CN106571142A - Automobile navigation speech recognition rate automatic test system - Google Patents
Automobile navigation speech recognition rate automatic test system Download PDFInfo
- Publication number
- CN106571142A CN106571142A CN201610886353.5A CN201610886353A CN106571142A CN 106571142 A CN106571142 A CN 106571142A CN 201610886353 A CN201610886353 A CN 201610886353A CN 106571142 A CN106571142 A CN 106571142A
- Authority
- CN
- China
- Prior art keywords
- auto
- module
- test system
- phonetic recognization
- recognization rate
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 72
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000004891 communication Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 6
- 230000003247 decreasing effect Effects 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides an automobile navigation speech recognition rate automatic test system. The automobile navigation speech recognition rate automatic test system comprises an operation module and a speech recognition rate automatic test tool; the operation module is connected with the speech recognition rate automatic test tool; the speech recognition rate automatic testing tool is connected with an automobile navigator; the operation module is used for external command input, transmitting commands to a processing module, and displaying information fed-back by a processor; and the speech recognition rate automatic test tool is used for processing signals from the operation module so as to emit sound and collecting signals fed-back by the automobile navigator. With the automobile navigation speech recognition rate automatic test system adopted, manual labor in a speech test process can be greatly decreased, test quality can be improved, influence on measurement results caused by manual pronunciation factors can be prevented, the measurement results can be collected and put into statistics conveniently, speech test efficiency and quality can be greatly improved, and test costs can be significantly reduced.
Description
Technical field
The present invention relates to phonetic recognization rate field tests, more particularly to a kind of auto navigation phonetic recognization rate tests work automatically
Tool.
Background technology
At present, speech recognition technology has been enter into industry, household electrical appliances, communication, automotive electronics, medical treatment, home services, consumer electronics
The every field such as product, such as auto navigation, the increase of speech identifying function greatly increases driving safety, but for language
The test of sound discrimination but not systematic method of testing.
At present phonetic recognization rate method of testing is substantially all and adopts manual testing, particularly in the test of auto navigation,
Tester also needs to be carried out under different automobilism speed according to the reading of the word of one word of entry one, and identical entry
Read, because impact of the engine sound to voice is different under friction speed, need separately measurement, so considerably increase
The workload of manual testing.In addition, being easily caused language because the tone of test man, sound decibel are inconsistent in test process
The result of sound discrimination is inconsistent.I.e. during whole test, need to put into substantial amounts of man power and material, but obtain
Test result but be cannot be completely convincing.
The content of the invention
The problem to be solved in the present invention be how to solve the test of current artificial speech work repeatability it is big, thereby increases and it is possible to because
The measured deviation that test man's difference is caused.
In order to solve the above problems, the invention provides a kind of auto navigation phonetic recognization rate Auto-Test System, including
Operation module and phonetic recognization rate automatic testing instrument, described operation module is connected with phonetic recognization rate automatic testing instrument,
Phonetic recognization rate automatic testing instrument is connected with auto navigation, wherein described operation module is used for extraneous input instruction, will refer to
Order is transmitted to processing module, additionally it is possible to shown processor feedack;
Described phonetic recognization rate automatic testing instrument is used to send sound to the signal processing from operation module, and collects
From the signal of auto navigation feedback.The entry for needing test is input into by unified input equipment, by speech recognition
Have the unified audio of standard after the process of rate automatic testing instrument carries out the conversion of sound to testing entry, can accomplish testing
Ensure the concordance of tone harmony cent shellfish size in journey during different vocabulary tests, exclude because the problem of test source itself is made
Into the measurement error in measurement process, measurement quality can be preferably improved, in addition testing tool can also do to auto navigation
The judgement for going out is recorded, greatly reduce on the whole existing manual testing waste time and energy and test quality difference the characteristics of, and
It is with low cost.
Phonetic recognization rate automatic testing instrument includes processing module and audio-frequency module, described processing module and operation module
Connection, processing module is connected with auto navigation, and described audio-frequency module is connected with processing module, wherein described processing module is used
In processing from operation module and the information of auto navigation, instruction is sent to audio-frequency module;Described audio-frequency module is used to process
From the signal of processing module, and send sound.Specific phonetic recognization rate automatic testing instrument includes two parts, it is therefore an objective to
In order to preferably divide the work, on the one hand processor passes to audio processing modules and carries out sending out after the responsible information to input is processed
Sound, also on the other hand is responsible for being collected the information that auto navigation feeds back, and operation mould will be fed back to after information processing
Block.
Audio-frequency module includes loudspeaker drive division and loudspeaker, and described loudspeaker drive division is connected with processing module, described loudspeaker
Be connected with loudspeaker drive division.The entry signal that audio-frequency module is sent by receiving processing module, is converted and amplifies Chinese idiom
Message number, drives loudspeaker to carry out the generation of sound.Sound source during analog voice in this way, allows in auto navigation and connects
Quiet down sound, measures judgement.
Processing module is connected with auto navigation by connection.The effect of connection connection is to allow auto navigation to be known
Not afterwards by the information of identification to processing module transmission, allow processing module to judge the result of speech recognition, preserve as survey
Examination data.
Connection type is serial ports or USB.Data transfer can be faster carried out using serial ports, and uses USB interface then
With bigger versatility and portability, two kinds of different connection types can carry out selection under different scenes and use.
Operation module is PC ends or mobile terminal.It is can quickly to carry out word using the benefit at PC ends or mobile terminal
The input of bar, is also convenient in addition direct processing module and is shown after feedback of the information so that operator can be readily understood by surveying
Data during examination
Processing module includes process chip, and described process chip is DSP, ARM or MCU.The above-mentioned chip enumerated is with place
Reason function, and is the common and conventional chip in foot position on the market, the characteristics of with versatility height, good stability, and price
It is relatively reasonable, can be cost-effective.
Audio-frequency module includes audio processing chip, and described audio processing chip is DSP, ARM or FPGA.It is above-mentioned to enumerate
Chip carries Audio Processing function, and is the common and conventional chip in foot position on the market, high with versatility, good stability
The characteristics of, and price is relatively reasonable, and can be cost-effective.
Processing module is provided with data output interface.Data output interface is provided with, can be by the generation in test process
Test data is derived, and facilitates tester to be for further processing data.
The present invention has following beneficial effect:
1. a large amount of repeater's power machinery work are reduced.By using mechanical sounding, the heavy labor of manual testing's voice is solved
It is dynamic.
2. the quality of detection is improve.Because by mechanical sounding, it is ensured that the effect of sounding, reducing because sounding is inaccurate
Or pronounce wrong and affect test result, it is ensured that the unitary variant of test.
3. the efficiency of detection is improve.Because using the character input modes of operation module, and word input can be direct
Input, greatly improves the efficiency of detection.
4. the trouble of artificial data record is reduced.In test process operation module can record automatically auto navigation institute it is defeated
The judgement vocabulary for going out, and judged with the vocabulary of input, and will determine that result automatically records, solve heavy record
Work.
Description of the drawings
Fig. 1 is a kind of structured flowchart of auto navigation phonetic recognization rate Auto-Test System of the invention.
Specific embodiment
Presently preferred embodiments of the present invention is described in detail below in conjunction with the accompanying drawings so that the present invention a little with feature more
Easily it is readily appreciated by one skilled in the art, so as to make apparent defining to protection scope of the present invention.
Embodiment 1
As shown in Figure 1, its structure of a kind of auto navigation phonetic recognization rate Auto-Test System of the invention is specifically by operation module,
Processing module, loudspeaker drive division and loudspeaker are constituted, and operation module is connected with processing module both-way communication, and processing module, loudspeaker drive
Dynamic portion and loudspeaker are sequentially connected.By sending acoustical signal to auto navigation, auto navigation is obtained loudspeaker after itself judgement
The result of speech recognition, the result leads processing module by the transmission of connection, and processing module is surveyed through the comparison of information
The result of examination, and result is fed back to into operation module shown.
After the completion of test, test data can be led by being related to the data output interface in processing module
Go out.
Embodiment 2
As described in Figure 1, when test starts, test man is input into after corresponding entry in operation module, and operation module will be input into
Entry send to processing module and processed, on the one hand processing module is carried out after entry information is received to input information
Preserve, on the other hand the entry information that this is input into is sent to loudspeaker drive division, loudspeaker drive division leads entry information in reception
Afterwards after audio processing chip carries out Audio Processing, the information to sending is amplified, and produces this input word by loudspeaker
The pronunciation of bar, by spreading out of in loudspeaker, now, auto navigation can receive acoustic information and carry out receiving what is led sound
Information is identified, meanwhile, because during automobile is currently running, the GPS in auto navigation can be recorded in record input language
The path travelled during sound, so as to calculate the Vehicle Speed in Recording Process, the information of integrated voice record
With calculated velocity information, auto navigation to vocabulary make identification after, can be by the velocity information for calculating and recognition result
Transmitted into processing module by connection string, the process chip in processing module will receive the voice identification result and test led
The result of input is compared, and judgement identifies whether correctly, and speed information, and by this test feedback of the information to behaviour
Make module, you can carry out the tone testing in next cycle.
