Audio processing method and device, computer equipment and storage medium

Abstract

The invention discloses an audio processing method and device, computer equipment and a storage medium. The method belongs to the technical field of audio processing, and specifically comprises the following steps: performing voice activity detection on an audio file, and determining a target audio segment in the audio file; wherein the target audio segment comprises a silent audio segment. And determining the service type of the target audio segment. And compressing the target audio segment in the audio file according to the service type. In the embodiment, the target audio segment of the audio file is identified, and the service type of the target audio segment is determined. According to the method, the target audio segment in the audio file is compressed according to the service type, the target audio segment comprises the silent audio segment, that is, only the low-value audio segment is compressed, so that the integrity of the audio file is kept, the legality of the audio file and the audio quality of the normal audio segment are not influenced, and the service quality of the audio file is improved. And storage resources occupied when the audio file is stored are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of audio processing, and in particular to an audio processing method and device, computer equipment and a storage medium. BACKGROUND

[0002] A call center is an important window for an enterprise to provide services to the outside world, and needs to handle a large number of service requests from multimedia channels such as voice, video and text every day. Therefore, the storage space required to save audio files (for example, business recording files) is large and the cost is high.

[0003] At present, in order to reduce the storage cost of business recording files and improve resource utilization, the business recording files are usually processed by means of code rate compression, format conversion or mute clipping. Although this reduces the storage cost of business recording files, it also affects the audio quality of the business recording files, and the clipping method also affects the legality of the business recording files. SUMMARY

[0004] Therefore, it is necessary to provide an audio processing method and device, computer equipment and a storage medium that can effectively improve the resource utilization of service equipment to solve the above technical problems.

[0005] In a first aspect, the present application provides an audio processing method, which comprises:

[0006] performing voice activity detection on an audio file to determine a target audio segment in the audio file; wherein the target audio segment comprises a silent audio segment;

[0007] determining a business type of the target audio segment;

[0008] performing compression processing on the target audio segment in the audio file according to the business type.

[0009] In one embodiment, determining the business type of the target audio segment comprises:

[0010] determining a start time and an end time of the target audio segment;

[0011] determining the business type of the target audio segment according to the start time and the end time.

[0012] In one embodiment, determining the business type of the target audio segment according to the start time and the end time comprises:

[0013] obtaining a first audio segment of a preset time period before the start time from the audio file; wherein the end time of the first audio segment is the start time of the target audio segment;

[0014] The second audio segment after a preset time period from the end time is obtained from the audio file; wherein the start time of the second audio segment is the end time of the target audio segment;

[0015] The service type of the target audio segment is determined according to the first audio segment and / or the second audio segment.

[0016] In one of the embodiments, the voice activity detection is performed on the audio file to determine the target audio segment in the audio file, including:

[0017] The voice activity detection is performed on the audio file to obtain a candidate audio segment in the audio file;

[0018] The semantic analysis is performed on the candidate audio segment to obtain a semantic analysis result;

[0019] The target audio segment in the audio file is determined from the candidate audio segment according to the semantic analysis result.

[0020] In one of the embodiments, the target audio segment in the audio file is compressed according to the service type, including:

[0021] The compression strategy for the target audio segment is determined according to the service type;

[0022] The target audio segment in the audio file is compressed based on the compression strategy.

[0023] In one of the embodiments, the method further includes:

[0024] The structured index label corresponding to the target audio segment is determined according to the audio segment information of the target audio segment;

[0025] The structured index label, the audio content of the first audio segment and the audio content of the second audio segment are sent to the blockchain device, so that the blockchain device hashes the structured index label based on a first hash function to obtain a composite index label; and hashes the composite index label, the audio content of the first audio segment and the audio content of the second audio segment based on a second hash function to obtain a second hash value;

[0026] The composite index label and the blockchain evidence identification sent by the blockchain device are received; wherein the blockchain evidence identification is a storage identification obtained by the blockchain device storing the second hash value.

[0027] In one of the embodiments, the method further includes:

[0028] The composite index label and the blockchain evidence identification are stored in the metadata area of the audio file.

[0029] In one of the embodiments, the structured index tag includes at least one of a start time, an end time, a service type, a semantic abstract, and a compression parameter of the target audio segment.

[0030] In a second aspect, the present application provides an audio processing apparatus, which comprises:

[0031] a first determining module configured to perform voice activity detection on the audio file to determine a target audio segment in the audio file, wherein the target audio segment includes a silent audio segment;

[0032] a second determining module configured to determine a service type of the target audio segment;

[0033] a compression processing module configured to perform compression processing on the target audio segment in the audio file according to the service type.

[0034] In a third aspect, the present application further provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0035] performing voice activity detection on the audio file to determine a target audio segment in the audio file, wherein the target audio segment includes a silent audio segment;

[0036] determining a service type of the target audio segment;

[0037] performing compression processing on the target audio segment in the audio file according to the service type.

[0038] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the following steps when executed by a processor:

[0039] performing voice activity detection on the audio file to determine a target audio segment in the audio file, wherein the target audio segment includes a silent audio segment;

[0040] determining a service type of the target audio segment;

[0041] performing compression processing on the target audio segment in the audio file according to the service type.

[0042] In a fifth aspect, the present application further provides a computer program product, which comprises a computer program, and the computer program implements the following steps when executed by a processor:

[0043] performing voice activity detection on the audio file to determine a target audio segment in the audio file, wherein the target audio segment includes a silent audio segment;

[0044] determining a service type of the target audio segment;

[0045] According to the service type, the target audio segment in the audio file is compressed.

[0046] The audio processing method, device, computer device and storage medium described above perform voice activity detection on the audio file to determine a target audio segment in the audio file, wherein the target audio segment includes a silent audio segment. The service type of the target audio segment is determined. According to the service type, the target audio segment in the audio file is compressed. In this embodiment, the target audio segment of the audio file is identified, and the service type of the target audio segment is determined. According to the service type, the target audio segment in the audio file is compressed. In this application, the target audio segment includes a silent audio segment, that is, only the low-value audio segment is compressed. Not only the integrity of the audio file is preserved, but also the audio quality of the legal and normal audio segment is not affected, and the storage resources occupied by the storage of the audio file are reduced. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 An application environment diagram of an audio processing method provided in this embodiment is shown in the figure.

[0048] Figure 2 A flowchart of the first audio processing method provided in this embodiment is shown in the figure.

[0049] Figure 3 A flowchart of determining the service type of the target audio segment provided in this embodiment is shown in the figure.

[0050] Figure 4 A flowchart of receiving the composite index label and the blockchain notarization identifier sent by the blockchain device provided in this embodiment is shown in the figure.

[0051] Figure 5 A flowchart of the second audio processing method provided in this embodiment is shown in the figure.

[0052] Figure 6 A structure block diagram of an audio processing device provided in this embodiment is shown in the figure.

[0053] Figure 7 An internal structure diagram of a computer device provided in this embodiment is shown in the figure. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical scheme and advantages of the present application clearer, the following further describes the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0055] The audio processing method provided in the embodiments of the present application can be applied to, for example Figure 1The application environment shown. Among them, the server 104 obtains the audio file from the terminal 102 that needs to be processed. The server 104 performs voice activity detection on the audio file to determine the target audio segment in the audio file and determine the service type of the target audio segment. Finally, the server 104 compresses the target audio segment in the audio file according to the service type. Based on the associated media gateway, call the target service device to provide the media stream corresponding to the first service service request. Among them, the target audio segment includes a silent audio segment.

[0056] Among them, the server refers to a device that can identify, analyze, and compress and fold the audio file. The server can be a server or other processing device. If the server is a server, it can be a standalone server or a server cluster.

[0057] The terminal refers to a terminal device that can directly or indirectly communicate with the server, such as a mobile phone, a computer, and other intelligent terminals.

[0058] In one embodiment, Figure 2 is a flowchart of an audio processing method according to an embodiment of the present application. The method is applied to the server in Figure 1 The method includes the following steps:

[0059] S201, performing voice activity detection on the audio file to determine the target audio segment in the audio file.

[0060] Among them, the audio file refers to an audio format file that needs to be compressed. The target audio segment refers to a low-value audio segment in the audio file. The target audio segment includes a silent audio segment. The silent audio segment refers to an audio interval in the audio file that has no valid speech.

[0061] Optionally, the audio file in this embodiment can be a file containing audio information extracted from a video file, and the audio file can also be an audio format file collected through a microphone, such as a call recording.

[0062] Optionally, the embodiment classifies and processes the received multi-modal raw data through an intelligent analysis model to identify the audio file from the multi-modal raw data.

[0063] As an optional implementation of an embodiment of the present application, the VAD (Voice Activity Detection) algorithm is used to perform voice activity detection on the audio file to determine the target audio segment in the audio file.

[0064] As another optional implementation of the embodiment of the present application, speech activity detection is performed on the audio file to obtain a candidate audio segment in the audio file. For example, a VAD algorithm is used to perform speech activity detection on the audio file to obtain a candidate audio segment in the audio file. It should be noted that the VAD algorithm can identify a silent audio segment and can also identify a noisy audio segment with background noise. Therefore, to eliminate the noisy audio segment, the embodiment further needs to perform semantic analysis on the candidate audio segment to obtain a semantic analysis result. For example, a speech analysis model is used to perform semantic analysis on the candidate audio segment to obtain a semantic analysis result. Finally, the target audio segment in the audio file is determined from the candidate audio segment according to the semantic analysis result.

[0065] Optionally, in the embodiment, speech activity detection is performed on the audio file to determine the target audio segment in the audio file and the start time and the end time of the target audio segment.

[0066] S202, a service type of the target audio segment is determined.

[0067] The service type includes a silent attribute type and / or a service attribute type. The silent attribute type refers to a silent attribute type of the target audio segment, for example, system waiting, customer input, and customer thinking. The service attribute type includes a type of a related service of a request processing corresponding to the audio file, for example, a traffic service, a broadband service, and a complaint service.

[0068] Optionally, in the embodiment, the service type of the target audio segment is determined in combination with context information of the target audio segment. For example, before the target audio segment, customer audio input "wait a moment, I want to think" is detected, and then a silent audio segment is entered. In this case, the service type is customer thinking.

[0069] S203, the target audio segment in the audio file is compressed according to the service type.

[0070] As an optional implementation of the embodiment of the present application, a compression strategy for the target audio segment is determined according to the silent attribute type and the service attribute type. The target audio segment in the audio file is compressed based on the compression strategy.

[0071] As another optional implementation of the embodiment of the present application, a compression strategy for the target audio segment is determined according to the silent attribute type in the service type. The target audio segment in the audio file is compressed based on the compression strategy. Optionally, in the embodiment, the compression strategy includes an audio folding rate. For example, if the silent attribute type is system waiting, the audio segment is considered to be a worthless audio segment, and the compression strategy is configured to have a folding rate equal to 90%. If the silent attribute type is customer thinking, the audio segment is considered to be a low-value audio segment, and the compression strategy is configured to have a folding rate equal to 80%.

[0072] Optionally, the target audio segment can also include a noise audio segment. In the case that the target audio segment is a noise audio segment, there is no need to determine the service type. The compression strategy is determined directly, and the folding rate in the compression strategy for the noise audio segment is fifty percent.

[0073] The audio processing method described above performs voice activity detection on the audio file to determine a target audio segment in the audio file; wherein the target audio segment includes a silent audio segment. The service type of the target audio segment is determined. The target audio segment in the audio file is compressed according to the service type. In this embodiment, the target audio segment of the audio file is identified, and the service type of the target audio segment is determined. The target audio segment in the audio file is compressed according to the service type. In this application, the target audio segment includes a silent audio segment, that is, only the low-value audio segment is compressed. Not only the integrity of the audio file is preserved, but also the audio quality of the legal and normal audio segment is not affected, and the storage resources occupied by the storage of the audio file are reduced.

[0074] In one of the embodiments, in order to more accurately determine the service type of the target audio segment, as shown in S202, an optional embodiment includes: Figure 3

[0075] S301, determining the start time and end time of the target audio segment.

[0076] Optionally, in this embodiment, when the voice activity detection is performed on the audio file or the voice analysis is performed on the audio file, the start time and end time of the target audio file are recorded.

[0077] S302, determining the service type of the target audio segment according to the start time and end time.

[0078] As an optional embodiment of the present application, a time difference is determined according to the start time and end time. If the time difference is greater than a preset time threshold, it is determined that the service type of the target audio segment is a silent caused by a customer.

[0079] ​As another optional implementation of the embodiment of the present application, a first audio segment of a preset time period before the start time is obtained from the audio file; wherein the end time of the first audio segment is the start time of the target audio segment. A second audio segment of a preset time period after the end time is obtained from the audio file; wherein the start time of the second audio segment is the end time of the target audio segment. The service type of the target audio segment is determined according to the first audio segment and / or the second audio segment. In the embodiment, one optional implementation of determining the service type of the target audio segment according to the first audio segment and / or the second audio segment is that the audio content of the first audio segment and the audio content of the second audio segment are subjected to semantic analysis, and the service type of the target audio segment is determined according to the result of the semantic analysis.

[0080] Optionally, the service type in the embodiment includes silence caused by system reasons and silence caused by customer reasons.

[0081] In the embodiment, the start time and the end time of the target audio segment are determined. A first audio segment of a preset time period before the start time is obtained from the audio file; wherein the end time of the first audio segment is the start time of the target audio segment. A second audio segment of a preset time period after the end time is obtained from the audio file; wherein the start time of the second audio segment is the end time of the target audio segment. The service type of the target audio segment is determined according to the first audio segment and / or the second audio segment. In the embodiment, the service type of the target audio segment determined is more accurate by combining the context information.

[0082] On the basis of the above-mentioned embodiments, the audio file and the related information are stored, and also in order to facilitate confirmation of whether the audio file and the related information are tampered with, as shown in FIG. 8, an optional implementation of an audio processing method includes the following steps. Figure 4

[0083] S401, the structured index label corresponding to the target audio segment is determined according to the audio segment information of the target audio segment.

[0084] The audio segment information refers to the related information of the target audio segment.

[0085] Optionally, in the embodiment, the structured index label corresponding to the target audio segment is obtained by converting the audio segment information of the target audio segment. The structured index label includes at least one of the start time, the end time, the service type, the semantic abstract, and the compression parameter of the target audio segment. The semantic abstract refers to the information abstract obtained by performing semantic analysis on the first audio segment and the second audio segment. The compression parameter refers to the related parameter of the compression processing of the target audio segment, mainly referring to the folding rate.

[0086] ​S402, send the structured index label, the audio content of the first audio segment and the audio content of the second audio segment to the blockchain device, so that the blockchain device hashes the structured index label based on a first hash function to obtain a composite index label; and hashes the composite index label, the audio content of the first audio segment and the audio content of the second audio segment based on a second hash function to obtain a second hash value.

[0087] Among them, the composite index label refers to the index label obtained by hashing the structured index label based on the first hash function. The blockchain device refers to a device related to blockchain technology, which can be a blockchain server.

[0088] Optionally, the composite index label can quickly locate the key data, and can ensure the integrity of the index and the content through the blockchain.

[0089] Among them, the second hash value refers to the hash value obtained by hashing the composite index label, the audio content of the first audio segment and the audio content of the second audio segment based on the second hash function. The function of the second hash value is mainly to confirm the integrity of the composite index label, the audio content of the first audio segment and the audio content of the second audio segment for subsequent, to prevent tampering by the outside world.

[0090] Optionally, in the embodiment, the first hash function and the second hash function can be the same hash function or different hash functions. The hash function can be a SHA-256 (Secure Hash Algorithm 256-bit, secure hash algorithm 256-bit) hash function.

[0091] S403, receive the composite index label and the blockchain storage identification sent by the blockchain device.

[0092] Among them, the blockchain storage identification is a storage identification obtained by the blockchain device storing the second hash value.

[0093] Optionally, in the embodiment, after receiving the composite index label and the blockchain storage identification sent by the blockchain device, the composite index label and the blockchain storage identification are stored in the metadata area of the audio file. It should be noted that the composite index label and the blockchain storage identification can be stored in the metadata area of the audio file before the audio file is compressed. The composite index label and the blockchain storage identification can also be stored in the metadata area of the compressed audio file after the audio file is compressed.

[0094] Optionally, in the embodiment, the compressed audio file is stored in encrypted form, and the storage location can be any of the blockchain, local storage and cloud storage.

[0095] When there is a requirement to obtain the complete audio file, the compressed audio file is called from the storage location. The compressed target audio segment is located according to the composite index tag or the structured index tag. The hash value is called from the blockchain device according to the blockchain storage identification. The composite index tag, the audio content of the first audio segment and the audio content of the second audio segment are hashed to obtain a verification hash value. The verification hash value is matched with the called hash value, and if the matching is successful, it means that the information has not been tampered with. Then the compressed target audio segment is decompressed or the target audio segment is recovered by using the difference algorithm, and then the complete audio file is obtained.

[0096] In the embodiment, the structured index tag corresponding to the target audio segment is determined according to the audio segment information of the target audio segment. The structured index tag, the audio content of the first audio segment and the audio content of the second audio segment are sent to the blockchain device, so that the blockchain device hashes the structured index tag based on a first hash function to obtain a composite index tag, and hashes the composite index tag, the audio content of the first audio segment and the audio content of the second audio segment based on a second hash function to obtain a second hash value. The composite index tag and the blockchain storage identification sent by the blockchain device are received. The blockchain storage identification is a storage identification obtained by the blockchain device storing the second hash value. Based on the embodiment, the compressed target audio segment can be quickly located subsequently, and whether the audio file is tampered with can also be quickly identified, thereby effectively ensuring the integrity of the audio file and the structured index tag.

[0097] In one of the embodiments, as shown in FIG. 1, an optional implementation of an audio processing method includes the following steps. Figure 5

[0098] S501, voice activity detection is performed on an audio file to obtain a candidate audio segment in the audio file.

[0099] S502, semantic analysis is performed on the candidate audio segment to obtain a semantic analysis result.

[0100] S503, a target audio segment in the audio file is determined from the candidate audio segment according to the semantic analysis result.

[0101] S504, a start time and an end time of the target audio segment are determined.

[0102] S505, a first audio segment before the start time by a preset time period is obtained from the audio file. The end time of the first audio segment is the start time of the target audio segment.

[0103] S506, a second audio segment after the end time by a preset time period is obtained from the audio file. The start time of the second audio segment is the end time of the target audio segment. ​

[0104] S507, determine a service type of the target audio segment according to the first audio segment and the second audio segment.

[0105] S508, determine a structured index label corresponding to the target audio segment according to audio segment information of the target audio segment. The structured index label includes at least one of a start time, an end time, the service type, a semantic abstract, and a compression parameter of the target audio segment.

[0106] S509, send the structured index label, audio content of the first audio segment, and audio content of the second audio segment to a blockchain device, so that the blockchain device performs hash processing on the structured index label based on a first hash function to obtain a composite index label, and performs hash processing on the composite index label, the audio content of the first audio segment, and the audio content of the second audio segment based on a second hash function to obtain a second hash value.

[0107] S510, receive the composite index label and a blockchain storage identification sent by the blockchain device. The blockchain storage identification is a storage identification obtained by the blockchain device storing the second hash value.

[0108] S511, store the composite index label and the blockchain storage identification into a metadata area of the audio file.

[0109] S512, determine a compression strategy for the target audio segment according to the service type.

[0110] S513, perform compression processing on the target audio segment in the audio file based on the compression strategy.

[0111] S514, perform encrypted storage on the compressed audio file.

[0112] In the embodiment, the target audio segment in the audio file is determined through voice activity detection, and the target audio segment includes a silent audio segment. The service type of the target audio segment is determined. The target audio segment in the audio file is compressed according to the service type. In the embodiment, the target audio segment of the audio file is recognized, and the service type of the target audio segment is determined. The target audio segment in the audio file is compressed according to the service type. In the application, the target audio segment includes a silent audio segment, that is, only the low-value audio segment is compressed. The integrity of the audio file is preserved, the legality and the audio quality of the normal audio segment of the audio file are not affected, and the storage resources occupied by the audio file are reduced.

[0113] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least some of the other steps or the steps or stages in the other steps.

[0114] Based on the same inventive concept, the embodiments of the present application also provide an audio processing apparatus for implementing the above-mentioned audio processing method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more audio processing apparatus embodiments provided below can refer to the limitations of the audio processing method described above, which will not be repeated here.

[0115] In one embodiment, by Figure 6 A structural block diagram of an audio processing apparatus in an embodiment is shown. As Figure 6 shown, an audio processing apparatus 1 is provided, which includes a first determination module 10, a second determination module 20, and a compression processing module 30, wherein:

[0116] The first determination module 10 is configured to perform voice activity detection on an audio file to determine a target audio segment in the audio file; wherein the target audio segment includes a silent audio segment;

[0117] The second determination module 20 is configured to determine a service type of the target audio segment;

[0118] The compression processing module 30 is configured to perform compression processing on the target audio segment in the audio file according to the service type.

[0119] In one embodiment, the second determination module 20 is further configured to:

[0120] determine a start time and an end time of the target audio segment;

[0121] determine the service type of the target audio segment according to the start time and the end time.

[0122] In one embodiment, the second determination module 20 is further configured to:

[0123] From the audio file, a first audio segment of a preset time period before the start time is obtained; wherein the end time of the first audio segment is the start time of the target audio segment;

[0124] From the audio file, a second audio segment of a preset time period after the end time is obtained; wherein the start time of the second audio segment is the end time of the target audio segment;

[0125] According to the first audio segment and / or the second audio segment, the service type of the target audio segment is determined.

[0126] In one of the embodiments, the first determining module in the audio processing device 1 is further configured to: Figure 6

[0127] Voice activity detection is performed on the audio file to obtain a candidate audio segment in the audio file;

[0128] Semantic analysis is performed on the candidate audio segment to obtain a semantic analysis result;

[0129] According to the semantic analysis result, the target audio segment in the audio file is determined from the candidate audio segment.

[0130] In one of the embodiments, the compression processing module in the audio processing device 1 is further configured to: Figure 6 According to the service type, a compression strategy for the target audio segment is determined;

[0131] Based on the compression strategy, the target audio segment in the audio file is compressed.

[0132] In one of the embodiments, the audio processing device 1 is further configured to:

[0133] Figure 6 The third determining module is configured to determine a structured index label corresponding to the target audio segment according to the audio segment information of the target audio segment;

[0134] The sending module is configured to send the structured index label, the audio content of the first audio segment and the audio content of the second audio segment to the blockchain device, so that the blockchain device hashes the structured index label based on a first hash function to obtain a composite index label; and hashes the composite index label, the audio content of the first audio segment and the audio content of the second audio segment based on a second hash function to obtain a second hash value;

[0135] The receiving module is configured to receive the composite index label and the blockchain storage identification sent by the blockchain device; wherein the blockchain storage identification is a storage identification obtained by the blockchain device storing the second hash value.

[0136] In one of the embodiments, the audio processing device 1 is further configured to:

[0137] In one of the embodiments, the audio processing device 1 is further configured to:​​Figure 6 The audio processing device 1 in one of the embodiments further comprises:

[0138] A storage module, configured to store the composite index label and the blockchain notarization identifier into a metadata area of the audio file.

[0139] In one of the embodiments, the structured index label comprises at least one of a start time, an end time, a service type, a semantic abstract, and a compression parameter of the target audio segment.

[0140] The modules in the audio processing device described above can be realized by software, hardware, and combinations thereof in whole or in part. The modules described above can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the modules.

[0141] In one of the embodiments, a computer device is provided, which can be a platform side, and an internal structure diagram thereof can be as shown in Figure 7 The computer device comprises a processor, a memory, and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store audio processing information. The network interface of the computer device is configured to communicate with a user side outside through a network connection. The computer program is executed by the processor to implement an audio processing method.

[0142] Those skilled in the art can understand that Figure 7 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. Specifically, the computer device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0143] In one of the embodiments, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0144] Performing voice activity detection on the audio file to determine a target audio segment in the audio file; wherein the target audio segment comprises a silent audio segment;

[0145] Determining a service type of the target audio segment;

[0146] According to the service type, the target audio segment in the audio file is compressed.

[0147] In one embodiment, the processor, when executing the computer program, also implements the following steps: determining the service type of the target audio segment, comprising:

[0148] determining the start time and the end time of the target audio segment;

[0149] determining the service type of the target audio segment according to the start time and the end time.

[0150] In one embodiment, the processor, when executing the computer program, also implements the following steps: determining the service type of the target audio segment according to the start time and the end time, comprising:

[0151] from the audio file, obtaining a first audio segment of a preset time period before the start time; wherein the end time of the first audio segment is the start time of the target audio segment;

[0152] from the audio file, obtaining a second audio segment of a preset time period after the end time; wherein the start time of the second audio segment is the end time of the target audio segment;

[0153] determining the service type of the target audio segment according to the first audio segment and / or the second audio segment.

[0154] In one embodiment, the processor, when executing the computer program, also implements the following steps: performing voice activity detection on the audio file to determine the target audio segment in the audio file, comprising:

[0155] performing voice activity detection on the audio file to obtain a candidate audio segment in the audio file;

[0156] performing semantic analysis on the candidate audio segment to obtain a semantic analysis result;

[0157] determining the target audio segment in the audio file from the candidate audio segment according to the semantic analysis result.

[0158] In one embodiment, the processor, when executing the computer program, also implements the following steps: compressing the target audio segment in the audio file according to the service type, comprising:

[0159] determining a compression strategy for the target audio segment according to the service type;

[0160] compressing the target audio segment in the audio file based on the compression strategy.

[0161] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0162] According to the audio segment information of the target audio segment, a structured index label corresponding to the target audio segment is determined;

[0163] The structured index label, the audio content of the first audio segment, and the audio content of the second audio segment are sent to the blockchain device, so that the blockchain device performs hash processing on the structured index label based on a first hash function to obtain a composite index label, and performs hash processing on the composite index label, the audio content of the first audio segment, and the audio content of the second audio segment based on a second hash function to obtain a second hash value;

[0164] The composite index label and a blockchain evidence identification sent by the blockchain device are received; the blockchain evidence identification is a storage identification obtained by the blockchain device storing the second hash value.

[0165] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0166] The composite index label and the blockchain evidence identification are stored in a metadata area of the audio file.

[0167] In one embodiment, the processor, when executing the computer program, further implements the following steps: the structured index label includes at least one of a start time, an end time, a service type, a semantic abstract, and a compression parameter of the target audio segment.

[0168] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0169] Voice activity detection is performed on the audio file to determine a target audio segment in the audio file; the target audio segment includes a silent audio segment.

[0170] A service type of the target audio segment is determined.

[0171] According to the service type, the target audio segment in the audio file is compressed.

[0172] In one embodiment, the computer program is executed by the processor to further implement the following steps: determining the service type of the target audio segment includes:

[0173] A start time and an end time of the target audio segment are determined.

[0174] According to the start time and the end time, the service type of the target audio segment is determined.

[0175] In one embodiment, the computer program is executed by the processor to further implement the following steps: according to the start time and the end time, the service type of the target audio segment is determined, including:

[0176] From the audio file, a first audio segment of a preset time period before the start time is obtained; wherein the end time of the first audio segment is the start time of the target audio segment;

[0177] From the audio file, a second audio segment of a preset time period after the end time is obtained; wherein the start time of the second audio segment is the end time of the target audio segment;

[0178] According to the first audio segment and / or the second audio segment, the service type of the target audio segment is determined.

[0179] In one embodiment, the computer program is executed by the processor to further implement the following steps: performing voice activity detection on the audio file to determine the target audio segment in the audio file, comprising:

[0180] Performing voice activity detection on the audio file to obtain a candidate audio segment in the audio file;

[0181] Performing semantic analysis on the candidate audio segment to obtain a semantic analysis result;

[0182] According to the semantic analysis result, the target audio segment in the audio file is determined from the candidate audio segment.

[0183] In one embodiment, the computer program is executed by the processor to further implement the following steps: according to the service type, performing compression processing on the target audio segment in the audio file, comprising:

[0184] According to the service type, a compression strategy for the target audio segment is determined;

[0185] Based on the compression strategy, the target audio segment in the audio file is compressed.

[0186] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0187] According to the audio segment information of the target audio segment, a structured index label corresponding to the target audio segment is determined;

[0188] The structured index label, the audio content of the first audio segment and the audio content of the second audio segment are sent to the blockchain device, so that the blockchain device performs hash processing on the structured index label based on a first hash function to obtain a composite index label; and based on a second hash function, the composite index label, the audio content of the first audio segment and the audio content of the second audio segment are hash processed to obtain a second hash value;

[0189] The composite index label and the blockchain storage identification sent by the blockchain device are received; wherein the blockchain storage identification is a storage identification obtained by the blockchain device storing the second hash value.

[0190] In one embodiment, the computer program, which is executed by the processor, further implements the following steps:

[0191] The composite index label and the blockchain storage identification are stored in a metadata area of the audio file.

[0192] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: the structured index label comprises at least one of a start time, an end time, a service type, a semantic abstract, and a compression parameter of the target audio segment.

[0193] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0194] Voice activity detection is performed on the audio file to determine a target audio segment in the audio file; wherein the target audio segment comprises a silent audio segment;

[0195] A service type of the target audio segment is determined.

[0196] According to the service type, a compression process is performed on the target audio segment in the audio file.

[0197] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: determining the service type of the target audio segment comprises:

[0198] A start time and an end time of the target audio segment are determined.

[0199] According to the start time and the end time, the service type of the target audio segment is determined.

[0200] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: according to the start time and the end time, determining the service type of the target audio segment comprises:

[0201] From the audio file, a first audio segment of a preset time period before the start time is obtained; wherein an end time of the first audio segment is the start time of the target audio segment.

[0202] From the audio file, a second audio segment of a preset time period after the end time is obtained; wherein a start time of the second audio segment is the end time of the target audio segment.

[0203] According to the first audio segment and / or the second audio segment, the service type of the target audio segment is determined.

[0204] In one embodiment, the computer program, which is executed by the processor, further implements the following steps: performing voice activity detection on the audio file to determine a target audio segment in the audio file comprises:

[0205] Performing voice activity detection on the audio file to obtain a candidate audio segment in the audio file;

[0206] Performing semantic analysis on the candidate audio segment to obtain a semantic analysis result;

[0207] Determining a target audio segment in the audio file from the candidate audio segment according to the semantic analysis result.

[0208] In one embodiment, the computer program, when executed by the processor, further implements the following steps: according to the business type, performing compression processing on the target audio segment in the audio file, including:

[0209] According to the business type, determining a compression strategy for the target audio segment;

[0210] Based on the compression strategy, performing compression processing on the target audio segment in the audio file.

[0211] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0212] According to the audio segment information of the target audio segment, determining a structured index label corresponding to the target audio segment;

[0213] Sending the structured index label, the audio content of the first audio segment and the audio content of the second audio segment to the blockchain device, so that the blockchain device hashes the structured index label based on a first hash function to obtain a composite index label; and hashes the composite index label, the audio content of the first audio segment and the audio content of the second audio segment based on a second hash function to obtain a second hash value;

[0214] Receiving the composite index label and the blockchain evidence identification sent by the blockchain device; wherein the blockchain evidence identification is a storage identification obtained by the blockchain device storing the second hash value.

[0215] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0216] Storing the composite index label and the blockchain evidence identification into the metadata area of the audio file.

[0217] In one embodiment, the computer program, when executed by the processor, further implements the following steps: the structured index label includes at least one of the start time, the end time, the business type, the semantic abstract, and the compression parameter of the target audio segment.

[0218] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0219] Any combination of the technical features of the above embodiments can be performed, and in order to make the description concise, the description of all possible combinations of the technical features in the above embodiments is not performed, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0220] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An audio processing method, characterized in that: The method comprises: Performing voice activity detection on an audio file to determine a target audio segment in the audio file; wherein the target audio segment includes a silent audio segment; Determining the service type of the target audio segment; According to the service type, compression processing is performed on the target audio segment in the audio file.

2. The method according to claim 1, characterized in that The determining the service type of the target audio segment includes: Determine the start time and end time of the target audio segment; The service type of the target audio segment is determined according to the start time and the end time.

3. The method according to claim 2, characterized in that The determining the service type of the target audio segment according to the start time and the end time includes: Acquire a first audio segment of a preset period before the start time from the audio file; wherein the end time of the first audio segment is the start time of the target audio segment; Acquire a second audio segment of a preset period after the end time from the audio file; wherein the start time of the second audio segment is the end time of the target audio segment; The service type of the target audio segment is determined according to the first audio segment and / or the second audio segment.

4. The method according to claim 1, wherein The performing voice activity detection on the audio file to determine the target audio segment in the audio file includes: Performing voice activity detection on the audio file to obtain candidate audio segments in the audio file; Performing semantic analysis on the candidate audio segment to obtain a semantic analysis result; According to the semantic analysis result, a target audio segment in the audio file is determined from the candidate audio segments.

5. The method according to claim 1, wherein The compressing the target audio segment in the audio file according to the service type includes: determining a compression strategy for the target audio segment according to the service type; Based on the compression strategy, compression processing is performed on the target audio segment in the audio file.

6. The method according to claim 3, characterized in that The method further comprises: Determining, according to the audio segment information of the target audio segment, a structured index tag corresponding to the target audio segment; Sending the structured index tag, the audio content of the first audio segment, and the audio content of the second audio segment to a blockchain device, so that the blockchain device performs a hash process on the structured index tag based on a first hash function to obtain a compound index tag; and performs a hash process on the compound index tag, the audio content of the first audio segment, and the audio content of the second audio segment based on a second hash function to obtain a second hash value; Receive the composite index tag and blockchain evidence identifier sent by the blockchain device; wherein the blockchain evidence identifier is a storage identifier obtained by the blockchain device storing the second hash value.

7. The method according to claim 6, characterized in that The method further comprises: The composite index tag and the blockchain evidence identifier are stored in the metadata area of ​​the audio file.

8. The method according to claim 6, characterized in that The structured index tag includes at least one of the start time, end time, service type, semantic summary and compression parameter of the target audio segment.

9. An audio processing device, characterized in that: The device comprises: A first determining module is configured to perform voice activity detection on an audio file to determine a target audio segment in the audio file; wherein the target audio segment includes a silent audio segment; A second determining module, configured to determine a service type of the target audio segment; The compression processing module is used to compress the target audio segment in the audio file according to the service type.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product comprising 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 8 are implemented.

Images