CN208271559U - A kind of test device of voice recognition processing equipment - Google Patents
A kind of test device of voice recognition processing equipment Download PDFInfo
- Publication number
- CN208271559U CN208271559U CN201820244548.4U CN201820244548U CN208271559U CN 208271559 U CN208271559 U CN 208271559U CN 201820244548 U CN201820244548 U CN 201820244548U CN 208271559 U CN208271559 U CN 208271559U
- Authority
- CN
- China
- Prior art keywords
- module
- voice
- processing equipment
- recognition processing
- signal
- 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
Landscapes
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The utility model discloses a kind of test devices of voice recognition processing equipment, including power supply unit, information process unit, control unit and display unit, said supply unit is electrically connected with information process unit and control unit, described control unit is all connected with information process unit and display unit, described control unit is also connect with voice recognition processing equipment to be tested, the information process unit includes voice storage module, voice output module, signal receiving module, signal identification module and comparison module, the voice storage module is connect with voice output module, the signal receiving module is connected with signal identification module, the comparison module is connect with signal identification module and voice storage module, the voice output module, signal receiving module is connect with voice recognition processing equipment to be tested.Through the above technical solutions, test set can quickly be exported in the case where the scale of test set is bigger, do not need manually to be recorded again, testing efficiency is high.
Description
Technical field
The utility model relates to testing equipment field more particularly to a kind of test devices of voice recognition processing equipment.
Background technique
Speech recognition (Automatic speech recognition, ASR) be identified from speech waveform it is corresponding
The technology of word content is one of important technology of artificial intelligence field, and has been widely used in industry manufacture, family
In the industries such as electricity, vehicle electronics, medical treatment, smart home.Currently, speech recognition technology oneself be applied to each scene, for example, leading
Order is inputted using the voice of speech recognition technology identification user in boat system;Known in search engine or electric business platform using voice
The search key of other technology identification user speech input;Using the voice of speech recognition technology identification user's input to realize machine
Device people dialogue etc. scene, speech recognition technology are also applied to the voice entry system of smart television, and the voice of smart phone is defeated
Enter with identifying system etc..For any application scenarios exploitation speech recognition system online before use, being required to the language
Sound identifying system is tested for the property, that is, is tested the recognition accuracy of speech recognition system, thus according to performance
Test case determines whether current speech identifying system reaches online using standard, and can be according to recognition accuracy to speech recognition
System is improved appropriately.
Currently, when the test device of voice recognition processing equipment tests the performance of speech recognition system, need by
The voice command that user may issue allows man, woman, child with different tone colors etc. to read, and records at test set, by this
The test set manually recorded inputs in speech recognition system to be tested, quasi- with the identification of determination speech recognition system to be tested
True rate.The performance test methods of the speech recognition system can be rapidly completed in the case where test set scale is smaller.But
It is in the case that the scale for manually recording test set is bigger, then to take time and effort, be difficult the test quickly met the requirements
Collection, to influence the testing efficiency of speech recognition system, is unable to satisfy the demand that speech recognition system is quickly tested.
Utility model content
In view of the test device above shortcomings of current voice recognition processing equipment, the utility model provides a kind of language
The test device of sound identifying processing equipment, test set can be quickly exported in the case where the scale of test set is bigger, is not required to
It manually to be recorded again, testing efficiency is high.
In order to achieve the above objectives, the embodiments of the present invention adopt the following technical scheme that
A kind of test device of voice recognition processing equipment, including power supply unit, information process unit, control unit and aobvious
Show unit, said supply unit is electrically connected with information process unit and control unit, described control unit and information process unit
It is all connected with display unit, described control unit is also connect with voice recognition processing equipment to be tested, the information processing list
Member includes voice storage module, voice output module, signal receiving module, signal identification module and comparison module, the voice
Memory module is connect with voice output module, and the signal receiving module is connected with signal identification module, the comparison module with
Signal identification module is connected with voice storage module, the voice output module, signal receiving module with voice to be tested
The connection of identifying processing equipment, power supply are used to for the voltage of utility power being converted into and information process unit and control unit phase
The voltage of adaptation, control unit are used to information process unit, and display unit and voice recognition processing equipment to be tested carry out
It manages and controls, information process unit is used to and speech recognition apparatus to be tested carries out the transmission of audio signal, and to be measured
The recognition result of the speech recognition apparatus feedback of examination is handled, and display unit is used to show pair handled through information process unit
The running state parameter of the test result of speech recognition apparatus to be tested and speech recognition apparatus to be tested.Information processing list
The voice storage module of member is stored with the sound materials of the magnanimity containing multiple parameters, these parameters include sound library parameter, environment spy
Levy parameter and keyword parameter, sound library parameter refers to gender in initial voice signal, age, tone color, word speed and intonation etc.
Parameter, the voice parameter in the substantially initial voice signal of environment characteristic parameters, such as noise, reverberation, sense of hearing distance
Parameter, keyword parameter refer to the parameter of the expression specifying information content in initial voice signal, such as initial voice signal
It is a commodity to be scanned for, then keyword parameter then refers to the product name in initial voice signal, model etc., i.e.,
Whom sound library parameter refers to read the parameter of initial voice signal, and environment characteristic parameters refer to the ginseng that initial voice signal is read where
Number, keyword parameter refers to that parameter is initial voice signal read, under the synergistic effect of control unit, the voice of each parameter
Material is combined into initial voice signal as required, for example, voice recognition processing equipment to be tested is for automobile
Middle control navigation system, the environmental parameter that we select are stored in the compartment of the car in voice storage module when driving
Sound, sound when bus driving in compartment, the keyword parameter of selection is then place name, cell name, road name
Deng the word in expression place, the sound library parameter of selection is then 3-80 year old male, women, old man, child and with provincialism
Male, women, old man, child, initial voice signal is the voice signal after these parameter combinations, i.e., broadcasts in environmental parameter
In the case where putting, sound library parameter reads the voice signal that keyword parameter is formed, and voice output module is initial by above-mentioned formation
Transmitting voice signal to speech recognition apparatus, signal receiving module to corresponding time of voice recognition processing equipment to be tested and
Feedback time is recorded and is received, and is transferred to signal identification module, signal identification module identification after can by the result of identification,
The operating parameter etc. of corresponding time and voice recognition processing equipment to be tested is transferred to display unit and is shown, while
Recognition result can be transferred to comparison module to be compared with initial voice signal, comparison result is exported to control module, control
Molding block, which issues instruction, makes display unit show comparison result, and the magnanimity sound materials stored in above-mentioned voice storage device can be with
It is self-service under the action of control unit to be converted to satisfactory large scale test collection, it can satisfy industrial manufacture, household electrical appliances, vapour
The needs of the speech recognition of multiple industries such as vehicle electronic equipment, medical treatment, smart home and processing equipment test, do not need to carry out again
It is artificial to record, and continual can test, testing efficiency is high.
Preferably, said supply unit is equipped with first voltage conversion module, and the first voltage conversion module is deposited with voice
Storage module, voice output module, signal receiving module, signal identification module and comparison module and control unit are all connected with, and are supplied
The voltage of external power supply is converted into two kinds of specifications by electric unit, and a kind of specification and control unit required voltage are adapted, another
Kind specification and control unit required voltage are adapted.
Preferably, described control unit includes control module and second voltage conversion module, the control module and voice
Memory module, signal identification module and comparison module and display unit are all connected with, the second voltage conversion module with it is to be measured
The voice recognition processing equipment and display unit of examination are all connected with, and control module is used to manage and control voice storage module, signal
Identification module and comparison module and display unit can run according to the program of setting, and monitor their operation shape
State can find and handle in time if mistake occurs in the program of operation, and second voltage conversion module is used to first voltage
The voltage of the power supply of conversion module input is converted into the list adaptable with voice recognition processing equipment to be tested and display unit
Member, and power for it.
Preferably, the display unit includes display apparatus module and function panel module, the display apparatus module and function
Panel module is connect with control unit, and display apparatus module is used to make each result and to be tested language of the operator to identification
The parameter of the operating status of sound identifying processing equipment is observed, and function panel is used to show the voice recognition processing equipment of test
Operating status parameter, such as voltage, electric current.
Preferably, the information process unit language further includes speech recognition module, and the speech recognition module is deposited with voice
Module connection is stored up, speech recognition module is used to that operator is allowed to be instructed with voice input test, i.e. operator's voice for saying standard
The initial voice signal to be synthesized is defined, the sound being such as selected as environmental parameter in the automobile bodies of traveling.
Preferably, the voice output module is equipped with wireless communication device or signal wire interface, initial for transmitting
Voice signal.
Preferably, the wireless communication device is set as blue-tooth device.
Preferably, the signal receiving module is equipped with wireless communication device or signal wire interface, for transmitting through to be measured
Audio signal that the voice recognition processing equipment of examination identifies and treated.
Preferably, the signal wire interface is USB interface.
