoder is used to encode the extracted features so that the encoded data format is suitable for the processing format of the environmental noise suppression module.

[0023] The digital signal processor is configured as a DSP processor, such as Figure 2 As shown, the process of feature extraction by the digital signal processor is as follows: A1. Cut the long-time audio signal in the converted digital signal into short-frame audio signals. Each short-frame audio signal contains hundreds to thousands of sample points. There will be overlap between two adjacent short-frame audio signals to ensure the continuity and smooth transition of the signal. A2. Perform windowing on each short-frame audio signal and select a suitable window function based on the signal characteristics and analysis requirements. The window functions include Hamming window and Hanning window. The Hamming window is suitable for most applications because it can provide a good balance between spectrum resolution and leakage. A3. Determine the window length based on the selected window function; the window length determines the frequency resolution. A longer window can provide higher frequency resolution but reduce time resolution; a shorter window has the opposite effect. A4, applying the selected window function to each frame signal, multiplying the window function with the original signal, thereby changing the shape of the signal; A5. Perform fast Fourier transform on the windowed signal to obtain frequency domain representation; A6. Extract the required features or parameters from the spectrum graph, including peak value and bandwidth; A7. Adjust the parameters of the window function according to the analysis results to optimize the performance; By extracting features through a digital signal processor, spectrum leakage can be effectively reduced and the accuracy and reliability of signal analysis can be improved.

[0024] When encoding the extracted features, the encoder first converts the continuous value of the extracted features into a finite number of discrete values ​​to quantize the extracted features, and then digitally represents the quantized signal through the encoder to facilitate processing and storage by the environmental noise suppression module.

[0025] The environmental noise suppression module is used to monitor the environmental noise level in real time and adjust the audio signal accordingly to eliminate or reduce the impact of the noise; like Figure 3 As shown, the process of the environmental noise suppression module monitoring the environmental noise level is as follows: B1. Perform time domain and frequency domain analysis on the collected noise samples to identify the noise type, intensity and frequency distribution. The noise categories include white noise and colored noise. B2. Use Fourier transform to convert the time domain signal to the frequency domain, then calculate the energy of each frequency component and estimate the power spectral density; B3. Determine the noise level based on the power spectrum density estimation result. The noise level includes the signal-to-noise ratio index. B4. Dynamically adjust audio processing parameters, such as filter coefficients, based on the results of the noise level assessment to optimize the noise suppression effect; B5. Continuously monitor changes in environmental noise and update noise models and processing strategies accordingly; B6. Establish a noise suppression feedback system to continuously adjust the noise suppression strategy based on the quality of the processed signal to improve performance; B7, outputting the signal after noise suppression processing to the dynamic frequency gain adjustment module for processing; B8. Regularly evaluate the performance of the environmental noise suppression module to ensure that it can effectively reduce the impact of noise in different environments; B9. Continuously optimize the noise suppression algorithm and parameter settings based on the results of the performance evaluation.

[0026] The environmental noise suppression module can effectively evaluate and optimize the signal-to-noise ratio in the signal processing system, thereby improving the quality and reliability of the signal.

[0027] The dynamic frequency gain adjustment module automatically adjusts the gain values ​​of different frequency bands by analyzing the frequency distribution of the audio signal to ensure the balance and clarity of the sound quality; like Figure 4 As shown, the process of the dynamic frequency gain adjustment module automatically adjusting the gain values ​​of different frequency bands is as follows: C1. Perform Fourier transform on the input signal to obtain the frequency domain representation of the signal, i.e., the spectrum diagram; C2. Calculate the gain values ​​of different frequency bands according to the spectrum analysis results; C3, applying the calculated gain value to the corresponding frequency band, and then converting the signal back to the time domain through inverse Fourier transform to obtain the processed audio signal; C4, continuously monitor the frequency distribution changes of the audio signal and update the gain value as needed to keep the gain value at the target level; C5. Establish a gain feedback system to continuously adjust the gain strategy based on the quality of the processed signal to improve performance; C6. Regularly evaluate the performance of the dynamic frequency gain adjustment module to ensure that it can effectively optimize the frequency response of the audio signal in different environments; C7. Continuously optimize the gain adjustment algorithm and parameter settings based on the results of performance evaluation; Dynamic frequency gain adjustment is widely used in audio and speech processing fields such as music production, broadcasting and communication systems.

