Audio signal processing method, audio signal processing device and storage medium

Abstract

The present application discloses an audio signal processing method, an audio signal processing device and a storage medium, and relates to the field of speech signal processing technology. The present application discloses an audio signal processing method, including: when receiving an audio signal to be played, determining filter setting parameters for processing the audio signal to be played according to an audio preference model and a user's hearing characteristic curve; based on the filter setting parameters, adjusting the audio signal to be played through an adaptive filter to obtain a target audio signal; and outputting the target audio signal. When adjusting the audio signal, the output audio is adjusted in real time by analyzing the user's hearing characteristics and audio preferences, providing a personalized auditory experience and improving the audio adjustment effect.

Description

Technical Field

[0001] The present application relates to the technical field of speech signal processing, and in particular to an audio signal processing method, an audio signal processing device and a storage medium. Background Art

[0002] In the existing audio signal processing technology, the received audio signal is usually improved through equalizers, adaptive filters and dynamic range compression technologies. However, in the actual processing process, fixed parameters are usually used to process the audio signal. For example, the equalizer adjusts the frequency components of the audio signal through fixed parameters, the compression ratio and threshold of the dynamic range compression are preset, and the parameters of the adaptive filter and the algorithm used are preset. Therefore, the existing audio signal processing technology cannot make personalized adjustments to the audio signal, resulting in poor audio adjustment effect.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide an audio signal processing method, an audio signal processing device and a storage medium, aiming to solve the technical problem that the existing audio signal processing technology cannot perform personalized adjustment on the audio signal, resulting in poor audio adjustment effect.

[0005] To achieve the above object, the present application proposes an audio signal processing method, the method comprising:

[0006] When receiving an audio signal to be played, determining filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user;

[0007] Based on the filter setting parameters, the audio signal to be played is adjusted by an adaptive filter to obtain a target audio signal;

[0008] The target audio signal is output.

[0009] In one embodiment, when the audio signal to be played is received, the step of determining the filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user comprises:

[0010] When the audio signal to be played is received, a gain curve of the hearing characteristic curve at each frequency point is calculated based on the audio preference model, wherein the gain curve includes the hearing characteristics and audio preferences of the user;

[0011] The gain values ​​of the filter in different frequency bands and the filter coefficients defining the frequency response characteristics of the filter are determined based on the gain curve, and the gain values ​​and the filter coefficients are used as the filter setting parameters.

[0012] In one embodiment, the step of adjusting the audio signal to be played by an adaptive filter based on the filter setting parameters to obtain a target audio signal includes:

[0013] Adjusting the current filter according to the filter coefficient to obtain the adaptive filter;

[0014] The audio signal to be played is filtered by the adaptive filter, and based on the gain value, the amplitude of the audio signal to be played is adjusted by the gain control algorithm of the adaptive filter to obtain the target audio signal.

[0015] In one embodiment, when the audio signal to be played is received, before the step of determining the filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user, the step further includes:

[0016] Acquire a training data set and a test data set, wherein the training data set includes the preprocessed audio playback history and historical feedback information of the user;

[0017] Training a pre-stored deep learning model based on the training data set to obtain an initial model;

[0018] Generate an enhanced training set according to the received current feedback information, and iteratively optimize and adjust the initial model based on the enhanced training set to obtain a target model;

[0019] The target model is subjected to performance evaluation processing based on the test data set, and when the performance evaluation result meets the preset requirements, the target model is used as the audio preference model.

[0020] In one embodiment, when the audio signal to be played is received, before the step of determining the filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user, the step further includes:

[0021] Acquiring hearing test data of the user;

[0022] Processing the hearing test data based on a machine learning model to obtain the hearing sensitivity of the user corresponding to different audio frequency bands;

[0023] The hearing characteristic curve is generated according to the hearing sensitivity.

[0024] In one embodiment, after the step of outputting the target audio signal, the method further includes:

[0025] Acquiring target feedback information of the target audio signal;

[0026] Determining an audio adjustment parameter that needs to be adjusted based on the target feedback information;

[0027] The audio preference model is updated according to the audio adjustment parameter.

[0028] In one embodiment, the step of determining the audio adjustment parameter to be adjusted based on the target feedback information includes:

[0029] Determining an adjustment parameter associated with the target feedback information;

[0030] The adjustment parameters are processed based on a reinforcement learning algorithm to obtain the adjusted audio adjustment parameters.

[0031] In one embodiment, after the step of outputting the target audio signal, the method further includes:

[0032] The audio adjustment instruction input by the user is obtained, and based on the audio adjustment instruction, the step of adjusting the audio signal to be played by using an adaptive filter to obtain a target audio signal is performed.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes an audio signal processing device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the audio signal processing method described above.

[0034] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, and stores a computer program on the storage medium. When the computer program is executed by a processor, the steps of the audio signal processing method described above are implemented.

[0035] One or more technical solutions proposed in this application have at least the following technical effects:

[0036] After receiving the audio signal to be played, the user's hearing characteristic curve is analyzed and processed through the audio preference model to obtain the filter setting parameters. Based on these parameters, the content of the output audio is adjusted in real time through the adaptive filter, and then personalized adjustment is achieved for the audio signal, providing users with personalized auditory experience and improving the audio adjustment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 A schematic diagram of a flow chart of a first embodiment of the audio signal processing method provided by the present application;

[0040] Figure 2 A schematic diagram of a flow chart of a second embodiment of the audio signal processing method provided by the present application;

[0041] Figure 3 Another flowchart of the second embodiment of the audio signal processing method provided by the present application;

[0042] Figure 4 A schematic diagram of a flow chart of a third embodiment of the audio signal processing method provided by the present application;

[0043] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the audio signal processing method in the embodiment of the present application.

[0044] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0046] The main solution of the embodiment of the present application is: when receiving an audio signal to be played, determining filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user;

[0047] Based on the filter setting parameters, the audio signal to be played is adjusted by an adaptive filter to obtain a target audio signal;

[0048] The target audio signal is output.

[0049] In this embodiment, for ease of description, the following description is made by taking the audio signal processing device as the execution subject.

[0050] In the existing audio signal processing technology, the received audio signal is usually improved through equalizers, adaptive filters and dynamic range compression technologies. However, in the actual processing process, fixed parameters are usually used to process the audio signal. For example, the equalizer adjusts the frequency components of the audio signal through fixed parameters, the compression ratio and threshold of the dynamic range compression are preset, and the parameters of the adaptive filter and the algorithm used are preset. Therefore, the existing audio signal processing technology cannot make personalized adjustments to the audio signal, resulting in poor audio adjustment effect.

[0051] The present application provides a solution. When an audio signal is received, the control parameters for adjusting the audio signal are determined based on the hearing characteristic curve of the current user and the audio preference model constructed based on the actual preferences of the user. Subsequently, based on the control parameters, the audio signal is adjusted through a filter and a gain control algorithm of the filter. Finally, the target audio signal is output. Based on this, the output audio can be adjusted according to the actual needs of the user, namely the hearing characteristics and audio preferences, thereby providing the user with a personalized auditory experience and improving the audio adjustment effect.

[0052] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, an audio signal processing device, etc. The following takes an audio signal processing device as an example to illustrate this embodiment and the following embodiments.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The present application provides an audio signal processing method, referring to Figure 1 , Figure 1 This is a flowchart diagram of the first embodiment of the audio signal processing method of the present application.

[0055] In this embodiment, the audio signal processing method includes steps S10 to S30:

[0056] Step S10, when receiving an audio signal to be played, determining filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user;

[0057] It should be noted that the audio signal to be played refers to the audio signal to be output and played in the scenarios of audio playback, voice communication, audio recording, and spatial audio rendering. For example, the next or current music to be played in the music player software. Hearing characteristics refer to the human ear's ability to perceive sound and its characteristics, including the sensitivity to sound frequency, loudness, direction and timbre. The hearing characteristic curve is the degree of hearing loss of the user in different frequency bands including low, medium and high audio frequency bands. For example, in the scenario of 100-300 Hz, the user will lose 5 decibels of hearing value. At this time, based on increasing 5 decibels in the frequency band, or increasing the loudness by 5 decibels at 100 Hz audio. The audio preference model is constructed based on the user's actual audio preferences, where audio preferences refer to the subjective preferences and choices of individuals or groups for different sound quality, style, and type of sound in audio listening and evaluation. Audio preference information includes the user's listening content type, sound quality and content preferences, usage habits and duration, as well as social and creative tendencies.

[0058] Optionally, the filter setting parameters include filter coefficients for defining the frequency response characteristics of the filter and gain values ​​for adjusting the gain of the filter at different frequencies, wherein the frequency response characteristics can be used to determine the type of filter and the processing effect of the filter on signals of different frequencies, for example, the filter needs to filter signals in a certain frequency band.

[0059] In this embodiment, after receiving the audio signal to be played, the user's hearing characteristic curve can be obtained through the user's hearing test data, for example, by analyzing the user's hearing test data through a machine learning model to obtain the user's hearing characteristic curve. The audio preference model can be obtained through the user's audio playback history and feedback information, etc., through learning processing and continuous feedback optimization iteration using a deep learning algorithm.

[0060] After obtaining the hearing characteristic curve and the audio preference model, it is necessary to generate the filter coefficients of the adaptive filter and the gain parameters of the filter gain control algorithm (AGC) based on the audio preference model, and then filter and gain process the audio signal. Based on the obtained filter setting parameters, the adaptive filter can adapt to different signal environments and requirements, and when processing the audio signal, it can not only compensate for hearing loss, but also meet the user's audio preferences. For example, when processing the audio signal, it can adapt to the actual needs of the user to ensure that the best audio experience can be provided to the user in various scenarios. The gain parameter includes the amplitude adjustment value of a certain frequency in the audio signal. For example, if the gain adjustment of the mid-frequency band is +5dB (Decibel, decibel), it means that the amplitude of all frequency points in the mid-frequency band will increase by 5dB. At the same time, according to the user's preference for audio, sound quality and specific frequency bands, an adaptive filter that meets the needs is selected, or the parameters of the adaptive filter are adjusted to make the filter meet the user's preferences for audio, sound quality and specific frequency bands.

[0061] In the existing method of adjusting audio, the control parameters of the adaptive filter are fixed, and the gain parameters corresponding to the gain control algorithm are fixed. The audio signal can only be adjusted based on specific adjustment parameters, so that the adjusted audio signal does not meet the user's needs, resulting in poor adjustment effect. In the embodiment of the present application, these control parameters are dynamically determined through the audio preference model and the user's hearing characteristic curve, so as to adjust the audio signal to an audio signal that meets the actual hearing needs of the current user, thereby improving the audio adjustment effect.

[0062] In the process of determining the filter setting parameters, the hearing characteristic curve is directly input into the audio preference model, and then the filter setting parameters are generated by the model. Specifically, in this process, when the audio signal to be played is received, the gain curve of the hearing characteristic curve at each frequency point is calculated based on the audio preference model, and the gain value in the gain curve is used to compensate for the user's hearing loss at a specific frequency, wherein before calculating the gain curve, the hearing characteristic curve needs to be preprocessed based on the audio preference model, including smoothing it to reduce noise and errors, and mapping the frequency points of the hearing characteristic curve to the frequency range required for filter design, and designing the corresponding filter type according to the processed hearing data, including finite pulse filter and infinite pulse filter. In the process of calculating the gain curve, linear interpolation can be performed between known frequency points to generate a continuous gain curve, and / or the gain curve can be fitted by a polynomial function, and the calculated gain curve contains the user's hearing characteristics and audio preferences.

[0063] Finally, the gain curve is applied to the design process of the filter setting parameters of the audio preference model, so as to determine the gain value of the filter in different frequency bands and the filter coefficient that defines the frequency response characteristics of the filter based on the gain curve, and the gain value and the filter coefficient are used as filter setting parameters. Through the filter parameters, the actual control parameters of the adaptive filter can be determined, and the gain of the processed audio can be adjusted based on the gain value to improve the audio processing effect.

[0064] By inputting the hearing characteristic curve into the audio preference model, the filter setting parameters of the adaptive filter and the gain parameters of the gain control algorithm of the filter are obtained. When the audio signal is processed based on the adaptive filter and the gain control algorithm of the filter, its parameters can be automatically adjusted according to the characteristics of the input signal and environmental changes, thereby effectively optimizing the computational efficiency of the algorithm and ensuring real-time processing with low latency, so that users can instantly enjoy the optimized audio effect, and at the same time make the processed custom audio signal meet user needs, thereby improving the effectiveness of audio processing.

[0065] Step S20, adjusting the audio signal to be played through an adaptive filter based on the filter setting parameters to obtain a target audio signal;

[0066] In this embodiment, the audio output can be adjusted in real time through the adaptive filter and the gain control algorithm of the adaptive filter so that the adjusted audio meets the actual needs of the user. During the adjustment process, the audio signal can be mainly subjected to filtering processing such as noise suppression, signal enhancement and echo cancellation based on the adaptive filter, and the amplitude of the audio signal to be processed can be adjusted based on the gain control algorithm.

[0067] Specifically, the current filter can be adjusted based on the filter coefficient to obtain the adaptive filter, and then the audio signal to be played is filtered by the adaptive filter. At the same time, based on the gain parameter, the amplitude of the audio signal to be played is adjusted by the gain control algorithm of the adaptive filter to obtain the target audio signal.

[0068] Based on the filter setting parameters, the adaptive filter filters the audio signal to be played, so that the processed audio signal meets the actual personalized needs of the user. At the same time, based on the generated gain parameters, the gain control algorithm adjusts the amplitude of the audio signal to be played, so that the target audio signal meets the personalized needs of the user.

[0069] Step S30: output the target audio signal.

[0070] After obtaining the target audio signal, the target audio signal is played in the playback interface or through a speaker, so that the user can intuitively experience the personalized adjusted audio data.

[0071] This embodiment provides an audio signal processing method. When receiving an audio signal to be played, the audio preference model generated based on the user's audio preference information processes the user's hearing characteristic curve, generates filter setting parameters including filter coefficients and gain parameters, and finally adjusts the audio signal to be played through an adaptive filter corresponding to the filter setting parameters and a gain control algorithm of the adaptive filter to ensure that the output target audio signal matches the user's hearing characteristics and preferences. Based on this, by analyzing the user's hearing characteristics and audio preferences, and outputting audio based on machine learning and deep learning technologies, the audio adjustment effect is improved.

[0072] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 2 Before step S10, it is also necessary to obtain the user's hearing characteristic curve and audio preference model. Based on this, the audio signal processing method further includes steps S01 to S03:

[0073] Step S01, obtaining hearing test data of the user;

[0074] Step S02, processing the hearing test data based on a machine learning model to obtain the hearing sensitivity of the user corresponding to different audio frequency bands;

[0075] Step S03: generating the hearing characteristic curve according to the hearing sensitivity.

[0076] In this embodiment, the user's hearing test data can be collected through hearing test equipment or music playback applications, programs, and web pages. After the hearing test data is obtained, the user's hearing sensitivity in different frequency bands such as low frequency, medium frequency, and high frequency is extracted based on the machine learning model. Finally, the extracted hearing sensitivity data is used to train a machine learning model, such as a support vector machine (SVM) or a random forest, to learn how to predict the user's hearing characteristic curve based on the input hearing data, that is, to obtain the hearing characteristic curve based on the trained model. Based on the hearing characteristic curve, the user's sensitivity to sounds of different frequencies is displayed, thereby helping to understand the user's hearing condition. Improve the effectiveness of processing audio signals based on the hearing characteristic curve.

[0077] For further information, please refer to Figure 3 , before step S10, it also includes steps S04 to S07:

[0078] Step S04, obtaining a training data set and a test data set;

[0079] In this embodiment, the training data set includes the preprocessed audio playback history and historical feedback information of the user, wherein, in the process of preprocessing the data, the user's audio playback history and historical feedback information when using the audio preference model are first collected, and then these data are cleaned to remove noise and outliers, and then the audio playback history data and historical feedback information are annotated to obtain the training data set. Using the audio playback history data as part of the training data set helps the model to accurately learn the user's audio preferences. The user can input feedback information through questionnaires, audio file evaluations, etc.

[0080] Step S05, training a pre-stored deep learning model based on the training data set to obtain an initial model;

[0081] During the model training process, you can select a model that meets your needs from the pre-existing deep learning models, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), and initialize the model parameters. During the training process, the training data set is used as the initial training set to train the model and obtain the initial model.

[0082] Step S06, generating an enhanced training set according to the received feedback information, and iteratively optimizing and adjusting the initial model based on the enhanced training set to obtain a target model;

[0083] In this embodiment, after the initial model is obtained, the model needs to be continuously iterated and optimized. During the iterative process, user feedback information of the initial model after each iteration can be obtained, and then the model is continuously iterated and optimized based on the feedback information.

[0084] Specifically, the feedback information can be integrated into the training data set to form an enhanced training set. During the optimization iteration and adjustment process, weights can be allocated according to the importance of the current feedback to ensure the importance of key feedback information when iterative optimization training of the model is performed based on the enhanced training set, while improving the accuracy of the model.

[0085] In the process of iterative optimization and adjustment of the initial model, the loss function can also be adjusted based on the content of user feedback to better reflect user needs, for example, user satisfaction in the feedback information can be used as part of the loss function. In terms of the selection of optimization algorithms, algorithms such as Adam and RMSprop can be selected to improve training efficiency and effect. Furthermore, the gradient can be calculated through the back-propagation algorithm, and the model parameters can be updated according to the gradient.

[0086] Step S07, performing performance evaluation processing on the target model based on the test data set, and when the performance evaluation result meets the preset requirements, using the target model as the audio preference model.

[0087] In this embodiment, the target model after each iteration is usually evaluated based on the test data set, and the evaluation process includes evaluation of indicators such as model accuracy, recall rate and F1 value. Then, when the evaluation result meets the preset requirements, the target model is used as the audio preference model, that is, the audio preference model is obtained.

[0088] This embodiment provides an audio signal processing method, which generates the hearing characteristic curves corresponding to different frequency bands through the user's hearing sensitivity, so that when the hearing characteristic curves are input into the audio preference model, the output parameters meet the user's actual hearing needs. At the same time, by utilizing machine learning and deep learning technologies, the model is trained on the user's audio playback history and feedback information, and the model is further optimized based on the feedback information of the model iterative optimization process to improve the model training effect.

[0089] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can refer to the above introduction, and will not be repeated later. Figure 4 After step S30, the audio signal processing method of the present application further includes steps S40 to S60:

[0090] Step S40, obtaining target feedback information of the target audio signal;

[0091] In this embodiment, the user can input target feedback information of the target audio after audio adjustment through questionnaires, audio file evaluation, etc., so that the audio signal processing device can update the audio preference model or update the user's preference information based on the feedback information.

[0092] Step S50, determining the audio adjustment parameters that need to be adjusted based on the target feedback information;

[0093] The audio adjustment parameter may be a gain parameter of an adaptive filter. After the user obtains the target audio signal, based on the audio signal, the user may feedback that the current audio bass is too strong, the treble is harsh, etc., and then obtain a new gain parameter for adjusting the gain of the low-frequency band and the high-frequency band. In addition, the audio adjustment parameter may also be used to update the audio preference model. For example, the user may input the content that needs to be iteratively optimized for the current audio preference model in the historical feedback information, and the audio preference model may be iteratively optimized based on the obtained content.

[0094] In this embodiment, as an optional implementation, the adjustment parameters associated with the target feedback information can be determined first, and then the adjustment parameters are processed based on the reinforcement learning algorithm to obtain the audio adjustment parameters. For example, the user enters content such as too strong bass and harsh treble in the questionnaire, and then the content is semantically parsed to identify specific parameters that need to be adjusted, such as bass, treble or volume balance, and then processed by reinforcement learning algorithms such as Q-learning, so as to obtain audio adjustment parameters for iterative optimization of the audio preference model.

[0095] Step S60: updating the audio preference model according to the audio adjustment parameter.

[0096] In this embodiment, the audio preference model is updated based on the obtained audio adjustment parameters, so that in the subsequent audio processing process, the target audio that meets the actual hearing characteristics of the user can be generated based on the latest model parameters. Based on this, through the reinforcement learning algorithm, the audio adjustment parameters and related processing models are continuously optimized according to user feedback to improve the user experience, so that the system can continuously improve and adapt to user needs, thereby improving the effectiveness of subsequent audio processing.

[0097] Optionally, in another optional implementation, in addition to adjusting the audio preference model through feedback information or updating the user's preference information, the target audio may also be adjusted based on an audio adjustment instruction input by the user.

[0098] Specifically, after outputting the target audio signal, the audio adjustment instruction input by the user can be obtained, and then the target adjustment parameters associated with the audio adjustment instruction can be determined. The target adjustment parameters can be obtained by analyzing and processing the audio adjustment instruction through an artificial intelligence model, which includes new filter setting parameters. Then, based on the parameters, the audio signal to be played, i.e., the target audio signal, is adjusted through an adaptive filter. That is, after obtaining the audio adjustment instruction, the step of adjusting the audio signal to be played through an adaptive filter to obtain the target audio signal can be executed based on the audio adjustment instruction. The target audio signal is adjusted in real time through the parameters input by the user to improve the audio adjustment efficiency.

[0099] This embodiment provides an audio signal processing method, which provides an information feedback function for the user after outputting the adjusted target audio signal, and continuously optimizes the audio adjustment parameters, audio preference model, etc. according to the feedback information input by the user. At the same time, it can also adjust the target audio signal in real time, further improve the accuracy of audio processing, and thus improve the audio adjustment effect.

[0100] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the audio signal processing method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0101] The present application provides an audio signal processing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the audio signal processing method in the first embodiment described above.

[0102] Reference below Figure 5 , which shows a schematic diagram of the structure of an audio signal processing device suitable for implementing an embodiment of the present application. The audio signal processing device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The audio signal processing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0103] like Figure 5As shown, the audio signal processing device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the audio signal processing device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the audio signal processing device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an audio signal processing device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0104] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0105] The audio signal processing device provided by the present application adopts the audio signal processing method in the above embodiment, which can solve the technical problem that the existing audio signal processing technology cannot make personalized adjustments to the audio signal, resulting in poor audio adjustment effect. Compared with the prior art, the beneficial effects of the audio signal processing device provided by the present application are the same as the beneficial effects of the audio signal processing method provided by the above embodiment, and other technical features in the audio signal processing device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0106] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0108] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the audio signal processing method in the above-mentioned embodiment.

[0109] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0110] The computer-readable storage medium may be included in the audio signal processing device; or may exist independently without being assembled into the audio signal processing device.

[0111] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the audio signal processing device, the audio signal processing device:

[0112] When receiving an audio signal to be played, determining filter setting parameters for processing the audio signal to be played according to the audio preference model and the hearing characteristic curve of the user;

[0113] Based on the filter setting parameters, the audio signal to be played is adjusted by an adaptive filter to obtain a target audio signal;

[0114] The target audio signal is output.

[0115] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] The modules involved in the embodiments of the present application may be implemented by software or hardware, wherein the name of the module does not limit the unit itself in some cases.

[0118] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned audio signal processing method, and can solve the technical problem that the existing audio signal processing technology cannot perform personalized adjustment on the audio signal, resulting in poor audio adjustment effect. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the audio signal processing method provided by the above-mentioned embodiment, and will not be repeated here.

[0119] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An audio signal processing method, characterized in that: The method comprises: When receiving an audio signal to be played, a gain curve of the user's hearing characteristic curve at each frequency point is calculated based on the audio preference model, wherein the audio preference model performs linear interpolation between known frequency points of the hearing characteristic curve to generate a continuous gain curve, wherein the gain curve includes the user's hearing characteristics and audio preferences; Determining the gain values ​​of the filter in different frequency bands and the filter coefficients defining the frequency response characteristics of the filter based on the gain curve; Adjusting the current filter according to the filter coefficients to obtain an adaptive filter; The audio signal to be played is filtered by the adaptive filter, and based on the gain value, the amplitude of the audio signal to be played is adjusted by the gain control algorithm of the adaptive filter to obtain a target audio signal; The target audio signal is output.

2. The method according to claim 1, characterized in that When receiving the audio signal to be played, the gain curve of the user's hearing characteristic curve at each frequency point is calculated based on the audio preference model, wherein the audio preference model performs linear interpolation between known frequency points of the hearing characteristic curve to generate a continuous gain curve, and the gain curve includes the hearing characteristics and audio preferences of the user, and also includes: Acquire a training data set and a test data set, wherein the training data set includes the preprocessed audio playback history and historical feedback information of the user; Training a pre-stored deep learning model based on the training data set to obtain an initial model; Generate an enhanced training set according to the received current feedback information, and iteratively optimize and adjust the initial model based on the enhanced training set to obtain a target model; The target model is subjected to performance evaluation processing based on the test data set, and when the performance evaluation result meets the preset requirements, the target model is used as the audio preference model.

3. The method according to claim 1, characterized in that Before the step of calculating the gain curve of the user's hearing characteristic curve at each frequency point based on the audio preference model when receiving the audio signal to be played, the method further includes: Acquiring hearing test data of the user; Processing the hearing test data based on a machine learning model to obtain the hearing sensitivity of the user corresponding to different audio frequency bands; The hearing characteristic curve is generated according to the hearing sensitivity.

4. The method according to claim 1, characterized in that After the step of outputting the target audio signal, the method further includes: Acquiring target feedback information of the target audio signal; Determining an audio adjustment parameter that needs to be adjusted based on the target feedback information; The audio preference model is updated according to the audio adjustment parameter.

5. The method according to claim 4, characterized in that The step of determining the audio adjustment parameters to be adjusted based on the target feedback information includes: Determining an adjustment parameter associated with the target feedback information; The adjustment parameters are processed based on a reinforcement learning algorithm to obtain the adjusted audio adjustment parameters.

6. The method according to claim 1, characterized in that After the step of outputting the target audio signal, the method further includes: The audio adjustment instruction input by the user is obtained, and based on the audio adjustment instruction, the audio signal to be played is adjusted by an adaptive filter to obtain a target audio signal.

7. An audio signal processing device, characterized in that: The audio signal processing device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the audio signal processing method according to any one of claims 1 to 6.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the audio signal processing method according to any one of claims 1 to 6 are implemented.

Images