The advantages of the utility model is implemented: the utility model provides a kind of test device of voice recognition processing equipment, packet
Power supply unit, information process unit, control unit and display unit are included, said supply unit and information process unit and control are single
Member electrical connection, described control unit is all connected with information process unit and display unit, described control unit also with it is to be tested
The connection of voice recognition processing equipment, the information process unit include voice storage module, voice output module, signal reception mould
Block, signal identification module and comparison module, the voice storage module are connect with voice output module, the signal receiving module
It is connected with signal identification module, the comparison module is connect with signal identification module and voice storage module, the voice output
Module, signal receiving module are connect with voice recognition processing equipment to be tested, through the above technical solutions, can be in test set
Scale it is bigger in the case where quickly export test set, can satisfy industrial manufacture, household electrical appliances, vehicle electronics, medical treatment,
The needs of the speech recognition of multiple industries such as smart home and processing equipment test, do not need manually to be recorded again, test effect
Rate is high.
Detailed description of the invention
In order to illustrate more clearly of the technical scheme in the embodiment of the utility model, will make below to required in embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are merely some embodiments of the present invention,
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings
Other attached drawings.
Fig. 1 is a kind of schematic diagram of the test device of voice recognition processing equipment described in the utility model.
Specific embodiment
The following will be combined with the drawings in the embodiments of the present invention, carries out the technical scheme in the embodiment of the utility model
Clearly and completely describe, it is clear that the described embodiments are only a part of the embodiments of the utility model, rather than whole
Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are without making creative work
Every other embodiment obtained, fall within the protection scope of the utility model.
As shown in Figure 1, a kind of test device of voice recognition processing equipment, including power supply unit 1, information process unit 2,
Control unit 3 and display unit 4, said supply unit 1 are electrically connected with information process unit 2 and control unit 3, and the control is single
Member 3 is all connected with information process unit 2 and display unit 4, described control unit 3 also with voice recognition processing equipment to be tested
Connection, the information process unit 2 include voice storage module 21, voice output module 22, signal receiving module 23, signal knowledge
Other module 24 and comparison module 25, the voice storage module 21 are connect with voice output module 22, the signal receiving module
23 and signal identification module 24 connect, the comparison module 25 connect with signal identification module 24 and voice storage module 21, institute
It states voice output module 22, signal receiving module 23 to connect with voice recognition processing equipment to be tested, power supply is used to
The voltage of utility power is converted into the voltage adaptable with information process unit 2 and control unit 3, control unit 3 is used to pair
Information process unit 2, display unit 4 and voice recognition processing equipment to be tested are managed and control, information process unit 2
For carrying out the transmission of audio signal, and the knowledge to speech recognition apparatus feedback to be tested with speech recognition apparatus to be tested
Other result is handled, display unit 4 be used to show through information process unit 2 handle to speech recognition apparatus to be tested
The running state parameter of test result and speech recognition apparatus to be tested.The voice storage module 21 of information process unit 2 is deposited
The sound materials of the magnanimity containing multiple parameters are contained, these parameters include sound library parameter, environment characteristic parameters and keyword parameter,
Sound library parameter refers to gender in initial voice signal, age, the parameters such as tone color, word speed and intonation, and environment characteristic parameters are real
Voice parameter in the initial voice signal of matter, such as noise, reverberation, sense of hearing distance parameter, keyword parameter refers to
The parameter of expression specifying information content in initial voice signal, such as initial voice signal is to search to a commodity
Rope, then keyword parameter then refers to that whom the product name in initial voice signal, model etc., i.e. sound library parameter refer to read just
The parameter of beginning voice signal, environment characteristic parameters refer to the parameter that initial voice signal is read where, and keyword parameter refers to initially
What parameter voice signal read, and under the synergistic effect of control unit 3, the sound materials of each parameter are combined into as required
Initial voice signal, for example, voice recognition processing equipment to be tested is the middle control navigation system for automobile, we are selected
Environmental parameter is stored in the sound in the compartment of the car in voice storage module 21 when driving, vehicle when bus driving
Sound in compartment, the keyword parameter of selection are then place name, cell name, and road name etc. expresses the word in place, choosing
Sound library parameter is then 3-80 years old male, women, old man, child and male, women with provincialism, old man, small
Child, initial voice signal are the voice signals after these parameter combinations, i.e., in the case where environmental parameter plays, sound library parameter
The voice signal that keyword parameter is formed is read, the initial voice signal of above-mentioned formation is transferred to voice by voice output module 22
Identify equipment, signal receiving module 23 records the corresponding time of voice recognition processing equipment to be tested and feedback time
And reception, and be transferred to signal identification module 24, signal identification module 24 identify after can by the result of identification, the corresponding time and
The operating parameter etc. of voice recognition processing equipment to be tested is transferred to display unit 4 and is shown, while identification can also be tied
Fruit is transferred to comparison module 25 and is compared with initial voice signal, and comparison result is exported to control module, control module hair
Instruction makes display unit 4 show comparison result out, and the magnanimity sound materials stored in above-mentioned voice storage device can control
It is self-service under the action of unit 3 to be converted to satisfactory large scale test collection, it does not need manually to be recorded again, and can not
Intermittent test, testing efficiency are high.
Said supply unit 1 is equipped with first voltage conversion module, the first voltage conversion module and voice storage module
21, voice output module 22, signal receiving module 23, signal identification module 24 and comparison module 25 and control unit 3 connect
It connects, the voltage of external power supply is converted into two kinds of specifications by power supply unit 1, and a kind of specification is mutually fitted with 3 required voltage of control unit
It answers, another specification and 3 required voltage of control unit are adapted.
Described control unit 3 includes control module 31 and second voltage conversion module 32, the control module 31 and voice
Memory module 21, signal identification module 24 and comparison module 25 and display unit 4 are all connected with, the second voltage modulus of conversion
Block 32 is all connected with voice recognition processing equipment to be tested and display unit 4, and control module 31 is used to manage and control voice
Memory module 21, signal identification module 24 and comparison module 25 and display unit 4 can be run according to the program of setting,
And the operating status for monitoring them can find and handle in time if mistake occurs in the program of operation, second voltage conversion
Module 32 is used to for the voltage for the power supply that first voltage conversion module inputs being converted into and voice recognition processing equipment to be tested
The unit being adapted with display unit 4, and power for it.
The display unit 4 includes display apparatus module 41 and function panel module 42, the display apparatus module 41 and function
Panel module 42 is connect with control unit 3, and display apparatus module 41 is used to make operator to each result of identification and to be measured
The parameter of the operating status of the voice recognition processing equipment of examination is observed, and function panel is used to show at the speech recognition of test
Manage the parameter of the operating status of equipment, such as voltage, electric current.
2 language of information process unit further includes speech recognition module, the speech recognition module and voice storage module
21 connections, speech recognition module are used to that operator is allowed to be instructed with voice input test, i.e., operator says the voice of standard to desire
The initial voice signal of synthesis is defined, the sound being such as selected as environmental parameter in the automobile bodies of traveling.
The voice output module 22 is equipped with wireless communication device or signal wire interface, for transmitting initial voice letter
Number.
The wireless communication device is set as blue-tooth device.
The signal receiving module 23 is equipped with wireless communication device or signal wire interface, for transmitting through language to be tested
Audio signal that sound identifying processing equipment identifies and treated.
The signal wire interface is USB interface.
The advantages of the utility model is implemented: the utility model provides a kind of test device of voice recognition processing equipment, packet
Power supply unit, information process unit, control unit and display unit are included, said supply unit and information process unit and control are single
Member electrical connection, described control unit is all connected with information process unit and display unit, described control unit also with it is to be tested
The connection of voice recognition processing equipment, the information process unit include voice storage module, voice output module, signal reception mould
Block, signal identification module and comparison module, the voice storage module are connect with voice output module, the signal receiving module
It is connected with signal identification module, the comparison module is connect with signal identification module and voice storage module, the voice output
Module, signal receiving module are connect with voice recognition processing equipment to be tested, through the above technical solutions, can be in test set
Scale it is bigger in the case where quickly export test set, can satisfy industrial manufacture, household electrical appliances, vehicle electronics, medical treatment,
The needs of the speech recognition of multiple industries such as smart home and processing equipment test, do not need manually to be recorded again, test effect
Rate is high.
Above description is only a specific implementation of the present invention, but the protection scope of the utility model is not limited to
In this, any those skilled in the art is in technical scope disclosed by the utility model, the change that can readily occur in
Change or replace, should be covered within the scope of the utility model.Therefore, the protection scope of the utility model should be with described
Subject to scope of protection of the claims.
Claims (9)
1. a kind of test device of voice recognition processing equipment, which is characterized in that including power supply unit, information process unit, control
Unit and display unit processed, said supply unit are electrically connected with information process unit and control unit, described control unit and letter
Breath processing unit and display unit are all connected with, and described control unit is also connect with voice recognition processing equipment to be tested, described
Information process unit includes voice storage module, voice output module, signal receiving module, signal identification module and compares mould
Block, the voice storage module are connect with voice output module, and the signal receiving module is connected with signal identification module, described
Comparison module is connect with signal identification module and voice storage module, the voice output module, signal receiving module with to
The voice recognition processing equipment of test connects.
2. the test device of voice recognition processing equipment according to claim 1, which is characterized in that said supply unit is set
There is first voltage conversion module, the first voltage conversion module and voice storage module, voice output module, signal receive mould
Block, signal identification module and comparison module and control unit are all connected with.
3. the test device of voice recognition processing equipment according to claim 1, which is characterized in that described control unit packet
It includes control module and second voltage conversion module, the control module and voice storage module, signal identification module and compares mould
Block and display unit are all connected with, and the second voltage conversion module and voice recognition processing equipment to be tested and display are single
Member is all connected with.
4. the test device of voice recognition processing equipment according to claim 1, which is characterized in that the display unit packet
Display apparatus module and function panel module are included, the display apparatus module and function panel module are connect with control unit.
5. the test device of voice recognition processing equipment described in one of -4 according to claim 1, which is characterized in that the information
Processing unit further includes speech recognition module, and the speech recognition module is connect with voice storage module.
6. the test device of voice recognition processing equipment according to claim 1, which is characterized in that the voice output mould
Block is equipped with wireless communication device or signal wire interface.
7. the test device of voice recognition processing equipment according to claim 6, which is characterized in that the wireless communication dress
It installs as blue-tooth device.
8. the test device of voice recognition processing equipment according to claim 1, which is characterized in that the signal receives mould
Block is equipped with wireless communication device or signal wire interface.
9. the test device of voice recognition processing equipment according to claim 8, which is characterized in that the signal wire interface
For USB interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820244548.4U CN208271559U (en) | 2018-02-09 | 2018-02-09 | A kind of test device of voice recognition processing equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820244548.4U CN208271559U (en) | 2018-02-09 | 2018-02-09 | A kind of test device of voice recognition processing equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN208271559U true CN208271559U (en) | 2018-12-21 |
Family
ID=64675143
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201820244548.4U Active CN208271559U (en) | 2018-02-09 | 2018-02-09 | A kind of test device of voice recognition processing equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN208271559U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110164474A (en) * | 2019-05-08 | 2019-08-23 | 北京百度网讯科技有限公司 | Voice wakes up automated testing method and system |
CN112331213A (en) * | 2020-11-06 | 2021-02-05 | 深圳市欧瑞博科技股份有限公司 | Intelligent household equipment control method and device, electronic equipment and storage medium |
-
2018
- 2018-02-09 CN CN201820244548.4U patent/CN208271559U/en active Active
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110164474A (en) * | 2019-05-08 | 2019-08-23 | 北京百度网讯科技有限公司 | Voice wakes up automated testing method and system |
CN112331213A (en) * | 2020-11-06 | 2021-02-05 | 深圳市欧瑞博科技股份有限公司 | Intelligent household equipment control method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110136694A (en) | A kind of test device of voice recognition processing equipment | |
CN110853618B (en) | Language identification method, model training method, device and equipment | |
CN107516510A (en) | A kind of smart machine automated voice method of testing and device | |
CN208271559U (en) | A kind of test device of voice recognition processing equipment | |
CN107146612A (en) | Voice guide method, device, smart machine and server | |
CN210489237U (en) | Vehicle-mounted intelligent terminal voice control system | |
CN107554456A (en) | Vehicle-mounted voice control system and its control method | |
CN107097718A (en) | Active speech synthesizing device and the vehicles | |
DE112018006101T5 (en) | Dynamic registration of a user-defined wake-up key phrase for a speech-enabled computer system | |
CN110838285A (en) | System, method and device for terminal voice test | |
CN110348002A (en) | The system and method for realizing voice request | |
CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
CN106847291A (en) | Speech recognition system and method that a kind of local and high in the clouds is combined | |
CN109376363A (en) | A kind of real-time voice interpretation method and device based on earphone | |
CN104795065A (en) | Method for increasing speech recognition rate and electronic device | |
CN106328133A (en) | Voice response responding device | |
CN108492819A (en) | Language exercise method, apparatus, intelligent vehicle mounted terminal and storage medium | |
CN109147764A (en) | Voice interactive method, device, equipment and computer-readable medium | |
CN108091323A (en) | For identifying the method and apparatus of emotion from voice | |
CN107274900A (en) | Information processing method and its system for control terminal | |
CN110428835A (en) | A kind of adjusting method of speech ciphering equipment, device, storage medium and speech ciphering equipment | |
CN206856594U (en) | Active speech synthesizing device and the vehicles | |
CN101241872B (en) | A distributed online detection system for ultrasonic lead key connection quality | |
CN111710339A (en) | Voice recognition interaction system and method based on data visualization display technology | |
CN107566896A (en) | Multimedia messages recommend method and device, storage medium, terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |