CN101154175A - Audio testing method and system combining with voice recognition - Google Patents
Audio testing method and system combining with voice recognition Download PDFInfo
- Publication number
- CN101154175A CN101154175A CNA2006101223619A CN200610122361A CN101154175A CN 101154175 A CN101154175 A CN 101154175A CN A2006101223619 A CNA2006101223619 A CN A2006101223619A CN 200610122361 A CN200610122361 A CN 200610122361A CN 101154175 A CN101154175 A CN 101154175A
- Authority
- CN
- China
- Prior art keywords
- speech
- test
- audio
- voice
- value
- 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.)
- Pending
Links
Images
Abstract
The invention discloses an audio frequency testing method and system with speech recognition, which carries out testing by comparing a numerical value inputted by a tester to the testing system according to the heard speech with a value assigned to the played speech in the testing system. That is to say, a speech is read from a speech database and assigned a corresponding value; then the system plays the read speech, after hearing the speech, the user inputs a value determined by the speech content in a data selecting unit which transmits the value to the system; at last the system judges whether the returned numerical value is consistent with the value assigned to the played speech, if they are consistent, the system outputs a 'pass' information and starts testing the next project; otherwise the system outputs an error information 'fail' and stops the audio frequency testing. The invention avoids man-made error in audio frequency testing, has easy realization, simple and reliable result.
Description
Technical field
The present invention relates to a kind of audio-frequency test, particularly a kind of method of testing and system in conjunction with speech recognition.
Background technology
For comprehensive testing apparatus, the perhaps audio performance of motherboard, at present, habitual a kind of mode promptly is the purpose that reaches by playing sound under operating system the audio-frequency test of equipment or motherboard, wherein, it can play sound file by exporting with L channel respectively by playout software, R channel output and three kinds of modes of left and right acoustic channels output, and realize test to audio frequency by the mode of recording playback, though these several modes all can realize the test to audio frequency, but it is all the sense of hearing that need examine the operator and judges whether this equipment or motherboard audio-frequency function be normal, because each is variant for everyone sense of hearing and identification capability, so under this kind mode, survey owing to human factor causes mistake extremely easily, thereby draw to the not objective test result that gets of audio frequency.
Summary of the invention
In view of the above problems, fundamental purpose of the present invention is to provide a kind of method and system that audio performance is tested of coming in conjunction with voice, it compares the purpose that reaches test by the tester according to the phonetic entry of hearing to the digital value of test macro and the value of giving the voice of playing in the test macro, this test is simple and practical, avoid artificially survey problem appearance by mistake, its result precision height.
In order to achieve the above object, the technical solution adopted in the present invention is:
A kind of audio testing method in conjunction with speech recognition, it comprises the steps: to set up a speech database in system; From speech database, read voice at random, and give its corresponding value; The system plays voice, and a data input window is provided; Select a numerical value according to the voice content of being play, and this numerical value of echo-plex is in system; Whether the numerical value that relatively returns is consistent with the value that the broadcast voice are endowed, if then the test of system output " pass " is by information for unanimity, system begins the test of next project; Otherwise, the then error message of output " fail ", the while also finishes this audio-frequency test.
In addition, the present invention also provides a kind of audio test system in conjunction with speech recognition, it comprises a speech data storage element, a test cell and a data selecting unit, again, this described test cell also comprises also that voice are chosen and assignment unit, a comparing unit and an output display unit.Wherein, described test cell is that an end is connected in the speech data storage element, and the other end then is connected to described data selecting unit; In addition, this described data selecting unit also is connected with a test subscriber unit, works as this test subscriber with order and can select input one numerical value in this data selecting unit hearing the voice that test macro is play.
Can realize the objective evaluation of audio performance by the present invention, and it is realized easily, reliable results, it reads voice at random, then value that voice were endowed and the user who reads at random compared according to the numerical value of being heard, avoided owing objective and problem appearance accurately owing to human factor causes test result in original test process, it is simple and reliable, has practical value.
Description of drawings
Fig. 1 is the process flow diagram of the audio testing method of a kind of speech recognition of the present invention;
Fig. 2 is the structure calcspar of the audio test system of a kind of speech recognition of the present invention.
Embodiment
With embodiment the present invention is described in further detail with reference to the accompanying drawings below.
Consult shown in Fig. 2, the audio test system of a kind of speech recognition of the present invention comprises that a speech data storage element 201, a data selecting unit 202 and an end are connected with this speech data storage element 201, the test cell 200 that the other end is connected with data selecting unit 202, and this described test cell 200 comprises that also voice are chosen and an assignment unit 2001 and a comparing unit 2002, and also comprises an output display unit 2003; In addition, this system also comprises a test subscriber unit 203, and this test subscriber unit 203 be connected in described data selecting unit in addition, and this test subscriber unit 203 is the test subscriber for choosing with the voice of described test cell 200 and assignment unit 2001 is connected.
Wherein, described data selecting unit 202 is with the data input window, offering the platform of user's one input value, and the numerical value of user's input is sent back in the test cell 200 of test macro, promptly offers the comparing unit 2002 of described test cell 200; In addition, described test cell 200 is for choosing by voice and assignment unit 2001 removes to read at random voice signal file 2011 from described speech data storage element 201, these described voice are chosen and 2001 pairs of these voice signal files 2011 in assignment unit carry out assignment, and the value that this institute composes is sent in this described comparing unit 2002 so that compare with the numerical value of the user's input that from data selecting unit 202, transmits, then by output display unit 2003 with this test result output and show.
In addition, again in conjunction with shown in Fig. 2, at described speech data storage element 201 is a database, wherein store some voice signal files 2011, and this described voice signal file 2011 can prerecord and montage is deposited in the data storage cell 201 by the user, and this described voice signal file 2011 all can just can be play by general media play software, as Windows Media Player, RealPlay or the like.In addition, described data selecting unit 202 is a numerical value input window.
Shown in Fig. 1, it is a kind of audio testing method of speech recognition.At first, set up a speech database (step 100) that stores some voice signal files in system, it is a speech data storage element 201; When audio-frequency test, the voice of test cell 200 choose and assignment unit 2001 can be earlier from speech data storage element 201 at random read a voice signal file 2011, simultaneously, this test macro is given this values of voice that read at random (step 101); Test cell 200 reads this voice signal file 2011 and by this voice signal file 2011 of media play software real-time play, simultaneously, this test macro starts this described data selecting unit 202 (step 102); The test subscriber is after hearing these broadcast voice, and according to the voice of being heard input value in described data selecting unit 202, test macro is with being about to this numerical value echo-plex (step 103) in the comparing unit 2002 of test cell 200; Under above-mentioned condition, the comparing unit 2002 of test cell 200 begins to contrast from speech value that voice are chosen and assignment unit 2001 reads at random and the numerical value that returns from data selecting unit 202, if both values are consistent, then promptly represent the information that audio-frequency test passes through by output display unit 2003 output one " Pass " printed words of test cell 200, test macro begins to carry out the test (step 104, step 105 and step 107) of next test event; If both values are inconsistent, then export the information (step 106) that the audio-frequency test mistake promptly represented in one " Fail " printed words, end of test (EOT).
The present invention is by reading voice at random from speech data storage element 201, and pass through its assignment, and combination compares with the numerical value that the user selects to be imported at the voice of the broadcast of being heard, reach the purpose of testing audio according to its comparative result, both realized test to audio performance, also reached the effect of an objective evaluation, avoided the situation of the artificial false judgment that causes under the existing audio-frequency test technology, this mode is at audio-frequency test, simple and reliable property.
Claims (6)
1. audio testing method in conjunction with speech recognition, it is characterized in that: it comprises the steps:
A) in system, set up a speech database;
B) in speech database, read voice at random, and give its corresponding value;
C) system plays voice, and a data input window is provided;
D) import a numerical value according to the voice content of being play, and this numerical value of echo-plex is in system;
Whether the numerical value that E) relatively returns consistent with the value that the broadcast voice are endowed, if result relatively be unanimity then the test of system's output " pass " is by information, system carries out the test of next test event.
2. a kind of according to claim 1 audio testing method in conjunction with speech recognition, it is characterized in that: described speech database comprises some speech datas.
3. a kind of according to claim 1 audio testing method in conjunction with speech recognition is characterized in that: in step e, if result relatively is inconsistent, and the then error message of system's output " fail ", the while also finishes this audio-frequency test.
4. audio test system in conjunction with speech recognition, it is characterized in that: comprise a speech data storage element, a test cell and a data selecting unit, wherein, described test cell one end is for to interconnect with described speech data storage element, and the other end then is to be connected in a data selecting unit.
5. as a kind of audio test system in conjunction with speech recognition as described in the claim 4, it is characterized in that: described test cell comprises that voice are chosen and assignment unit, a comparing unit and an output display unit.
6. as a kind of audio test system in conjunction with speech recognition as described in the claim 4, it is characterized in that: described data selecting unit also is connected to the test subscriber unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006101223619A CN101154175A (en) | 2006-09-25 | 2006-09-25 | Audio testing method and system combining with voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006101223619A CN101154175A (en) | 2006-09-25 | 2006-09-25 | Audio testing method and system combining with voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101154175A true CN101154175A (en) | 2008-04-02 |
Family
ID=39255848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006101223619A Pending CN101154175A (en) | 2006-09-25 | 2006-09-25 | Audio testing method and system combining with voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101154175A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101592693B (en) * | 2008-05-30 | 2013-11-06 | 鸿富锦精密工业（深圳）有限公司 | System and method for audio tests |
| WO2016165056A1 (en) * | 2015-04-13 | 2016-10-20 | 华为技术有限公司 | Board testing method, board and system |
| CN106559729A (en) * | 2015-09-25 | 2017-04-05 | 神讯电脑(昆山)有限公司 | MIC automatic recognition of speech test system and method |
| CN110335628A (en) * | 2019-06-28 | 2019-10-15 | 百度在线网络技术（北京）有限公司 | The tone testing method, apparatus and electronic equipment of smart machine |
| CN113094223A (en) * | 2021-04-14 | 2021-07-09 | 成都启英泰伦科技有限公司 | Method for detecting voice recognition module audio channel hardware function |
-
2006
- 2006-09-25 CN CNA2006101223619A patent/CN101154175A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101592693B (en) * | 2008-05-30 | 2013-11-06 | 鸿富锦精密工业（深圳）有限公司 | System and method for audio tests |
| WO2016165056A1 (en) * | 2015-04-13 | 2016-10-20 | 华为技术有限公司 | Board testing method, board and system |
| CN106559729A (en) * | 2015-09-25 | 2017-04-05 | 神讯电脑(昆山)有限公司 | MIC automatic recognition of speech test system and method |
| CN110335628A (en) * | 2019-06-28 | 2019-10-15 | 百度在线网络技术（北京）有限公司 | The tone testing method, apparatus and electronic equipment of smart machine |
| CN113094223A (en) * | 2021-04-14 | 2021-07-09 | 成都启英泰伦科技有限公司 | Method for detecting voice recognition module audio channel hardware function |
| CN113094223B (en) * | 2021-04-14 | 2023-05-02 | 成都启英泰伦科技有限公司 | Method for detecting hardware function of voice recognition module audio channel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103745731B (en) | A kind of speech recognition effect automatization test system and method for testing | |
| CN107274916B (en) | Method and device for operating audio/video file based on voiceprint information | |
| US7903510B2 (en) | Apparatus and method for reproducing audio file | |
| CN101714380B (en) | Testing device and testing method of audio file formats supported by audio player | |
| CN104065928B (en) | A kind of behavior pattern statistic device and method | |
| CN108597494A (en) | Tone testing method and device | |
| US20090299699A1 (en) | Audio testing system and method | |
| CN110337055A (en) | Detection method, device, electronic equipment and the storage medium of speaker | |
| CN104123115A (en) | Audio information processing method and electronic device | |
| CN109712608B (en) | Multi-sound zone awakening test method, device and storage medium | |
| CN101374306A (en) | Method for prompting key-press sound of mobile phone keys | |
| CN104867494B (en) | The name sorting technique and system of a kind of recording file | |
| CN101154175A (en) | Audio testing method and system combining with voice recognition | |
| CN102014333A (en) | Test method for sound system of computer | |
| CN101540183A (en) | Playing device and audio output method | |
| CN101345047B (en) | Sound mixing system and method for automatic human voice correction | |
| CN106601220A (en) | Method and device for recording antiphonal singing of multiple persons | |
| CN110381336A (en) | Video clip emotion determination method, device and computer equipment based on 5.1 sound channels | |
| TW200948163A (en) | Method for manufacturing array microphones and system for categorizing microphones | |
| CN101819797B (en) | Electronic device with interactive audio recording function and recording method thereof | |
| CN101807415B (en) | Audio playing device with interactive function and interactive method thereof | |
| US9609277B1 (en) | Playback system of video conference record and method for video conferencing record | |
| CN110390954A (en) | Method and device for evaluating quality of voice product | |
| CN109243472A (en) | A kind of audio-frequency processing method and audio processing system | |
| CN109195072A (en) | Audio broadcasting control system and method based on automobile |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |