Sound recording file processing method and device, equipment and medium
By setting properties, intelligent extraction and noise reduction of recording files of the visual network terminal, the problem of unclear voice playback caused by noise interference is solved, and the compatibility of sound quality and multi-terminal playback is improved.
Patent Information
- Application Number
- CN202411033641.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-15
AI Technical Summary
There is external noise interference during recording of video network terminals, resulting in unclear voice playback.
By setting attributes, analyzing and intelligently extracting voice signals on the recording file, and denoising the noise threshold based on the noise threshold, clear voice signals are obtained and saved, supporting multi-terminal playback.
The background noise in the recording file is removed, the sound quality and accuracy of the recording file are improved, and the recording file is clearly streamed and played on the APP, mini-program, and WEB.
Smart Images

Figure CN118969003A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method, device, equipment and medium for processing a recording file. Background Art
[0002] With the development of visual networking technology, visual networking terminals can provide more and more functions, such as recording function. While providing convenience to users, it also makes users have higher and higher requirements for recording function, especially the voice recognition requirement for recording function is relatively high.
[0003] In the existing related technologies, when grassroots grid workers are handling events or reporting conflicts, they directly use the recording function of the visual network terminal to input the description process of the event or conflict. Due to external noise interference during the recording process of the visual network terminal, the voice playback is unclear during the recording playback process. Summary of the invention
[0004] The present invention provides a method, device, equipment and medium for processing a recording file, so as to solve the problem of unclear voice playback caused by excessive noise interference during the recording process of a video network terminal.
[0005] In order to solve the above problem, the present invention discloses a method for processing a recording file, comprising:
[0006] Set the properties of the recording file and obtain the recording file after the settings;
[0007] Analyze the recorded file after the setting to obtain a voice signal;
[0008] Intelligently extract the voice signal according to key parameters in the voice signal to obtain a first voice signal;
[0009] The first speech signal is subjected to noise reduction processing based on the noise threshold value to obtain a second speech signal, and the second speech signal is saved.
[0010] Optionally, the step of setting the attributes of the recording file to obtain the recording file after the settings includes:
[0011] Encode the recording file according to the ACC format to obtain an encoded recording file;
[0012] The encoded recording file is stored in MPEG format to obtain the set recording file.
[0013] Optionally, the intelligently extracting the voice signal according to key parameters in the voice signal to obtain the first voice signal includes:
[0014] The voice signal is intelligently extracted according to a keyword in the voice signal, or a center frequency of the voice signal, or a bandwidth of the voice signal to obtain a first voice signal.
[0015] Optionally, the performing noise reduction processing on the first speech signal based on a noise threshold value to obtain a second speech signal, and saving the second speech signal comprises:
[0016] Acquiring the amplitude of the first speech signal;
[0017] The amplitude is compared with the noise threshold, and the first speech signal whose amplitude is greater than the noise threshold is taken as the second speech signal and saved.
[0018] Optionally, the method further comprises:
[0019] Detecting the noise volume of speech signals;
[0020] When the noise volume is greater than or equal to the volume threshold, the noise threshold is increased;
[0021] When the noise volume is less than the volume threshold, the noise threshold is lowered.
[0022] In order to solve the above problem, the present invention also discloses a recording file processing device, comprising:
[0023] The attribute setting module is used to set the attributes of the recording file and obtain the recording file after the settings;
[0024] An acquisition module is used to parse the set recording file to obtain a voice signal;
[0025] An intelligent extraction module, used to intelligently extract the voice signal according to key parameters in the voice signal to obtain a first voice signal;
[0026] The noise reduction module is used to perform noise reduction processing on the first speech signal based on a noise threshold value to obtain a second speech signal and save it.
[0027] Optionally, the property setting module includes:
[0028] An encoding unit, used for encoding the recording file according to the ACC format to obtain an encoded recording file;
[0029] The storage unit is used to store the encoded recording file in MPEG format to obtain the set recording file.
[0030] Optionally, the intelligent extraction module is specifically configured to perform intelligent extraction on the voice signal according to keywords in the voice signal, or a center frequency or a signal bandwidth of the signal, to obtain a first voice signal.
[0031] In order to solve the above problems, the present invention also discloses an electronic device, including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for processing a recording file when executing the computer program.
[0032] In order to solve the above problem, the present invention further discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for implementing the method for processing a recording file when executed by a processor.
[0033] Compared with the prior art, the present invention has the following advantages:
[0034] First, obtain the voice signal in the recording file after setting; intelligently extract the voice signal according to the key parameters in the voice signal to obtain the first voice signal; perform noise reduction processing on the first voice signal based on the noise threshold value to obtain the second voice signal, and save it. By performing intelligent noise reduction processing on the voice signal, the background noise in the recording file is removed, the sound quality effect of the recording file playback is improved, and the accuracy of speech-to-text conversion is also improved.
[0035] Secondly, set the properties of the recording file so that the recording file can support multi-terminal playback, that is, the recording file can be circulated and played clearly on the APP end, mini program end, WEB end, etc., solving the problem that the recording file cannot be played on other terminals.
[0036] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 It is a schematic diagram of the overall flow of a method for processing a recording file according to an embodiment of the present invention;
[0038] Figure 2 is a flow chart of a method for processing a recording file according to an embodiment of the present invention;
[0039] Figure 3 is a flow chart of a method for processing a recording file according to an embodiment of the present invention;
[0040] Figure 4 It is a structural diagram of a recording file processing device described in an embodiment of the present invention. DETAILED DESCRIPTION
[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0042] See also Figure 1 , which shows a schematic diagram of the overall flow of a method for processing a recording file according to an embodiment of the present invention, specifically comprising:
[0043] Step 101: The grid worker starts recording using the video network terminal and generates a recording file.
[0044] Step 102: Setting properties of the recording file to obtain the recording file after the settings.
[0045] Step 103: Perform intelligent noise reduction processing on the set recording file.
[0046] Step 104: Send the noise-reduced recording file to different terminals through the video network protocol for display or convert the noise-reduced recording file into text, or send it to a video network conference.
[0047] Among them, the terminals include: APP end, mini program end and WEB end.
[0048] Based on the above concept, Figure 2 , which shows a flow chart of a method for processing a recording file according to an embodiment of the present invention, specifically comprising:
[0049] Step 201: Setting attributes of the recording file to obtain the recording file after the settings.
[0050] In a specific application, step 201 includes the following sub-steps:
[0051] Sub-step 2011: Encode the recording file according to the ACC format to obtain an encoded recording file.
[0052] Sub-step 2012: storing the encoded recording file in MPEG format to obtain a set recording file.
[0053] In the existing related technology, the terminal in the Internet encodes the recording file by using the AMR_NB encoding format, and the encoded recording file is stored in the 3GP format. However, the above-mentioned encoded recording file generally does not support playback on the WEB end or the mini-program end. Therefore, the present invention proposes to re-set the attributes of the recording file, encode the recording file using the ACC format to obtain the encoded recording file, and then store the encoded recording file in the MPEG format to obtain the set recording file. By resetting the attributes of the recording file, the recording file recorded by the visual network terminal can be displayed and played on the WEB end, the mini-program end, and the APP end.
[0054] Step 202: Analyze the set recording file to obtain a voice signal.
[0055] In this embodiment, a recording file is collected by a microphone or other device, and the sound signal in the recording file is converted into an electrical signal, which is then further processed into a digital signal recognizable by a computer.
[0056] Step 203: intelligently extract the speech signal according to key parameters in the speech signal to obtain a first speech signal.
[0057] The solution of the present invention can be applied in video network conferences or in meetings for remote mediation of conflicts. The keywords in the voice signal will be different in different application scenarios. Therefore, in specific applications, the voice signal can be intelligently extracted based on the keywords in the voice signal, or the voice signal, and the bandwidth of the voice signal to obtain a first voice signal. For example, when the solution of the present application is applied in the application scenario of remote mediation of conflicts, the judge's verdict information in the voice signal is used as a keyword.
[0058] Step 204: Perform noise reduction processing on the first speech signal based on the noise threshold value to obtain a second speech signal and save it.
[0059] In a specific application, the first voice signal is converted into an electrical signal through a microphone or other equipment, and then further processed into a digital signal recognizable by a computer. The second voice signal is obtained by identifying and removing background noise in the recording, such as wind noise, traffic noise, etc., thereby improving the clarity of the recording;
[0060] In a specific application, step 204 includes the following sub-steps:
[0061] Sub-step 2041: Obtain the amplitude of the first speech signal.
[0062] Sub-step 2042: Compare the amplitude with the noise threshold, take the first speech signal whose amplitude is greater than the noise threshold as the second speech signal, and save it.
[0063] In a specific application, the amplitude of the first speech signal is compared with the noise threshold. If the amplitude of the first speech signal is less than the noise threshold, the first speech signal is considered to be noise and is filtered out, thereby reducing background noise. If the amplitude of the first speech signal is greater than or equal to the first speech signal of the noise threshold, the first speech signal is retained and the retained first speech signal is used as the second speech signal. The noise threshold can be used to quickly and accurately estimate noise in different frequency bands, different electromagnetic environments, and different time periods. This method based on real-time statistical analysis overcomes the limitation of traditional methods that rely on manual experience to set the noise threshold.
[0064] In this embodiment, a voice signal in a recording file after setting is obtained; the voice signal is intelligently extracted according to key parameters in the voice signal to obtain a first voice signal; the first voice signal is subjected to noise reduction processing based on a noise threshold value to obtain a second voice signal, and the second voice signal is saved. By performing intelligent noise reduction processing on the voice signal, background noise in the recording file is removed, the sound quality effect of the recording file playback is improved, and the accuracy of speech-to-text conversion is also improved.
[0065] Based on the above concept, Figure 3 , which shows a flow chart of a method for processing a recording file according to an embodiment of the present invention, specifically comprising:
[0066] Step 301: Setting attributes of the recording file to obtain the recording file after the settings.
[0067] Step 302: Analyze the set recording file to obtain a voice signal.
[0068] Step 303: intelligently extract the speech signal according to key parameters in the speech signal to obtain a first speech signal.
[0069] By intelligently extracting the voice signal according to key parameters in the voice signal to obtain the first voice signal, the accuracy and efficiency of signal processing are improved, and a more accurate data basis is provided for subsequent audio or spectrum analysis.
[0070] Step 304: Perform noise reduction processing on the first speech signal based on the noise threshold value to obtain a second speech signal and save it.
[0071] Step 305: Detect the noise volume of the speech signal.
[0072] Noise volume refers to the intensity of sound that has a negative impact on people's lives, work and studies. Noise volume can also be quantified by physical quantities such as sound pressure level, but it focuses more on the degree of interference with human activities. Noise volume is usually used to describe the size or strength of a sound. When a change in noise volume is detected, the noise threshold effector will automatically adjust the noise threshold. When the noise volume is greater than or equal to the volume threshold value, the noise threshold is increased to control the noise within a certain range and effectively suppress the impact of noise. When the noise volume is less than the volume threshold value, the noise threshold is lowered to avoid mistakenly eliminating useful sound signals. By dynamically adjusting the noise threshold, the adaptability and robustness of the system are improved.
[0073] Step 306: When the noise volume is greater than or equal to the volume threshold, the noise threshold is increased.
[0074] Step 307: When the noise volume is less than the volume threshold, lower the noise threshold.
[0075] In this embodiment, the noise threshold is dynamically adjusted by the noise volume, which can adapt to the changes in noise levels in various complex environments, and also overcomes the limitation of the traditional method of relying on manual experience to set the noise threshold.
[0076] It should be noted that, for the above method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present invention.
[0077] Based on the description of the above method embodiments, the present invention also provides corresponding device embodiments to implement the contents described in the above method embodiments.
[0078] Reference Figure 4 , which shows a structural diagram of a recording file processing device according to an embodiment of the present invention, specifically comprising:
[0079] The attribute setting module 401 is used to set the attributes of the recording file and obtain the recording file after the settings.
[0080] The acquisition module 402 is used to parse the set recording file to obtain a voice signal.
[0081] The intelligent extraction module 403 is used to perform intelligent extraction on the speech signal according to key parameters in the speech signal to obtain a first speech signal.
[0082] The noise reduction module 404 is used to perform noise reduction processing on the first speech signal based on a noise threshold value to obtain a second speech signal and save it.
[0083] Optionally, the property setting module includes:
[0084] An encoding unit, used for encoding the recording file according to the ACC format to obtain an encoded recording file;
[0085] The storage unit is used to store the encoded recording file in MPEG format to obtain the set recording file.
[0086] Optionally, the intelligent extraction module is specifically configured to perform intelligent extraction on the voice signal according to keywords in the voice signal, or a center frequency or a signal bandwidth of the signal, to obtain a first voice signal.
[0087] Optionally, the noise reduction module includes:
[0088] an amplitude unit, used to obtain the amplitude of the first speech signal;
[0089] A comparing unit is used to compare the amplitude with the noise threshold, and take the first speech signal whose amplitude is greater than the noise threshold as the second speech signal, and save it.
[0090] Optionally, the device further comprises:
[0091] A detection module, used for detecting the noise volume of a speech signal;
[0092] The threshold value adjustment module is used to increase the noise threshold when the noise volume is greater than or equal to the volume threshold; and to lower the noise threshold when the noise volume is less than the volume threshold.
[0093] In this embodiment, first, a voice signal in a set recording file is obtained; the voice signal is intelligently extracted according to key parameters in the voice signal to obtain a first voice signal; the first voice signal is subjected to noise reduction processing based on a noise threshold value to obtain a second voice signal, and the second voice signal is saved. By performing intelligent noise reduction processing on the voice signal, background noise in the recording file is removed, the sound quality effect of the recording file playback is improved, and the accuracy of speech-to-text conversion is also improved.
[0094] Secondly, set the properties of the recording file so that the recording file can support multi-terminal playback, that is, the recording file can be circulated and played clearly on the APP end, mini program end, WEB end, etc., solving the problem that the recording file cannot be played on other terminals.
[0095] As for the above-mentioned device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts may refer to the partial description of the method embodiment.
[0096] An embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for processing, monitoring and recommending a recording file when executing the computer program.
[0097] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program that implements the method for processing a recording file when executed by a processor.
[0098] Alternatively, the computer-readable storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
[0099] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0100] It is easy for a person skilled in the art to think that any combination of the above embodiments is feasible, so any combination of the above embodiments is an implementation scheme of the present invention, but due to space limitations, this specification will not be described in detail here. Although the preferred embodiments of the present invention have been described, once a person skilled in the art knows the basic creative concept, he can make other changes and modifications to these embodiments. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0101] The above is a detailed introduction to the recording file processing method, device, equipment and medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A method for processing a recording file, characterized in that: include: Set the properties of the recording file and obtain the recording file after the settings; Analyze the recorded file after the setting to obtain a voice signal; Intelligently extract the voice signal according to key parameters in the voice signal to obtain a first voice signal; The first speech signal is subjected to noise reduction processing based on the noise threshold value to obtain a second speech signal, and the second speech signal is saved.
2. The method according to claim 1, characterized in that The recording file is set with attributes to obtain the recording file after the settings include: Encode the recording file according to the ACC format to obtain an encoded recording file; The encoded recording file is stored in MPEG format to obtain the set recording file.
3. The method according to claim 1, characterized in that The intelligently extracting the voice signal according to the key parameters in the voice signal to obtain the first voice signal comprises: The voice signal is intelligently extracted according to a keyword in the voice signal, or a center frequency of the voice signal, or a bandwidth of the voice signal to obtain a first voice signal.
4. The method according to claim 1, characterized in that: The performing noise reduction processing on the first speech signal based on the noise threshold value to obtain a second speech signal, and saving the second speech signal includes: Acquiring the amplitude of the first speech signal; The amplitude is compared with the noise threshold, and the first speech signal whose amplitude is greater than the noise threshold is taken as the second speech signal and saved.
5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Detecting the noise volume of speech signals; When the noise volume is greater than or equal to the volume threshold, the noise threshold is increased; When the noise volume is less than the volume threshold, the noise threshold is lowered.
6. A recording file processing device, characterized in that: include: The attribute setting module is used to set the attributes of the recording file and obtain the recording file after the settings; An acquisition module is used to parse the set recording file to obtain a voice signal; An intelligent extraction module, used to intelligently extract the voice signal according to key parameters in the voice signal to obtain a first voice signal; The noise reduction module is used to perform noise reduction processing on the first speech signal based on a noise threshold value to obtain a second speech signal and save it.
7. The processing device according to claim 6, characterized in that The attribute setting module includes: An encoding unit, used for encoding the recording file according to the ACC format to obtain an encoded recording file; The storage unit is used to store the encoded recording file in MPEG format to obtain the set recording file.
8. The processing device according to claim 6, characterized in that The intelligent extraction module is specifically used to intelligently extract the voice signal according to keywords in the voice signal, or the center frequency or signal bandwidth of the signal, to obtain the first voice signal.
9. An electronic device 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, a method for processing a recording file according to any one of claims 1 to 5 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, implements a method for processing a recording file according to any one of claims 1 to 5.
