Audio detection method and device, computer equipment and storage medium

Abstract

The invention relates to an audio detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring to-be-detected recorded audio data; wherein the recorded audio data comprises radio audio data and broadcast audio data; according to the broadcast audio data, eliminating broadcast audio in the radio audio data to obtain voice audio data; performing voice recognition on the voice audio data, and converting the voice audio data into voice text information; and carrying out sensitive content detection on the voice text information to obtain a sensitive content detection result. The method can improve the detection accuracy of the sensitive content in the audio.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an audio detection method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] During the dual recording process, video quality inspection needs to be performed simultaneously to detect whether there are any illegal guidance issues.

[0003] At present, the relevant technologies use voiceprint recognition, motion recognition, speech recognition and other methods for quality inspection. Voiceprint recognition refers to accurately identifying the speaker's identity by extracting and verifying the voiceprint, but in order to protect user privacy, it is impossible to record and store the voice of each customer in advance to extract voiceprint features, which leads to poor accuracy of voiceprint recognition; motion recognition refers to identification and detection through the user's lip movements when speaking, but because the illegal guiding words are generally short and the lip movements last for a very short time, they cannot be effectively and correctly identified; and because the sounds of the recognition scenes are more complex, speech recognition will lead to poor accuracy of recognition and detection. Summary of the invention

[0004] Based on this, it is necessary to provide an audio detection method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of detecting sensitive content in audio in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides an audio detection method, comprising:

[0006] Acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data;

[0007] According to the broadcast audio data, the broadcast audio in the received audio data is eliminated to obtain voice audio data;

[0008] Performing speech recognition on the speech audio data, and converting the speech audio data into speech text information;

[0009] Perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0010] In one embodiment, the recorded audio data is divided into a plurality of audio segments, and the recorded audio data further includes a start timestamp and an end timestamp of each of the audio segments; and the step of eliminating the broadcast audio in the received audio data according to the broadcast audio data to obtain the voice audio data includes:

[0011] According to the start timestamp and the end timestamp, the recorded audio data is segmented to obtain a plurality of recorded audio segments;

[0012] For each of the recorded audio segments, according to the reported audio data, the reported audio in the recorded audio segment is eliminated to obtain a voice audio segment;

[0013] Each of the voice audio segments is concatenated according to the start timestamp and the end timestamp to obtain voice audio data.

[0014] In one embodiment, for each of the recorded audio segments, eliminating the broadcast audio in the recorded audio segment according to the broadcast audio data to obtain the voice audio segment includes:

[0015] According to the broadcast audio data, waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data are obtained;

[0016] The broadcast audio in the received audio segment is removed according to the waveform data and the waveform generation time to obtain a voice audio segment.

[0017] In one embodiment, before obtaining the waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data according to the broadcast audio data, the method further includes:

[0018] For each of the recorded audio segments, audio synchronization processing is performed on the recorded audio segment and the corresponding portion of the broadcast audio data.

[0019] In one embodiment, the step of performing audio synchronization processing on the recorded audio segment and the corresponding portion of the broadcast audio data includes:

[0020] Acquire the radio waveform data and radio audio time axis of the radio audio segment;

[0021] For the recorded audio segment, obtaining the broadcast waveform data and the broadcast time axis of the corresponding part of the broadcast audio data;

[0022] According to the sound reception waveform data and the announcement waveform data, the announcement time axis is translated to be aligned with the sound reception audio time axis, so as to obtain the announcement audio data after audio synchronization processing.

[0023] In one embodiment, the performing sensitive content detection on the voice text information to obtain a sensitive content detection result includes:

[0024] Detecting all text content in the voice text information;

[0025] When it is detected that the text content contains sensitive words in a preset sensitive word library, a sensitive content detection result is obtained;

[0026] The method further includes: outputting sensitive word prompt information.

[0027] In a second aspect, the present application further provides an audio detection device, comprising:

[0028] A data acquisition module, used to acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data;

[0029] An audio processing module, used for eliminating the broadcast audio in the received audio data according to the broadcast audio data, so as to obtain voice audio data;

[0030] A speech recognition module, used to perform speech recognition on the speech audio data and convert the speech audio data into speech text information;

[0031] The content detection module is used to perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data;

[0034] According to the broadcast audio data, the broadcast audio in the received audio data is eliminated to obtain voice audio data;

[0035] Performing speech recognition on the speech audio data, and converting the speech audio data into speech text information;

[0036] Perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0038] Acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data;

[0039] According to the broadcast audio data, the broadcast audio in the received audio data is eliminated to obtain voice audio data;

[0040] Performing speech recognition on the speech audio data, and converting the speech audio data into speech text information;

[0041] Perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

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

[0043] Acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data;

[0044] According to the broadcast audio data, the broadcast audio in the received audio data is eliminated to obtain voice audio data;

[0045] Performing speech recognition on the speech audio data, and converting the speech audio data into speech text information;

[0046] Perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0047] The above-mentioned audio detection method, device, computer equipment, storage medium and computer program product obtain the recorded audio data to be detected to obtain the received audio data corresponding to the sound emitted by the receiving object in the current receiving scene and the broadcast audio data corresponding to the broadcast sound automatically emitted by the system. According to the broadcast audio data, the broadcast audio in the received audio data can be correspondingly eliminated to obtain voice audio data, and then the voice audio data can be converted into voice text information by performing voice recognition on the voice audio data, so as to perform sensitive content detection on the voice text information to obtain a sensitive content detection result, and can perform sensitive content detection based on the pure received audio with the broadcast audio removed, can remove the broadcast audio and eliminate the interference of the broadcast audio, and only perform quality inspection on the on-site received audio, thereby improving the accuracy of sensitive content detection in the audio. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are 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 creative work.

[0049] Figure 1 A diagram showing an application environment of an audio detection method in an embodiment;

[0050] Figure 2 is a schematic diagram of a flow chart of an audio detection method in an embodiment;

[0051] Figure 3 is a flowchart of an audio detection method in another embodiment;

[0052] Figure 4 is a structural block diagram of an audio detection device in an embodiment;

[0053] Figure 5 is an internal structure diagram of a computer device in one embodiment;

[0054] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying 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.

[0056] The audio detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The data storage system can be used to store recorded audio data to be detected, and can be used to store radio audio data and broadcast audio data and the timestamp information corresponding to the two. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0057] In an exemplary embodiment, Figure 2 As shown, an audio detection method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S208. Among them:

[0058] Step S202, obtaining recorded audio data to be detected.

[0059] Among them, the recorded audio data includes radio audio data and broadcast audio data. Radio audio data refers to the audio data from the sound source to be detected in the recorded audio at the detection site. The sound source to be detected can be a human voice. Further, the broadcast audio data can be audio data recorded by a microphone. Broadcast audio data refers to the broadcast sound automatically generated by the system in the recorded audio at the detection site, which is the part of audio data returned to the recorded audio data due to the playback during the recording process. Furthermore, the broadcast audio data can be TTS (Text-to-Speech, voice broadcast sound) audio data.

[0060] Exemplarily, the server 104 can directly obtain the recorded audio data by setting a recording terminal in the detection scenario. The recorded audio data can be divided into multiple audio segments, and the recorded audio data also includes a start timestamp and an end timestamp of each audio segment.

[0061] For example, the duration of the recorded audio may be about 20 minutes, and the server 104 may segment the audio data according to the start timestamp and the end timestamp to obtain multiple audio segments. Further, the audio data and the broadcast audio data may be uploaded by the terminal 102 to the content storage system of the server 104, and an Object Id for file storage may be generated. The dual recording is divided into different chapters. To ensure the effect, the server 104 may simultaneously record the start time and end time of the broadcast audio of each chapter, so as to segment the audio data according to the start timestamp and the end timestamp to obtain multiple audio segments.

[0062] Step S204, according to the broadcast audio data, the broadcast audio in the received audio data is eliminated to obtain the voice audio data.

[0063] For example, the server 104 can eliminate the broadcast audio in the received audio segment according to the broadcast audio data for each received audio segment to obtain a voice audio segment, and then splice each voice audio segment according to the start timestamp and the end timestamp to obtain voice audio data. Furthermore, the server 104 can also filter out the portion of each voice audio segment that contains the broadcast audio, and then perform echo cancellation processing on the filtered voice audio segment.

[0064] Furthermore, the server 104 can obtain the waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data according to the broadcast audio data; remove the broadcast audio in the received audio segment according to the waveform data and the waveform occurrence time to obtain the voice audio segment. Specifically, first, the server 104 can extract the corresponding waveform data according to the known broadcast audio data, and accurately record the specific time when these waveforms occur on the time axis. These waveform data and time information constitute the "acoustic fingerprint" of the broadcast audio, which can be used as a reference for echo cancellation. Then, the server 104 can compare these waveforms with the waveforms in the received audio segment, and identify the position of the broadcast audio by detecting similar waveform parts in the two audio segments. After the recognition is completed, the server 104 can remove these echo waveforms from the received audio segment, thereby retaining the audio content containing only the actual voice of the user, and finally generating a pure voice audio segment for use in subsequent processing links such as voice recognition.

[0065] Furthermore, before obtaining the waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data based on the broadcast audio data, the server 104 can also perform audio synchronization processing on the received audio segment and the corresponding part of the broadcast audio data for each received audio segment.

[0066] Step S206: perform speech recognition on the speech and audio data, and convert the speech and audio data into speech text information.

[0067] Exemplarily, after obtaining the voice audio data with echo eliminated, the server will perform voice recognition processing on it. First, the voice audio will be sent to the voice recognition engine, and the audio signal will be analyzed by the front-end processing module, including noise reduction, feature extraction and other steps, from which the acoustic features representing the audio content are extracted. Next, these acoustic features will be matched with the acoustic model, language model and pronunciation dictionary in the speech recognition model, and the model will determine the text or word corresponding to each segment in the audio through probability calculation. By gradually combining these results, the speech recognition engine will eventually convert the complete voice audio into voice text information. These text data can be further used for storage, analysis or real-time feedback to users, thereby completing the speech-to-text conversion process.

[0068] Step S208: Perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0069] For example, the server 104 can detect all text content in the voice text information; if sensitive words in a preset sensitive word library are detected in the text content, a sensitive content detection result is obtained. The server 104 can deploy a sensitive word recognition service to detect whether the incoming voice text information contains sensitive words. The server 104 can create a sensitive word library in advance. If a sensitive word is hit in the detection, it can be considered that there is an illegal guidance problem.

[0070] Exemplarily, the server 104 may also output sensitive word prompt information. The server 104 may output the sensitive content detection result to the terminal 102 , prompt the detection personnel through the terminal 102 , and may also display the specific hit sensitive content information through the terminal 102 .

[0071] In the above-mentioned audio detection method, the recorded audio data to be detected is obtained to obtain the received audio data corresponding to the sound emitted by the receiving object in the current receiving scene and the broadcast audio data corresponding to the broadcast sound automatically emitted by the system. According to the broadcast audio data, the broadcast audio in the received audio data can be correspondingly eliminated to obtain voice audio data, and then the voice audio data is subjected to voice recognition to convert the voice audio data into voice text information, thereby performing sensitive content detection on the voice text information to obtain a sensitive content detection result. Sensitive content detection can be performed based on the pure received audio from which the broadcast audio has been removed, and the broadcast audio can be removed to eliminate the interference of the broadcast audio, thereby improving the accuracy of sensitive content detection in the audio.

[0072] In an exemplary embodiment, Figure 3 As shown, for each recorded audio segment, the step of performing audio synchronization processing on the recorded audio segment and the corresponding part of the broadcast audio data may include steps S302 to S306. Among them:

[0073] Step S302, obtaining the sound recording waveform data and the sound recording audio time axis of the sound recording audio segment.

[0074] For example, the server 104 can parse the recorded audio clips and extract the corresponding waveform data, which reflects the intensity and frequency changes of the audio signal over time. At the same time, the server 104 can extract the time axis information of the recorded audio from the metadata of the audio, and record the specific time position of each waveform data to form a complete time-series waveform mapping.

[0075] Step S304, for the recorded audio segment, obtaining the broadcast waveform data and the broadcast time axis of the corresponding part of the broadcast audio data.

[0076] For example, the server 104 can locate the corresponding broadcast audio data range according to the currently processed radio audio segment, which is generated and played by the system. The server 104 can retrieve the corresponding broadcast audio segment from the content storage system, perform waveform analysis on it, and extract the waveform data of the broadcast audio. In addition, the server 104 can read the time axis information of the broadcast audio, which records the occurrence time of each waveform of the broadcast audio. Through this process, the server 104 obtains the detailed waveform and time information of the broadcast audio.

[0077] Step S306, according to the sound recording waveform data and the announcement waveform data, the announcement time axis is translated to be aligned with the sound recording audio time axis, so as to obtain the announcement audio data after audio synchronization processing.

[0078] Exemplarily, the server 104 can compare the waveform data of the radio audio and the broadcast audio, and analyze the delay difference between the two audio segments on the time axis, and the delay time can be 200-500ms. According to the result of the waveform matching, the server 104 can shift the time axis of the broadcast audio by a certain time offset to align it with the time axis of the radio audio. Through this time axis translation operation, the waveform data of the broadcast audio and the waveform data of the radio audio can be matched at the same time position, thereby achieving synchronization of the two audio segments. The synchronized broadcast audio data will be used for subsequent echo cancellation processing to ensure accurate identification and removal of the echo part.

[0079] In another exemplary embodiment, the server 104 acquires the recorded audio data to be detected to obtain the received audio data and the broadcast audio data, and then segments the received audio data according to the start timestamp and the end timestamp to obtain multiple received audio segments.

[0080] Next, for each radio audio segment, the server 104 obtains the radio waveform data and the radio audio timeline of the radio audio segment, and obtains the broadcast waveform data and the broadcast timeline of the corresponding part of the broadcast audio data, so that according to the radio waveform data and the broadcast waveform data, the broadcast timeline is translated to align with the radio audio timeline, and the broadcast audio data after audio synchronization processing is obtained.

[0081] Subsequently, the server 104 obtains the waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data based on the broadcast audio data, and then removes the broadcast audio in the received audio segment based on the waveform data and the waveform occurrence time to obtain the voice audio segment, and splices each voice audio segment according to the start timestamp and the end timestamp to obtain the voice audio data.

[0082] Finally, the server 104 performs speech recognition on the voice audio data, converts the voice audio data into voice text information, detects all text content in the voice text information, and obtains sensitive content detection results when sensitive words in a preset sensitive word library are detected in the text content, and outputs sensitive word prompt information through the terminal 102.

[0083] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0084] Based on the same inventive concept, the embodiment of the present application also provides an audio detection device for implementing the audio detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more audio detection device embodiments provided below can refer to the limitations on the audio detection method above, and will not be repeated here.

[0085] In an exemplary embodiment, as shown in Figure 4, an audio detection device is provided, including: a data acquisition module 402, an audio processing module 404, a speech recognition module 406 and a content detection module 408, wherein:

[0086] The data acquisition module 402 is used to acquire the recorded audio data to be detected; wherein the recorded audio data includes the received audio data and the broadcast audio data;

[0087] The audio processing module 404 is used to eliminate the broadcast audio in the received audio data according to the broadcast audio data to obtain the voice audio data;

[0088] The speech recognition module 406 is used to perform speech recognition on the speech audio data and convert the speech audio data into speech text information;

[0089] The content detection module 408 is used to perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0090] In one embodiment, the recorded audio data is divided into a plurality of audio segments, and the recorded audio data also includes a start timestamp and an end timestamp of each audio segment; the audio processing module 404 includes:

[0091] A data segmentation unit, used to segment the received audio data according to the start timestamp and the end timestamp to obtain multiple received audio segments;

[0092] A segmented silencing unit is used to eliminate the broadcast audio in each received audio segment according to the broadcast audio data to obtain a voice audio segment;

[0093] The data splicing unit is used to splice each voice audio segment according to the start timestamp and the end timestamp to obtain voice audio data.

[0094] In one of the embodiments, the segmented silencing unit is specifically used to: obtain waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data based on the broadcast audio data; remove the broadcast audio in the received audio segment based on the waveform data and the waveform occurrence time to obtain the voice audio segment.

[0095] In one embodiment, the audio processing module 404 further includes:

[0096] The audio synchronization unit is used to perform audio synchronization processing on the received audio segment and the corresponding part of the broadcast audio data for each received audio segment.

[0097] In one of the embodiments, the audio synchronization unit is specifically used to: obtain the radio waveform data and the radio audio timeline of the radio audio segment; for the radio audio segment, obtain the broadcast waveform data and the broadcast timeline of the corresponding part of the broadcast audio data; according to the radio waveform data and the broadcast waveform data, shift the broadcast timeline to align with the radio audio timeline to obtain the broadcast audio data after audio synchronization processing.

[0098] In one embodiment, the content detection module 408 is specifically used to: detect all text content in the voice text information; obtain sensitive content detection results when sensitive words in a preset sensitive word library are detected in the text content; and output sensitive word prompt information.

[0099] Each module in the above-mentioned audio detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0100] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes 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 the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store recorded audio data to be detected, and can be used to store radio audio data and broadcast audio data and the corresponding timestamp information of the two. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an audio detection method is implemented.

[0101] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an audio detection method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0102] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0103] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining recorded audio data to be detected; wherein the recorded audio data includes received audio data and broadcast audio data; based on the broadcast audio data, eliminating the broadcast audio in the received audio data to obtain voice audio data; performing voice recognition on the voice audio data to convert the voice audio data into voice text information; performing sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0104] In one embodiment, the processor also implements the following steps when executing the computer program: according to the start timestamp and the end timestamp, the received audio data is segmented to obtain multiple received audio segments; for each received audio segment, according to the broadcast audio data, the broadcast audio in the received audio segment is eliminated to obtain a voice audio segment; and each voice audio segment is spliced ​​according to the start timestamp and the end timestamp to obtain voice audio data.

[0105] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the broadcast audio data, waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data are obtained; based on the waveform data and the waveform occurrence time, the broadcast audio in the received audio segment is removed to obtain the voice audio segment.

[0106] In one embodiment, when the processor executes the computer program, the following steps are further implemented: for each recorded audio segment, audio synchronization processing is performed on the recorded audio segment and the corresponding part of the broadcast audio data.

[0107] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the radio waveform data and the radio audio timeline of the radio audio segment; for the radio audio segment, obtaining the broadcast waveform data and the broadcast timeline of the corresponding part of the broadcast audio data; based on the radio waveform data and the broadcast waveform data, shifting the broadcast timeline to align with the radio audio timeline to obtain the broadcast audio data after audio synchronization processing.

[0108] In one embodiment, when the processor executes the computer program, the following steps are also implemented: detecting all text content in the voice text information; obtaining sensitive content detection results when sensitive words in a preset sensitive word library are detected in the text content; and outputting sensitive word prompt information.

[0109] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining recorded audio data to be detected; wherein the recorded audio data includes received audio data and broadcast audio data; based on the broadcast audio data, eliminating the broadcast audio in the received audio data to obtain voice audio data; performing voice recognition on the voice audio data to convert the voice audio data into voice text information; performing sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0110] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to the start timestamp and the end timestamp, the received audio data is segmented to obtain multiple received audio segments; for each received audio segment, according to the broadcast audio data, the broadcast audio in the received audio segment is eliminated to obtain a voice audio segment; and each voice audio segment is spliced ​​according to the start timestamp and the end timestamp to obtain voice audio data.

[0111] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the broadcast audio data, waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data are obtained; based on the waveform data and the waveform occurrence time, the broadcast audio in the received audio segment is removed to obtain the voice audio segment.

[0112] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each recorded audio segment, audio synchronization processing is performed on the recorded audio segment and the corresponding part of the broadcast audio data.

[0113] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the radio waveform data and the radio audio timeline of the radio audio segment; for the radio audio segment, obtaining the broadcast waveform data and the broadcast timeline of the corresponding part of the broadcast audio data; based on the radio waveform data and the broadcast waveform data, shifting the broadcast timeline to align with the radio audio timeline to obtain the broadcast audio data after audio synchronization processing.

[0114] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: detecting all text content in the voice text information; obtaining sensitive content detection results when sensitive words in a preset sensitive word library are detected in the text content; and outputting sensitive word prompt information.

[0115] In one embodiment, a computer program product is provided, including a computer program, which implements the following steps when executed by a processor: obtaining recorded audio data to be detected; wherein the recorded audio data includes received audio data and broadcast audio data; based on the broadcast audio data, eliminating the broadcast audio in the received audio data to obtain voice audio data; performing voice recognition on the voice audio data to convert the voice audio data into voice text information; performing sensitive content detection on the voice text information to obtain a sensitive content detection result.

[0116] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to the start timestamp and the end timestamp, the received audio data is segmented to obtain multiple received audio segments; for each received audio segment, according to the broadcast audio data, the broadcast audio in the received audio segment is eliminated to obtain a voice audio segment; and each voice audio segment is spliced ​​according to the start timestamp and the end timestamp to obtain voice audio data.

[0117] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the broadcast audio data, waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data are obtained; based on the waveform data and the waveform occurrence time, the broadcast audio in the received audio segment is removed to obtain the voice audio segment.

[0118] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for each recorded audio segment, audio synchronization processing is performed on the recorded audio segment and the corresponding part of the broadcast audio data.

[0119] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the radio waveform data and the radio audio timeline of the radio audio segment; for the radio audio segment, obtaining the broadcast waveform data and the broadcast timeline of the corresponding part of the broadcast audio data; based on the radio waveform data and the broadcast waveform data, shifting the broadcast timeline to align with the radio audio timeline to obtain the broadcast audio data after audio synchronization processing.

[0120] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: detecting all text content in the voice text information; obtaining sensitive content detection results when sensitive words in a preset sensitive word library are detected in the text content; and outputting sensitive word prompt information.

[0121] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0122] 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, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this 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 memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access 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 and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0123] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An audio detection method, characterized in that: The method comprises: Acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data; According to the broadcast audio data, the broadcast audio in the received audio data is eliminated to obtain voice audio data; Performing speech recognition on the speech audio data, and converting the speech audio data into speech text information; Perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

2. The method according to claim 1, characterized in that The recorded audio data is divided into a plurality of audio segments, and the recorded audio data also includes a start timestamp and an end timestamp of each of the audio segments; the method of eliminating the broadcast audio in the received audio data according to the broadcast audio data to obtain the voice audio data includes: According to the start timestamp and the end timestamp, the recorded audio data is segmented to obtain a plurality of recorded audio segments; For each of the recorded audio segments, according to the reported audio data, the reported audio in the recorded audio segment is eliminated to obtain a voice audio segment; Each of the voice audio segments is concatenated according to the start timestamp and the end timestamp to obtain voice audio data.

3. The method according to claim 2, characterized in that For each of the recorded audio segments, according to the reported audio data, eliminating the reported audio in the recorded audio segment to obtain the voice audio segment, including: According to the broadcast audio data, waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data are obtained; The broadcast audio in the received audio segment is removed according to the waveform data and the waveform generation time to obtain a voice audio segment.

4. The method according to claim 3, characterized in that Before obtaining the waveform data of the broadcast audio and the waveform occurrence time corresponding to the waveform data according to the broadcast audio data, the method further comprises: For each of the recorded audio segments, audio synchronization processing is performed on the recorded audio segment and the corresponding portion of the broadcast audio data.

5. The method according to claim 4, characterized in that The step of performing audio synchronization processing on the recorded audio segment and the corresponding portion of the broadcast audio data comprises: Acquire the radio waveform data and radio audio time axis of the radio audio segment; For the recorded audio segment, obtaining the broadcast waveform data and the broadcast time axis of the corresponding part of the broadcast audio data; According to the sound reception waveform data and the announcement waveform data, the announcement time axis is translated to be aligned with the sound reception audio time axis, so as to obtain the announcement audio data after audio synchronization processing.

6. The method according to any one of claims 1 to 5, characterized in that: The performing sensitive content detection on the voice text information to obtain a sensitive content detection result includes: Detecting all text content in the voice text information; When it is detected that the text content contains sensitive words in a preset sensitive word library, a sensitive content detection result is obtained; The method further includes: outputting sensitive word prompt information.

7. An audio detection device, characterized in that: The device comprises: A data acquisition module, used to acquire recorded audio data to be detected; wherein the recorded audio data includes radio audio data and broadcast audio data; An audio processing module, used for eliminating the broadcast audio in the received audio data according to the broadcast audio data, so as to obtain voice audio data; A speech recognition module, used to perform speech recognition on the speech audio data and convert the speech audio data into speech text information; The content detection module is used to perform sensitive content detection on the voice text information to obtain a sensitive content detection result.

8. 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 6 are implemented.

9. 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 6 are implemented.

10. 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 6 are implemented.

Images