[0028] In step C1, the process of Fourier transform is as follows: C11, set the time domain signal to , the number of sampling points is N; C12. For each frequency k, calculate the corresponding frequency domain signal X(k), the calculation formula is: in, is the kth frequency component of the frequency domain signal, is the time domain signal samples, N is the number of sampling points, k is the frequency index, e is the base of the natural logarithm, and j is the imaginary unit used to represent complex numbers; C13. Convert the time domain signal into a frequency domain signal to obtain a spectrum diagram; In step C2, the calculation process of the gain value is as follows: C21, use spectrum analysis to measure the current signal level Dn; C22, set a target level Dm according to the application scenario and requirements; C23. Use the gain calculation formula to calculate the gain value G. The gain calculation formula is as follows: , where Dm is the target level, is the average value of the current signal level; C24, if the current level Dn is lower than the target level Dm, the gain value is positive, and the gain is amplified; if the current level Dn is higher than the target level Dm, the gain value is negative, and the gain is attenuated; By dynamically adjusting the frequency gain, the audio signal can be improved to provide a more balanced and pleasant listening experience.

[0029] The user interaction interface module provides a user interaction platform, allowing the user to adjust the sound effect settings according to personal preferences; The user interaction interface module includes an input unit responsible for receiving user input, an event processing unit that encapsulates user input into an event object, a UI component that performs corresponding operations according to the received event, a parameter adjustment unit that allows the user to select preset or adjust parameters, and a sound effect processing unit that adjusts the audio signal according to the user-set parameters; when the user interaction interface module is working, it receives the user's physical input, such as keystrokes, sliding, etc., through a hardware interface, and converts it into a digital signal, and then parses the received digital signal through the event processing unit and converts it into a specific event object, such as a click event, a sliding event, etc., uses the UI component to monitor these event objects, and triggers corresponding actions when an event occurs, such as updating the interface display, playing a sound, etc., and provides user-friendly interface elements, such as a slider, a drop-down menu, etc., through the parameter adjustment unit, so that the user can adjust the parameters intuitively; the sound effect processing unit processes the audio signal according to the parameters set by the user, such as changing the frequency response, adding a reverberation effect, etc.

[0030] The process for users to adjust the sound settings according to their personal preferences is as follows: D1. The user first interacts with the interface through input devices, including keyboard and mouse; D2. The user clicks a button or selects an option in a drop-down menu to select a preset sound effect mode; D3. Users use slider tools to fine-tune parameters, such as adjusting the volume, bass and treble intensity, etc. D3. When the user completes the settings, the system will generate corresponding sound effects based on the user's selections and adjustments; D4. Users can preview the adjusted sound effects in real time through the audition function and make further adjustments as needed until they are satisfied; D5. Users save their own settings as new presets to quickly apply the same sound effects in the future.

[0031] Through the setting of the user interaction interface module, users can easily customize the personalized sound experience according to their preferences.

[0032] The intelligent learning module collects the user's listening data, analyzes the user's preferences and behavior patterns, continuously optimizes the sound effect parameters, and realizes intelligent sound effect adjustment.

[0033] like Figure 5 As shown, the process of the intelligent learning module analyzing user preferences and behavior patterns is as follows: E1. Collect the user's listening data from the user interaction interface module. The listening data includes the user's playback history, music selection, volume adjustment and sound effect settings.

[0034] E2. Conduct in-depth analysis of the collected data to identify user behavior patterns and preferences; for example, by analyzing the user's playback history and music selection, understand the user's preferred music genre or artist; E3. Based on the user's behavior data and preferences, the intelligent learning module provides users with personalized sound setting suggestions. The sound setting suggestions are designed to improve the user experience and make the audio output more in line with personal preferences; E4. Analyze user feedback and evaluation to further understand the user's emotional response and adjust the sound effect settings to meet the user's emotional needs; E5. Use deep learning and neural network technology to continuously learn and optimize its algorithms to more accurately predict user needs and preferences; E6. Continuously monitor the user's listening behavior and adjust the sound settings based on the user's real-time feedback; E7. Regularly evaluate the performance of the intelligent learning module to ensure that it can effectively optimize the frequency response of the audio signal in different environments. Based on the results of the performance evaluation, continuously optimize the gain adjustment algorithm and parameter settings. In step E5, the specific operations of continuously learning and optimizing the algorithm using deep learning and neural network technology are as follows: E51. Collect and organize users’ listening data, clean and standardize the data to facilitate neural network training and analysis; E52. Extract input features from the raw data. The input features include music genre, artist, and album. The input features help the network better understand the user's behavior patterns and preferences. E53. Select a suitable neural network architecture and design the network structure according to specific application scenarios and requirements. The network structure includes the number of layers, activation function and loss function. The neural network architecture is set to one of the following: convolutional neural network (CNN), recurrent neural network (RNN) and long short-term memory network (LSTM). E54. Use the collected data to train the neural network and adjust the network parameters through the back propagation algorithm to minimize the prediction error. During the training process, you need to use one of the gradient descent method, stochastic gradient descent method and Adam optimizer to improve the performance of the model. E55. Evaluate the performance of the trained model on an independent test set. Common evaluation indicators include accuracy, recall, F1 score, etc. Based on the evaluation results, determine whether the model meets the requirements and decide whether further optimization is needed. E56. Adjust the hyperparameters of the neural network, including learning rate, batch size, and regularization coefficient, to improve the performance of the model; E57: Continuously monitor the performance of the system and make adjustments based on user feedback. If you find that the model's prediction results are not accurate enough or cannot meet user needs, you need to return to E51 and optimize again.

[0035] In step E53, if the performance of a single model is limited, the prediction results of multiple models need to be integrated to improve the overall performance. The integration methods include voting method, weighted average method and model fusion technology in deep learning. The integration methods are common knowledge in the art and will not be described in detail here. In step E54, during training, the user's behavior and preferences may change over time. In order to adapt to these changes, an online learning method is used to allow the neural network to continuously learn from new data and update its prediction model; the trained neural network model is deployed to the actual system to predict the user's needs and preferences in real time, and the sound effect settings are dynamically adjusted according to the model's prediction results to provide a more personalized listening experience.

[0036] Through the setting of the intelligent learning module, it is possible to effectively collect and analyze user listening data, understand user preferences and behavior patterns, and provide optimization suggestions to the dynamic frequency gain adjustment module, thereby achieving a more personalized and high-quality sound experience.

[0037] The audio signal processing module receives the original audio signal from the sound source, which can be generated by a microphone or a speaker, and the processed audio signal is sent to the environmental noise suppression module for noise suppression processing. The environmental noise suppression module transmits the audio signal after noise suppression processing to the dynamic frequency gain adjustment module. The audio signal after the dynamic frequency gain adjustment module adjusts the gain according to the frequency distribution is sent to the user interaction interface module and the intelligent learning module. The user interaction interface module receives the audio signal from the dynamic frequency gain adjustment module, allows the user to adjust the sound effect settings according to personal preferences, and feeds back the adjusted parameters to the dynamic frequency gain adjustment module. The intelligent learning module collects user listening data from the user interaction interface module, analyzes the user's preferences and behavior patterns, and then provides optimization suggestions to the dynamic frequency gain adjustment module. The dynamic frequency gain adjustment can be used to make real-time adjustments according to different acoustic environments and audio signal characteristics, ensuring that the best sound effect experience can be provided in any environment, thereby improving the effect of sound effect optimization in complex environments.

[0038] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent sound effect optimization system based on dynamic frequency gain adjustment, characterized in that: include: An audio signal processing module, the audio signal processing module is used to receive the original audio signal and perform preliminary processing and analysis; An environmental noise suppression module, which is used to monitor the environmental noise level in real time and adjust the audio signal accordingly to eliminate or reduce the impact of the noise; A dynamic frequency gain adjustment module, which automatically adjusts the gain values ​​of different frequency bands by analyzing the frequency distribution of the audio signal to ensure the balance and clarity of the sound quality; A user interaction interface module, wherein the user interaction interface module provides a user interaction platform, allowing the user to adjust the sound effect settings according to personal preferences; An intelligent learning module collects the user's listening data, analyzes the user's preferences and behavior patterns, continuously optimizes the sound effect parameters, and realizes intelligent sound effect adjustment; The audio signal processing module is connected to the environmental noise suppression module, the environmental noise suppression module is connected to the dynamic frequency gain adjustment module, the dynamic frequency gain adjustment module is respectively connected to the user interaction interface module and the intelligent learning module, and the user interaction interface module is connected to the intelligent learning module.

2. According to claim 1, the intelligent sound effect optimization system based on dynamic frequency gain adjustment is characterized in that: The audio signal processing module includes an analog-to-digital converter, a digital signal processor and an encoder. The analog-to-digital converter is used to convert a continuous analog original audio signal into a digital signal. The digital signal processor is used to extract features from the converted digital signal. The encoder is used to encode the extracted features so that the encoded data format is suitable for the processing format of the environmental noise suppression module.

3. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 2, characterized in that: The digital signal processor is set as a DSP processor, and the process of feature extraction performed by the digital signal processor is as follows: A1. Cut the long-time series audio signal in the converted digital signal into short-frame audio signals. Each short-frame audio signal contains hundreds to thousands of sample points. There will be overlap between two adjacent short-frame audio signals. A2. Perform windowing processing on each short-frame audio signal, and select a suitable window function according to the signal characteristics and analysis requirements. The window functions include Hamming window and Hanning window. A3. Determine the window length according to the selected window function; A4, applying the selected window function to each frame signal, multiplying the window function with the original signal, thereby changing the shape of the signal; A5. Perform fast Fourier transform on the windowed signal to obtain frequency domain representation; A6. Extract the required features or parameters from the spectrum graph, including peak value and bandwidth; A7. Adjust the parameters of the window function according to the analysis results.

4. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 3, characterized in that: The process of the environmental noise suppression module monitoring the environmental noise level is as follows: B1. Perform time domain and frequency domain analysis on the collected noise samples to identify the noise type, intensity and frequency distribution. The noise categories include white noise and colored noise. B2. Use Fourier transform to convert the time domain signal to the frequency domain, then calculate the energy of each frequency component and estimate the power spectral density; B3. Determine the noise level based on the power spectrum density estimation result; B4. Dynamically adjust audio processing parameters based on the results of noise level assessment; B5. Continuously monitor changes in environmental noise and update noise models and processing strategies accordingly; B6. Establish a noise suppression feedback system to continuously adjust the noise suppression strategy based on the quality of the processed signal; B7, outputting the signal after noise suppression processing to the dynamic frequency gain adjustment module for processing; B8. Regularly evaluate the performance of the ambient noise suppression module; B9. Continuously optimize the noise suppression algorithm and parameter settings based on the results of the performance evaluation.

5. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 4, characterized in that: The process of the dynamic frequency gain adjustment module automatically adjusting the gain values ​​of different frequency bands is as follows: C1. Perform Fourier transform on the input signal to obtain the frequency domain representation of the signal, i.e., the spectrum diagram; C2. Calculate the gain values ​​of different frequency bands according to the spectrum analysis results; C3, applying the calculated gain value to the corresponding frequency band, and then converting the signal back to the time domain through inverse Fourier transform to obtain the processed audio signal; C4, continuously monitor the frequency distribution changes of the audio signal and update the gain value as needed to keep the gain value at the target level; C5. Establish a gain feedback system to continuously adjust the gain strategy based on the quality of the processed signal; C6. Regularly evaluate the performance of the dynamic frequency gain adjustment module to ensure that it can effectively optimize the frequency response of the audio signal in different environments; C7. Based on the results of performance evaluation, continuously optimize the gain adjustment algorithm and parameter settings.

6. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 5, characterized in that: In step C1, the process of Fourier transform is as follows: C11, set the time domain signal to , the number of sampling points is N; C12. For each frequency k, calculate the corresponding frequency domain signal X(k), the calculation formula is: ,in, is the kth frequency component of the frequency domain signal, is the time domain signal samples, N is the number of sampling points, k is the frequency index, e is the base of the natural logarithm, and j is the imaginary unit used to represent complex numbers; C13. Convert the time domain signal into a frequency domain signal to obtain a spectrum diagram.

7. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 6, characterized in that: In step C2, the calculation process of the gain value is as follows: C21, use spectrum analysis to measure the current signal level Dn; C22, set a target level Dm according to the application scenario and requirements; C23. Use the gain calculation formula to calculate the gain value G. The gain calculation formula is as follows: , where Dm is the target level, is the average value of the current signal level; C24. If the current level Dn is lower than the target level Dm, the gain value is positive and the gain is amplified; if the current level Dn is higher than the target level Dm, the gain value is negative and the gain is attenuated.

8. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 7, characterized in that: The user interaction interface module includes an input unit responsible for receiving user input, an event processing unit that encapsulates user input into event objects, a UI component that performs corresponding operations based on received events, a parameter adjustment unit that allows the user to select preset or adjust parameters, and a sound effect processing unit that adjusts audio signals based on user-set parameters.

9. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 8, characterized in that: The process of the intelligent learning module analyzing user preferences and behavior patterns is as follows: E1. Collecting the user's listening data from the user interaction interface module, the listening data including the user's playing history, music selection, volume adjustment and sound effect settings; E2. Conduct in-depth analysis of the collected data to identify user behavior patterns and preferences; E3. Based on the user's behavior data and preferences, the intelligent learning module provides users with personalized sound setting suggestions; E4. Analyze user feedback and comments to further understand users’ emotional responses; E5. Use deep learning and neural network technology to continuously learn and optimize its algorithms; E6. Continuously monitor the user's listening behavior and adjust the sound settings based on the user's real-time feedback; E7. Regularly evaluate the performance of the intelligent learning module and continuously optimize the gain adjustment algorithm and parameter settings based on the results of the performance evaluation.

10. The intelligent sound effect optimization system based on dynamic frequency gain adjustment according to claim 9, characterized in that: In step E5, the specific operations of continuously learning and optimizing the algorithm using deep learning and neural network technology are as follows: E51. Collect and organize users’ listening data, clean and standardize the data; E52. Extract input features from the raw data, where the input features include music genre, artist, and album; E53. Select a suitable neural network architecture and design the network structure according to specific application scenarios and requirements. The network structure includes the number of layers, activation function and loss function. The neural network architecture is set to one of the following: convolutional neural network, recurrent neural network and long short-term memory network. E54. Use the collected data to train the neural network and adjust the network parameters through the back propagation algorithm to minimize the prediction error. During the training process, one of the following methods should be used for optimization: gradient descent, stochastic gradient descent, and Adam optimizer. E55. Evaluate the performance of the trained model on an independent test set. Based on the evaluation results, determine whether the model meets the requirements and decide whether further optimization is needed. E56. Adjust the hyperparameters of the neural network, including learning rate, batch size, and regularization coefficient; E57: Continuously monitor the performance of the system and make adjustments based on user feedback. If you find that the model's prediction results are not accurate enough or cannot meet user needs, you need to return to E51 and optimize again.

Images