After the completion of test, tester can lead to the data output interface being arranged in processing module and enter test data
Row is derived, and is carried out data analysiss and is used.
Embodiment 3
It is when audio processing modules carry out signal processing, male voice can be processed into and adjusted or female voice with the difference of embodiment 2
Adjust, and the size of signal can be adjusted, i.e., can control the tone height and sound size of loudspeaker output sound.
Embodiments of the present invention are explained in detail above in conjunction with accompanying drawing, but the present invention is not limited to above-mentioned enforcement
Mode, in the ken that those of ordinary skill in the art possess, can be with the premise of without departing from present inventive concept
Various changes can be made.
Claims (9)
1. a kind of auto navigation phonetic recognization rate Auto-Test System, it is characterised in that including operation module and phonetic recognization rate
Automatic testing instrument, described operation module is connected with phonetic recognization rate automatic testing instrument, and phonetic recognization rate tests work automatically
Tool is connected with auto navigation, wherein
Described operation module is used for extraneous input instruction, and instruction is transmitted to processing module, additionally it is possible to feed back processor
Information is shown;
Described phonetic recognization rate automatic testing instrument is used to send sound to the signal processing from operation module, and collects
From the signal of auto navigation feedback.
2. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described voice
Discrimination automatic testing instrument includes processing module and audio-frequency module, and described processing module is connected with operation module, processes mould
Block is connected with auto navigation, and described audio-frequency module is connected with processing module, wherein
Described processing module is used to process from operation module and the information of auto navigation, sends instruction to audio-frequency module;
Described audio-frequency module is used to process the signal from processing module, and sends sound.
3. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described audio frequency
Module includes loudspeaker drive division and loudspeaker, and described loudspeaker drive division is connected with processing module, and described loudspeaker drive with loudspeaker
Portion connects.
4. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described process
Module is connected with auto navigation by connection.
5. auto navigation phonetic recognization rate Auto-Test System according to claim 4, it is characterised in that described communication
Line type is serial ports or USB.
6. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described operation
Module is PC ends or mobile terminal.
7. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described process
Module includes process chip, and described process chip is DSP, ARM or MCU.
8. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described audio frequency
Module includes audio processing chip, and described audio processing chip is DSP, ARM or FPGA.
9. auto navigation phonetic recognization rate Auto-Test System according to claim 1, it is characterised in that described process
Module is provided with data output interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610886353.5A CN106571142A (en) | 2016-10-11 | 2016-10-11 | Automobile navigation speech recognition rate automatic test system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610886353.5A CN106571142A (en) | 2016-10-11 | 2016-10-11 | Automobile navigation speech recognition rate automatic test system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106571142A true CN106571142A (en) | 2017-04-19 |
Family
ID=58531827
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610886353.5A Pending CN106571142A (en) | 2016-10-11 | 2016-10-11 | Automobile navigation speech recognition rate automatic test system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106571142A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108511000A (en) * | 2018-03-06 | 2018-09-07 | 福州瑞芯微电子股份有限公司 | A kind of test intelligent sound box wakes up the method and system of word discrimination |
CN109256115A (en) * | 2018-10-22 | 2019-01-22 | 四川虹美智能科技有限公司 | A kind of speech detection system and method for intelligent appliance |
CN110379426A (en) * | 2019-08-26 | 2019-10-25 | 北京汽车股份有限公司 | Vehicle-mounted voice system test device and tone testing system |
CN110503960A (en) * | 2019-09-26 | 2019-11-26 | 大众问问(北京)信息科技有限公司 | Uploaded in real time method, apparatus, equipment and the storage medium of speech recognition result |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080154590A1 (en) * | 2006-12-22 | 2008-06-26 | Sap Ag | Automated speech recognition application testing |
DE102009059138A1 (en) * | 2009-12-19 | 2010-07-29 | Daimler Ag | Test system for automatic testing of speech recognition system in motor vehicle, has application programming interface connected to speech recognition system to be tested and designed as logical abstraction layer |
CN102723080A (en) * | 2012-06-25 | 2012-10-10 | 惠州市德赛西威汽车电子有限公司 | Voice recognition test system and voice recognition test method |
CN202710079U (en) * | 2012-06-28 | 2013-01-30 | 惠州市德赛西威汽车电子有限公司 | Navigation voice guidance automatic testing system based on voice recognition technology |
CN103578463A (en) * | 2012-07-27 | 2014-02-12 | 腾讯科技(深圳)有限公司 | Automatic testing method and automatic testing device |
CN103745731A (en) * | 2013-12-31 | 2014-04-23 | 安徽科大讯飞信息科技股份有限公司 | Automatic voice recognition effect testing system and automatic voice recognition effect testing method |
-
2016
- 2016-10-11 CN CN201610886353.5A patent/CN106571142A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080154590A1 (en) * | 2006-12-22 | 2008-06-26 | Sap Ag | Automated speech recognition application testing |
DE102009059138A1 (en) * | 2009-12-19 | 2010-07-29 | Daimler Ag | Test system for automatic testing of speech recognition system in motor vehicle, has application programming interface connected to speech recognition system to be tested and designed as logical abstraction layer |
CN102723080A (en) * | 2012-06-25 | 2012-10-10 | 惠州市德赛西威汽车电子有限公司 | Voice recognition test system and voice recognition test method |
CN202710079U (en) * | 2012-06-28 | 2013-01-30 | 惠州市德赛西威汽车电子有限公司 | Navigation voice guidance automatic testing system based on voice recognition technology |
CN103578463A (en) * | 2012-07-27 | 2014-02-12 | 腾讯科技(深圳)有限公司 | Automatic testing method and automatic testing device |
CN103745731A (en) * | 2013-12-31 | 2014-04-23 | 安徽科大讯飞信息科技股份有限公司 | Automatic voice recognition effect testing system and automatic voice recognition effect testing method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108511000A (en) * | 2018-03-06 | 2018-09-07 | 福州瑞芯微电子股份有限公司 | A kind of test intelligent sound box wakes up the method and system of word discrimination |
CN108511000B (en) * | 2018-03-06 | 2020-11-03 | 福州瑞芯微电子股份有限公司 | Method and system for testing identification rate of awakening words of intelligent sound box |
CN109256115A (en) * | 2018-10-22 | 2019-01-22 | 四川虹美智能科技有限公司 | A kind of speech detection system and method for intelligent appliance |
CN110379426A (en) * | 2019-08-26 | 2019-10-25 | 北京汽车股份有限公司 | Vehicle-mounted voice system test device and tone testing system |
CN110503960A (en) * | 2019-09-26 | 2019-11-26 | 大众问问(北京)信息科技有限公司 | Uploaded in real time method, apparatus, equipment and the storage medium of speech recognition result |
CN110503960B (en) * | 2019-09-26 | 2022-02-11 | 大众问问(北京)信息科技有限公司 | Real-time uploading method, device and equipment of voice recognition result and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106571142A (en) | Automobile navigation speech recognition rate automatic test system | |
CN102857857B (en) | Loudspeaker box channel matching method of multi-channel wireless audio system | |
CN201403203Y (en) | Microphone electro-acoustic testing system | |
EP1299996B1 (en) | Speech quality estimation for off-line speech recognition | |
CN109326305B (en) | Method and system for batch testing of speech recognition and text synthesis | |
CN109547910B (en) | Electronic equipment acoustic assembly performance testing method, device, equipment and storage medium | |
CN104618846A (en) | Electronic product loudspeaker and microphone testing system and testing method | |
CN104538042A (en) | Intelligent voice test system and method for terminal | |
CN107907206A (en) | A kind of intrinsic frequency on-line detecting system | |
CN109187029A (en) | The abnormal sound position recognition positioning method and system of aero-engine | |
CN111276160A (en) | Audio detection method and device | |
CN201464092U (en) | Wireless stress tester of hydroelectric generator set | |
CN101336011A (en) | Microphone assembling test system and method thereof | |
CN110891236A (en) | Method and device for realizing production test of multi-microphone array | |
CN117577098A (en) | Voice communication method and system for satellite broadband short message communication | |
CN101645716A (en) | Vehicle-borne communication system having voice recognition function and recognition method thereof | |
CN204440902U (en) | Terminal intelligent tone testing system | |
CN202634696U (en) | Intelligent tester for electret microphone | |
CN206756741U (en) | A kind of blood glucose meter based on the communication of mobile device Lightning mouths | |
CN216356901U (en) | Vehicle-mounted information acquisition device for motorcycle examination | |
CN109900809A (en) | For the bed die of ultrasonic bonding quality testing, detection system and method | |
CN101409859B (en) | Method for measuring buzzer sensitivity | |
CN204961271U (en) | A noise mixing arrangement for slush pump failure diagnosis | |
CN111785113A (en) | Intelligent cable typical fault positioning simulation training system based on multi-dimensional information fusion | |
CN212463511U (en) | Accurate testing arrangement of wireless earphone silica gel cover |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170419 |