Method and system for optimizing sound effect of game earphone through voiceprint recognition

Through voiceprint signal preprocessing and LSTM model prediction, combined with user feedback to adjust weights, the accuracy and personalization problems of traditional voiceprint recognition technology in the sound effect optimization of gaming headsets are solved, and efficient personalized sound effect adjustment is achieved, which improves users Experience.

CN118918899APending Publication Date: 2024-11-08MINAMI ACOUSTICS LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411126187.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Traditional voiceprint recognition technology has low recognition accuracy in gaming headset sound effects optimization, and cannot accurately map soundprint signals and sound effect adjustment parameters. It lacks dynamic adjustments from user needs, resulting in limitations in the sound effect experience.

Method used

By collecting user voiceprint signals for preprocessing and feature analysis, an LSTM neural network model is constructed to predict voiceprint signal change parameters, and map them to sound effect adjustment parameters, collect user feedback data to adjust weights, and realize personalized optimization of sound effects.

Benefits of technology

It significantly improves the predictiveness and personalization level of sound effect adjustment, realizes the precise mapping of voiceprint characteristics and sound effect parameters, and improves the personalized experience and user satisfaction of sound effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918899A_ABST
    Figure CN118918899A_ABST
Patent Text Reader

Abstract

The invention discloses a method and system for optimizing the sound effect of a game earphone through voiceprint recognition, and relates to the technical field of audio optimization, and the method comprises the steps: collecting a user voiceprint signal, and carrying out the preprocessing; analyzing voiceprint signal features and extracting change parameters of the voiceprint signals; constructing a voiceprint prediction model to analyze change parameters of the voiceprint signals and predict change parameters of future voiceprint signals; mapping the predicted change parameter of the voiceprint signal to a sound effect adjustment parameter; and collecting and analyzing user feedback data, and adjusting the change parameter weight of the voiceprint signal. According to the method, the voiceprint signals of the user are collected, the voiceprint features and the change parameters are extracted through frequency domain analysis, a key basis is provided for personalized sound effect adjustment, the LSTM model is constructed, predictability and foresight of sound effect adjustment are improved, accurate mapping of the voiceprint features and the sound effect parameters is achieved by defining the sound effect adjustment rule, and the user experience is improved. The personalized level of the sound effect is remarkably improved, user feedback is collected, the voiceprint parameter weight is adjusted, and a closed-loop feedback system is formed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of audio processing, and in particular to a method and system for optimizing the sound effects of gaming headphones through voiceprint recognition. Background Art

[0002] Voiceprint recognition technology has developed rapidly in recent years due to its unique individual recognition ability and broad application prospects. With the prosperity of the game industry, the personalized demand for game headset sound effects is growing. Existing game headset sound effect optimization technologies mostly rely on users to manually adjust sound effect parameters, or use preset sound effect modes to meet the auditory needs in different scenarios. However, these methods cannot accurately optimize the personalized auditory characteristics of each user, resulting in certain limitations in the sound effect experience. The shortcomings of existing voiceprint recognition technology in optimizing game headset sound effects are mainly reflected in the following aspects: traditional voiceprint recognition technology fails to effectively combine the complex and changeable characteristics of game sound effects, and the existing technology fails to achieve accurate mapping between voiceprint signals and sound effect adjustment parameters, resulting in unsatisfactory sound effect optimization effects. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing methods and systems for optimizing the sound effects of gaming headphones through voiceprint recognition, the present invention is proposed;

[0004] Therefore, the problems to be solved by the present invention are that the recognition accuracy of traditional voiceprint recognition technology is low, the mapping of voiceprint signals and sound effect adjustment parameters is inaccurate, there is a lack of dynamic adjustment of user needs, and how to achieve personalized optimization of gaming headset sound effects through voiceprint recognition technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method and system for optimizing the sound effects of gaming headphones through voiceprint recognition, comprising:

[0006] Collect user voiceprint signals and pre-process them;

[0007] Analyze the voiceprint signal characteristics and extract the change parameters of the voiceprint signal;

[0008] Construct a voiceprint prediction model to analyze the change parameters of voiceprint signals and predict the change parameters of future voiceprint signals;

[0009] Mapping the predicted change parameters of the voiceprint signal to the sound effect adjustment parameters;

[0010] Collect and analyze user feedback data and adjust the weight of the change parameters of the voiceprint signal;

[0011] Store data in the database to create indexes, perform backup and integrity checks.

[0012] As a preferred solution of the method and system for optimizing the sound effect of a gaming headset through voiceprint recognition according to the present invention, where: collecting the user's voiceprint signal and performing preprocessing means collecting the user's voiceprint signal during the game in real time through the microphone of the gaming headset, and performing preprocessing on the collected voiceprint signal, including denoising, normalization, and frame segmentation processing;

[0013] Performing short-time Fourier transform on each frame of the voiceprint signal after frame segmentation processing for frequency domain conversion to obtain the spectrum of each frame.

[0014] As a preferred solution of the method and system for optimizing the sound effect of a gaming headset through voiceprint recognition according to the present invention, where: analyzing the characteristics of the voiceprint signal and extracting the change parameters of the voiceprint signal means filtering the spectrum through a Mel filter bank to obtain the Mel spectrum energy spectrum, taking the logarithm of each Mel frequency energy spectrum and then performing discrete cosine transform to obtain the MFCC coefficients, forming the feature vector MFCC with the MFCC coefficients, and using the feature vector MFCC to calculate the Euclidean distance d between the current frame and the previous frame. The formula is:

[0015]

[0016] where d is the Euclidean distance between the current frame and the previous frame, N MFCC is the number of MFCC coefficients extracted, C c,n represents the nth MFCC coefficient of the current frame, C p,n represents the nth MFCC coefficient of the previous frame;

[0017] Define a change threshold T, and compare the calculated Euclidean distance d with the change threshold T to judge the type of change of the voiceprint signal:

[0018] If d≥T, it is judged that the voiceprint signal has changed, record this change, and extract the change parameters of the voiceprint signal, including emotion, speech rate, and intonation;

[0019] If d<T, it is judged that the voiceprint signal has not changed, and the change is not recorded;

[0020] Analyze the extracted change parameters of the voiceprint signal and classify and store the change parameters of the voiceprint signal, including:

[0021] For the spectrum of each frame of the voiceprint signal after frequency domain conversion, extract the high-frequency components in the spectrum, calculate the total energy of the high-frequency components and the total energy of the high-frequency components of the historical frame. If the total energy of the high-frequency components of the current frame is greater than the total energy of the high-frequency components of the historical frame, it is determined that the emotional change is excitement and tension. If the total energy of the high-frequency components of the current frame is less than the total energy of the high-frequency components of the historical frame, it is determined that the emotional change is relaxation and calmness;

[0022] Use VAD voice activity detection to determine the effective voiceprint signal of each frame, mark the state of each voiceprint signal frame, including voice frames and silent frames, record the timestamp of each detected voice frame, calculate the time interval between adjacent voice frames and the historical average interval time between all adjacent voice frames, if the time interval between voice frames is greater than the historical average interval time between all adjacent voice frames, then determine that the speech speed change is faster, if the time interval between voice frames is less than the historical average interval time between all adjacent voice frames, then determine that the speech speed change is slower;

[0023] Use the autocorrelation method to determine the periodicity and frequency characteristics of each voiceprint signal. Calculate the peak position of the autocorrelation function and the basic frequency of each voiceprint signal. Use a sliding average filter to smooth the extracted basic frequency. Calculate the difference f between the basic frequency of the current frame and the previous frame, and define the intonation change threshold T. p , if f ≥ T p , then determine that the tone has changed and record the basic frequency. If f <T p , the tone is judged to have not changed and the basic frequency is not recorded.

[0024] As a preferred solution of the method and system for optimizing the sound effects of gaming headphones through voiceprint recognition described in the present invention, wherein: the construction of a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the future voiceprint signal refers to using an LSTM neural network to construct a voiceprint prediction model, including an input layer, a hidden layer and an output layer;

[0025] The input layer is the change parameters of the voiceprint signal;

[0026] The hidden layer has multiple LSTM units to capture time series features, including the user's emotions, speech speed, and tone changes at different time points;

[0027] The output layer is the change parameter of the predicted voiceprint signal;

[0028] The change parameters of the voiceprint signal stored in the cell state are determined through the input gate and the forget gate, the cell state is updated based on the results of the input gate and the forget gate, and the predicted change parameters of the voiceprint signal are output through the output gate;

[0029] Divide the change parameters of the voiceprint signal into a training set and a test set;

[0030] The input data passes through the LSTM layer, and the error between the predicted value and the true value is calculated, using the mean square error as the loss function;

[0031] The model parameters are updated through the error direction propagation algorithm, and the Adam optimization algorithm is used to adjust the learning rate and weight;

[0032] The user's real-time voiceprint data is input into the trained LSTM model to obtain the predicted change parameters of the voiceprint signal.

[0033] As a preferred solution of the method and system for optimizing the sound effects of gaming headsets through voiceprint recognition described in the present invention, the mapping of the predicted change parameters of the voiceprint signal to the sound effect adjustment parameters refers to defining corresponding sound effect adjustment rules to adjust the sound effect adjustment parameters according to the predicted voiceprint change parameters, including the total energy of high-frequency components, the time interval between speech frames, and the difference f between the basic frequencies of the current frame and the previous frame, and the sound effect adjustment parameters include volume, frequency components, and surround sound:

[0034] If the emotion changes to excitement and tension, increase the high-frequency components of the sound effects, increase the intensity of the background music, and enhance the clarity of the ambient sound. If the emotion changes to relaxation and calmness, reduce the high-frequency components of the sound effects, smooth the background music, and reduce the irritation of the ambient sound.

[0035] If the speech speed changes to faster speech speed, the rhythm and dynamic range of the surround sound are improved; if the speech speed changes to slower speech speed, the rhythm and dynamic range of the surround sound are reduced;

[0036] If the tone changes to a rising tone, the volume and the clarity of the ambient sound are increased; if the tone changes to a falling tone, the volume and the fullness of the ambient sound are decreased;

[0037] A dynamic voiceprint matching algorithm is designed to map the predicted voiceprint change parameters to the sound effect adjustment parameters. The formula is:

[0038] Y=W·P+b

[0039] Among them, Y is the sound effect adjustment parameter, W is the weight matrix, P is the predicted voiceprint change parameter, and b is the bias vector.

[0040] As a preferred solution of the method and system for optimizing the sound effects of gaming headphones through voiceprint recognition as described in the present invention, wherein: the collection and analysis of user feedback data and adjustment of the weights of the change parameters of the voiceprint signal refer to collecting user feedback data on the sound effects through a user interface, converting the feedback data into structured data, analyzing the feedback data using statistical methods, determining the sound effect adjustment parameters based on the feedback data using linear regression, and adjusting the weights of each voiceprint change parameter.

[0041] As a preferred solution of the method and system for optimizing the sound effects of gaming headphones through voiceprint recognition described in the present invention, wherein: the storing of data in a database to establish an index, and performing backup and integrity testing refers to collecting and analyzing user feedback data, storing the collected, analyzed and user interface feedback data in a database, establishing a data index, retrieving the stored data as needed, backing up the database, and regularly performing integrity testing on the stored data.

[0042] Another object of the present invention is to provide a system for optimizing the sound effects of gaming headsets through voiceprint recognition.

[0043] These include,

[0044] Voiceprint collection module, used to collect user voiceprint signals and perform preprocessing;

[0045] Voiceprint analysis module, used to analyze the voiceprint signal characteristics and extract the change parameters of the voiceprint signal;

[0046] The voiceprint prediction module is used to build a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the voiceprint signal in the future;

[0047] A sound effect optimization module, used to map the change parameters of the predicted voiceprint signal to sound effect adjustment parameters;

[0048] Feedback adjustment module, used to collect and analyze user feedback data and adjust the weight of the change parameters of the voiceprint signal;

[0049] The storage module is used to store data in the database to create indexes, perform backup and integrity checks.

[0050] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned method and system for optimizing the sound effects of gaming headphones through voiceprint recognition when executing the computer program.

[0051] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method and system for optimizing the sound effects of gaming headphones through voiceprint recognition.

[0052] The beneficial effects of the present invention are as follows: the present invention collects the voiceprint signal of the user, uses frequency domain analysis to extract voiceprint features and change parameters, provides a key basis for personalized sound effect adjustment, constructs an LSTM model, improves the predictability and foresight of sound effect adjustment, and achieves accurate mapping of voiceprint features and sound effect parameters by defining sound effect adjustment rules, significantly improves the level of sound effect personalization, collects user feedback and adjusts voiceprint parameter weights to form a closed-loop feedback system. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0054] Figure 1 A flowchart of a method for optimizing the sound effects of gaming headsets through voiceprint recognition;

[0055] Figure 2 A flow chart for analyzing the characteristics of voiceprint signals and extracting the change parameters of voiceprint signals;

[0056] Figure 3 A flowchart of a system for optimizing the sound effects of gaming headsets through voiceprint recognition; DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and which provides a method and system for optimizing the sound effects of gaming headsets through voiceprint recognition. The method for optimizing the sound effects of gaming headsets through voiceprint recognition includes:

[0061] S1. Collect user voiceprint signals and pre-process them;

[0062] Specifically, collecting the user's voiceprint signal and preprocessing it means collecting the user's voiceprint signal in real time during the game through the microphone of the gaming headset, and preprocessing the collected voiceprint signal, including denoising, normalization and frame processing;

[0063] Perform short-time Fourier transform on each frame of voiceprint signal after the frame processing to convert it into frequency domain and obtain the spectrum of each frame.

[0064] By collecting user voiceprint signals in real time through gaming headsets and performing preprocessing, including denoising, normalization and framing processing, as well as subsequent short-time Fourier transform frequency domain conversion, the accuracy and stability of voiceprint recognition can be effectively improved, providing a better experience for voice interaction during the game, and laying the foundation for the realization of gaming functions based on voiceprint recognition.

[0065] S2. Analyze the characteristics of the voiceprint signal and extract the change parameters of the voiceprint signal;

[0066] Specifically, analyzing the voiceprint signal characteristics and extracting the change parameters of the voiceprint signal means filtering the spectrum through a Mel filter bank to obtain a Mel spectrum energy spectrum, and the formula is:

[0067]

[0068] Among them, M m is the output of the mth Mel filter, X(k) is the spectrum of each frame, H m (k) is the frequency response of the m-th Mel filter, k is the frequency index, and N is the number of sampling points in each frame;

[0069] After taking the logarithm of each Mel frequency energy spectrum and performing discrete cosine transform, the MFCC coefficient is obtained. The formula is:

[0070]

[0071] Among them, C n is the nth MFCC coefficient, log(M m) is the logarithmic energy of the output of the mth Mel filter, M is the number of Mel filter banks;

[0072] The MFCC coefficients are combined into a feature vector MFCC, and the Euclidean distance d between the current frame and the previous frame is calculated using the feature vector MFCC. The formula is:

[0073]

[0074] Where d is the Euclidean distance between the current frame and the previous frame, N MFCC is the number of MFCC coefficients extracted, C c,n Indicates the nth MFCC coefficient of the current frame, C p,n Indicates the nth MFCC coefficient of the previous frame;

[0075] According to the suggestions of the literature, the change threshold T is preliminarily defined, the impact of the threshold on the detection of voiceprint signal changes is observed, and the threshold T is adjusted by statistically analyzing the detection accuracy and false alarm rate under different thresholds;

[0076] Compare the calculated Euclidean distance d with the change threshold T to determine the type of voiceprint signal change:

[0077] If d ≥ T, it is determined that the voiceprint signal has changed. Record this change and extract the change parameters of the voiceprint signal, including emotion, speech rate, and intonation.

[0078] If d < T, it is determined that the voiceprint signal has not changed and no change is recorded.

[0079] Analyze the extracted change parameters of the voiceprint signal and classify and store the change parameters of the voiceprint signal, including:

[0080] For the spectrum of each frame of the voiceprint signal after frequency-domain conversion, extract the high-frequency components in the spectrum, calculate the total energy of the high-frequency components and the total energy of the high-frequency components of the historical frames. If the total energy of the high-frequency components of the current frame is greater than the total energy of the high-frequency components of the historical frames, it is determined that the emotional change is excitement and tension. If the total energy of the high-frequency components of the current frame is less than the total energy of the high-frequency components of the historical frames, it is determined that the emotional change is relaxation and calm.

[0081] Use VAD (Voice Activity Detection) to detect the voiceprint activity in the voiceprint signal, distinguish the states in each frame of the voiceprint signal, including speech frames and silence frames. For each detected speech frame, record its timestamp, calculate the time interval between adjacent speech frames and the historical average interval time between all adjacent speech frames. If the time interval between speech frames is greater than the historical average interval time between all adjacent speech frames, it is determined that the speech rate change is an increase in speech rate. If the time interval between speech frames is less than the historical average interval time between all adjacent speech frames, it is determined that the speech rate change is a decrease in speech rate.

[0082] Use the autocorrelation method to determine the periodicity and frequency characteristics of the voiceprint signal, and calculate the autocorrelation function R(γ) for each frame of the voiceprint signal:

[0083]

[0084] where v(u) is each frame of the voiceprint signal after frame processing, γ is the delay amount between each frame of the voiceprint signal, Q is the length of each frame, and u is the sampling point index of each frame of the voiceprint signal.

[0085] Find the peak position of the autocorrelation function and calculate the fundamental frequency. Smooth the extracted fundamental frequency using a moving average filter, calculate the difference f between the fundamental frequency of the current frame and the previous frame. According to the suggestions in the literature, initially define the intonation change threshold T p , and adjust the value of T by comparing the actual intonation change situation. p If f ≥ T p , it is determined that the intonation has changed and the fundamental frequency is recorded. If f < T p , it is determined that the intonation has not changed and the fundamental frequency is not recorded.

[0086] By analyzing the characteristics of voiceprint signals and extracting change parameters, we can achieve a deep understanding and high-precision monitoring of voiceprint signals. By calculating the Euclidean distance of the MFCC feature vector, we can effectively identify subtle changes in voiceprint signals, thereby determining whether the voiceprint signal has changed. By identifying emotional changes, we can better understand the speaker's psychological state and provide support for emotional computing and user experience optimization. By monitoring changes in speaking speed, we can accurately grasp the speaker's expression rhythm, which is of great significance to language teaching, speech recognition and other fields. By analyzing changes in intonation, it helps to improve the naturalness and expressiveness of speech synthesis and speech interaction systems. This method can also classify and store the change parameters of voiceprint signals, providing a rich data basis for subsequent data analysis and application, which not only improves the accuracy and efficiency of voiceprint signal processing, but also enhances the naturalness and intelligence of human-computer interaction.

[0087] S3, constructing a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the voiceprint signal in the future;

[0088] Specifically, constructing a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the future voiceprint signal refers to using an LSTM neural network to construct a voiceprint prediction model, including an input layer, a hidden layer, and an output layer;

[0089] The input layer is the change parameters of the voiceprint signal;

[0090] The hidden layer has multiple LSTM units to capture time series features, including the user's emotions, speech speed, and tone changes at different time points;

[0091] The output layer is the change parameter of the predicted voiceprint signal;

[0092] The change parameters of the voiceprint signal stored in the cell state are determined through the input gate and the forget gate, the cell state is updated based on the results of the input gate and the forget gate, and the predicted change parameters of the voiceprint signal are output through the output gate;

[0093] Divide the change parameters of the voiceprint signal into a training set and a test set;

[0094] The input data passes through the LSTM layer, and the error between the predicted value and the true value is calculated, using the mean square error as the loss function;

[0095] The model parameters are updated through the error direction propagation algorithm, and the Adam optimization algorithm is used to adjust the learning rate and weight;

[0096] The user's real-time voiceprint data is input into the trained LSTM model to obtain the predicted change parameters of the voiceprint signal.

[0097] The voiceprint prediction model based on LSTM neural network is constructed, which can effectively analyze the changing parameters of voiceprint signals and predict future voiceprint change trends. By capturing the changes in users' emotions, speaking speed and intonation at different time points, the ability to understand the dynamic characteristics of voiceprint signals is improved. By utilizing the storage and forgetting mechanism of LSTM units, the model can learn and memorize the time series characteristics of voiceprint signals, thereby more accurately predicting voiceprint changes. By dividing the training set and the test set, and using the mean square error as the loss function, the model is continuously optimized during the training process to improve the accuracy of the prediction. The Adam optimization algorithm is used to adjust the learning rate and weights to further improve the convergence speed and prediction performance of the model. By inputting real-time voiceprint data into the model, the future change trend of the voiceprint signal can be predicted. This has important practical application value in improving the robustness of speech recognition systems, optimizing human-computer interaction experience, and developing personalized voice applications.

[0098] S4, mapping the predicted change parameters of the voiceprint signal to the sound effect adjustment parameters;

[0099] Specifically, mapping the predicted change parameters of the voiceprint signal to the sound effect adjustment parameters means defining corresponding sound effect adjustment rules to adjust the sound effect adjustment parameters according to the predicted voiceprint change parameters, including the total energy of high-frequency components, the time interval between speech frames, and the difference f between the basic frequencies of the current frame and the previous frame. The sound effect adjustment parameters include volume, frequency components, and surround sound:

[0100] If the emotion changes to excitement and tension, increase the high-frequency components of the sound effects, increase the intensity of the background music, and enhance the clarity of the ambient sound. If the emotion changes to relaxation and calmness, reduce the high-frequency components of the sound effects, smooth the background music, and reduce the irritation of the ambient sound.

[0101] If the speech speed changes to faster speech speed, the rhythm and dynamic range of the surround sound are improved; if the speech speed changes to slower speech speed, the rhythm and dynamic range of the surround sound are reduced;

[0102] If the tone changes to a rising tone, the volume and the clarity of the ambient sound are increased; if the tone changes to a falling tone, the volume and the fullness of the ambient sound are decreased;

[0103] A dynamic voiceprint matching algorithm is designed to map the predicted voiceprint change parameters to the sound effect adjustment parameters. The formula is:

[0104] Y=W·P+b

[0105] Among them, Y is the sound effect adjustment parameter, W is the weight matrix, P is the predicted voiceprint change parameter, and b is the bias vector;

[0106] The weight matrix W is expressed as:

[0107]

[0108] Among them, the weight matrix W is a 3×3 matrix, and each element W ij represents the weight between the i-th sound effect adjustment parameter and the j-th voiceprint signal change parameter;

[0109] The bias vector b is expressed as:

[0110]

[0111] Among them, the bias vector b is a three-dimensional vector, each element b i Represented as the bias value of the i-th sound effect adjustment parameter;

[0112] Find relevant literature and industry standards, and define weight matrices and bias vectors based on them.

[0113] The predicted voiceprint change parameters are mapped to the sound effect adjustment parameters. By designing a dynamic voiceprint matching algorithm, intelligent adjustment of the sound effects is achieved. The sound effect parameters are adjusted in real time according to the user's emotions, speaking speed and intonation changes, thereby improving the personalization and interactivity of the audio experience. By increasing or decreasing the high-frequency components of the sound effects, the system can better match the user's emotional state and enhance the immersion and comfort of music and ambient sound. The rhythm and dynamic range of the surround sound are adjusted according to changes in speaking speed, so that the sound effects are synchronized with the speaking rhythm, thereby improving the naturalness of the auditory experience. The clarity or fullness of the volume and ambient sound is adjusted through changes in intonation to further enrich the auditory experience. This intelligent sound effect adjustment not only enhances the emotional transmission effect of the audio content, but also enhances the user's auditory enjoyment in different scenarios.

[0114] S5. Collect and analyze user feedback data and adjust the weight of the change parameters of the voiceprint signal;

[0115] Specifically, collecting and analyzing user feedback data and adjusting the weights of the change parameters of the voiceprint signal means collecting user feedback data on sound effects through the user interface, converting the feedback data into structured data, analyzing the feedback data using statistical methods, and based on the feedback data, using linear regression to determine the sound effect adjustment parameters and adjust the weights of each voiceprint change parameter.

[0116] Sound effect feedback data is collected through the user interface and converted into structured data. Then, statistical methods and linear regression analysis are used to determine the sound effect adjustment parameters and adjust the weights of the voiceprint change parameters, forming a closed-loop feedback mechanism. This makes the sound effect adjustment more in line with the user's personalized needs and preferences, and can effectively improve the adaptability of the sound effect system and user satisfaction. By continuously optimizing the weight configuration, the sound effect is made more delicate and accurate, thereby enhancing the comfort and immersion of the user experience.

[0117] S6. Store the data in a database to create an index, perform backup and integrity check;

[0118] Specifically, storing data in a database, creating an index, and performing backup and integrity checks refers to collecting and analyzing user feedback data, storing the collected and analyzed data as well as the user interface feedback data in a database, creating a data index, retrieving the stored data as needed, backing up the database, and regularly performing integrity checks on the stored data.

[0119] Storing user feedback data in the database and indexing it, as well as performing backup and integrity testing, ensures data security and manageability. Indexing improves data retrieval efficiency, enabling quick access and analysis of user feedback information. Regular backup ensures that data will not be lost accidentally, maintaining data persistence and reliability. Integrity testing ensures the accuracy and consistency of stored data, preventing potential problems caused by data corruption or tampering.

[0120] Example 2, reference Figure 3 , which is the second embodiment of the present invention, and is different from the previous embodiment, and provides a system for optimizing the sound effects of gaming headsets through voiceprint recognition, which includes:

[0121] Voiceprint collection module, used to collect user voiceprint signals and perform preprocessing;

[0122] Voiceprint analysis module, used to analyze the voiceprint signal characteristics and extract the change parameters of the voiceprint signal;

[0123] The voiceprint prediction module is used to build a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the voiceprint signal in the future;

[0124] A sound effect optimization module, used to map the change parameters of the predicted voiceprint signal to sound effect adjustment parameters;

[0125] Feedback adjustment module, used to collect and analyze user feedback data and adjust the weight of the change parameters of the voiceprint signal;

[0126] The storage module is used to store data in the database to create indexes, perform backup and integrity checks.

[0127] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0128] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0129] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0130] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0131] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the sound effects of gaming headphones through voiceprint recognition, characterized in that: including collecting the user's voiceprint signal and performing preprocessing analyzing the voiceprint signal features and extracting the change parameters of the voiceprint signal constructing a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the future voiceprint signal mapping the predicted change parameters of the voiceprint signal to the sound effect adjustment parameters collecting and analyzing the user feedback data and adjusting the weight of the change parameters of the voiceprint signal storing the data in a database, establishing an index, and performing backup and integrity detection 2. The method for optimizing the sound effects of gaming headsets through voiceprint recognition according to claim 1, characterized in that: The step of collecting the user's voiceprint signal and performing preprocessing refers to collecting the user's voiceprint signal during the game in real time through the microphone of the game headset, and performing preprocessing on the collected voiceprint signal, including denoising, normalization, and framing processing performing short-time Fourier transform on each frame of the voiceprint signal after the framing process to perform frequency domain conversion, and obtaining the spectrum of each frame 3. The method for optimizing the sound effects of gaming headsets through voiceprint recognition as claimed in claim 2, characterized in that: The step of analyzing the voiceprint signal features and extracting the change parameters of the voiceprint signal refers to filtering the spectrum through a Mel filter bank to obtain the Mel spectrum energy spectrum, taking the logarithm of each Mel frequency energy spectrum and then performing discrete cosine transform to obtain the MFCC coefficients, forming the feature vector MFCC with the MFCC coefficients, and using the feature vector MFCC to calculate the Euclidean distance d between the current frame and the previous frame. The formula is Where d is the Euclidean distance between the current frame and the previous frame, N MFCC is the number of MFCC coefficients extracted, C c,n Indicates the nth MFCC coefficient of the current frame, C p,n Indicates the nth MFCC coefficient of the previous frame; defining a change threshold T, and comparing the calculated Euclidean distance d with the change threshold T to judge the type of change of the voiceprint signal If d≥T, it is judged that the voiceprint signal has changed, record the change, and extract the change parameters of the voiceprint signal, including emotion, speech rate, and intonation If d<T, it is judged that the voiceprint signal has not changed, and the change is not recorded analyzing the extracted change parameters of the voiceprint signal and classifying and storing the change parameters of the voiceprint signal, including For the spectrum of each frame of the voiceprint signal after frequency domain conversion, extract the high-frequency components in the spectrum, calculate the total energy of the high-frequency components and the total energy of the high-frequency components of the historical frames. If the total energy of the high-frequency components of the current frame is greater than the total energy of the high-frequency components of the historical frames, it is determined that the emotional change is excitement and tension. If the total energy of the high-frequency components of the current frame is less than the total energy of the high-frequency components of the historical frames, it is determined that the emotional change is relaxation and calm Using VAD voice activity detection to mark the state of each frame of the voiceprint signal, including voice frames and silent frames. For each detected voice frame, record its timestamp, calculate the time interval between adjacent voice frames and the historical average interval time between all adjacent voice frames. If the time interval between voice frames is greater than the historical average interval time between all adjacent voice frames, it is determined that the speech rate change is an increase in speech rate. If the time interval between voice frames is less than the historical average interval time between all adjacent voice frames, it is determined that the speech rate change is a decrease in speech rate Use the autocorrelation method to determine the periodicity and frequency characteristics of each frame of the voiceprint signal. Calculate the peak position of the autocorrelation function and the basic frequency of each frame of the voiceprint signal. Use a sliding average filter to smooth the extracted basic frequency. Calculate the difference f between the basic frequency of the current frame and the previous frame, and define the intonation change threshold T. p , if f ≥ T p , then determine that the tone has changed and record the basic frequency. If f <T p , the tone is judged to have not changed and the basic frequency is not recorded.

4. The method for optimizing the sound effects of gaming headsets through voiceprint recognition as claimed in claim 3, characterized in that: The step of constructing a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the future voiceprint signal refers to using an LSTM neural network to construct a voiceprint prediction model, including an input layer, a hidden layer, and an output layer The input layer is the change parameters of the voiceprint signal The hidden layer has multiple LSTM units to capture time series features, and capturing time series features includes the changes in emotion, speech rate, and intonation of the user at different time points The output layer is the predicted change parameters of the voiceprint signal The change parameters of the voiceprint signal stored in the cell state are determined through the input gate and the forget gate, the cell state is updated based on the results of the input gate and the forget gate, and the predicted change parameters of the voiceprint signal are output through the output gate; Divide the change parameters of the voiceprint signal into a training set and a test set; The input data passes through the LSTM layer, and the error between the predicted value and the true value is calculated, using the mean square error as the loss function; The model parameters are updated through the error direction propagation algorithm, and the Adam optimization algorithm is used to adjust the learning rate and weight; The user's real-time voiceprint data is input into the trained LSTM model to obtain the predicted change parameters of the voiceprint signal.

5. The method for optimizing the sound effects of gaming headsets through voiceprint recognition as claimed in claim 4, characterized in that: Mapping the predicted change parameters of the voiceprint signal to the sound effect adjustment parameters refers to defining corresponding sound effect adjustment rules to adjust the sound effect adjustment parameters according to the predicted voiceprint change parameters, including the total energy of high-frequency components, the time interval between speech frames, and the difference f between the basic frequencies of the current frame and the previous frame. The sound effect adjustment parameters include volume, frequency components, and surround sound: If the emotion changes to excitement and tension, increase the high-frequency components of the sound effects, increase the intensity of the background music, and enhance the clarity of the ambient sound. If the emotion changes to relaxation and calmness, reduce the high-frequency components of the sound effects, smooth the background music, and reduce the irritation of the ambient sound. If the speech speed changes to faster speech speed, the rhythm and dynamic range of the surround sound are improved; if the speech speed changes to slower speech speed, the rhythm and dynamic range of the surround sound are reduced; If the tone changes to a rising tone, the volume and the clarity of the ambient sound are increased; if the tone changes to a falling tone, the volume and the fullness of the ambient sound are decreased; A dynamic voiceprint matching algorithm is designed to map the predicted voiceprint change parameters to the sound effect adjustment parameters. The formula is: Y=W·P+b Among them, Y is the sound effect adjustment parameter, W is the weight matrix, P is the predicted voiceprint change parameter, and b is the bias vector.

6. The method for optimizing the sound effects of gaming headsets through voiceprint recognition as claimed in claim 5, characterized in that: The collecting and analyzing of user feedback data and adjusting the weights of the change parameters of the voiceprint signal refers to collecting user feedback data on the sound effects through a user interface, converting the feedback data into structured data, analyzing the feedback data using statistical methods, and determining the sound effect adjustment parameters based on the feedback data using linear regression, and adjusting the weights of various voiceprint change parameters.

7. The method for optimizing the sound effects of gaming headsets through voiceprint recognition according to claim 6, characterized in that: The storing of data in a database, indexing, backing up and integrity checking refers to collecting and analyzing user feedback data, storing the collected and analyzed data as well as the feedback data from the user interface in a database, establishing a data index, retrieving the stored data as needed, backing up the database, and regularly performing integrity checks on the stored data.

8. A system for optimizing gaming headset sound effects through voiceprint recognition according to any one of claims 1 to 7, characterized in that: include, Voiceprint collection module, used to collect user voiceprint signals and perform preprocessing; Voiceprint analysis module, used to analyze the voiceprint signal characteristics and extract the change parameters of the voiceprint signal; The voiceprint prediction module is used to build a voiceprint prediction model to analyze the change parameters of the voiceprint signal and predict the change parameters of the voiceprint signal in the future; A sound effect optimization module, used to map the predicted voiceprint change parameters to sound effect adjustment parameters; Feedback adjustment module, used to collect and analyze user feedback data and adjust the weight of voiceprint change parameters; The storage module is used to store data in the database to create indexes, perform backup and integrity checks.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method and system for optimizing the sound effects of gaming headphones through voiceprint recognition as described in any one of claims 1 to 7 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 and system for optimizing the sound effects of gaming headphones through voiceprint recognition described in any one of claims 1 to 7 are implemented.