CN107340054B - Method and device for testing noise of acoustic product - Google Patents
Method and device for testing noise of acoustic product Download PDFInfo
- Publication number
- CN107340054B CN107340054B CN201710486554.0A CN201710486554A CN107340054B CN 107340054 B CN107340054 B CN 107340054B CN 201710486554 A CN201710486554 A CN 201710486554A CN 107340054 B CN107340054 B CN 107340054B
- Authority
- CN
- China
- Prior art keywords
- energy spectrogram
- rgb
- section
- acoustic product
- noise
- 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
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Abstract
The invention discloses a method and a device for testing noise of an acoustic product. The method comprises the following steps: acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file; dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating the RGB of each section of energy spectrogram; comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be tested is qualified, so that the noise test of the acoustic product is more accurate, and the quality of the acoustic product is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for testing noise of an acoustic product.
Background
With the rapid development of society, the requirements of people on the quality of life are higher and higher. The acoustic product is favored by the majority of users by virtue of the advantages of being pleasant and relaxing. However, if the acoustic product has noise, the experience of people is greatly reduced, and even the acoustic product is very dysphoric. In the production process of the acoustic products, the acoustic products with noise are detected and are not allowed to flow to the market, so that the acoustic product detection method is the most effective and direct way for solving the problems that consumers are dissatisfied and brand images are influenced.
The current methods for testing noise in an acoustic production line mainly include the following two methods:
the first method is that the test result is extremely unstable and has larger error due to strong subjectivity through manual auditory judgment;
the second method is to determine by testing the magnitude of the signal noise in the whole time domain, and the magnitude of the noise value is generally the average value of the signal noise in the whole time domain. However, noise occurs randomly, and if the average value of signal noise in the whole time domain is tested according to a noise test method, noise occurring at a certain moment is likely to be within a qualified range after being averaged, so that the detection result is inaccurate.
To illustrate the drawbacks of the second noise testing method, a buzzer is taken as an example, and fig. 1 shows that buzzers of different individuals of the same product work under a rated working voltage and the same standard microphone is used for recording an energy spectrum of a signal acquired within 0.8 s. The energy spectrum can be generated by audio file analysis software such as Adobe Audio or Cool Editor. In this example, the abscissa is the time axis and the ordinate is the frequency axis.
The noise test result of two sections of recording files through AdobeAudition comparative analysis is as follows: the noise test result of the first buzzer is NG 1.05dB, the noise test result of the second buzzer is OK 1.07dB, and the difference between the two is only 0.02 dB. Therefore, the method for testing the noise of the signal in the whole time domain cannot accurately judge whether the noise exists.
Disclosure of Invention
The invention provides a method and a device for testing noise of an acoustic product, which are used for solving the problems that the existing noise test of the acoustic product has strong subjectivity through artificial auditory judgment, so that the test result is extremely unstable, the error is large, the test result is inaccurate due to the average value of signal noise in the whole time domain, and the like.
According to an aspect of the present invention, there is provided a method of testing acoustic product noise, the method comprising:
acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file;
dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating the RGB of each section of energy spectrogram;
comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is qualified.
According to another aspect of the invention, there is provided an apparatus for testing the noise of an acoustic product, the apparatus comprising a memory and a processor, the memory storing a computer program executable by the processor, the computer program when executed by the processor being operable to:
acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file;
dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating the RGB of each section of energy spectrogram;
comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is qualified.
The invention has the beneficial effects that: according to the technical scheme, an audio file generated by an acoustic product to be tested is obtained, and an energy spectrogram of the audio file is generated; then dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating RGB of each section of energy spectrogram; comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, the noise of the acoustic product to be tested is judged to be qualified, the problem of inaccurate test result caused by testing the noise of the whole time domain of the acoustic product in the prior art is solved, the noise test of the acoustic product is more accurate, the quality of the acoustic product is improved, the user experience is further improved, and the brand image of the acoustic product is maintained.
Drawings
FIG. 1 is a prior art energy spectrum of a test acoustic product murmur over the time domain;
FIG. 2 is a flow chart of a method of testing acoustic product noise in accordance with one embodiment of the present invention;
FIG. 3 is a detailed flow chart of a method of testing the noise of an acoustic product according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of a process for segmenting an energy spectrum according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating the result of calculating each energy spectrum RGB according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a device for testing noise of an acoustic product according to an embodiment of the present invention.
Detailed Description
The design concept of the invention is as follows: in order to enable the noise test of the acoustic product to be more accurate and improve the quality of the acoustic product, an audio file generated by the acoustic product to be tested is obtained, and an energy spectrogram of the audio file is generated; then dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating RGB of each section of energy spectrogram; and comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and further judging whether the noise of the acoustic product to be detected is qualified.
Example one
Fig. 2 is a flow chart of a method of testing the noise of an acoustic product, as shown in fig. 2, according to an embodiment of the present invention, the method comprising:
in step S110, an audio file generated by an acoustic product to be tested is obtained, and an energy spectrogram of the audio file is generated;
in step S120, dividing the energy spectrogram into a plurality of segments according to a time domain, and calculating RGB of each segment of the energy spectrogram;
in step S130, comparing the calculated RGB of each energy spectrum with a pre-stored RGB preset value of the energy spectrum of the corresponding segment, and if any one of the calculated RGB of the energy spectrum is greater than the pre-stored RGB preset value of the energy spectrum of the corresponding segment, determining that the noise of the acoustic product to be tested is not qualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is qualified.
By the method shown in fig. 2, it can be known that the technical scheme of the invention generates an audio file by acquiring an acoustic product to be tested, and generates an energy spectrogram of the audio file; then dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating RGB of each section of energy spectrogram; comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, the noise of the acoustic product to be tested is judged to be qualified, the problem of inaccuracy of a test result caused by testing the noise of the whole time domain of the acoustic product in the prior art is solved, the noise test of the acoustic product is more accurate, and the quality of the acoustic product is improved.
In an embodiment of the present invention, the dividing the energy spectrogram into several segments according to a time domain includes: and determining the noise testing time length of each section according to the noise testing time length of the acoustic product production line to be tested, and dividing the energy spectrogram into a plurality of sections according to the noise testing time length of each section. In practical application, since the production line test requires a short time, which generally does not exceed 10 seconds(s), the test time period can be preset to 2s-5 s. And in the testing process, the testing time lengths of a plurality of sections divided by the energy spectrogram are the same or different. If the testing time is the same and is preset to be 2s and the testing time is 8s, the energy spectrogram to be tested can be equally divided into 4 sections; if the test duration is different, for example, the test duration of the first segment is 1s, the test duration of the second segment is 2s, the test duration of the third segment is 3s, and the test duration of the fourth segment is 2s, the energy spectrogram to be tested is divided into 4 segments according to the test duration. In practical application, the duration to be tested can be preset according to the characteristics of the acoustic product to be tested, and the duration of the test is not limited in the application.
In an embodiment of the present invention, the pre-stored RGB preset values of the energy spectrograms of the corresponding segments may be the same or different;
if the acoustic product to be tested is an acoustic product of a constant-frequency sound wave, the pre-stored RGB preset values of each section of energy spectrogram are the same; for example, if the acoustic product to be tested is a buzzer, the pre-stored RGB preset values of each energy spectrum may be set to be the same.
And if the acoustic product to be tested is an acoustic product with variable frequency sound waves, the pre-stored RGB preset values of each section of energy spectrogram are different. For example, if the acoustic product to be tested is a horn, the pre-stored RGB preset values of each energy spectrum may be set to be different. It should be noted that, in practical application, the RGB preset value of each energy spectrogram can be set according to the characteristics of the acoustic product to be measured.
In an embodiment of the invention, the pre-stored preset value of RGB of the energy spectrum of the corresponding segment is set according to the acquired RGB of the corresponding segment of the energy spectrum of the qualified acoustic product. It should be noted that, due to different sound characteristics or different sound source sizes of the acoustic product to be measured, RGB of the corresponding segment of the energy spectrogram of the corresponding qualified acoustic product may be the same or different.
In order to make the solution of the present invention clearer, the following explains the solution of the present invention with a specific example. Fig. 3 is a detailed flowchart of a method for testing the noise of an acoustic product according to an embodiment of the present invention, as shown in fig. 3,
and S21, acquiring an audio file of the acoustic product to be tested. It should be noted that, in practical application, a standard microphone is used to acquire a sound signal played by a corresponding acoustic product, so as to generate a corresponding audio file; or acquiring a sound signal emitted by the sound simulation mouth by using a microphone, and further generating a corresponding audio file. In addition, in the process, the acquisition of the audio file of the corresponding qualified acoustic product is finished and is used as a basis for judging whether the subsequent acoustic product is qualified or not. In this embodiment, the acoustic product to be tested is a buzzer.
And S22, inputting the audio file obtained in the S21 into audio file analysis software such as AdobeAudition or Cool Editor and the like, and generating a corresponding energy spectrogram.
And S23, carrying out segmentation processing on the energy spectrogram in the S22. In the embodiment, the energy spectrogram is divided mainly according to the test duration, and if the test duration of each section is the same, the energy spectrogram is equally divided; if the testing time of each section is different, the energy spectrogram is subjected to unequal division, and in practical application, the testing time can be preset according to the sound characteristics of the acoustic product to be tested. As shown in fig. 4, the generated energy spectrum of 8s is divided into 4 equal parts according to the test duration of 2 s.
And S24, calculating RGB corresponding to each energy spectrum in S23. Since the difference between the red elements of each part is large in this example, statistics can be performed on the red elements of each part, and as shown in fig. 5, the calculation results are sequentially: 186.92dB, 181.79dB, 181.73dB, 181.63 dB.
S25, determining whether RGB of each energy spectrum segment is smaller than RGB preset value of the corresponding segment? In this embodiment, since the buzzer is an acoustic product of constant frequency sound waves, the RGB preset value of each segment is set to 182 dB. 186.92dB, 181.79dB, 181.73dB, 181.63dB calculated in S24 are compared with 182dB, respectively. If each calculation result in S24 is less than 182dB, then S26 is performed; otherwise, S27 is executed.
And S26, if each calculation result in the S24 is less than 182dB, judging that the noise of the acoustic product is qualified.
And S26, if each calculation result in the S24 is less than 182dB, judging the acoustic product to be qualified. In the present embodiment, 186.92dB calculated in S24 is greater than 182dB, which is the RGB preset value, and thus, the acoustic product noise is determined to be not qualified. In practical application, if the noise of the corresponding acoustic product is judged to be unqualified, the noise of the corresponding acoustic product can be judged again through artificial ear listening, and if the noise of the corresponding acoustic product is judged to be qualified, the corresponding acoustic product can be detected again through the steps, or the corresponding acoustic product is judged to be qualified and is directly put into the market. And sampling inspection can be performed on the acoustic products judged to be qualified by a manual ear re-judgment mode, so that the noise accuracy of the acoustic products is further ensured.
Example two
Fig. 6 is a schematic structural diagram of an apparatus for testing noise of an acoustic product according to an embodiment of the present invention, as shown in fig. 6, the apparatus 300 includes a memory 320 and a processor 310, the memory 320 stores a computer program capable of being executed by the processor 310, and the computer program is capable of implementing the following operations when executed by the processor:
acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file;
dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating the RGB of each section of energy spectrogram;
comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is qualified.
Through the device shown in fig. 6, it can be known that the technical scheme of the invention solves the problem of inaccurate test result caused by testing the noise of the whole time domain of the acoustic product in the prior art, so that the noise test of the acoustic product is more accurate, and the quality of the acoustic product is improved.
In an embodiment of the present invention, the dividing the energy spectrogram into several segments according to a time domain includes:
and determining the noise testing time length of each section according to the noise testing time length of the acoustic product production line to be tested, and dividing the energy spectrogram into a plurality of sections according to the noise testing time length of each section.
In one embodiment of the present invention, the test duration of each energy spectrum is the same or different.
In an embodiment of the present invention, the pre-stored RGB preset values of the energy spectrograms of the corresponding segments may be the same or different;
if the acoustic product to be tested is an acoustic product of a constant-frequency sound wave, the pre-stored RGB preset values of each section of energy spectrogram are the same;
and if the acoustic product to be tested is an acoustic product with variable frequency sound waves, the pre-stored RGB preset values of each section of energy spectrogram are different.
In an embodiment of the invention, the pre-stored preset value of RGB of the energy spectrum of the corresponding segment is set according to the acquired RGB of the corresponding segment of the energy spectrum of the qualified acoustic product.
It should be noted that the working process of the apparatus 300 for testing noise of an acoustic product claimed in this embodiment is the same as the implementation steps of each embodiment of the method shown in fig. 2, and the description of the same parts is omitted.
In summary, the technical scheme of the invention includes acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file; then dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating RGB of each section of energy spectrogram; comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, the noise of the acoustic product to be tested is judged to be qualified, the problem of inaccurate test result caused by testing the noise of the whole time domain of the acoustic product in the prior art is solved, the noise test of the acoustic product is more accurate, the quality of the acoustic product is improved, the user experience is further improved, and the brand image of the acoustic product is maintained.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modifications, equivalents, improvements and the like which come within the teachings of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A method of testing acoustic product noise, the method comprising:
acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file;
dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating the RGB of each section of energy spectrogram;
comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is qualified, wherein the pre-stored RGB preset value of the energy spectrogram of the corresponding section is set according to the RGB of the corresponding section of the energy spectrogram of the acquired qualified acoustic product.
2. The method of claim 1, wherein said dividing said energy spectrogram into segments in the time domain comprises:
and determining the noise testing time length of each section according to the noise testing time length of the acoustic product production line to be tested, and dividing the energy spectrogram into a plurality of sections according to the noise testing time length of each section.
3. The method of claim 2, wherein the test duration of each energy spectrum is the same or different.
4. The method of claim 1, wherein the pre-stored RGB preset values of the energy spectrum of the corresponding segment may be the same or different;
if the acoustic product to be tested is an acoustic product of a constant-frequency sound wave, the pre-stored RGB preset values of each section of energy spectrogram are the same;
and if the acoustic product to be tested is an acoustic product with variable frequency sound waves, the pre-stored RGB preset values of each section of energy spectrogram are different.
5. An apparatus for testing the noise of an acoustic product, the apparatus comprising a memory and a processor, the memory storing a computer program executable by the processor, the computer program when executed by the processor being operable to:
acquiring an audio file generated by an acoustic product to be tested, and generating an energy spectrogram of the audio file;
dividing the energy spectrogram into a plurality of sections according to a time domain, and calculating the RGB of each section of energy spectrogram;
comparing the calculated RGB of each section of energy spectrogram with a prestored RGB preset value of the energy spectrogram of the corresponding section, and if the RGB of any section of the calculated energy spectrogram is greater than the prestored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is unqualified; and if the RGB of the energy spectrogram calculated by each section is smaller than the pre-stored RGB preset value of the energy spectrogram of the corresponding section, judging that the noise of the acoustic product to be detected is qualified, wherein the pre-stored RGB preset value of the energy spectrogram of the corresponding section is set according to the RGB of the corresponding section of the energy spectrogram of the acquired qualified acoustic product.
6. The apparatus of claim 5, wherein the dividing the energy spectrogram into segments in the time domain comprises:
and determining the noise testing time length of each section according to the noise testing time length of the acoustic product production line to be tested, and dividing the energy spectrogram into a plurality of sections according to the noise testing time length of each section.
