Theater center channel sound reproduction failure detection method, system, terminal and medium

Abstract

The application discloses a cinema center channel sound reproduction fault detection method and system, a terminal and a medium. Audio data of a center channel is obtained frame by frame from a target audio stream, the audio data is input into a room acoustic model to obtain a reference signal, the audio data is played by using the center channel and is recorded to obtain a recording signal, whether the human voice of the reference signal and the recording signal is consistent is compared, a fault counter is used to record the number of frames in which the human voice is inconsistent, and whether the center channel has a sound reproduction fault is determined according to the value of the fault counter. Compared with the prior art, the center channel can be automatically detected, and whether the center channel has a sound reproduction fault can be determined.

Description

Technical Field

[0001] This invention relates to the field of cinema fault detection technology, and in particular to a method, system, terminal and medium for detecting faults in the center channel sound reproduction of a cinema. Background Technology

[0002] Center channel audio playback failure is a common problem in movie theaters. Since dialogue is output from the center channel, a malfunction in the center channel prevents listeners from hearing the dialogue, making the movie unwatchable.

[0003] Current cinema playback systems use an audio mixing and routing module to output audio data from each channel to an amplifier, which then transmits the data to the speakers. This is a one-way audio data transmission. It cannot automatically detect a playback fault in the center channel; a center channel malfunction is only discovered through audience complaints or staff inspections, negatively impacting the customer's viewing experience.

[0004] Therefore, existing technologies need to be improved and enhanced. Summary of the Invention

[0005] The main objective of this invention is to provide a method, system, smart terminal, and storage medium for detecting sound playback faults in the center channel of a cinema, aiming to solve the problem of not being able to automatically detect whether there are sound playback faults in the center channel.

[0006] To achieve the above objectives, a first aspect of the present invention provides a method for detecting sound playback faults in the center channel of a cinema, the method comprising:

[0007] Obtain the center channel audio data of the current frame from the target audio stream;

[0008] The audio data is input into a pre-built room acoustic model for acoustic simulation to obtain a reference signal;

[0009] The audio data is input into the center channel for playback and recording to obtain a recording signal;

[0010] The audio delay value is obtained by comparing the time offset between the reference signal and the recording signal;

[0011] Based on the audio delay value, align the reference signal and the recording signal;

[0012] The reference signal and the recording signal are compared for human voices. When the human voices do not match, the value of the fault counter is incremented.

[0013] Set the next frame of the target audio stream as the current frame, and perform loop detection until the set conditions are met;

[0014] Based on the value of the fault counter, the sound reproduction fault detection result of the center channel is obtained and output.

[0015] Optionally, the step of comparing the reference signal and the recording signal for human voice includes:

[0016] Human voice detection is performed on the reference signal to obtain a first human voice signal;

[0017] When a human voice is present in the reference signal, human voice detection is performed on the recording signal to obtain a second human voice signal, and the first human voice signal and the second human voice signal are compared based on the consistency of human voices.

[0018] Otherwise, the voices are judged to be consistent.

[0019] Optionally, the step of comparing the first voice signal and the second voice signal based on voice consistency includes:

[0020] Based on the waveforms, compare the first voice signal and the second voice signal;

[0021] If the waveforms are the same, the voices are considered to be consistent; otherwise, the voices are considered to be inconsistent.

[0022] Optionally, the step of comparing the first voice signal and the second voice signal based on voice consistency includes:

[0023] Speech recognition is performed on the first human voice signal to obtain the content of the first human voice;

[0024] The second voice signal is subjected to speech recognition to obtain the content of the second voice;

[0025] If the first voice content is the same as the second voice content, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

[0026] A second aspect of the present invention provides a cinema center channel sound playback fault detection system, wherein the system comprises:

[0027] The audio data acquisition module is used to acquire the audio data of the center channel of the current frame from the target audio stream;

[0028] An acoustic simulation module is used to input the audio data into a pre-built room acoustic model to perform acoustic simulation and obtain a reference signal;

[0029] The recording module is used to input the audio data into the center channel for playback and recording to obtain a recording signal;

[0030] An audio delay module is used to compare the time offset between the reference signal and the recording signal to obtain an audio delay value, and to align the reference signal and the recording signal based on the audio delay value;

[0031] The voice comparison module is used to compare the voices of the reference signal and the recording signal. When the voices are inconsistent, the value of the fault counter is incremented.

[0032] The detection result module is used to obtain and output the sound reproduction fault detection result of the center channel based on the value of the fault counter.

[0033] Optionally, the voice comparison module includes a voice detection unit, which is used to perform voice detection on the reference signal to obtain a first voice signal; and to perform voice detection on the recording signal to obtain a second voice signal; the voice comparison module is also used to compare the first voice signal and the second voice signal based on voice consistency.

[0034] Optionally, the voice comparison module further includes a waveform comparison unit, which is used to compare the first voice signal and the second voice signal based on the waveform. When the waveforms are the same, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

[0035] Optionally, the voice comparison module further includes a speech recognition unit, which is used to perform speech recognition on the first voice signal to obtain the first voice content, and to perform speech recognition on the second voice signal to obtain the second voice content. When the first voice content and the second voice content are the same, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

[0036] A third aspect of the present invention provides a smart terminal, the smart terminal including a memory, a processor, and a cinema center channel sound return fault detection program stored in the memory and executable on the processor, wherein the cinema center channel sound return fault detection program, when executed by the processor, implements any one of the steps of the cinema center channel sound return fault detection method.

[0037] A fourth aspect of the present invention provides a computer-readable storage medium storing a cinema center channel sound playback fault detection program, wherein when the cinema center channel sound playback fault detection program is executed by a processor, it implements any of the steps of the above-described cinema center channel sound playback fault detection method.

[0038] As can be seen from the above, this invention acquires the center channel audio data frame by frame from the target audio stream, inputs the audio data into a room acoustic model to obtain a reference signal, plays and records the audio data using the center channel to obtain a recording signal, compares the voice in the reference signal and the recording signal to see if they are consistent, uses a fault counter to record the number of frames with inconsistent voices, and determines whether there is a playback fault in the center channel based on the value of the fault counter. Compared with the prior art, this invention can automatically detect the center channel and determine whether there is a playback fault in the center channel. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic flowchart of the cinema center channel sound reproduction fault detection method provided in an embodiment of the present invention;

[0041] Figure 2 yes Figure 1 Block diagram of cinema center channel sound playback fault detection function in an embodiment;

[0042] Figure 3 yes Figure 1 A detailed flowchart of step S600 in the embodiment;

[0043] Figure 4 This is a schematic diagram of the structure of the cinema center channel sound reproduction fault detection system provided in an embodiment of the present invention;

[0044] Figure 5 This is a block diagram illustrating the internal structure of a smart terminal provided in an embodiment of the present invention. Detailed Implementation

[0045] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0046] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0047] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0048] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0049] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0052] With the development of the film and television industry, watching movies in cinemas has become a trend. Cinemas rely on projection equipment to project films onto a screen. If this equipment malfunctions, it will affect the audience's viewing experience and may even threaten the safety of the cinema environment. Therefore, timely resolution of projection equipment malfunctions is crucial for maintaining the smooth operation of cinemas.

[0053] Current cinema playback systems cannot automatically detect whether the center channel is faulty. A faulty center channel is only discovered when a viewer complains or when staff conduct inspections, which affects the customer's movie-watching experience.

[0054] To address the aforementioned issues, this invention provides a method for detecting sound reproduction faults in the center channel of a cinema. The method involves inputting the audio data of the center channel into a room acoustic model for simulation to obtain a reference signal. The audio data of the center channel is then played and recorded using a center channel speaker to obtain a recorded signal. The presence of a sound reproduction fault in the center channel is determined by comparing the voice in the reference signal with that in the recorded signal.

[0055] Exemplary methods

[0056] This invention provides a method for detecting sound playback faults in the center channel of a cinema. The method is a detection module that runs on the cinema's backend server and is used to automatically detect whether there are sound playback faults in the cinema's center channel.

[0057] Specifically, such as Figure 1 As shown, this embodiment includes the following steps:

[0058] Step S100: Obtain the audio data of the center channel of the current frame from the target audio stream;

[0059] Specifically, the stereo sound systems currently used in cinemas are typically 5.1 channels, including a center channel, front left and right channels, rear left and right surround channels, and a subwoofer channel. The center channel, also known as the main channel, contains human voices and close-up action sounds (including breathing and footsteps). The left and right channels mainly contain background music and ambient sounds from distant scenes. The target audio stream refers to the audio stream used for channel sound reproduction testing, and is a 5.1 channel audio stream. It can be a pre-recorded audio stream or a selected clip from a film, as long as the target audio stream is not purely background music but contains human voices. At the start of the test, the target audio stream is divided into frames according to a preset time length (e.g., 5 seconds), starting from the beginning or a preset position. The length of each frame of the target audio stream is the preset time length. Then, the audio stream of the current frame is read and analyzed to obtain the audio data of the center channel of the current frame. The preset position can be set as needed, such as 5 minutes after the start of the target audio stream, or by analyzing the target audio stream to obtain the start of the sound signal in the center channel as the preset position.

[0060] In some possible implementations, the stereo sound system used in the cinema is 7.1 channel or 15.1 channel, and correspondingly, the target audio stream is also a 7.1 channel audio stream or a 15.1 channel audio stream; if the target audio stream is still a 5.1 channel audio stream, it can be converted into a 7.1 channel audio stream or a 15.1 channel audio stream through a channel mapping table, and then used for sound fault detection of the center channel.

[0061] like Figure 2 As shown, in this embodiment, the target audio stream originates from a digital cinema media server. The audio streams for each channel are input to the audio mixing and routing module. Then, after equalization and delay processing by the equalization and delay module, the audio data for each channel is input to the power amplifier and transmitted to the speakers. Therefore, the audio data for the center channel can be obtained from the audio mixing and routing module.

[0062] Step S200: Input the audio data into the pre-built room acoustic model to perform acoustic simulation and obtain a reference signal;

[0063] Specifically, based on the structure of the cinema's playback space, room acoustic environment modeling is used to obtain a room acoustic model containing one sound source and one receiver. The room acoustic model models the propagation process of sound signals according to the structure of the acoustic environment, accurately simulating the room's impulse response.

[0064] After the room acoustic model is established, the audio data of the center channel is input, and the audio data is simulated to be played in the cinema using the center speaker. The sound signal at the set position in the cinema is obtained according to the room acoustic model and used as a reference signal to compare with the sound signal collected on site in the cinema.

[0065] Constructing a room acoustic model based on acoustic parameters and obtaining sound signals at a set location is a conventional technique in this field, and will not be elaborated upon here.

[0066] Step S300: Input the audio data into the center channel for playback and recording to obtain a recording signal;

[0067] Specifically, the audio data of the center channel is transmitted to the center channel speaker, and the audio data is played in the cinema through the center channel speaker. At the same time, a microphone is used to collect sound signals at a set position in the cinema room to obtain a recording signal.

[0068] Since the sound signals emitted by other speakers can interfere with the sound signal emitted by the center channel when multiple speakers are emitting sound at the same time, it is preferable to let the center channel output the sound signal separately during non-screening times.

[0069] If the center channel audio signal is recorded during the screening period to determine in real time whether a malfunction has occurred in the center channel, a microphone can be installed slightly to the left or right of the cinema's center axis. Based on the energy and time differences of the audio signals collected by the microphone, the audio signals from other channels can be filtered to obtain the center channel audio signal.

[0070] Step S400: Compare the time offset between the reference signal and the recording signal to obtain the audio delay value;

[0071] Specifically, there will be a time delay between the reference signal obtained from the room acoustic model and the recording signal obtained from the cinema recording. When the two sound signals are out of sync, a time offset will occur. By analyzing and comparing the waveforms of the reference signal and the recording signal, the time offset between the reference signal and the recording signal can be obtained, that is, the audio delay value.

[0072] In some examples, the reference signal and the recording signal are transformed using FFT (Fast Fourier Transform) to obtain the corresponding phase spectrum and amplitude spectrum, and the difference between the phase spectra is compared to determine the audio delay value.

[0073] Step S500: Align the reference signal and the recording signal based on the audio delay value;

[0074] Specifically, given a time offset between the reference signal and the recording signal, it is necessary to first correct the phase of the reference signal or the recording signal based on the obtained audio delay value to achieve alignment between the two signals. The technique of correcting audio signals based on audio delay is widely used in remote conferencing and cinema projection, and is a standard technique in this field, so it will not be elaborated upon here.

[0075] Step S600: Compare the reference signal and the recording signal for human voice; if the human voices do not match, increment the value of the fault counter.

[0076] Specifically, the center channel is mainly used to play dialogue in an audio stream. Therefore, by comparing whether the voices are consistent, it can be determined whether the center channel can reproduce sound correctly. Whether the voices are consistent can be measured by whether the voices are synchronized and whether the voices are the same, such as whether the sound wave waveforms displayed at different times are the same and whether the content of the dialogue is the same.

[0077] The system acquires human voice data from both the reference signal and the recorded signal. If the two voice segments match, the system determines that the sound reproduction in the current frame is normal. If the voice segments do not match, the system determines that the sound reproduction in the current frame is faulty.

[0078] Considering the many reasons that can cause a center channel malfunction, such as problems with the digital signal input cable connection, issues with the IMB board, problems with the DA converter, or a faulty tweeter, it's crucial not to judge whether the center channel is functioning correctly solely based on whether there is sound, nor to determine a center channel playback malfunction based on a single frame of audio playback failure. For example, poor contact could cause discontinuous or intermittent sound; low-frequency or high-frequency sounds might not be reproduced correctly; resulting in no sound or muffled sound from the center channel, making dialogue difficult to understand.

[0079] Therefore, this embodiment does not determine that the center channel is faulty simply because it malfunctions in a single frame. Instead, it sets a fault counter. A fault in the center channel in a single frame only indicates a possible fault, and the fault counter is incremented. Only when the fault counter reaches a set threshold is a fault determined to be in the center channel. By setting a fault counter, smoothing processing can also be performed to prevent false alarms caused by system jitter.

[0080] Step S700: Set the next frame of the target audio stream as the current frame and perform loop detection until the set conditions are met;

[0081] Specifically, after the current frame is detected, the next frame of the target audio stream is obtained and set as the current frame. The process returns to step S100 to perform loop detection until a set condition is met, at which point the loop detection ends. The set condition is not limited and can be one or more of the following: all frames of the target audio stream have been detected, the fault counter value has reached a set threshold, a set number of frames have been detected, etc.

[0082] Step S800: Based on the value of the fault counter, obtain and output the sound reproduction fault detection result of the center channel.

[0083] Specifically, after the test is completed, if the value of the fault counter is greater than or equal to the set threshold, the center channel is determined to have a sound fault; otherwise, the center channel is determined to have a normal sound.

[0084] In one example, when a center channel playback malfunction is detected, an alarm signal is sent to the monitoring system to notify relevant personnel to handle the situation promptly. The center channel signal can be mixed into the left and right channel signals, or the left, center, and right channels can be mixed and output.

[0085] As described above, by acquiring the center channel audio data frame by frame from the target audio stream, inputting the audio data into a room acoustic model to obtain a reference signal, playing and recording the audio data using the center channel to obtain a recording signal, comparing the voice in the reference signal and the recording signal to see if they are consistent, using a fault counter to record the number of frames with inconsistent voices, and determining whether there is a playback fault in the center channel based on the value of the fault counter. This automatically determines whether a playback fault occurs in the center channel.

[0086] like Figure 3 As shown, in some embodiments, the human voice comparison between the reference signal and the recording signal in step S600 above includes the following steps:

[0087] Step S610: Perform human voice detection on the reference signal to obtain the first human voice signal;

[0088] Specifically, power spectrum feature extraction can be performed on the reference signal to identify human voice, or a neural network model can be used for human voice recognition to obtain the first human voice signal.

[0089] In one example, a neural network model is first trained using the AudioSet audio dataset to obtain a human voice recognition model. Then, a reference signal is input into the human voice recognition model. If the probability of the human voice recognition model determining that the human voice signal exceeds a preset threshold, then the reference signal is the first human voice signal.

[0090] In another example, a Fourier transform is first performed on the reference signal, transforming it from the time domain to the frequency domain to obtain the spectrum relative to the time domain. The power spectrum of the reference signal is then obtained based on this spectrum. Next, the power spectrum is divided into frequency bands in the frequency domain according to the Mel scale, resulting in m sub-power spectra. For each sub-power spectrum, K harmonic components of different orders are extracted. The features of each sub-power spectrum and the features of the K harmonic components of different orders are extracted and concatenated to obtain the spectrum enhancement features. The probability that the reference signal contains human voice is obtained based on the spectrum enhancement features. When the probability exceeds a preset threshold, the reference signal is considered to be the first human voice signal.

[0091] Step S620: When there is human voice in the reference signal, human voice detection is performed on the recording signal to obtain the second human voice signal, and the first human voice signal and the second human voice signal are compared based on the consistency of human voice.

[0092] Specifically, the reference signal may or may not contain human voice signals.

[0093] When no human voice is detected in the reference signal, it means that there is no dialogue in the target audio stream. There is no need for comparison. The next frame of the target audio stream can be directly obtained as the current frame, and the audio data can be re-acquired for detection.

[0094] When a human voice is detected in the reference signal, the recording signal is also subjected to human voice detection using the same method as in step S610 to obtain a second human voice signal. The recording signal may or may not contain a human voice signal.

[0095] If no human voice is detected in the recording signal, a hardware failure may occur, indicating a fault in the center channel of the current frame.

[0096] When a human voice is detected in the recorded signal, if the center channel can reproduce the sound normally, the first human voice signal obtained from the reference signal should be consistent with the second human voice signal obtained from the recorded signal. The consistency of the human voice signals can be compared from multiple perspectives, such as judging whether the waveforms of the human voice signals are consistent, and extracting the human voice content from the human voice signal to judge whether the content is consistent. When the first and second human voice signals are consistent, it can be determined that the center channel in the current frame is normal. Otherwise, it can be determined that there is a fault in the center channel in the current frame.

[0097] In one example, a fast Fourier transform is used to obtain multiple frequency points of the first and second voice signals. Then, the amplitude and time values ​​of each frequency point are compared to determine whether the two voice signals are consistent.

[0098] In another example, the first and second voice signals are input into the speech recognition module respectively, the corresponding text content is extracted, and the consistency of the text content is compared to determine whether the two voice signals are consistent.

[0099] As described above, by comparing the reference signal and the recording signal with human voice, the judgment of the center channel playback fault is more accurate, and it can detect playback faults such as muffled, unclear, or unclear sound in the center channel.

[0100] Exemplary System

[0101] like Figure 4 As shown, corresponding to the above-described cinema center channel sound reproduction fault detection method, this embodiment of the invention also provides a cinema center channel sound reproduction fault detection system, the system comprising:

[0102] The audio data acquisition module 600 is used to acquire the audio data of the center channel of the current frame from the target audio stream;

[0103] Acoustic simulation module 610 is used to input the audio data into a pre-constructed room acoustic model to perform acoustic simulation and obtain a reference signal;

[0104] Recording module 620 is used to input the audio data into the center channel for playback and recording to obtain a recording signal;

[0105] The audio delay module 630 is used to compare the time offset between the reference signal and the recording signal to obtain an audio delay value, and to align the reference signal and the recording signal based on the audio delay value;

[0106] The voice comparison module 640 is used to compare the voices of the reference signal and the recording signal, and increment the value of the fault counter when the voices are inconsistent.

[0107] The detection result module 650 is used to obtain and output the sound reproduction fault detection result of the center channel based on the value of the fault counter.

[0108] Optionally, the voice comparison module 640 includes a voice detection unit, which is used to perform voice detection on the reference signal to obtain a first voice signal; and to perform voice detection on the recording signal to obtain a second voice signal; the voice comparison module 640 is also used to compare the first voice signal and the second voice signal based on voice consistency.

[0109] Optionally, the voice comparison module 640 further includes a waveform comparison unit, which is used to compare the first voice signal and the second voice signal based on the waveform. When the waveforms are the same, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

[0110] Optionally, the voice comparison module 640 further includes a speech recognition unit, which is used to perform speech recognition on the first voice signal to obtain the first voice content, and to perform speech recognition on the second voice signal to obtain the second voice content. When the first voice content and the second voice content are the same, it is determined that the voices are consistent; otherwise, it is determined that the voices are inconsistent.

[0111] Specifically, in this embodiment, the specific functions of each module of the above-mentioned cinema center channel sound playback fault detection system can be referred to the corresponding description in the above-mentioned cinema center channel sound playback fault detection method, and will not be repeated here.

[0112] Based on the above embodiments, the present invention also provides a smart terminal, the principle block diagram of which can be as follows: Figure 5 As shown. The aforementioned smart terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a cinema center channel sound fault detection program. The internal memory provides an environment for the operation of the operating system and the cinema center channel sound fault detection program stored in the non-volatile storage medium. The network interface of the smart terminal is used for communication with external terminals via a network connection. When the cinema center channel sound fault detection program is executed by the processor, it implements the steps of any of the aforementioned cinema center channel sound fault detection methods. The display screen of the smart terminal can be a liquid crystal display (LCD) or an e-ink display.

[0113] Those skilled in the art will understand that Figure 5 The block diagram shown is merely a partial structural diagram related to the present invention and does not constitute a limitation on the smart terminal to which the present invention is applied. A specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In one embodiment, a smart terminal is provided, the smart terminal including a memory, a processor, and a cinema center channel sound playback fault detection program stored in the memory and executable on the processor, wherein the cinema center channel sound playback fault detection program performs the following operation instructions when executed by the processor:

[0115] Obtain the center channel audio data of the current frame from the target audio stream;

[0116] The audio data is input into a pre-built room acoustic model for acoustic simulation to obtain a reference signal;

[0117] The audio data is input into the center channel for playback and recording to obtain a recording signal;

[0118] The audio delay value is obtained by comparing the time offset between the reference signal and the recording signal;

[0119] Based on the audio delay value, align the reference signal and the recording signal;

[0120] The reference signal and the recording signal are compared for human voices. When the human voices do not match, the value of the fault counter is incremented.

[0121] Set the next frame of the target audio stream as the current frame, and perform loop detection until the set conditions are met;

[0122] Based on the value of the fault counter, the sound reproduction fault detection result of the center channel is obtained and output.

[0123] Optionally, the step of comparing the reference signal and the recording signal for human voice includes:

[0124] Human voice detection is performed on the reference signal to obtain a first human voice signal;

[0125] When a human voice is present in the reference signal, human voice detection is performed on the recording signal to obtain a second human voice signal, and the first human voice signal and the second human voice signal are compared based on the consistency of human voices.

[0126] Otherwise, the voices are judged to be consistent.

[0127] Optionally, the step of comparing the first voice signal and the second voice signal based on voice consistency includes:

[0128] Based on the waveforms, compare the first voice signal and the second voice signal;

[0129] If the waveforms are the same, the voices are considered to be consistent; otherwise, the voices are considered to be inconsistent.

[0130] Optionally, the step of comparing the first voice signal and the second voice signal based on voice consistency includes:

[0131] Speech recognition is performed on the first human voice signal to obtain the content of the first human voice;

[0132] The second voice signal is subjected to speech recognition to obtain the content of the second voice;

[0133] If the first voice content is the same as the second voice content, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

[0134] This invention also provides a computer-readable storage medium storing a cinema center channel sound playback fault detection program. When the cinema center channel sound playback fault detection program is executed by a processor, it implements the steps of any of the cinema center channel sound playback fault detection methods provided in this invention.

[0135] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0136] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this invention. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0137] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0138] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0139] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of the above modules or units is merely a logical functional division, and in actual implementation, it can be divided in other ways. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0140] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0141] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not mean that the essence of the corresponding technical solutions deviates from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for detecting sound playback faults in the center channel of a cinema, characterized in that, Obtain the center channel audio data of the current frame from the target audio stream; The audio data is input into a pre-built room acoustic model for acoustic simulation to obtain a reference signal; The audio data is input into the center channel for playback and recording to obtain a recording signal; The audio delay value is obtained by comparing the time offset between the reference signal and the recording signal; Based on the audio delay value, align the reference signal and the recording signal; The reference signal and the recording signal are compared for human voices. When the human voices do not match, the value of the fault counter is incremented. Set the next frame of the target audio stream as the current frame, and perform loop detection until the set conditions are met; Based on the value of the fault counter, the sound reproduction fault detection result of the center channel is obtained and output; the comparison of the reference signal and the recording signal for human voice includes: Human voice detection is performed on the reference signal to obtain a first human voice signal; when human voice is present in the reference signal, human voice detection is performed on the recording signal to obtain a second human voice signal; the first human voice signal and the second human voice signal are compared based on human voice consistency. The steps for detecting human voice in the reference signal to obtain a first human voice signal include: firstly, performing a Fourier transform on the reference signal from the time domain to the frequency domain to obtain a spectrum relative to the time domain, and obtaining the power spectrum of the reference signal based on the spectrum; then, dividing the power spectrum into frequency bands in the frequency domain according to the Mel scale to obtain m sub-power spectra; extracting K harmonic components of different orders from the sub-power spectrum of each frequency band; extracting the features of the sub-power spectrum of each frequency band and the features of the K harmonic components of different orders; concatenating these features to obtain spectrum enhancement features; obtaining the probability that the reference signal contains human voice based on the spectrum enhancement features; and when the probability exceeds a preset threshold, the reference signal is the first human voice signal.

2. The cinema center channel sound reproduction fault detection method as described in claim 1, characterized in that, The comparison of the first voice signal and the second voice signal based on voice consistency includes: Based on the waveforms, compare the first voice signal and the second voice signal; If the waveforms are the same, the voices are considered to be consistent; otherwise, the voices are considered to be inconsistent.

3. The cinema center channel sound reproduction fault detection method as described in claim 1, characterized in that, The comparison of the first voice signal and the second voice signal based on voice consistency includes: Speech recognition is performed on the first human voice signal to obtain the content of the first human voice; The second voice signal is subjected to speech recognition to obtain the content of the second voice; If the first voice content is the same as the second voice content, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

4. A cinema center channel sound reproduction fault detection system, characterized in that, The system includes: The audio data acquisition module is used to acquire the audio data of the center channel of the current frame from the target audio stream; An acoustic simulation module is used to input the audio data into a pre-built room acoustic model to perform acoustic simulation and obtain a reference signal; The recording module is used to input the audio data into the center channel for playback and recording to obtain a recording signal; An audio delay module is used to compare the time offset between the reference signal and the recording signal to obtain an audio delay value, and to align the reference signal and the recording signal based on the audio delay value; The voice comparison module is used to compare the voices of the reference signal and the recording signal. When the voices are inconsistent, the value of the fault counter is incremented. The detection result module is used to obtain and output the sound reproduction fault detection result of the center channel based on the value of the fault counter. The voice comparison module includes a voice detection unit, which is used to perform voice detection on the reference signal to obtain a first voice signal; when there is a voice in the reference signal, it performs voice detection on the recording signal to obtain a second voice signal; the voice comparison module is also used to compare the first voice signal and the second voice signal based on voice consistency. The voice detection unit is further configured to first perform a Fourier transform on the reference signal, transforming it from the time domain to the frequency domain, to obtain the spectrum relative to the time domain, and obtain the power spectrum of the reference signal based on the spectrum; then, according to the Mel scale, divide the power spectrum into frequency bands in the frequency domain to obtain m sub-power spectra; for each sub-power spectrum of the frequency band, extract K harmonic components of different orders; extract the features of the sub-power spectrum of each frequency band and the features of the K harmonic components of different orders; splice them together to obtain spectrum enhancement features; obtain the probability that the reference signal contains a human voice based on the spectrum enhancement features; when the probability exceeds a preset threshold, the reference signal is the first human voice signal.

5. The cinema center channel sound reproduction fault detection system as described in claim 4, characterized in that, The voice comparison module further includes a waveform comparison unit, which is used to compare the first voice signal and the second voice signal based on the waveform. When the waveforms are the same, the voices are determined to be consistent; otherwise, the voices are determined to be inconsistent.

6. The cinema center channel sound reproduction fault detection system as described in claim 4, characterized in that, The voice comparison module further includes a speech recognition unit, which is used to perform speech recognition on the first voice signal to obtain the first voice content, and to perform speech recognition on the second voice signal to obtain the second voice content. When the first voice content and the second voice content are the same, it is determined that the voices are consistent; otherwise, it is determined that the voices are inconsistent.

7. A smart terminal, characterized in that, The smart terminal includes a memory, a processor, and a cinema center channel sound playback fault detection program stored in the memory and executable on the processor. When the cinema center channel sound playback fault detection program is executed by the processor, it implements the steps of the cinema center channel sound playback fault detection method as described in any one of claims 1-3.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a cinema center channel sound reproduction fault detection program, which, when executed by a processor, implements the steps of the cinema center channel sound reproduction fault detection method as described in any one of claims 1-3.

Images