Audio detection method and audio detection apparatus
By using audio detection methods to perform frame-by-frame processing and pitch calculation, the blind spots in the accident monitoring of the elderly and school-aged children by image tracking technology are solved, and a simple and effective sound source number detection is achieved.
Patent Information
- Application Number
- CN202510210598.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-25
- Publication Date
- 2026-08-25
AI Technical Summary
Existing accident detection methods typically rely on image tracking technology, which is difficult to effectively monitor, especially when the elderly and school-aged children fall or faint, and also has blind spots.
An audio detection method is adopted, which uses a processor to perform frame processing, signal strength analysis, pitch calculation, and threshold counting of audio to determine the number of sound sources, avoiding blind spots in image tracking technology and achieving simplified calculation.
It effectively monitors the number of sound sources, avoids blind spots in image tracking technology, has low computational requirements and is easy to implement, and is suitable for various electronic systems.
Smart Images
Figure CN122637802A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to an audio detection method and an audio detection apparatus, and more particularly to an audio detection method and an audio detection apparatus for detecting audio to obtain the number of sound sources. Background Technology
[0002] In the event of an accident, the elderly and school-aged children are more in need of assistance. Using electronic devices to detect accidents and notifying emergency contacts of the results would help them understand the situation in real time, thus facilitating appropriate action.
[0003] However, existing detection methods typically utilize image tracking technology, which requires the installation of additional cameras. Furthermore, in cases of falls, fainting, or other unexpected situations, it is difficult to use image tracking technology to monitor the actual accidental situations of the elderly and school-aged children. Summary of the Invention
[0004] In view of the shortcomings of the prior art, one of the objectives of this disclosure is (but not limited to) to provide an audio detection method and an audio detection device to improve the shortcomings of the prior art.
[0005] In some embodiments, this disclosure provides an audio detection method executed by a processor reading at least one instruction stored in a memory. The audio detection method includes the following steps: performing frame processing on audio to generate multiple sound frames; dividing the audio into multiple segments based on multiple signal intensities of the multiple sound frames; calculating multiple actual pitches of the multiple sound frames of a target segment; calculating multiple predicted pitches based on the multiple actual pitches of the target segment; calculating multiple pitch differences based on the multiple actual pitches and the multiple predicted pitches of the target segment; calculating an over-threshold count based on the multiple pitch differences of the target segment and a pitch threshold; if the over-threshold count is greater than a portion of the total number of pitches of the multiple actual pitches of the target segment, the target segment is a multiple sound source segment; and if the over-threshold count is zero, the target segment is a single sound source segment.
[0006] In some embodiments, the audio detection device includes a memory and a processor. The memory is used to store at least one instruction. The processor is used to read at least one instruction to perform the following steps: framing the audio to generate multiple sound frames; dividing the audio into multiple segments based on multiple signal intensities of the multiple sound frames; calculating multiple actual pitches of multiple sound frames of a target segment; calculating multiple predicted pitches based on the multiple actual pitches of the target segment; calculating multiple pitch differences based on the multiple actual pitches and multiple predicted pitches of the target segment; calculating an over-threshold count based on the multiple pitch differences of the target segment and a pitch threshold; if the over-threshold count is greater than a portion of the total number of pitches of the multiple actual pitches of the target segment, the target segment is a multiple sound source segment; and if the over-threshold count is zero, the target segment is a single sound source segment.
[0007] The technical means embodied in the embodiments of this disclosure can improve at least one of the shortcomings of the prior art. The audio detection method and audio detection device of this disclosure can be applied to various electronic systems. By receiving audio through the electronic system and calculating the audio, the number of users can be determined. This not only avoids the problem of blind spots in image tracking technology, which makes it impossible to effectively monitor users, but also has the advantages of low computational load and simple implementation.
[0008] The features, implementation, and technical effects of this disclosure are described in detail below with reference to the accompanying drawings. Attached Figure Description
[0009] Figure 1 This is a schematic diagram of an audio detection device according to some embodiments of the present disclosure;
[0010] Figure 2 This is a flowchart illustrating an audio detection method according to some embodiments of the present disclosure;
[0011] Figure 3 This is a schematic diagram of an audio and sound frame drawn according to some embodiments of the present disclosure;
[0012] Figure 4 This is a schematic diagram of an audio signal and pitch according to some embodiments of the present disclosure;
[0013] Figure 5 This is a schematic diagram of an audio signal and pitch according to some embodiments of the present disclosure;
[0014] Figure 6 This is a flowchart illustrating an audio detection method according to some embodiments of the present disclosure;
[0015] Figure 7 This is a schematic diagram of an audio signal and pitch according to some embodiments of the present disclosure;
[0016] Figure 8 A schematic diagram of an audio signal and pitch drawn according to some embodiments of the present disclosure; and
[0017] Figure 9 This is a schematic diagram of an audio signal and pitch according to some embodiments of the present disclosure.
[0018] Symbol Explanation
[0019] 100: Audio detection device
[0020] 110: Radio
[0021] 120: Audio Input Interface
[0022] 130: Processor
[0023] 140: Memory
[0024] 200: Method
[0025] 210-280: Steps
[0026] 600: Method
[0027] 610~661: Steps
[0028] fn~fn+2: Sound frame
[0029] p1~p10: Peaks
[0030] s1~s9: Segment
[0031] t1~t10: troughs Detailed Implementation
[0032] All terms used herein have their ordinary meanings. The definitions of the terms above in commonly used dictionaries, and the examples of any term used in this disclosure, are merely illustrative and should not be construed as limiting the scope or meaning of this disclosure. Similarly, this disclosure is not limited to the various embodiments shown in this specification.
[0033] As used herein, “coupled” or “connected” can refer to two or more components making direct physical or electrical contact with each other, or indirectly making direct physical or electrical contact with each other, or to two or more components operating or acting on each other. As used herein, “circuit” can refer to a device consisting of at least one transistor and / or at least one active or passive component connected in a certain manner to process signals.
[0034] As used herein, the term "and / or" includes any combination of one or more of the listed related items. The terms first, second, third, etc., are used herein to describe and identify individual elements. Therefore, a first element herein may also be referred to as a second element without departing from the intent of this disclosure. For ease of understanding, similar elements in the figures will be designated with the same reference numerals.
[0035] To avoid the problem of blind spots in image tracking technology that prevent effective user monitoring, this disclosure proposes an audio detection method and an audio detection device, which are described in detail below.
[0036] Figure 1This is a schematic diagram of an audio detection device 100 according to some embodiments of the present disclosure. As shown, the audio detection device 100 includes a microphone 110, an audio input interface 120, a processor 130, and a memory 140. The microphone 110 receives sound and converts it into digital audio. Subsequently, the microphone 110 inputs the digital audio to the processor 130 through the audio input interface 120. The memory 140 stores at least one instruction. The processor 130 reads at least one instruction to execute the audio detection process. For ease of understanding of the operation of the audio detection device 100, please also refer to... Figure 2 , Figure 2 This is a flowchart of an audio detection method 200 according to some embodiments of the present disclosure.
[0037] Please see Figure 2 Step 210 involves segmenting the audio into frames to generate multiple audio frames. For example, see... Figure 1 and Figure 3 The processor 130 of the audio detection device 100 disclosed herein can perform framing processing on the audio to generate multiple sound frames fn to fn+2. In detail, the processor 130 of the audio detection device 100 disclosed herein can divide the audio into multiple overlapping sound frames fn to fn+2, and then perform further acoustic analysis on a unit of sound frames fn to fn+2.
[0038] The sampling rate of the processor 130 of the audio detection device 100 disclosed herein varies depending on the audio input interface 120, and can be 16000Hz, 24000Hz, 44100Hz, or 48000Hz. In some embodiments, the frame size of the audio frame can be 20 milliseconds (ms). If the sampling rate is 48000Hz, then 960 samples are sampled. The overlap rate between audio frames can be 25%, and the overlap time between audio frames is 5 milliseconds (ms), resulting in 240 overlapping samples between audio frames. Each audio frame is separated by a hop size, which can be the frame size minus the overlap time. For example, 20 milliseconds minus 5 milliseconds equals 15 milliseconds, and the hop size contains 720 samples. However, this disclosure is not limited to the values given in this embodiment, and other suitable values may also be used, depending on actual needs.
[0039] Please see Figure 2 Step 220 involves dividing the audio into multiple segments based on the multiple signal intensities of the multiple sound frames. For example, please refer to... Figure 1 and Figure 3 The processor 130 of the audio detection device 100 disclosed herein can calculate the signal strength of the sound frame fn to fn+2, and the formula for the signal strength is as follows:
[0040]
[0041] As shown in Formula 1, E is the signal strength, x i is the sample value of the sound frame, and N is the frame size of the sound frame.
[0042] In addition, please see Figure 1 and Figure 4 The processor 130 of the audio detection device 100 disclosed herein can obtain multiple peaks p1 to p10 and multiple troughs t1 to t10 based on multiple signal strengths. For example, to obtain a peak, the signal strength of the frame must first be calculated, and the signal strength of the frame must be greater than the signal strength of the frames on both sides. In this way, the frame with the largest relative signal strength can be found as a candidate peak. Furthermore, this disclosure sets thresholds to filter candidate peaks, such as setting a maximum height, a minimum height, a minimum distance between peaks, etc. In detail, this disclosure can set the minimum height to 1 dB, the maximum height to 25 dB, and the minimum distance between peaks to 5 hop sizes. If the hop size is 15 milliseconds, then the minimum distance between peaks is 75 milliseconds. In addition, the method of obtaining troughs is similar to that of obtaining peaks, except that the signal strength of the frame needs to be changed to a negative value (multiplied by -1) for related calculations. The other calculation methods are the same and will not be described in detail here. The processor 130 of the audio detection device 100 of this disclosure can obtain the peak array as described above:
[0043] peaks=[12,30,47,60,78,97,116,129,155,176]......Formula 2
[0044] As shown in Formula 2, "peak" represents a peak, and the number in parentheses represents the frame number. For example, "12" in parentheses indicates the 12th frame, meaning the 12th frame is a peak. Similarly, "30" in parentheses indicates the 30th frame, meaning the 30th frame is a peak, and so on.
[0045] The processor 130 of the audio detection device 100 of this disclosure can obtain the valley array as described above:
[0046] troughs=[1,23,56,65,88,125,150,162,170,189,196]...Formula 3
[0047] As shown in Formula 3, "trough" represents a trough, and the number in parentheses represents the frame number. For example, "1" in parentheses represents the first frame, indicating that the first frame is a trough. Similarly, "23" in parentheses represents the 23rd frame, indicating that the 23rd frame is a trough, and so on.
[0048] Furthermore, the processor 130 of the audio detection device 100 of this disclosure can divide the audio into multiple segments s1 to s9 based on multiple troughs t1 to t10. For example, the processor 130 of the audio detection device 100 of this disclosure can divide the audio into segment s1 based on troughs t1 and t2, and the processor 130 can divide the audio into segment s2 based on troughs t2 and t3, and so on. In detail, assuming that trough t1 is the first trough in the trough array of Formula 3, according to Formula 3, trough t1 is the first sound frame. In addition, assuming that trough t2 is the second trough in the trough array of Formula 3, according to Formula 3, trough t2 is the 23rd sound frame. The calculation formula for the segment s1 divided by troughs t1 and t2 is as follows:
[0049] T1=trough(1)×hop=1×15=15(ms)…Formula 4
[0050] T2=trough(2)×hop=23×15=345(ms)…Formula 5
[0051] As shown in Formulas 4 and 5, T1 is the time point of trough t1, T2 is the time point of trough t2, trough(1) is the first trough in the trough array of Formula 3, trough(2) is the second trough in the trough array of Formula 3, and hop is the jump distance. Assuming trough(1) is the first frame and the jump distance is 15 milliseconds, substituting into Formula 4, we can obtain the time point of trough t1 as 15 milliseconds. Assuming trough(2) is the 23rd frame and the jump distance is 15 milliseconds, substituting into Formula 5, we can obtain the time point of trough t2 as 345 milliseconds. Therefore, the segment s1 divided by troughs t1 and t2 is between 15 milliseconds and 345 milliseconds. The processor 130 of the audio detection device 100 of this disclosure can obtain the time intervals of all segments s1 to s9 in the above manner. However, this disclosure is not limited to the values given in this embodiment, and other suitable values may also be used, depending on actual needs.
[0052] Please see Figure 2 Step 230 involves calculating multiple actual pitches for multiple tone frames of the target tone segment across multiple tone segments. For example, please refer to... Figure 1 and Figure 4 The processor 130 of the audio detection device 100 of this disclosure can calculate multiple actual pitches of multiple sound frames in a target sound segment s1 of multiple sound segments s1 to s9. Specifically, the processor 130 of the audio detection device 100 of this disclosure can use the YIN algorithm to calculate the actual pitches of the sound frames in sound segment s1. However, this disclosure is not limited to the YIN algorithm described in this embodiment; other suitable algorithms may also be used, depending on actual needs.
[0053] Please see Figure 2 Step 240 involves calculating multiple predicted pitches based on multiple actual pitches of the target segment. For example, please refer to... Figure 1 and Figure 4 The processor 130 of the audio detection device 100 of this disclosure can calculate the predicted pitch based on the actual pitch of the voice frame in the target audio segment s1. Specifically, the processor 130 of the audio detection device 100 of this disclosure can use Kalman filter tracking to calculate the predicted pitch, and the formula for the predicted pitch is as follows:
[0054]
[0055] As shown in Formula 6, z t The actual pitch at time t. The predicted pitch for time t, Let K be the predicted pitch at time t-1. t This refers to the Kalman gain. This disclosure uses Formula 6 to calculate the predicted pitch based on the actual pitch of the tone frame in the target pitch segment s1. Please refer to the above-mentioned actual pitch and calculated predicted pitch. Figure 5 The solid line represents the actual pitch, and the dashed line represents the predicted pitch calculated by formula 6 in this disclosure. However, this disclosure is not limited to the Kalman filter tracking described in this embodiment, and other suitable algorithms may also be used, depending on the actual needs.
[0056] Please see Figure 2 Step 250 calculates multiple pitch differences based on multiple actual pitches and multiple predicted pitches of the target segment. For example, please refer to... Figure 1 and Figure 5 The processor 130 of the audio detection device 100 disclosed herein can calculate the pitch difference based on the actual pitch (solid line) and the predicted pitch (dashed line) of the target pitch segment. The formula for the pitch difference is as follows:
[0057] diff i =fr i (P true )-fr i (P track )…Formula 7
[0058] As shown in Formula 7, diff i For pitch difference, fr i (P true ) represents the actual pitch, fr i (P track () indicates the predicted pitch. Please refer to [link / reference]. Figure 5If the actual pitch is close to the predicted pitch, it indicates a single sound source (e.g., only one person speaking). In this case, the actual pitch is close to the predicted pitch, and the pitch difference is small. Conversely, if the actual pitch is far from the predicted pitch, it indicates that the inaccurate prediction is not due to a single sound source, but rather multiple sound sources (e.g., multiple people speaking). In this case, the actual pitch deviates from the predicted pitch, and the pitch difference is large.
[0059] Please see Figure 2 Step 260 calculates the threshold exceedance count based on multiple pitch differences and pitch thresholds of the target segment. For example, please refer to... Figure 1 The processor 130 of the audio detection device 100 disclosed herein can calculate the threshold exceedance count based on the pitch difference of the target audio segment and the pitch threshold. The formula for the threshold exceedance count is as follows:
[0060]
[0061] As shown in Formula 8, S is the over-threshold count, and diff i diff represents pitch difference. thd For pitch threshold, 1(·) in Formula 8 is an indicator function, which is 1 when the condition in parentheses is true, and 0 otherwise.
[0062] Please see Figure 2 Step 270: If the threshold count exceeds a portion of the total number of actual pitches in the target segment, the target segment is a multiple sound source segment. For example, please refer to... Figure 1 and Figure 4 The processor 130 of the audio detection device 100 of this disclosure can use the YIN algorithm to calculate the actual pitch of the sound frames in the audio segment s1. If the YIN algorithm calculates that sound frame 1 has an actual pitch, then sound frame 1 is set as a sound frame with pitch. If the YIN algorithm calculates that sound frame 2 does not have an actual pitch, then sound frame 2 is set as a sound frame without pitch. This disclosure can perform pitch detection on all sound frames in the audio segment s1 in the above manner, and the number of sound frames with pitch is the total number of pitches. Furthermore, if the over-threshold count S in Formula 8 is greater than half of the total number of pitches, then the target audio segment s1 is determined to be a multiple sound source segment, indicating that multiple people are speaking in the target audio segment s1.
[0063] Please see Figure 2 In step 280, if the threshold count is zero, the target segment is a single-source segment. For example, please refer to... Figure 1 and Figure 4If the threshold count S in Formula 8 is 0, then the target audio segment s1 is determined to be a single sound source segment, meaning that only one person is speaking in the target audio segment s1. As described above, the audio detection device 100 and audio detection method 200 of this disclosure can collect audio through the microphone 110 and calculate the number of users on site. In this way, the audio detection device 100 and audio detection method 200 of this disclosure can not only avoid the problem of blind spots in image tracking technology, which makes it impossible to effectively monitor users, but also have the advantages of low computational load and simple implementation.
[0064] Figure 6 This is a flowchart illustrating an audio detection method 600 according to some embodiments of the present disclosure. The present disclosure allows for the use of the audio detection method 600 to detect audio... Figure 4 All the segments s1 to s9 are judged to determine which type of segment each segment belongs to, thereby understanding how many speakers each segment s1 to s9 has.
[0065] Please see Figure 6 In step 610, the audio detection method 600 of this disclosure can determine whether a sound segment has no peaks. Assuming that the sound segment s1 does indeed have no peaks, then in step 611, the sound segment s1 is determined to be a sound source-less sound segment; in other words, there is no speaker in the sound segment s1. Alternatively, assuming that the sound segment s1 has peaks, then step 620 is executed.
[0066] Please see Figure 6 In step 620, the audio detection method 600 of this disclosure can determine whether the total number of pitches is zero. If the total number of pitches is zero, then in step 621, it is determined that segment s1 is a breathy segment; in other words, segment s1 contains only breathy sounds. Furthermore, if the total number of pitches in segment s1 is not zero, then step 630 is executed.
[0067] Please see Figure 6 In step 630, the audio detection method 600 of this disclosure can determine whether the signal strength of the boundary frame is greater than the intensity threshold. Assuming that the range of the sound segment s1 is between the first and 23rd frame, then both the first and 23rd frame are boundary frames of the sound segment s1. The audio detection method 600 of this disclosure can set the intensity threshold to -3dB. If the signal strength of the first frame is greater than -3dB or the signal strength of the 23rd frame is greater than -3dB, then in step 631, it is determined that the sound segment s1 is a multiple sound source segment; in other words, there are multiple speakers in the sound segment s1. Furthermore, assuming that the signal strength of neither the first nor the 23rd frame is greater than -3dB, then step 640 is executed.
[0068] Please see Figure 6In step 640, the audio detection method 600 of this disclosure can determine whether the threshold count is greater than a portion of the total number of pitches. For example, if the threshold count S of Formula 8 is greater than half of the total number of pitches, then in step 641, it is determined that the sound segment s1 is a multiple sound source segment; in other words, there are multiple speakers in the sound segment s1. Furthermore, if the threshold count S of Formula 8 is not greater than half of the total number of pitches, then step 650 is executed.
[0069] Please see Figure 6 In step 650, the audio detection method 600 of this disclosure can determine whether the threshold count is zero. For example, if the threshold count S of Formula 8 is 0, then in step 651, it is determined that the sound segment s1 is a single sound source segment; in other words, there is only one speaker in the sound segment s1. Furthermore, if the threshold count S of Formula 8 is not 0, then step 660 is executed.
[0070] Please see Figure 6 In step 660, the audio detection method 600 of this disclosure can determine whether the over-threshold count is between a portion of the total number of pitches and zero. For example, if the over-threshold count S of Formula 8 is between half of the total number of pitches and 0, then in step 661, the pitch segment s1 is determined to be a sound source conversion pitch segment; in other words, the speaker in the pitch segment s1 is changing from speaker A to speaker B.
[0071] Figures 7 to 9 This is a schematic diagram illustrating an audio signal and pitch according to some embodiments of the present disclosure. Figures 7 to 9 As shown, after detecting audio according to the audio detection method 600 of this disclosure, the number of speakers in different segments can be determined, and each segment can contain multiple pitches. For example, in a single-source segment, the actual pitch (solid line) and the predicted pitch (dashed line) are relatively close, indicating that there is currently a single sound source (e.g., only one person is speaking). In a multi-source segment, the actual pitch (solid line) and the predicted pitch (dashed line) are far apart, indicating that the inaccurate prediction is due to the presence of multiple sound sources (e.g., multiple people speaking). Furthermore, if the state is between single-source and multi-source, it indicates that there is currently a sound source transition segment, in other words, the speaker in this segment is transitioning from speaker A to speaker B. Moreover, if there are no peaks in a segment, it is a no-sound-source segment, in other words, there are no sound sources in the segment (e.g., no one is speaking). In addition, in a breathy segment, the total number of pitches is zero, indicating that there is only breathy sound.
[0072] It should be noted that this disclosure does not imply... Figures 1 to 9The embodiments shown are limited and are merely illustrative of one implementation of the present disclosure to facilitate understanding of the technology of the present disclosure. The claims of the present disclosure shall be construed as invention claims. Modifications and refinements made by those skilled in the art to the embodiments of the present disclosure without departing from the concept of the present disclosure shall still fall within the scope of invention claims of the present disclosure.
[0073] The technical means embodied in the embodiments of this disclosure can improve at least one of the shortcomings of the prior art. The audio detection method and audio detection device of this disclosure can be applied to various electronic systems. By receiving audio through the electronic system and calculating the audio, the number of users can be determined. This not only avoids the problem of blind spots in image tracking technology, which makes it impossible to effectively monitor users, but also has the advantages of low computational load and simple implementation.
[0074] Although the embodiments of this disclosure are described above, they are not intended to limit this disclosure. Those skilled in the art can make changes to the technical features of this disclosure based on its express or implied content. All such changes may fall within the scope of patent protection sought by this disclosure. In other words, the scope of patent protection of this disclosure shall be determined by the claims of this specification.
Claims
1. An audio detection method, executed by a processor reading at least one instruction stored in a memory, the audio detection method comprising: Perform frame-by-frame processing on an audio file to generate multiple audio frames; The audio is divided into multiple segments based on the multiple signal intensities of the multiple sound frames; Calculate the actual pitches of the multiple pitch frames of a target pitch segment from the multiple pitch segments; Multiple predicted pitches are calculated based on the multiple actual pitches of the target pitch segment; Multiple pitch differences are calculated based on the multiple actual pitches and the multiple predicted pitches of the target pitch segment; A threshold count is calculated based on the multiple pitch differences of the target pitch segment and a pitch threshold. If the count exceeding the threshold is greater than a portion of the total number of pitches of the multiple actual pitches of the target pitch segment, then the target pitch segment is a multiple sound source pitch segment; and If the threshold count is zero, the target audio segment is a single-source audio segment.
2. The audio detection method as described in claim 1, further comprising: If the over-threshold count is between half the total number of pitches in the target segment and zero, the target segment is a source-converted segment.
3. The audio detection method of claim 1, wherein dividing the audio into multiple segments based on the multiple signal intensities of the multiple sound frames comprises: Calculate the multiple signal strengths of the multiple sound frames; Multiple peaks and multiple troughs are obtained based on the multiple signal intensities; and The audio is divided into multiple segments based on the multiple troughs.
4. The audio detection method as described in claim 1, further comprising: If the target sound segment does not contain any peaks, then the target sound segment is a sound segment without a sound source; and If the total number of actual pitches in the target pitch segment is zero, the target pitch segment is a breathy pitch segment.
5. The audio detection method as described in claim 1, further comprising: If the first signal intensity of a first boundary frame of the target sound segment is greater than an intensity threshold or the second signal intensity of a second boundary frame of the target sound segment is greater than the intensity threshold, the target sound segment is one of the plurality of sound source sound segments.
6. An audio detection device, comprising: A memory for storing at least one instruction; A processor for reading the at least one instruction from the memory to perform the following steps: Perform frame-by-frame processing on an audio file to generate multiple audio frames; The audio is divided into multiple segments based on the multiple signal intensities of the multiple sound frames; Calculate the actual pitches of the multiple pitch frames of a target pitch segment from the multiple pitch segments; Multiple predicted pitches are calculated based on the multiple actual pitches of the target pitch segment; Multiple pitch differences are calculated based on the multiple actual pitches and the multiple predicted pitches of the target pitch segment; A threshold count is calculated based on the multiple pitch differences of the target pitch segment and a pitch threshold. If the count exceeding the threshold is greater than a portion of the total number of pitches of the multiple actual pitches of the target pitch segment, then the target pitch segment is a multiple sound source pitch segment; and If the threshold count is zero, the target audio segment is a single-source audio segment.
7. The audio detection apparatus of claim 6, wherein the processor further reads the at least one instruction from the memory to perform the following steps: If the over-threshold count is between half the total number of pitches in the target segment and zero, the target segment is a source-converted segment.
8. The audio detection apparatus of claim 6, wherein the processor further reads the at least one instruction from the memory to perform the following steps: Calculate the multiple signal strengths of the multiple sound frames; Multiple peaks and multiple troughs are obtained based on the multiple signal intensities; and The audio is divided into multiple segments based on the multiple troughs.
9. The audio detection apparatus of claim 6, wherein the processor further reads the at least one instruction from the memory to perform the following steps: If the target sound segment does not contain any peaks, then the target sound segment is a sound segment without a sound source; and If the total number of actual pitches in the target pitch segment is zero, the target pitch segment is a breathy pitch segment.
10. The audio detection apparatus of claim 6, wherein the processor further reads the at least one instruction from the memory to perform the following steps: If the first signal intensity of a first boundary frame of the target sound segment is greater than an intensity threshold or the second signal intensity of a second boundary frame of the target sound segment is greater than the intensity threshold, the target sound segment is one of the plurality of sound source sound segments.