7. The apparatus of claim 6, wherein the test duration of each energy spectrum is the same or different.
8. The apparatus of claim 5, wherein the pre-stored RGB pre-set values of the energy spectra of the corresponding segments may be the same or different;
if the acoustic product to be tested is an acoustic product of a constant-frequency sound wave, the pre-stored RGB preset values of each section of energy spectrogram are the same;
and if the acoustic product to be tested is an acoustic product with variable frequency sound waves, the pre-stored RGB preset values of each section of energy spectrogram are different.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710486554.0A CN107340054B (en) | 2017-06-23 | 2017-06-23 | Method and device for testing noise of acoustic product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710486554.0A CN107340054B (en) | 2017-06-23 | 2017-06-23 | Method and device for testing noise of acoustic product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107340054A CN107340054A (en) | 2017-11-10 |
| CN107340054B true CN107340054B (en) | 2020-02-07 |
Family
ID=60220055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710486554.0A Active CN107340054B (en) | 2017-06-23 | 2017-06-23 | Method and device for testing noise of acoustic product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107340054B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112135235B (en) * | 2020-09-22 | 2022-05-24 | 歌尔科技有限公司 | Quality detection method, system and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005283227A (en) * | 2004-03-29 | 2005-10-13 | Matsushita Electric Ind Co Ltd | Abnormal sound inspection method and its device |
| CN1959352A (en) * | 2005-11-02 | 2007-05-09 | 鸿富锦精密工业（深圳）有限公司 | System and method for testing buzzer |
| CN102759571A (en) * | 2011-04-29 | 2012-10-31 | 比亚迪股份有限公司 | Product quality test process and test device |
| CN102967817A (en) * | 2011-09-01 | 2013-03-13 | 安凯(广州)微电子技术有限公司 | Testing system and testing method for chip audio module |
| CN104807540A (en) * | 2014-01-28 | 2015-07-29 | 致伸科技股份有限公司 | Noise inspection method and system |
-
2017
- 2017-06-23 CN CN201710486554.0A patent/CN107340054B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005283227A (en) * | 2004-03-29 | 2005-10-13 | Matsushita Electric Ind Co Ltd | Abnormal sound inspection method and its device |
| CN1959352A (en) * | 2005-11-02 | 2007-05-09 | 鸿富锦精密工业（深圳）有限公司 | System and method for testing buzzer |
| CN102759571A (en) * | 2011-04-29 | 2012-10-31 | 比亚迪股份有限公司 | Product quality test process and test device |
| CN102967817A (en) * | 2011-09-01 | 2013-03-13 | 安凯(广州)微电子技术有限公司 | Testing system and testing method for chip audio module |
| CN104807540A (en) * | 2014-01-28 | 2015-07-29 | 致伸科技股份有限公司 | Noise inspection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107340054A (en) | 2017-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9666183B2 (en) | Deep neural net based filter prediction for audio event classification and extraction | |
| Hines et al. | Robustness of speech quality metrics to background noise and network degradations: Comparing ViSQOL, PESQ and POLQA | |
| WO2016015461A1 (en) | Method and apparatus for detecting abnormal frame | |
| KR101430321B1 (en) | Method and system for determining a perceived quality of an audio system | |
| US9058821B2 (en) | Computer-readable medium for recording audio signal processing estimating a selected frequency by comparison of voice and noise frame levels | |
| WO2015034633A1 (en) | Method for non-intrusive acoustic parameter estimation | |
| Ward et al. | BSS Eval or PEASS? Predicting the perception of singing-voice separation | |
| US10089999B2 (en) | Frequency domain noise detection of audio with tone parameter | |
| CN106663450A (en) | Method of and apparatus for evaluating quality of a degraded speech signal | |
| CN107123427A (en) | A kind of method and device for determining sound quality | |
| CN112700399B (en) | Defect detection visualization method and system | |
| CN107340054B (en) | Method and device for testing noise of acoustic product | |
| Schaeffler et al. | Reliability of clinical voice parameters captured with smartphones–measurements of added noise and spectral tilt | |
| Rennies et al. | Loudness of complex time-varying sounds? A challenge for current loudness models | |
| JP6724290B2 (en) | Sound processing device, sound processing method, and program | |
| DK3232906T3 (en) | HEARING TEST SYSTEM | |
| CN115243183A (en) | Audio detection method, device and storage medium | |
| Mittag et al. | Single-ended packet loss rate estimation of transmitted speech signals | |
| Veras et al. | Speech quality enhancement based on spectral subtraction | |
| EP2958343B1 (en) | Apparatus for testing directionality in hearing instruments | |
| Zhu et al. | Relative Contribution of Frequency and Parameter Values to Selectivity for Interaural Correlation | |
| Yuhong et al. | Auditory attention based mobile audio quality assessment | |
| You et al. | Quality Evaluation | |
| US9729975B2 (en) | Apparatus for testing directionality in hearing instruments | |
| JP2005077885A (en) | Device and method for speech quality objective evaluation |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210721 Address after: 266104 No. 699, Jiangjun South Road, Rongcheng City, Weihai City, Shandong Province Patentee after: Rongcheng goer Technology Co.,Ltd. Address before: 266104 Room 308, North Investment Street Service Center, Laoshan District, Qingdao, Shandong. Patentee before: GOERTEK TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |