Audio feature processing method, device, terminal and storage medium

Abstract

The present application is applicable to the field of audio processing technology, and provides an audio feature processing method, device, terminal and storage medium, wherein the method includes: obtaining a signal feature data set of audio and an audio set to be identified; performing feature extraction on each audio in the audio set to obtain feature extraction results and feature extraction time; using the signal feature data set and the standard duration as a reference, based on the feature extraction results and feature extraction time, screening the target audio from the audio set; when it is determined that the proportion of the target audio in the audio set is lower than a threshold, determining the updated audio set as the audio set to be identified, and returning to execute the above steps until the proportion of the target audio in the audio set is not lower than the threshold. This solution can ensure the sample validity and improve the processing efficiency of sample identification and modification.

Description

Technical Field

[0001] The present application belongs to the field of audio processing technology, and in particular, relates to an audio feature processing method, device, terminal and storage medium. Background Art

[0002] With the development of network media and electronic technology, people's visual and auditory enjoyment requirements are getting higher and higher. In daily life, we often encounter occasions where audio and video are played in real time, such as car radio, TV live broadcast, network live broadcast, etc. There are also built-in walkman, CD player and other music playback devices. The audio signals played by these players have various popping sounds, noise, strange tones and other problems, which are unbearable for customers with sensitive hearing. Although with the development of Internet technology, various audio repair software has also been provided, these software can only input a section of audio through large tools such as computers for later sorting and repair, which wastes a lot of time. Especially in some broadcasting or live broadcasting occasions, it is impossible to improve on the spot in real time, and some computers and other tools are troublesome to carry and inconvenient to use.

[0003] In order to effectively eliminate environmental noise, a large number of audio data samples need to be collected in order to learn the noise distribution in different external environments, different locations, and different usage modes based on enough audio data samples.

[0004] Therefore, the validity of audio data samples has a direct impact on the elimination of environmental noise. However, it is difficult to effectively identify and update the audio in the audio data set after the existing audio data samples are collected, making it difficult to ensure the validity of the samples and the processing efficiency of sample identification and modification when facing massive audio sample data. Summary of the invention

[0005] The embodiments of the present application provide an audio feature processing method, device, terminal and storage medium to solve the problem in the prior art that it is difficult to effectively identify and update the audio in an audio data set when faced with massive audio sample data, and it is impossible to ensure the sample validity and processing efficiency of sample identification and modification.

[0006] A first aspect of an embodiment of the present application provides an audio feature processing method, including:

[0007] Obtaining an audio signal feature data set and an audio set to be identified;

[0008] Performing feature extraction on each audio in the audio set to obtain a feature extraction result and a feature extraction time consumption;

[0009] Using the signal feature data set and the standard duration as reference, based on the feature extraction result and the feature extraction time, filter out the target audio from the audio set;

[0010] When it is determined that the proportion of the target audio in the audio set is lower than a threshold, updating the audio set;

[0011] The updated audio set is determined as the audio set to be identified, and the step of performing feature extraction on each audio in the audio set to obtain feature extraction results and feature extraction time is returned to execute until the proportion of the target audio in the audio set is not less than the threshold.

[0012] A second aspect of an embodiment of the present application provides an audio feature processing device, including:

[0013] An acquisition module is used to acquire a data set of audio signal characteristics and an audio set to be identified;

[0014] An extraction module, used for performing feature extraction on each audio in the audio set, and obtaining a feature extraction result and a feature extraction time consumption;

[0015] A selection module, for selecting target audio from the audio set based on the signal feature data set and the standard duration as a reference and based on the feature extraction result and the feature extraction time consumption;

[0016] An updating module is used to update the audio set when it is determined that the proportion of the target audio in the audio set is lower than a threshold, determine the updated audio set as the audio set to be identified, and enable the extraction module to return to execute the step of extracting features from each audio in the audio set to obtain feature extraction results and feature extraction time until the proportion of the target audio in the audio set is not lower than the threshold.

[0017] A third aspect of an embodiment of the present application provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0018] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0019] A fifth aspect of the present application provides a computer program product, which, when executed on a terminal, enables the terminal to execute the steps of the method described in the first aspect.

[0020] As can be seen from the above, in the embodiment of the present application, by obtaining a signal feature data set of audio and an audio set to be identified, feature extraction is performed on each audio in the audio set to obtain feature extraction results and feature extraction time, and with reference to the signal feature data set and the standard time, based on the feature extraction results and feature extraction time, the target audio is screened from the audio set, and then when it is determined that the proportion of the target audio in the audio set is lower than a threshold, the audio set is updated, and the aforementioned processing is re-executed with the updated audio set, and the cycle is repeated until the proportion of the target audio in the final audio set is not lower than the threshold, so that when faced with massive audio sample data, the audio in the audio data set can be effectively identified and the content updated, thereby ensuring the sample validity and improving the processing efficiency of sample identification and modification. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 This is a flow chart of an audio feature processing method provided in an embodiment of the present application. Figure 1 ;

[0023] Figure 2 This is a flow chart of an audio feature processing method provided in an embodiment of the present application. Figure 2 ;

[0024] Figure 3 is a structural diagram of an audio feature processing device provided in an embodiment of the present application;

[0025] Figure 4 It is a structural diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0028] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0029] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0031] In a specific implementation, the terminal described in the embodiments of the present application includes, but is not limited to, other portable devices such as mobile phones, laptop computers, or tablet computers with touch-sensitive surfaces (e.g., touch screen displays and / or touch pads). It should also be understood that in some embodiments, the device is not a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., touch screen displays and / or touch pads).

[0032] In the following discussion, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse and / or joystick.

[0033] The terminal supports various applications, such as one or more of the following: a drawing application, a presentation application, a word processing application, a website creation application, a disk burning application, a spreadsheet application, a game application, a telephone application, a video conferencing application, an email application, an instant messaging application, a workout support application, a photo management application, a digital camera application, a digital camcorder application, a web browsing application, a digital music player application, and / or a digital video player application.

[0034] Various applications that can be executed on the terminal can use at least one common physical user interface device such as a touch-sensitive surface. One or more functions of the touch-sensitive surface and corresponding information displayed on the terminal can be adjusted and / or changed between applications and / or within corresponding applications. In this way, the common physical architecture of the terminal (e.g., the touch-sensitive surface) can support various applications with user interfaces that are intuitive and transparent to the user.

[0035] It should be understood that the size of the serial numbers of the steps in this embodiment does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0036] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0037] See also Figure 1 , Figure 1 This is a flow chart of an audio feature processing method provided in an embodiment of the present application. Figure 1 .like Figure 1 As shown, a method for processing audio features comprises the following steps:

[0038] Step 101: Obtain an audio signal feature data set and an audio set to be identified.

[0039] The audio includes, for example, the audio of a car horn, the audio of a car radio, the audio of people talking in the car, etc.

[0040] Here, a signal feature data set is obtained as a control group, and audio feature comparison is implemented later.

[0041] The audio signal feature data set may be a data set prepared in advance.

[0042] The audio set to be recognized may be a data set prepared in advance or an audio data set formed by an audio data stream collected in real time. The audio set to be recognized includes multiple audios to be recognized.

[0043] The data in the signal feature data set include, for example, audio type, audio frequency, audio decibel, etc. Taking the sound of a car horn as an example, when obtaining the signal feature data set of the audio, it can be:

[0044] Obtain standard horn audios of different cars, perform deep learning of horn sound features through a feature learning model based on the horn audios of different cars, and build a signal feature dataset based on the model after feature learning.

[0045] In one embodiment, obtaining an audio set to be recognized includes:

[0046] Get multiple audio files to be processed;

[0047] According to the set audio processing steps, data preprocessing is performed on each of the audios to be processed;

[0048] A set formed based on the pre-processed audio to be processed is used as the audio set to be recognized.

[0049] The set audio processing step includes, for example, enhancing the audio signal, pre-emphasizing the audio signal, framing and windowing the audio signal, and performing endpoint detection on the audio signal.

[0050] In one embodiment, the method of performing data preprocessing on each of the to-be-processed audios according to the set audio processing steps includes:

[0051] Segment each of the to-be-processed audios to obtain audio segments, and add an index sequence to each of the audio segments;

[0052] Audio processing is performed on each of the audio segments, and the audio segments after the audio processing are combined based on the index sequence to obtain the audio to be processed after data preprocessing.

[0053] Among them, audio processing is performed on each of the audio clips, and specifically, the audio signal is enhanced, the audio signal is pre-emphasized, the audio signal is framed and windowed, the audio signal is endpoint detected, the noise in the audio clip is identified, the noise in the identified audio clip is blurred, the audio is filtered, the audio is decomposed by wavelet, etc.

[0054] In this process, an audio preprocessing process is built in, through which the audio fragments can be captured and segmented, which can effectively divide the audio into different paragraphs, effectively reduce the length and size of a single processed audio paragraph, abandon the traditional design of lengthy audio extraction, and effectively improve the detail and accuracy of audio feature extraction.

[0055] At the same time, the signal can be enhanced and pre-emphasized, which can effectively improve the audio signal strength and ensure the overall audio effect.

[0056] Furthermore, a built-in audio reprocessing process can be used to identify and blur the contour noise within the audio, which can effectively eliminate the interference of environmental noise on audio feature extraction, thereby greatly improving the accuracy of subsequent audio feature extraction.

[0057] Step 102: extract features from each audio in the audio set to obtain feature extraction results and feature extraction time consumption.

[0058] The feature extraction for each audio in the audio set may be implemented based on an audio feature extraction model, and the audio feature extraction model is, for example, a CNN (Convolutional Neural Network) model.

[0059] The feature extraction for each audio may be specifically the extraction of the car horn feature for each audio, and the corresponding signal feature data set is also the car horn feature data set.

[0060] When extracting features from each audio in the audio set, the time taken to extract features from each audio can be timed, and the processing time from the start of processing to the output of the result of each audio can be obtained as the feature extraction time. The feature extraction time is used as a reference for whether the audio sample meets the sample validity requirements.

[0061] Similarly, the feature extraction result of each audio is combined as another reference for whether the audio sample meets the sample validity requirements.

[0062] Step 103 , using the signal feature data set and the standard duration as reference, based on the feature extraction result and the feature extraction time, select the target audio from the audio set.

[0063] The standard duration may be the average duration required for feature extraction of ambient audio in a certain scenario. When the feature extraction time of the audio exceeds the standard duration, it can be determined that the current audio may not belong to the ambient audio in the certain scenario, and based on the comparison of the feature extraction time, it can be assisted in determining whether the current audio is valid audio.

[0064] In addition, the signal feature data set is used as a reference to determine whether the feature extraction result corresponding to the current audio is consistent with the audio features in the signal feature data set, so as to assist in determining whether the current audio is valid audio.

[0065] In an optional implementation, the target audio is screened from the audio set based on the feature extraction result and the feature extraction time, with reference to the signal feature data set and the standard duration, including:

[0066] Based on the feature extraction result, a first audio that matches the data feature in the signal feature data set is obtained by screening from the audio set;

[0067] Based on the feature extraction time consumption, audio whose time consumption is less than or equal to the standard time length is screened out from the first audio as the target audio.

[0068] That is, the audio in the audio set that is consistent with the data features in the signal feature data set and whose feature extraction time is less than or equal to the standard time length is taken as the target audio.

[0069] Step 104: Determine the relationship between the proportion of the target audio in the audio set and the threshold.

[0070] Specifically, it is necessary to determine whether the proportion of the target audio in the audio set is lower than a threshold, or whether the proportion of the target audio in the audio set is not lower than a threshold, so as to measure the sample validity of the audio set.

[0071] Step 105 : When it is determined that the proportion of the target audio in the audio set is lower than the threshold, the audio set is updated, and the updated audio set is determined as the audio set to be identified.

[0072] When the proportion of the target audio in the audio set is lower than the threshold, the sample validity of the audio set is considered to be low.

[0073] Furthermore, after step 105, it is necessary to return to execute step 102 to perform feature extraction on each audio in the audio set, and obtain the feature extraction result and the feature extraction time, so as to continue the audio processing according to the processing process from step 102 to step 104 in the above embodiment, until after step 104, it is determined that the proportion of the target audio in the audio set is not less than the threshold, and then the loop processing process stops.

[0074] In one example, when the audio set is updated, the following steps are specifically included:

[0075] According to the set ratio, other audios in the audio set except the target audio are eliminated to obtain the updated audio set.

[0076] The ratio can be 100%, that is, all other audios except the target audio in the audio set are removed. Alternatively, the ratio is greater than 0 and less than 100%, that is, other audios except the target audio in the audio set are partially removed to update the audio set. The set ratio is the proportion of the removed audio in all other audios except the target audio in the audio set.

[0077] Wherein, when the audio set is updated, in another example, it specifically includes:

[0078] Acquire supplementary audio having common features with the target audio;

[0079] According to the set ratio, other audios in the audio set except the target audio are eliminated, and the supplementary audio is added to the audio set to obtain the updated audio set.

[0080] The acquisition of the supplementary audio may be based on an artificial intelligence model trained after feature learning of the target audio, and the target audio may be expanded based on the model to obtain the supplementary audio. Alternatively, audio may be obtained from other data sources, and audio having common features with the target audio may be selected as the supplementary audio.

[0081] Among them, the common features include characteristic data such as audio type, audio frequency, audio decibel, etc.

[0082] The supplementary audio is then incorporated into the audio collection, and all or part of the audio in the audio collection except the target audio is removed to update the audio collection.

[0083] In an embodiment of the present application, by obtaining a signal feature data set of audio and an audio set to be identified, feature extraction is performed on each audio in the audio set to obtain feature extraction results and feature extraction time, and with reference to the signal feature data set and the standard time, based on the feature extraction results and feature extraction time, the target audio is screened from the audio set, and then when it is determined that the proportion of the target audio in the audio set is lower than a threshold, the audio set is updated, and the aforementioned processing is re-executed with the updated audio set, and the cycle is repeated until the proportion of the target audio in the final audio set is not lower than the threshold, so that when faced with massive audio sample data, the audio in the audio data set can be effectively identified and the content updated, thereby ensuring the sample validity and improving the processing efficiency of sample identification and modification.

[0084] The embodiments of the present application also provide different implementations of the audio feature processing method.

[0085] See also Figure 2 , Figure 2This is a flow chart of an audio feature processing method provided in an embodiment of the present application. Figure 2 .like Figure 2 As shown, a method for processing audio features comprises the following steps:

[0086] Step 201: Obtain an audio signal feature data set and an audio set to be identified.

[0087] The implementation process of this step is the same as the implementation process of step 101 in the aforementioned embodiment, and will not be repeated here.

[0088] Step 202: extract features from each audio in the audio set to obtain feature extraction results and feature extraction time consumption.

[0089] The implementation process of this step is the same as the implementation process of step 102 in the aforementioned embodiment, and will not be repeated here.

[0090] Step 203 , using the signal feature data set and the standard duration as reference, based on the feature extraction result and the feature extraction time, select the target audio from the audio set.

[0091] The implementation process of this step is the same as the implementation process of step 103 in the aforementioned embodiment, and will not be repeated here.

[0092] Step 204: determine the relationship between the proportion of the target audio in the audio set and the threshold.

[0093] The implementation process of this step is the same as the implementation process of step 104 in the aforementioned embodiment, and will not be repeated here.

[0094] Step 205: When it is determined that the proportion of the target audio in the audio set is lower than a threshold, the audio set is updated, and the updated audio set is determined as the audio set to be identified.

[0095] The implementation process of this step is the same as the implementation process of step 105 in the aforementioned embodiment, and will not be repeated here.

[0096] Furthermore, after step 205, it is necessary to return to execute step 202 to perform feature extraction on each audio in the audio set, obtain the feature extraction result and the feature extraction time, so as to continue the audio processing according to the processing process from step 202 to step 204 in the above embodiment, until it is determined in step 204 that the proportion of the target audio in the audio set is not less than the threshold, then the loop processing process stops, and further executes the subsequent steps.

[0097] Step 206: When it is determined that the proportion of the target audio in the audio set is not less than the threshold, the audio set is determined as a valid sample set.

[0098] When the proportion of the target audio in the audio set is not less than a threshold, it is considered that the sample validity of the audio set is high, and the audio set is determined as a valid sample set.

[0099] In an embodiment of the present application, by obtaining a signal feature data set of audio and an audio set to be identified, feature extraction is performed on each audio in the audio set to obtain feature extraction results and feature extraction time, and with the signal feature data set and the standard duration as a reference, based on the feature extraction results and feature extraction time, the target audio is screened from the audio set, and then, when it is determined that the proportion of the target audio in the audio set is lower than or not lower than a threshold, it is possible to effectively identify and update the audio in the audio data set when faced with massive audio sample data, thereby ensuring sample validity and improving the processing efficiency of sample identification and modification.

[0100] See also Figure 3 , Figure 3 This is a structural diagram of an audio feature processing device provided in an embodiment of the present application. For the sake of convenience of explanation, only the parts related to the embodiment of the present application are shown.

[0101] The audio feature processing device 300 comprises:

[0102] An acquisition module 301 is used to acquire an audio signal feature data set and an audio set to be identified;

[0103] An extraction module 302 is used to perform feature extraction on each audio in the audio set to obtain a feature extraction result and a feature extraction time consumption;

[0104] A selection module 303 is used to select a target audio from the audio set based on the signal feature data set and the standard duration and the feature extraction result and the feature extraction time;

[0105] The updating module 304 is used to update the audio set when it is determined that the proportion of the target audio in the audio set is lower than a threshold, determine the updated audio set as the audio set to be identified, and enable the extraction module 302 to return to execute the step of extracting features from each audio in the audio set to obtain feature extraction results and feature extraction time until the proportion of the target audio in the audio set is not lower than the threshold.

[0106] The selection module 303 is specifically used for:

[0107] Based on the feature extraction result, a first audio that matches the data feature in the signal feature data set is obtained by screening from the audio set;

[0108] Based on the feature extraction time consumption, audio whose time consumption is less than or equal to the standard time length is screened out from the first audio as the target audio.

[0109] The acquisition module 301 is specifically used for:

[0110] Get multiple audio files to be processed;

[0111] According to the set audio processing steps, data preprocessing is performed on each of the audios to be processed;

[0112] A set formed based on the pre-processed audio to be processed is used as the audio set to be recognized.

[0113] The acquisition module 301 is more specifically used for:

[0114] Segment each of the to-be-processed audios to obtain audio segments, and add an index sequence to each of the audio segments;

[0115] Audio processing is performed on each of the audio segments, and the audio segments after the audio processing are combined based on the index sequence to obtain the audio to be processed after data preprocessing.

[0116] The update module 304 is specifically used for:

[0117] According to the set ratio, other audios in the audio set except the target audio are eliminated to obtain the updated audio set.

[0118] The update module 304 is specifically used for:

[0119] Acquire supplementary audio having common features with the target audio;

[0120] According to the set ratio, other audios in the audio set except the target audio are eliminated, and the supplementary audio is added to the audio set to obtain the updated audio set.

[0121] The device further comprises:

[0122] The determination module is configured to determine the audio set as a valid sample set when it is determined that the proportion of the target audio in the audio set is not less than the threshold.

[0123] The audio feature processing device provided in the embodiment of the present application can implement each process of the embodiment of the above-mentioned audio feature processing method and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0124] Figure 4 4 is a structural diagram of a terminal provided in an embodiment of the present application. As shown in the figure, the terminal 4 of this embodiment includes: at least one processor 40 ( Figure 4 Only one is shown in the figure), a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, wherein the processor 40 implements the steps of any of the above-mentioned method embodiments when executing the computer program 42.

[0125] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0126] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0127] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0128] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0129] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0130] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0131] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0134] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0135] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be implemented through a computer program product. When the computer program product runs on a terminal, the terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0136] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An audio feature processing method, characterized in that: include: Obtaining an audio signal feature data set and an audio set to be identified; Performing feature extraction on each audio in the audio set to obtain a feature extraction result and a feature extraction time consumption; Using the signal feature data set and the standard duration as reference, based on the feature extraction result and the feature extraction time, filter out the target audio from the audio set; When it is determined that the proportion of the target audio in the audio set is lower than a threshold, updating the audio set; The updated audio set is determined as the audio set to be identified, and the step of performing feature extraction on each audio in the audio set to obtain feature extraction results and feature extraction time is returned to execute until the proportion of the target audio in the audio set is not less than the threshold.

2. The method according to claim 1, characterized in that The step of taking the signal feature data set and the standard duration as reference, and based on the feature extraction result and the feature extraction time, selecting the target audio from the audio set includes: Based on the feature extraction result, a first audio that matches the data feature in the signal feature data set is obtained by screening from the audio set; Based on the feature extraction time consumption, audio whose time consumption is less than or equal to the standard time length is screened out from the first audio as the target audio.

3. The method according to claim 1, characterized in that Get the audio collection to be recognized, including: Get multiple audio files to be processed; According to the set audio processing steps, data preprocessing is performed on each of the audios to be processed; A set formed based on the pre-processed audio to be processed is used as the audio set to be recognized.

4. The method according to claim 3, characterized in that According to the set audio processing steps, data preprocessing is performed on each of the to-be-processed audios, including: Segment each of the to-be-processed audios to obtain audio segments, and add an index sequence to each of the audio segments; Audio processing is performed on each of the audio segments, and the audio segments after the audio processing are combined based on the index sequence to obtain the audio to be processed after data preprocessing.

5. The method according to claim 1, characterized in that The updating of the audio set includes: According to the set ratio, other audios in the audio set except the target audio are eliminated to obtain the updated audio set.

6. The method according to claim 1, characterized in that The updating of the audio set includes: Acquire supplementary audio having common features with the target audio; According to the set ratio, other audios in the audio set except the target audio are eliminated, and the supplementary audio is added to the audio set to obtain the updated audio set.

7. The method according to claim 1, characterized in that The method further comprises: When it is determined that the proportion of the target audio in the audio set is not lower than the threshold, the audio set is determined as a valid sample set.

8. An audio feature processing device, characterized in that: include: An acquisition module is used to acquire a data set of audio signal characteristics and an audio set to be identified; An extraction module, used for performing feature extraction on each audio in the audio set, and obtaining a feature extraction result and a feature extraction time consumption; A selection module, for selecting target audio from the audio set based on the signal feature data set and the standard duration, based on the feature extraction result and the feature extraction time; An updating module is used to update the audio set when it is determined that the proportion of the target audio in the audio set is lower than a threshold, determine the updated audio set as the audio set to be identified, and enable the extraction module to return to execute the step of extracting features from each audio in the audio set to obtain feature extraction results and feature extraction time until the proportion of the target audio in the audio set is not lower than the threshold.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images