CN113096694B - Electronic terminal and play quality detection method thereof - Google Patents
Electronic terminal and play quality detection method thereof Download PDFInfo
- Publication number
- CN113096694B CN113096694B CN201911337164.2A CN201911337164A CN113096694B CN 113096694 B CN113096694 B CN 113096694B CN 201911337164 A CN201911337164 A CN 201911337164A CN 113096694 B CN113096694 B CN 113096694B
- Authority
- CN
- China
- Prior art keywords
- audio
- recording
- value
- parameter
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/18—Error detection or correction; Testing, e.g. of drop-outs
- G11B20/1816—Testing
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Signal Processing For Digital Recording And Reproducing (AREA)
Abstract
The invention relates to the technical field of equipment, and provides a play quality detection method of an electronic terminal and the electronic terminal, so as to solve the problem of inaccurate detection result. The method comprises the following steps: receiving a playing instruction; responding to a playing instruction, playing a test audio, and recording, wherein the test audio comprises N test sub-audios; stopping recording after the test audio is played, and acquiring a recording audio obtained by recording; splitting the recording audio to obtain N recording sub-audios; determining a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, each play quality parameter being associated with a corresponding test sub-audio and/or recording sub-audio; and determining a play quality detection result according to the value of at least one play quality parameter. Namely, each playing quality parameter is determined according to the associated testing sub-audio and/or recording sub-audio, namely, the targeted determination can be realized on different playing quality parameters, and the accuracy of the detection result can be improved.
Description
Technical Field
The present invention relates to the field of device technologies, and in particular, to a play quality detection method for an electronic terminal and an electronic terminal.
Background
Along with the continuous development of intelligent technology, various intelligent products come into operation, and the functions of the intelligent products are more and more powerful, so that great convenience is brought to the life and work of users. For example, an electronic terminal capable of playing audio can provide the user with the playing of audio, and the playing quality of the electronic terminal directly affects the user experience, so that the playing quality of the electronic terminal is particularly important.
In order to ensure the playing quality, the playing quality of the electronic terminal can be detected, and a manufacturer can improve the electronic terminal according to the detection result. Different index parameters can be used for evaluating the playing effect of the electronic terminal in different aspects, however, in the detection process, the different index parameters cannot be determined in a targeted manner, and the detection result is easy to be inaccurate.
Disclosure of Invention
The embodiment of the invention provides a play quality detection method of an electronic terminal and the electronic terminal, which aim to solve the problem that a play quality detection mode of the existing electronic terminal is inaccurate in detection result.
In order to solve the technical problem, the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a method for detecting a playing quality of an electronic terminal, where the method includes:
receiving a playing instruction;
responding to the playing instruction, playing a test audio and recording, wherein the test audio comprises N test sub-audios, and N is an integer greater than 1;
stopping recording after the test audio is played, and acquiring recorded audio obtained by recording;
splitting the recording audio to obtain N recording sub-audios;
determining a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, wherein each play quality parameter is associated with a corresponding test sub-audio and/or recording sub-audio;
and determining a play quality detection result according to the value of the at least one play quality parameter.
In a second aspect, an embodiment of the present invention further provides an electronic terminal, including:
the instruction receiving module is used for receiving a playing instruction;
the control module is used for responding to the playing instruction, playing test audio and recording, wherein the test audio comprises N test sub-audio, and N is an integer greater than 1;
the recording audio acquisition module is used for stopping recording after the test audio playing is finished and acquiring recording audio obtained by recording;
the splitting module is used for splitting the recording audio to obtain N recording sub-audio;
a parameter determination module, configured to determine a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, where each play quality parameter is associated with a corresponding test sub-audio and/or recording sub-audio;
and the detection result determining module is used for determining the playing quality detection result according to the value of the at least one playing quality parameter.
In a third aspect, an embodiment of the present invention further provides an electronic terminal, including: the invention further provides a method for detecting the play quality of the electronic terminal, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the method for detecting the play quality of the electronic terminal.
In a fourth aspect, an embodiment of the present invention further provides a readable storage medium, where a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps in the method for detecting the playing quality of an electronic terminal are implemented as described above.
In the embodiment of the invention, a playing instruction is received; responding to the playing instruction, playing a test audio and recording, wherein the test audio comprises N test sub-audios, and N is an integer greater than 1; stopping recording after the test audio is played, and acquiring recorded audio obtained by recording; splitting the recording audio to obtain N recording sub-audios; determining a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, wherein each play quality parameter is associated with a corresponding test sub-audio and/or recording sub-audio; and determining a play quality detection result according to the value of the at least one play quality parameter. That is, in this embodiment, in the process of determining the playing quality parameters, the N test sub-audios and the N recording sub-audios are adopted, and each playing quality parameter is determined according to its associated test sub-audio and/or recording sub-audio, and for different playing quality parameters, it may be determined according to its associated test sub-audio and/or recording sub-audio, that is, it may achieve targeted determination for different playing quality parameters, which is beneficial to improve the accuracy of the values of the playing quality parameters, thereby improving the accuracy of the detection results.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor.
Fig. 1 is a flowchart of a method for detecting a playing quality of an electronic terminal according to an embodiment of the present invention;
fig. 2 is a test audio diagram in the method for detecting the playing quality of the electronic terminal according to the embodiment of the present invention;
FIG. 3 is a graph of test results of return loss gain parameters for an embodiment of the present invention;
FIG. 4 is one of the graphs of the results of the tests for coherency parameters according to an embodiment of the present invention;
FIG. 5 is one of a chart of the results of a coherency test for coherency parameters according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating the results of a delay parameter test according to an embodiment of the present invention;
FIG. 7 is a graph of the test results of the background noise size parameter of an embodiment of the present invention;
FIG. 8 is a graph of the results of a test for sensitivity parameters according to an embodiment of the present invention;
FIG. 9 is a graph of test results for signal-to-noise ratio parameters for an embodiment of the present invention;
fig. 10 is a schematic block diagram of an electronic terminal according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a play quality detection method of an electronic terminal according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step 101: and receiving a playing instruction.
In the process of detecting the playing quality, the electronic terminal needs to play audio, the playing instruction is information which can trigger the electronic terminal to play audio, and the electronic terminal plays audio when receiving the playing instruction. In one example, the electronic terminal is connected to a control terminal (e.g., a computer) through a USB (Universal Serial Bus) interface, an adb (Android Debug Bridge) Command may be input in a cmd (Command Prompt) window of the control terminal, the control terminal may generate a play Command based on the adb Command, the play Command is used to trigger the electronic terminal to play audio and is transmitted to the electronic terminal, and the electronic terminal may play a test audio after receiving the play Command sent by the control terminal.
Step 102: and responding to the playing instruction, playing the test audio and recording, wherein the test audio comprises N test sub-audios.
N is an integer greater than 1. After receiving the playing instruction, the electronic terminal can respond to the playing instruction to play the test audio, and the test audio is led into the electronic terminal in advance, namely the electronic terminal stores the test audio in advance, and after receiving the playing instruction, the electronic terminal calls the test audio to play. In addition, a playing instruction is received, and recording is needed in response to the playing instruction so as to ensure that the played test audio can be completely recorded. In this embodiment, the test audio for play instruction detection includes N different test sub-audios.
Step 103: and after the test audio is played, stopping recording, and acquiring the recorded audio obtained by recording.
The test audio has corresponding duration, recording can be stopped after the test audio is played, and at the moment, the recorded audio obtained by recording can be obtained. In one example, since there is a distance between the playing unit playing the test audio and the recording unit recording the sound, and there is a time difference between the recording and the playing, the time difference is related to the distance, the recording may be stopped at a target time point spaced from the playing end time point by a preset time length after the playing of the test audio is ended, so as to ensure that the test audio can be completely recorded, wherein the preset time length is greater than or equal to a result of dividing a distance between the playing unit playing the test audio and the recording unit recording the sound by a sound propagation speed (340 m/s).
Step 104: and splitting the recording audio to obtain N recording sub-audio.
After the recording audio is obtained, the recording audio can be split, the split recording sub-audio corresponds to the test sub-audio one by one, namely each test sub-audio has a corresponding recording sub-audio in the recording audio.
Step 105: determining a value of at least one play quality parameter based on the N test sub-audios and the N recorded sub-audios.
After the N recording sub-audios are obtained, a value of at least one play quality parameter is determined based on the N test sub-audios and the N recording sub-audios, and the play quality parameter is a parameter for evaluating play quality. It can be understood that each playing quality parameter is determined by the corresponding testing sub-audio and/or recording sub-audio, for example, the testing sub-audio C1 in the N testing sub-audios and the recording sub-audio L1 in the N recording sub-audios are audio associated with the playing quality parameter B1, and the playing right amount parameter B1 is determined by the testing sub-audio C1 and the recording sub-audio L1. Namely, each playing quality parameter is determined based on the corresponding testing sub-audio and recording sub-audio, namely, the value of the playing quality parameter can be determined in a targeted manner, so that the accuracy of the playing quality parameter is improved.
Step 106: and determining a play quality detection result according to the value of at least one play quality parameter.
After the value of the at least one play quality parameter is obtained, a play quality detection result can be determined according to the value of the at least one play quality parameter. In one example, the detection result of the playing quality includes a qualified detection or an unqualified detection, and it can be understood that if the value of at least one playing quality parameter satisfies the corresponding preset requirement, the detection result of the playing quality may be determined as qualified, otherwise, the detection result of the playing quality may be determined as unqualified. And an improvement scheme of the electronic terminal can be formulated subsequently according to the quality detection result so as to perfect the electronic terminal.
In the embodiment of the present invention, the method for detecting the playing quality of the electronic terminal may be applied to an electronic terminal, for example: a speaker, a Mobile phone, a Tablet Personal Computer (Tablet Personal Computer), a Laptop Computer (Laptop Computer), a Personal Digital Assistant (PDA), a Mobile Internet Device (MID), a Wearable Device (Wearable Device), or the like.
In this embodiment, in the process of determining the playing quality parameters, the N test sub-audios and the N recording sub-audios are adopted, and each playing quality parameter is determined according to its associated test sub-audio and/or recording sub-audio, and for different playing quality parameters, it may be determined according to its associated test sub-audio and/or recording sub-audio, that is, it may achieve targeted determination for different playing quality parameters, which is beneficial to improve the accuracy of the values of the playing quality parameters, thereby improving the accuracy of the detection results.
In one embodiment, the at least one playback quality parameter includes at least one of: return loss gain parameters, time delay parameters, coherence parameters, background noise size parameters, sensitivity parameters and signal-to-noise ratio.
The electronic device records the test audio (e.g., audio collected by a recording unit (e.g., a microphone) in the electronic terminal) while playing the test audio, and then subtracts the test audio from the recorded audio, thereby implementing echo cancellation. The callback loss gain parameter is used for evaluating the echo cancellation effect of the electronic equipment. In the recording process, besides the recording of the test audio, the external audio can also be recorded. For example, in the process of playing the test audio, the user may perform voice control on the electronic terminal, for example, the user may send out a voice by controlling the volume by the voice, e.g., the voice with the volume increased, and the voice sent by the user may also be recorded by the electronic terminal, so that the obtained recording audio includes a recording corresponding to the voice sent by the user and a recording corresponding to the test audio, at this time, the electronic terminal needs to perform echo cancellation to extract the voice sent by the user, and then perform a control operation corresponding to the voice, i.e., subtracting the test audio from the recording audio, and if the recording corresponding to the test audio in the recording audio is closer to the test audio, the result obtained by the echo cancellation is closer to the voice sent by the user, and the more accurate voice control is performed. In one example, the callback loss gain parameter is a ratio of energy of the recorded audio to energy of the remaining audio (the recorded audio minus the test audio), and the larger the ratio is, the closer the recording in the recorded audio corresponding to the test audio is to the test audio, which means that the smaller the energy of the remaining audio is, the better the echo cancellation effect is.
The first audio in the test audio is transmitted to the playing unit for playing, and the time when the first audio is transmitted to the playing unit (which may be understood as the time when the test audio is transmitted to the playing unit) may be recorded, and in addition, the transmission time (which may be immediately the time when the transmission is started) of the first audio may also be recorded, because there is a certain distance in the channel through which the test audio is transmitted to the playing unit, if the transmission is normal in the channel, the starting time (the first audio is played and transmitted to the recording unit, and the recording unit performs recording, there is a time difference in this process, but the time difference is related to the distance between the playing unit and the recording unit, the distance is fixed, and the time difference is determined) and the transmission time (corresponding to the delay parameter) can be maintained at a substantially stable value, and if the delay parameter in the channel cannot be maintained at a stable value, it indicates that the playing delay (the time difference between the playing time and the transmission time) in the electronic terminal is unstable. Therefore, in the embodiment, the delay parameter is used as a parameter for evaluating the playing quality, and the delay condition of the electronic terminal can be accurately detected.
The coherence parameter (i.e. coherence coefficient) can be used to evaluate the similarity between the audios, and the larger the value is, the more similar the representation is, and the less noise the electronic terminal has in the recording process. Specifically, fourier transform may be performed on the recording sub-audio and the test sub-audio associated with the coherence parameter, respectively, to obtain a recording sub-frequency domain signal corresponding to the recording sub-audio and a test sub-frequency domain signal corresponding to the test sub-audio, abscissa of a curve corresponding to the recording sub-frequency domain signal and the test sub-frequency domain signal are both frequencies, and ordinate of a curve corresponding to the recording sub-frequency domain signal and the test sub-frequency domain signal are both frequency responses, and then normalization processing may be performed on the recording sub-frequency domain signal and the test sub-frequency domain signal, for example, both are divided by a preset normalization value (for example, may be 100). And then, the ratio between the normalized recording sub-frequency domain signal and the normalized test sub-frequency domain signal is used as a coherence parameter, which can be understood as a ratio curve between the normalized recording sub-frequency domain signal and the test sub-frequency domain signal, that is, the coherence parameter can be understood as a coherence curve, which is the ratio curve.
In addition, under the condition that the recording unit can record at least two paths of recording audio (each path is the audio obtained by recording when the test audio is played), the number of the values of each playing quality parameter is increased, so that under the condition that at least two values (the number of the values is the same as the number of the paths of the recording audio) of the coherence parameters are obtained, the condition that at least two coherence curves exist can be understood, and the consistency of the coherence parameters can also be tested, namely, the difference value of the maximum value minus the minimum value corresponding to the abscissa point of the same frequency in the at least two coherence curves is used as the consistency value corresponding to the abscissa point, and the smaller the consistency value of the abscissa point is, the better the consistency of the coherence parameters of the abscissa point is represented. In this way, the above difference calculation is performed for each abscissa point of the frequency, and a consistency curve representing the consistency of the plurality of coherence parameters is obtained, where the abscissa is the frequency and the ordinate is the frequency response difference. In this embodiment, a sub-curve with a frequency of 100 to 1000HZ in the consistency curve may be intercepted for evaluating the consistency of the coherence parameters, for example, if the frequency difference values in the sub-curve are all less than 0.1, it is determined that the consistency of the coherence parameters meets the requirement, and it may be determined that the consistency is qualified.
The background noise is also called background noise, and can be understood as total noise in the electronic terminal except for useful signals. The background noise size parameter is used for representing the size of the background noise, and the size of the background noise is determined by the energy of the background noise, for example, the larger the value is, the larger the noise of the electronic terminal is, the larger the value is, the more logarithm of the energy of the background noise is taken to be 10, and then the value is multiplied by 20 to be determined as the size of the background noise.
The sensitivity parameter represents the sensitivity degree of the test audio, and can be determined by the energy of the audio corresponding to the removal of the background noise in the recorded audio, and the larger the value is, the better the sensitivity of the electronic terminal to the test audio is.
The signal-to-noise ratio can be determined by the sensitivity parameter and the noise floor magnitude parameter, for example, the noise floor magnitude parameter is subtracted from the sensitivity parameter, and the signal-to-noise ratio is a value of the sensitivity parameter and a value of the noise floor magnitude parameter, and a larger value indicates more useful signals.
In one embodiment, the N test sub-audios include a start cue audio sequentially increasing in time order and at least one of: the audio comprises mute audio, sine wave audio, M first audios, synthesized voice audio, music audio, white noise audio and M second audios, wherein M is an integer larger than zero;
splitting the recording audio to obtain N recording sub-audios, including:
determining a reference starting point of the recording audio, wherein the reference starting point is a starting point of the reference recording audio in the recording audio, and the reference recording audio is matched with a starting prompt audio in the test audio;
splitting the recording audio based on a reference starting point to obtain N recording sub-audios, wherein the N recording sub-audios comprise a starting prompt recording audio with sequentially increasing time sequence and at least one of the following: the audio recording device comprises mute recording audio (audio obtained by playing the mute audio for recording), sine wave recording audio, M first recording audio, synthesized voice recording audio, music recording audio, white noise recording audio and M second recording audio.
Because the recording and the playing are started simultaneously, the time is required for transmitting the played audio to the recording unit, and the initial stage of the recorded audio is not the audio of the initial stage of the tested audio, so that the part needs to be removed, and the audio behind the reference initial point corresponding to the initial point of the tested audio in the recorded audio is only effective. In this implementation, in the splitting process of the recording audio, a reference starting point of the recording audio needs to be determined, for example, the recording audio and the initial prompt audio are matched, a reference recording audio matched with the initial prompt audio is determined in the recording audio (feature matching may be performed, and the reference recording audio is determined), which may be understood as the above-mentioned real prompt recording audio, then a starting time point of the reference recording audio, that is, the starting point, is taken as the reference starting point, since the relative position between each test sub-audio in the test audio and the duration of each test sub-audio are determined, the relative position between each recording sub-audio in the recording audio and the duration of each recording sub-audio are determined, the relative position between the recording sub-audio is the same as the relative position between the test sub-audio, and the duration of the recording sub-audio is the same as the duration of the corresponding test sub-audio. Therefore, the recording audio can be split according to the reference starting point, and N recording sub-audio corresponding to the N testing sub-audio can be obtained.
In an embodiment, the value of the at least one play quality parameter is determined based on the N test sub-audios and the N recorded sub-audios, including at least one of:
determining the value of a background noise size parameter according to the mute recorded audio;
determining the value of the sensitivity parameter according to the sine wave recording audio and the mute recording audio;
determining the value of the signal-to-noise ratio parameter according to the sine wave recording audio and the mute recording audio;
determining 2 × M values of the time delay parameter according to the starting time of the M first recording audios, the starting time of the M second recording audios, the transfer time of the M first audios and the transfer time of the M second audios;
determining at least one value of a return loss gain parameter based on at least one of the synthesized speech audio and the music audio, and at least one of the synthesized speech recorded audio and the music recorded audio;
and determining the value of the coherence parameter according to the white noise audio and the white noise recording audio.
That is, in the present application, each different playback quality parameter is determined according to its associated corresponding recorded sub-audio and/or test sub-audio. The mute recorded audio is associated with a noise floor size parameter, the value of which is determined according to the mute recorded audio. In one example, the energy of the silent recorded audio is logarithmically taken to be base 10 and multiplied by 20 to obtain the value of the base noise size parameter.
The sensitivity parameter is associated with the sinusoidal recording audio and the silent recording audio, and in one example, the value of the sensitivity parameter may be obtained by first subtracting the silent recording audio from the sinusoidal recording audio to obtain a difference audio, taking a base-10 logarithm of the difference audio, and then multiplying the difference audio by 20.
The signal-to-noise ratio parameter is associated with the sine wave recording audio and the mute recording audio pipe, and the value of the signal-to-noise ratio parameter is determined. In one example, the energy of the mute recording audio may be logarithmized by 10 and then multiplied by 20 to obtain a value of the bottom noise size parameter, then the sine wave recording audio is subtracted from the mute recording audio to obtain a difference audio, the difference audio is logarithmized by 10 and then multiplied by 20 to obtain a value of the sensitivity parameter, and then the value of the bottom noise size parameter is subtracted from the value of the sensitivity parameter to obtain a value of the signal-to-noise ratio parameter. That is, the value of the signal-to-noise ratio parameter can be obtained by the value of the background noise size parameter and the value of the sensitivity parameter, and if the value of the background noise size parameter and the value of the sensitivity parameter are determined, the value of the signal-to-noise ratio parameter can be obtained by directly subtracting the value of the background noise size parameter from the value of the sensitivity parameter.
The delay parameter is associated with the first recorded audio, the second recorded audio, the first audio and the second audio, each first audio and the corresponding first recorded audio can determine a value of the delay parameter, each second audio and the corresponding second recorded audio can determine a value of the delay parameter, and then 2 × M values of the delay parameter can be determined according to the starting time of the M first recorded audio, the starting time of the M second recorded audio, the transmission time of the M first audio and the transmission time of the M second audio.
The return loss gain parameter is associated with the synthesized speech audio and the synthesized speech recording audio, or/and the musical audio and the musical recording audio, and at least one value of the return loss gain parameter is determined based on at least one of the synthesized speech audio and the musical audio and at least one of the synthesized speech recording audio and the musical recording audio. The number of values of the return loss gain parameter is the same as the number of pairs of audio associated therewith, for example, one if only the pair of audio of the synthesized speech audio and the synthesized speech recording audio is associated, one if only the pair of audio of the music audio and the music recording audio is associated, or two if the pair of audio of the synthesized speech audio and the synthesized speech recording audio and the pair of audio of the music audio and the music recording audio are associated.
The coherence parameter is associated with the white noise audio and the white noise recorded audio, and a value of the coherence parameter can be determined according to the white noise audio and the white noise recorded audio.
In one embodiment, determining the playback quality detection result based on the value of at least one playback quality parameter comprises: comparing the value of each playing quality parameter with a preset standard value corresponding to the value of each playing quality parameter, and determining a comparison result of the value of at least one playing quality parameter; and determining a play quality detection result according to the comparison result of the values of the at least one play quality parameter.
Each playing quality parameter has a corresponding preset standard value, after the value of at least one playing quality parameter is obtained, the value of each playing quality parameter can be compared with the corresponding preset standard value to determine the comparison result of the value of at least one playing quality parameter, and then the playing quality detection result is determined according to the comparison result of the value of at least one playing quality parameter. For example, it is determined whether the comparison result of the value of each playback quality parameter satisfies the corresponding preset requirement (e.g., if the value of the return loss gain parameter is greater than the preset standard value of the return loss gain parameter, it indicates that the preset requirement corresponding to the return loss gain parameter is satisfied, the value of the delay parameter is less than the preset standard value of the delay parameter, it indicates that the preset requirement corresponding to the delay parameter is satisfied, the value of the coherence parameter is greater than the preset standard value of the coherence parameter, it indicates that the preset requirement corresponding to the coherence parameter is satisfied, the value of the bottom noise size parameter is less than the preset standard value of the bottom noise size parameter, it indicates that the preset requirement corresponding to the bottom noise size parameter is satisfied, the value of the sensitivity parameter is greater than the preset standard value of the sensitivity parameter, it indicates that the preset requirement corresponding to the bottom noise size parameter is satisfied, if the comparison result of the value of each playback quality parameter satisfies the corresponding preset requirement, it is determined that the detection is qualified, otherwise (i.e., if the comparison result of the value of at least one playback quality parameter does not satisfy the corresponding preset requirement), it is determined that the comparison result of the value of the playback quality parameter does not satisfy the corresponding preset requirement).
In one embodiment, after determining the value of the at least one playback quality parameter based on the N test sub-audios and the N recorded sub-audios, the method further includes: generating a corresponding quality parameter image based on the value of each play quality parameter; and respectively storing each quality parameter image in a corresponding folder.
After obtaining the value of at least one playing parameter, a quality parameter map corresponding to each playing quality parameter can be generated for the user to view. For example, it may be an image in jpg format. And storing each quality parameter image in a corresponding folder respectively so as to facilitate the subsequent calling of the images.
In an embodiment, the recording unit may be a microphone array, that is, includes at least two microphones, and each microphone may record, that is, the recording audio is at least two paths, and each path is an audio obtained by completely recording the test audio during playing. The process of determining the value of at least one playing quality parameter for each path of the recorded audio can be performed by the above splitting, so that the number of the values of each playing quality parameter is increased accordingly, for example, if there are two paths, the number of the values of each playing quality parameter is twice the original number, and if there are three paths, the number of the values of each playing quality parameter is three times the original number, that is, the number of the values of each playing quality parameter is doubled according to the number of paths of the recorded audio. The method includes the steps of splitting each path of recording audio to obtain N recording sub-audios corresponding to each path of recording audio, determining a value of at least one playing quality parameter corresponding to each path of recording audio based on the N testing sub-audios and the N recording sub-audios corresponding to each path of recording audio, wherein each playing quality parameter corresponding to one path of recording audio is associated with the corresponding testing sub-audio and/or the recording sub-audio in the path of recording audio, and determining a playing quality detection result according to the value of at least one playing quality parameter corresponding to each path of recording audio.
The process of the above method is described in detail below with an embodiment. The test program for realizing the method is pre-imported into the electronic terminal, the test program can be written in python language, matlab language, java preview and the like, and the test program needs to acquire the file name of the test audio, the transmission channel of the recording audio recorded by the microphone and the transmission channel of the test audio.
As shown in fig. 2, the test audio includes 9 different test sub-audios, i.e., N is 9, which are respectively a start prompt audio, a mute audio, a sine wave audio (e.g., a positive-wave audio with a frequency of 1 KHZ), 10 first chirp audio, a synthesized voice audio, a music audio, a white noise audio, 10 second chirp audio, and an end prompt audio sequentially increasing in time order. After recording, a recording audio is obtained, a reference starting point in the recording audio can be located firstly, the recording audio is split based on the reference starting point, after the reference starting point is determined, because the relative position and the duration between each section of audio are determined, the recording audio can be split based on the reference time point, 9 recording sub-audio is obtained, and the recording sub-audio is respectively a starting prompt recording audio, a mute recording audio, a sine wave recording audio, 10 first chirp recording audio, a synthetic voice recording audio, a music recording audio, a white noise recording audio, 10 second chirp recording audio and an ending prompt recording audio which are gradually increased according to a time sequence.
Namely, the starting prompting recorded audio is used for positioning the reference starting point, the starting point of each segment of sub-recorded audio is positioned according to the starting point of the audio, and the recorded audio is split. The silence recording audio is used for testing the background noise size parameter. The 1kHz sine wave recorded audio is used for testing sensitivity parameters, and signal-to-noise ratio parameters can be tested through mute recorded audio and sine wave recorded audio. The 10 first chirp tones and the 10 second chirp tones are used to test the test delay parameters and the consistency of the delay parameters. TTS audio (synthetic speech audio) and music audio users test the effect of echo cancellation. A white noise signal is used to test the coherence parameter. And the ending prompt tone is used for prompting the completion of the recording.
As shown in fig. 3, which is a test result diagram of the return loss gain parameters, the microphone array includes 4 microphones, each microphone performs recording to obtain a path of recording audio, each path of recording audio is split, and the return loss gain parameters are determined to obtain values of the 4 return loss gain parameters. Each microphone corresponds to a channel number, the abscissa in fig. 3 is the channel number corresponding to the microphone, and the ordinate is the value of the return loss gain parameter (ERLE), for example, a microphone with a channel number of 1, a microphone with a channel number of 2 and a microphone with a return loss gain parameter of 34, a microphone with a channel number of 3 and a microphone with a return loss gain parameter of 34, a microphone with a channel number of 4 and a microphone with a return loss gain parameter of 33, that is, the obtained values of the return loss gain parameters are different for the recorded audio of different microphones.
As shown in fig. 4, which is a test result diagram of coherence parameters, the 4 curves in the diagram are coherence parameter curves calculated for recorded audio of 4 microphones, and are respectively a curve corresponding to a microphone of channel number 1, a curve corresponding to a microphone of channel number 2, a curve corresponding to a microphone of channel number 3, and a curve corresponding to a microphone of channel number 4, and the closer the values of the curves are to 1, the more similar the recorded audio and the test audio are.
As shown in fig. 5, which is a graph of the coherence parameter consistency test result, the curve in fig. 5 is a curve obtained by subtracting the minimum value from the maximum value (i.e., the coherence coefficient difference) corresponding to each abscissa point in the 4 curves in fig. 4, and the coherence parameter consistency between different microphones can be tested by using the curve segment between 100 HZ and 1000HZ in the curve, for example, if the ordinate value of the curve segment between 100 HZ and 1000HZ in the curve is less than 0.1, the coherence parameter consistency is considered to be better.
As shown in fig. 6, it is a diagram of the test result of the delay parameter, where the abscissa represents the numbers of the first recorded audio and the second recorded audio, i.e., the number of the chirp recorded audio, and the ordinate represents the value of the delay parameter (i.e., the relative delay frame number in fig. 6), which is represented by the frame number, and one frame is 1/16 of a second, and since the test audio employs 20 chirp audios, and 20 chirp recorded audio corresponds to the recorded audio of each microphone, 20 values of the delay parameter can be corresponded to the recorded audio of each microphone. The 20 values of the delay parameter for the microphone of channel number 1 in fig. 6 correspond to the 20 values of the delay parameter for the microphone of channel number 2, which are coincident with the upper point in fig. 6, and the 20 values of the delay parameter for the microphone of channel number 3 correspond to the 20 values of the delay parameter for the microphone of channel number 4, which are coincident with the lower point in fig. 6. For 20 values of the delay parameter corresponding to each path of the recorded audio, the 20 values may be respectively compared with the preset standard value of the delay parameter, and if the 20 values of the delay parameter are all smaller than the corresponding preset standard value and the 20 values are maintained at the stable value corresponding to the path of the recorded audio, for example, 11 frames, the value of the delay parameter of the path of the recorded audio may be determined to be qualified. In one example, when the value of the delay parameter of each path of the recorded audio is smaller than a corresponding preset standard value, and each value is maintained at a stable value corresponding to the path of the recorded audio, the value of the delay parameter is determined to be qualified.
As shown in fig. 7, the graph is a test result graph of the noise floor size parameter, where the abscissa is the channel number corresponding to the microphone, and the ordinate is the value of the noise floor size parameter (i.e., the noise floor value). The low noise size parameter corresponding to the channel number of each microphone has different values. Ref in fig. 7 indicates a reference channel number, and the value of the corresponding noise floor size parameter is a noise floor reference value, and by comparing the reference channel number with the noise floor reference value, the difference between the value of the noise floor size parameter of the microphone of each channel number and the noise floor reference value can be determined, and the quality of the value of the noise floor size parameter of the microphone of each channel number can be determined.
As shown in fig. 8, the graph is a test result of the sensitivity parameter, the abscissa is the channel number corresponding to the microphone, and the ordinate is the value of the sensitivity parameter (i.e., the sensitivity value). The values of the sensitivity parameters corresponding to the channel numbers of each microphone are different. Ref in fig. 8 indicates a reference channel number, and the value of the sensitivity parameter corresponding thereto is a sensitivity reference value, and by comparing the reference channel number with the sensitivity reference value, the difference between the value of the sensitivity parameter of the microphone of each channel number and the sensitivity reference value can be determined, and the quality of the value of the sensitivity parameter of the microphone of each channel number can be determined.
As shown in fig. 9, it is a test result graph of the snr parameter, where the abscissa is the channel number corresponding to the microphone and the ordinate is the value of the snr parameter (i.e., the snr value). The values of the signal-to-noise ratio parameters corresponding to the channel numbers of all the microphones are different. Ref in fig. 9 represents a reference channel number, and the snr parameter value corresponding to the reference channel number is an snr reference value, and by comparing the snr reference value with the snr reference value, the difference between the snr parameter value of the microphone of each channel number and the snr reference value can be determined, and the quality of the snr parameter value of the microphone of each channel number can be determined.
Referring to fig. 1, fig. 1 is a schematic block diagram of an electronic terminal 100 according to an embodiment of the present invention, and as shown in fig. 1, the electronic terminal 100 includes:
an instruction receiving module 110, configured to receive a playing instruction;
the control module 120 is configured to play a test audio in response to the play instruction, and record the test audio, where the test audio includes N test sub-audios, and N is an integer greater than 1;
a recording audio obtaining module 130, configured to stop recording after the test audio is played, and obtain a recording audio obtained by recording;
the splitting module 140 is configured to split the recording audio to obtain N recording sub-audios;
a parameter determining module 150, configured to determine a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, where each play quality parameter is associated with a corresponding test sub-audio and/or recording sub-audio;
the detection result determining module 160 is configured to determine a playback quality detection result according to a value of at least one playback quality parameter.
In one embodiment, the at least one playback quality parameter comprises at least one of: return loss gain parameters, time delay parameters, coherence parameters, background noise size parameters, sensitivity parameters and signal-to-noise ratio.
In one embodiment, the N test sub-audios include a start cue audio sequentially increasing in time order and at least one of: the audio-frequency-based voice synthesis method comprises the following steps of (1) mute audio, sine wave audio, M first audios, synthesized voice audio, music audio, white noise audio and M second audios, wherein M is an integer larger than zero;
a splitting module comprising:
the reference starting point determining module is used for determining a reference starting point of the recording audio, the reference starting point is a starting point of a reference recording audio in the recording audio, and the reference recording audio is matched with a starting prompt audio in the test audio;
the splitting submodule is used for splitting the recording audio based on the reference starting point to obtain N recording sub-audios, and the N recording sub-audios comprise starting prompt recording audios sequentially increasing in time sequence and at least one of the following audios: the audio recording device comprises mute recording audio, sine wave recording audio, M first recording audio, synthesized voice recording audio, music recording audio, white noise recording audio and M second recording audio.
In one embodiment, the parameter determination module comprises at least one of:
the background noise size parameter determining module is used for determining the value of the background noise size parameter according to the mute recorded audio;
the sensitivity parameter determining module is used for determining the value of the sensitivity parameter according to the sine wave recording audio and the mute recording audio;
the signal-to-noise ratio determining module is used for determining the value of a signal-to-noise ratio parameter according to the sine wave recording audio and the mute recording audio;
the time delay parameter determining module is used for determining 2 x M values of the time delay parameter according to the starting time of the M first recording audios, the starting time of the M second recording audios, the transmission time of the M first audios and the transmission time of the M second audios;
a return loss gain parameter determination module for determining at least one value of a return loss gain parameter based on at least one of the synthesized speech audio and the music audio and at least one of the synthesized speech recording audio and the music recording audio;
and the coherence parameter determining module is used for determining the value of the coherence parameter according to the white noise audio and the white noise recording audio.
In one embodiment, the detection result determining module includes:
the comparison module is used for comparing the value of each playing quality parameter with a preset standard value corresponding to the value of each playing quality parameter and determining the comparison result of the value of at least one playing quality parameter;
and the detection result determining submodule is used for determining a play quality detection result according to the comparison result of the value of at least one play quality parameter.
In one embodiment, the electronic terminal further comprises:
the image generation module is used for generating a corresponding quality parameter image based on the value of each playing quality parameter;
and the storage module is used for respectively storing each quality parameter image into the corresponding folder.
The electronic terminal 300 can implement each process implemented by the method in the foregoing method embodiment, and details are not described here to avoid repetition.
In an embodiment, an embodiment of the present invention further provides an electronic terminal, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program is executed by the processor to implement each process in the foregoing method for detecting playback quality of the electronic terminal, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the above-mentioned method for detecting the playing quality of an electronic terminal, and can achieve the same technical effect, and is not described herein again to avoid repetition. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling an electronic terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method of the embodiments of the present invention.
While the present invention has been described with reference to the particular illustrative embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalent arrangements, and equivalents thereof, which may be made by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (12)
1. A method for detecting the playing quality of an electronic terminal is characterized by comprising the following steps:
receiving a playing instruction;
responding to the playing instruction, playing a test audio and recording, wherein the test audio comprises N test sub-audios, and N is an integer greater than 1;
stopping recording after the test audio is played, and acquiring a recording audio obtained by recording;
splitting the recording audio to obtain N recording sub-audios;
determining a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, wherein each play quality parameter is associated with a corresponding test sub-audio and/or recording sub-audio;
determining a play quality detection result according to the value of the at least one play quality parameter;
wherein the N test sub-audios include an initial prompt audio sequentially increasing in time order and at least one of: the audio-frequency-based voice synthesis method comprises the following steps of (1) mute audio, sine wave audio, M first audios, synthesized voice audio, music audio, white noise audio and M second audios, wherein M is an integer larger than zero;
splitting the recording audio to obtain N recording sub-audios, including:
determining a reference starting point of the recorded audio, wherein the reference starting point is a starting point of a reference recorded audio in the recorded audio, and the reference recorded audio is matched with a starting prompt audio in the test audio;
splitting the recording audio based on the reference starting point to obtain the N recording sub-audios, wherein the N recording sub-audios comprise a starting prompt recording audio with sequentially increasing time sequence and at least one of the following: the audio recording device comprises mute recording audio, sine wave recording audio, M first recording audio, synthesized voice recording audio, music recording audio, white noise recording audio and M second recording audio.
2. The method of claim 1, wherein the at least one playback quality parameter comprises at least one of: return loss gain parameters, time delay parameters, coherence parameters, background noise size parameters, sensitivity parameters and signal-to-noise ratio.
3. The method of claim 1, wherein determining a value of at least one playback quality parameter based on the N test sub-audios and the N recorded sub-audios comprises at least one of:
determining the value of a background noise size parameter according to the mute recording audio;
determining the value of a sensitivity parameter according to the sine wave recording audio and the mute recording audio;
determining the value of the signal-to-noise ratio parameter according to the sine wave recording audio and the mute recording audio;
determining 2 × M values of a time delay parameter according to the starting time of the M first recording audios, the starting time of the M second recording audios, the transfer time of the M first audios, and the transfer time of the M second audios;
determining at least one value of a return loss gain parameter based on at least one of the synthesized speech audio and the music audio and at least one of the synthesized speech recording audio and the music recording audio;
and determining the value of the coherence parameter according to the white noise audio and the white noise recording audio.
4. The method of claim 1, wherein said determining a playback quality measurement based on the value of the at least one playback quality parameter comprises:
comparing the value of each playing quality parameter with a preset standard value corresponding to the value of each playing quality parameter, and determining a comparison result of the value of at least one playing quality parameter;
and determining a play quality detection result according to the comparison result of the values of the at least one play quality parameter.
5. The method of claim 1, wherein after determining the value of at least one playback quality parameter based on the N test sub-audios and the N recorded sub-audios, further comprising:
generating a corresponding quality parameter image based on the value of each play quality parameter;
and respectively storing each quality parameter image in a corresponding folder.
6. An electronic terminal, comprising:
the instruction receiving module is used for receiving a playing instruction;
the control module is used for responding to the playing instruction, playing test audio and recording, wherein the test audio comprises N test sub-audio, and N is an integer greater than 1;
the recording audio acquisition module is used for stopping recording after the test audio playing is finished and acquiring recording audio obtained by recording;
the splitting module is used for splitting the recording audio to obtain N recording sub-audio;
a parameter determination module, configured to determine a value of at least one play quality parameter based on the N test sub-audios and the N recording sub-audios, where each play quality parameter is associated with a corresponding test sub-audio and/or recording sub-audio;
a detection result determining module for determining a play quality detection result according to the value of the at least one play quality parameter;
wherein the N test sub-audios include an initial prompt audio sequentially increasing in time order and at least one of: the audio-frequency-based voice synthesis method comprises the following steps of (1) mute audio, sine wave audio, M first audios, synthesized voice audio, music audio, white noise audio and M second audios, wherein M is an integer larger than zero;
the splitting module comprises:
a reference starting point determining module, configured to determine a reference starting point of the recorded audio, where the reference starting point is a starting point of a reference recorded audio in the recorded audio, and the reference recorded audio matches a starting prompt audio in the test audio;
a splitting submodule, configured to split the recording audio based on the reference starting point to obtain the N recording sub-audios, where the N recording sub-audios include a starting prompt recording audio whose time sequence is sequentially increased and at least one of the following: the audio recording device comprises mute recording audio, sine wave recording audio, M first recording audio, synthesized voice recording audio, music recording audio, white noise recording audio and M second recording audio.
7. The electronic terminal of claim 6, wherein the at least one playback quality parameter comprises at least one of: return loss gain parameters, time delay parameters, coherence parameters, background noise size parameters, sensitivity parameters and signal-to-noise ratio.
8. The electronic terminal of claim 6, wherein the parameter determination module comprises at least one of:
the background noise size parameter determining module is used for determining the value of the background noise size parameter according to the mute recording audio;
the sensitivity parameter determining module is used for determining the value of the sensitivity parameter according to the sine wave recording audio and the mute recording audio;
the signal-to-noise ratio determining module is used for determining the value of a signal-to-noise ratio parameter according to the sine wave recording audio and the mute recording audio;
a delay parameter determining module, configured to determine 2 × M values of a delay parameter according to the start times of the M first recorded audio, the start times of the M second recorded audio, the transfer times of the M first audio, and the transfer times of the M second audio;
a return loss gain parameter determination module for determining at least one value of the return loss gain parameter based on at least one of the synthesized speech audio and the music audio and at least one of the synthesized speech recording audio and the music recording audio;
and the coherence parameter determining module is used for determining the value of the coherence parameter according to the white noise audio and the white noise recording audio.
9. The electronic terminal of claim 6, wherein the detection result determination module comprises:
the comparison module is used for comparing the value of each playing quality parameter with a preset standard value corresponding to the value of each playing quality parameter and determining the comparison result of the value of the at least one playing quality parameter;
and the detection result determining submodule is used for determining a play quality detection result according to the comparison result of the values of the at least one play quality parameter.
10. The electronic terminal of claim 6, further comprising:
the image generation module is used for generating a corresponding quality parameter image based on the value of each playing quality parameter;
and the storage module is used for respectively storing each quality parameter image into a corresponding folder.
11. An electronic terminal, comprising: memory, processor and computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for detecting the playback quality of an electronic terminal according to any one of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps in the method for detecting the playback quality of an electronic terminal according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911337164.2A CN113096694B (en) | 2019-12-23 | 2019-12-23 | Electronic terminal and play quality detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911337164.2A CN113096694B (en) | 2019-12-23 | 2019-12-23 | Electronic terminal and play quality detection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113096694A CN113096694A (en) | 2021-07-09 |
| CN113096694B true CN113096694B (en) | 2023-02-21 |
Family
ID=76664016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911337164.2A Active CN113096694B (en) | 2019-12-23 | 2019-12-23 | Electronic terminal and play quality detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113096694B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113726939B (en) * | 2021-08-30 | 2024-05-28 | 展讯半导体(成都)有限公司 | System, method, medium and equipment for testing functions of terminal radio |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4746991A (en) * | 1982-01-12 | 1988-05-24 | Discovision Associates | Recording characteristic evaluation of a recording medium with a time sequence of test signals |
| JP2005018860A (en) * | 2003-06-24 | 2005-01-20 | Matsushita Electric Ind Co Ltd | Audio reproducing device |
| CN101089641A (en) * | 2007-07-12 | 2007-12-19 | 北京中星微电子有限公司 | Method system for implementing investigating audio-frequency equipment and audio-frequency equipment |
| CN104333752A (en) * | 2014-11-25 | 2015-02-04 | 杭州海康威视数字技术股份有限公司 | Audio quality diagnostic method and device |
| CN106161705A (en) * | 2015-04-22 | 2016-11-23 | 小米科技有限责任公司 | Audio frequency apparatus method of testing and device |
| CN107360530A (en) * | 2017-07-03 | 2017-11-17 | 苏州科达科技股份有限公司 | The method of testing and device of a kind of echo cancellor |
| CN108882115A (en) * | 2017-05-12 | 2018-11-23 | 华为技术有限公司 | loudness adjusting method, device and terminal |
| CN109275084A (en) * | 2018-09-12 | 2019-01-25 | 北京小米智能科技有限公司 | Test method, device, system, equipment and the storage medium of microphone array |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060002255A1 (en) * | 2004-07-01 | 2006-01-05 | Yung-Chiuan Weng | Optimized audio / video recording and playing system and method |
| US10032475B2 (en) * | 2015-12-28 | 2018-07-24 | Koninklijke Kpn N.V. | Enhancing an audio recording |
-
2019
- 2019-12-23 CN CN201911337164.2A patent/CN113096694B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4746991A (en) * | 1982-01-12 | 1988-05-24 | Discovision Associates | Recording characteristic evaluation of a recording medium with a time sequence of test signals |
| JP2005018860A (en) * | 2003-06-24 | 2005-01-20 | Matsushita Electric Ind Co Ltd | Audio reproducing device |
| CN101089641A (en) * | 2007-07-12 | 2007-12-19 | 北京中星微电子有限公司 | Method system for implementing investigating audio-frequency equipment and audio-frequency equipment |
| CN104333752A (en) * | 2014-11-25 | 2015-02-04 | 杭州海康威视数字技术股份有限公司 | Audio quality diagnostic method and device |
| CN106161705A (en) * | 2015-04-22 | 2016-11-23 | 小米科技有限责任公司 | Audio frequency apparatus method of testing and device |
| CN108882115A (en) * | 2017-05-12 | 2018-11-23 | 华为技术有限公司 | loudness adjusting method, device and terminal |
| CN107360530A (en) * | 2017-07-03 | 2017-11-17 | 苏州科达科技股份有限公司 | The method of testing and device of a kind of echo cancellor |
| CN109275084A (en) * | 2018-09-12 | 2019-01-25 | 北京小米智能科技有限公司 | Test method, device, system, equipment and the storage medium of microphone array |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113096694A (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7437286B2 (en) | Voice barge-in in telephony speech recognition | |
| US20140337021A1 (en) | Systems and methods for noise characteristic dependent speech enhancement | |
| CN110265064B (en) | Audio frequency crackle detection method, device and storage medium | |
| JP4745916B2 (en) | Noise suppression speech quality estimation apparatus, method and program | |
| US20020049587A1 (en) | Speech recognition method, storage medium storing speech recognition program, and speech recognition apparatus | |
| JP2021503633A (en) | Voice noise reduction methods, devices, servers and storage media | |
| KR20130108391A (en) | Method, apparatus and machine-readable storage medium for decomposing a multichannel audio signal | |
| CN113170024B (en) | Echo cancellation method, delay estimation device, storage medium and equipment | |
| CN108200526B (en) | Sound debugging method and device based on reliability curve | |
| US8050422B2 (en) | Audio test apparatus capable of decreasing noise influence in process of audio device testing and method thereof | |
| EP1501334A1 (en) | Transmission characteristic measuring device, transmission characteristic measuring method, and amplifier | |
| CN107452398B (en) | Echo acquisition method, electronic device and computer readable storage medium | |
| CN113096694B (en) | Electronic terminal and play quality detection method thereof | |
| CN111627460B (en) | Ambient reverberation detection method, device, equipment and computer readable storage medium | |
| CN109741761B (en) | Sound processing method and device | |
| CN111028854B (en) | Audio data processing method and device, electronic equipment and storage medium | |
| CN109979487B (en) | Voice signal detection method and device | |
| CN109121068A (en) | Sound effect control method, apparatus and electronic equipment | |
| WO2017135350A1 (en) | Recording medium, acoustic processing device, and acoustic processing method | |
| JP7347520B2 (en) | Sound signal processing device, sound signal processing method, and sound signal processing program | |
| CN113593604A (en) | Method, device and storage medium for detecting audio quality | |
| CN115148208B (en) | Audio data processing method and device, chip and electronic equipment | |
| CN113611276B (en) | Acoustic feedback suppression method, apparatus and storage medium | |
| CN114400022B (en) | Method, device and storage medium for comparing sound quality | |
| WO2023245700A1 (en) | Audio energy analysis method and related apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |