CN109785460A - Vehicle trouble recognition methods, device, computer equipment and storage medium - Google Patents
Vehicle trouble recognition methods, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109785460A CN109785460A CN201910003470.6A CN201910003470A CN109785460A CN 109785460 A CN109785460 A CN 109785460A CN 201910003470 A CN201910003470 A CN 201910003470A CN 109785460 A CN109785460 A CN 109785460A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- voice data
- trouble
- sound wave
- 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
Landscapes
- Telephonic Communication Services (AREA)
Abstract
This application involves voice recognition technologies, and in particular to a kind of vehicle trouble recognition methods, device, computer equipment and storage medium.The described method includes: acquiring the voice data of vehicle in the process of moving by mobile terminal;Processing is filtered to the voice data of acquisition, obtains vehicle sounds data relevant to the vehicle;Digitized processing is carried out to the vehicle sounds data, obtains vehicle audio data corresponding with the vehicle sounds data;Obtain the vehicle model information of the vehicle;According to the vehicle audio data and the vehicle model information, vehicle trouble messages corresponding with current vehicle are determined.Vehicle trouble recognition efficiency can be improved using this method.
Description
Technical field
This application involves technical field of vehicle, more particularly to a kind of vehicle trouble recognition methods, device, computer equipment
And storage medium.
Background technique
With the improvement of people ' s living standards with the progress of science and technology, more and more users select during trip
Vehicle is selected as walking-replacing tool.Vehicle due to user and does not know about vehicle in the process of moving it is possible that various problems
Construction or the relevant technologies can only send when vehicle breaks down in the process of moving to carrying out maintenance and inspection at vehicle maintenance.
Traditional vehicle trouble identification method is all to inquire fault condition to driver by professional technician, to vehicle
It is intuitively inspected, tentatively judges failure by rule of thumb, recycled diagnostic device further to screen, identify, finally confirm failure.But
Sometimes only temporarily there are some simple failures in the process of moving in vehicle, but nearby but can not find at vehicle maintenance
When, then it can not identify vehicle trouble, bring inconvenience to the trip of people.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of vehicle that can be improved vehicle trouble recognition efficiency
Fault recognition method, device, computer equipment and storage medium.
A kind of vehicle trouble recognition methods is applied to mobile terminal, which comprises
The voice data of vehicle in the process of moving is acquired by mobile terminal;
Processing is filtered to the voice data of acquisition, obtains vehicle sounds data relevant to the vehicle;
Digitized processing is carried out to the vehicle sounds data, obtains vehicle sound corresponding with the vehicle sounds data
Frequency evidence;
Obtain the vehicle model information of the vehicle;
According to the vehicle audio data and the vehicle model information, vehicle trouble corresponding with current vehicle is determined
Information.
A kind of vehicle trouble identification device, which is characterized in that described device includes:
Acquisition module, for acquiring the voice data of vehicle in the process of moving by mobile terminal;
Filter processing module obtains vehicle relevant to the vehicle for being filtered processing to the voice data of acquisition
Voice data;
Digital processing module obtains and the vehicle sound for carrying out digitized processing to the vehicle sounds data
The corresponding vehicle audio data of sound data;
Module is obtained, for obtaining the vehicle model information of the vehicle;
Determining module is used for according to the vehicle audio data and the vehicle model information, determining and current vehicle phase
Corresponding vehicle trouble messages.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
The voice data of vehicle in the process of moving is acquired by mobile terminal;
Processing is filtered to the voice data of acquisition, obtains vehicle sounds data relevant to the vehicle;
Digitized processing is carried out to the vehicle sounds data, obtains vehicle sound corresponding with the vehicle sounds data
Frequency evidence;
Obtain the vehicle model information of the vehicle;
According to the vehicle audio data and the vehicle model information, vehicle trouble corresponding with current vehicle is determined
Information.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
The voice data of vehicle in the process of moving is acquired by mobile terminal;
Processing is filtered to the voice data of acquisition, obtains vehicle sounds data relevant to the vehicle;
Digitized processing is carried out to the vehicle sounds data, obtains vehicle sound corresponding with the vehicle sounds data
Frequency evidence;
Obtain the vehicle model information of the vehicle;
According to the vehicle audio data and the vehicle model information, vehicle trouble corresponding with current vehicle is determined
Information.
Above-mentioned vehicle trouble recognition methods, device, computer equipment and storage medium acquire vehicle by mobile terminal and exist
Voice data in driving process is filtered processing to the voice data of acquisition, obtains vehicle sounds number relevant to vehicle
According to can filter out noise data in this way, improve the accuracy of vehicle trouble identification.Vehicle sounds data are digitized again
Processing, obtains corresponding vehicle audio data.And then it can be accurately determined according to vehicle audio data and vehicle model information
Vehicle trouble messages corresponding with current vehicle.In this way, can be realized by mobile terminal acquisition voice data quick, quasi-
Really, the fault message for easily determining current vehicle, is not limited by place and personnel, substantially increases the identification of vehicle trouble
Efficiency brings convenience for the trip of people.
Detailed description of the invention
Fig. 1 is the application scenario diagram of vehicle trouble recognition methods in one embodiment;
Fig. 2 is the flow diagram of vehicle trouble recognition methods in one embodiment;
Fig. 3 is the flow diagram of vehicle trouble recognition methods in another embodiment;
Fig. 4 is the structural block diagram of vehicle trouble identification device in one embodiment;
Fig. 5 is the structural block diagram of vehicle trouble identification device in another embodiment;
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Vehicle trouble recognition methods provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, it moves
Dynamic terminal 110 is communicated with server 120 by network.Vehicle 130 is communicated with mobile terminal 110 by network.With
Family can acquire the voice data of vehicle 130 in the process of moving by mobile terminal 110.The sound of 110 pairs of mobile terminal acquisitions
Data are filtered processing, obtain vehicle sounds data relevant to vehicle 130.Mobile terminal 110 to vehicle sounds data into
Digitized processing, obtains corresponding vehicle audio data.Mobile terminal 110 can be by vehicle audio data and vehicle model information
It is sent to server 120, vehicle trouble messages corresponding with current vehicle 130 are determined by server 120.
Wherein, terminal 110 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer
With portable wearable device, server 120 can use the server set of the either multiple server compositions of independent server
Group realizes.
In one embodiment, as shown in Fig. 2, providing a kind of vehicle trouble recognition methods, it is applied to Fig. 1 in this way
In mobile terminal for be illustrated, comprising the following steps:
S202 acquires the voice data of vehicle in the process of moving by mobile terminal.
Wherein, voice data is data relevant to sound, is the sonic data generated by object vibration.Specifically, when
Vehicle in the process of moving when, vehicle issue sound suspected malfunctions sound when, wherein suspected malfunctions sound such as vehicle startup
Machine exception sound of movement (not having oil such as, engine speed is abnormal, and product audio frequency is discontinuous), seat loosen sound, brake abnormal sound,
Car door abnormal sound, itself interior alarm etc., at this point, user can be acquired by the voice collection device (such as microphone) of mobile terminal
The voice data of vehicle in the process of moving.User can be by the voice collection device of mobile terminal closely close to sound source, to adopt
Collect true voice data.
In one embodiment, operation has vehicle trouble identification application in mobile terminal.When vehicle in the process of moving, hair
Out when suspected malfunctions sound, the openable vehicle trouble identification application of user identifies that sound collection is called in application by vehicle trouble
Device is to record current voice data.
In one embodiment, the vibration that voice data can be interpreted as in air, when data transmission in network telephony to movement
When the carbon film of the voice collection device (microphone) of terminal, carbon film can vibrate together with sound.And the carbon film of voice collection device
Under there are electrode, carbon film can contact electrode, time of contact length related (namely sound with the amplitude of vibration when vibration
Loudness), voice signal can be thus converted into electric signal, that is, acquire voice data.
S204 is filtered processing to the voice data of acquisition, obtains vehicle sounds data relevant to vehicle.
Wherein, vehicle sounds data relevant to vehicle refer to the sound that vehicle issues.It is appreciated that passing through mobile terminal
It may include noise data in the voice data of acquisition.Wherein, the sound of noise data such as people's one's voice in speech, music
Brake sound of sound, the tucket at crossing or adjacent vehicle etc..These noise datas, which can interfere, subsequent to be divided voice data
Analysis, it is therefore desirable to noise data is filtered out from the voice data of acquisition, to obtain the vehicle that clearly current vehicle issues
Voice data.
In one embodiment, mobile terminal can parse the voice data of acquisition, obtain sound wave.Mobile terminal can
Some noise sound waves, such as the sound of people's one's voice in speech, music etc. are stored in advance.Mobile terminal can make an uproar pre-stored
Speech wave is compared with the sound wave of acquisition, filters out and compares successful noise sound wave, to obtain vehicle relevant to vehicle
Voice data.
In one embodiment, when vehicle breaks down, for example automobile engine exception sound of movement (there is not oil, engine such as
Revolving speed is abnormal etc.), brake abnormal sound, car door abnormal sound etc., the sound that vehicle is issued is likely to sound regular, repeatedly
Sound.Therefore, mobile terminal can acquire the voice data in multiple periods when acquiring voice data.Mobile terminal can be according to sound
The frequency and waveform of sound wave in sound data determine a waveform of regular vibration in voice data.The wave of the regular vibration
Voice data corresponding to shape can be identified as vehicle sounds data relevant to vehicle.In turn, mobile terminal may filter that it
The voice data of his waveform.
S206 carries out digitized processing to vehicle sounds data, obtains vehicle audio corresponding with vehicle sounds data
Data.
Specifically, mobile terminal can carry out digitized processing to vehicle sounds data relevant to vehicle, by analog signal
It is converted into digital signal, obtains vehicle audio data.
In one embodiment, mobile terminal acquires voice data, that is, voice signal is converted to electric signal.It moves
The dynamic collected electric signal of terminal may be very weak, therefore available low noise operational amplifying circuit amplifies processing to sound.
In turn, sampling processing can be carried out to amplified vehicle sounds data.According to Nyquist's theorem (namely sampling theorem), press
The frequency of 2 times or more higher than sound highest frequency samples sound, that is, AD conversion (Analog-to-Digital
Convert, analog-to-digital conversion), analog signal is converted into digital signal.Quantization is finally carried out again and coded treatment obtains and vehicle
The corresponding binary code of voice data, specifically can be by the side PCM (Pulse Code Modulation, pulse code modulation)
Formula is quantified and is encoded.What this section of code indicated is exactly the intensity of upper sound at some time point.Namely by voice data
It is converted to digital signal, i.e. vehicle audio data.
S208 obtains the vehicle model information of vehicle.
Wherein, vehicle model information is information relevant to vehicle model, and vehicle model information includes vehicle identification code
(VIN, Vehicle Identification Number).Wherein, vehicle identification code includes manufacturer, age, vehicle, vehicle
The information such as body pattern and code, engine code and assembling place.Specifically, user can input vehicle identification in mobile terminal
Code, to obtain corresponding vehicle model information.
In one embodiment, step S208, that is, the step of obtaining the vehicle model information of vehicle specifically include: logical
It crosses mobile terminal and shows vehicle data input interface;Candidate vehicle model information is shown in information of vehicles input interface;Detection
Act on candidate vehicle model information chooses operation;When detect choose operation when, obtain to choose and operate acted on vehicle
Type information.
In one embodiment, mobile terminal can show vehicle data input interface, open up in information of vehicles input interface
Show candidate vehicle model information.In this way, user and can choose the vehicle type for meeting current vehicle in candidate vehicle model information
Number information.In one embodiment, input frame is also provided in information of vehicles input interface, user can input vehicle in input frame
Type information.
It, can be by choosing by showing candidate vehicle model information in information of vehicles input interface in above-described embodiment
The vehicle model information that current vehicle is determined from candidate vehicle model information is operated, it is convenient and efficient.
S210 determines vehicle trouble letter corresponding with current vehicle according to vehicle audio data and vehicle model information
Breath.
Wherein, vehicle trouble messages specifically may include the vehicle trouble analysis of causes and reparation suggestion etc..Implement at one
In example, mobile terminal can be analyzed vehicle audio data and vehicle model information in local, with determination and current vehicle phase
Corresponding vehicle trouble messages.Or vehicle audio data and vehicle model information can also be sent to server by mobile terminal,
Vehicle trouble messages corresponding with current vehicle are determined by server.
In one embodiment, mobile terminal or server can parse vehicle model information, obtain relevant to the vehicle
The information such as engine model, vehicle service life, vehicle manufacturers.Mobile terminal or server can be stored in advance and each vehicle type
Number corresponding vehicle trouble audio data.For example, when the automobile engine failure of A model, the voice data of automobile sending
Corresponding audio data is 01010101.And when the audio-frequency information that mobile terminal or server parse is: when 01010101,
Then illustrate that failure has occurred in the engine of the vehicle.
In one embodiment, step S210 is specifically included: determining that corresponding vehicle trouble is known according to vehicle model information
Other model;Vehicle audio data are input in vehicle trouble identification model, are exported by vehicle trouble identification model and vehicle
The corresponding fault category of audio data;Determine vehicle trouble messages corresponding with fault category.
In one embodiment, mobile terminal or server can according to vehicle trouble audio data sample gathered in advance and
Corresponding fault category, Lai Xunlian vehicle trouble identification model.Wherein, it is contemplated that different vehicle models, what vehicle was issued
Failure sound might have difference.Can corresponding failure audio data sample and correspondence be acquired for different vehicle models respectively
Fault category, then do model training respectively.Namely training vehicle trouble identification model corresponding with vehicle model.Specifically
Hidden Markov Model can be used as initial model, model training is carried out by training sample, to obtain and each vehicle model
Corresponding vehicle trouble identification model.
In one embodiment, for each vehicle trouble identification model, under type such as all can be used and be trained: determining
Vehicle trouble audio data sample and corresponding fault category label.Vehicle trouble audio data sample is input to initial vehicle
In fault identification model, class label belonging to vehicle trouble audio data sample is determined as the vehicle trouble identification model,
To using such distinguishing label as middle classification result.Compare the difference of middle classification result Yu fault category label, thus court
The direction of difference is reduced, the model parameter of vehicle trouble identification model is adjusted.If after adjusting model parameter, being unsatisfactory for training and stopping
Only condition then continues to train, and terminates to train when meeting training stop condition.In this way, the vehicle trouble identification that training obtains
Model is exactly trained vehicle trouble identification model.Wherein, training stop condition, which specifically can be, reaches preset iteration time
The classification performance index of vehicle trouble identification model after number, or adjustment model parameter reaches pre-set level etc..
In one embodiment, mobile terminal or server can determine that corresponding vehicle trouble is known according to vehicle model information
Other model.Vehicle audio data are input in trained vehicle trouble identification model again, pass through vehicle trouble identification model
Export fault category corresponding with vehicle audio data.And then vehicle trouble reason point corresponding with fault category is determined again
Analysis and corresponding repair are suggested.For example, vehicle audio data are input in trained vehicle trouble identification model, it is defeated
The fault category haveing is to start vehicle failure.Vehicle audio data vehicle model information is analyzed again, specific defect content can
It can be to start the engine speed in vehicle fault category abnormal.So suspected fault reason may be indicating oven temperature of engine, phase
The reparation suggestion answered finds anchor point parking such as to carry out natural cooling or think cooling etc..
In this way, determine corresponding vehicle trouble identification model according to vehicle model information, by vehicle trouble identification model,
Vehicle audio data are analyzed, can quickly and accurately determine vehicle trouble classification.
Above-mentioned vehicle trouble recognition methods acquires vehicle voice data in the process of moving by mobile terminal, to adopting
The voice data of collection is filtered processing, obtains vehicle sounds data relevant to vehicle, can filter out noise data in this way,
Improve the accuracy of vehicle trouble identification.Digitized processing is carried out to vehicle sounds data again, obtains corresponding vehicle audio number
According to.And then vehicle event corresponding with current vehicle can be accurately determined according to vehicle audio data and vehicle model information
Hinder information.In this way, by mobile terminal acquire voice data can realize quickly, accurately, easily determine current vehicle
Fault message is not limited by place and personnel, substantially increases the recognition efficiency of vehicle trouble, is brought for the trip of people
It is convenient.
In one embodiment, step S204, that is, be filtered processing to the voice data of acquisition, obtains and vehicle
The step of relevant vehicle sounds data, specifically includes: parsing voice data, determines and meets default rule vibration in voice data
First sound wave of condition;Obtain the second sound wave in voice data in addition to the first sound wave;It replicates the second sound wave and obtains duplicate sound wave;
It is overlapped processing after duplicate sound wave is postponed half of vibration period, with voice data, obtains vehicle sounds relevant to vehicle
Data.
Wherein, presetting regular vibration condition specifically can be sound wave regular vibration within a preset period of time.In a reality
It applies in example, includes vehicle sounds data relevant to vehicle and noise data in voice data.Wherein, noise data is such as
People's one's voice in speech, the sound of vehicle audio, the noise in roadside etc..It is understood that working as acquisition when acquiring voice data
When voice data in multiple periods, voice data relevant to vehicle will have certain rule.Therefore, mobile terminal can
According to the frequency and waveform of sound wave, a waveform of regular vibration in sonic data, that is, the first sound wave are determined.
Further, mobile terminal obtains the second sound wave in addition to the first sound wave from the voice data of acquisition.Here
Second sound wave is it can be understood that be noise sound wave.Reproducible second sound wave of mobile terminal obtains duplicate sound wave.Duplicate sound wave is prolonged
It is overlapped processing after slow half period, with voice data, mix up two same frequency sound waves makes a sound so together
The minimum point of the highest point of wave and another sound wave occurs in the same time, so that it may eliminate the sound wave, make an uproar to reach and filter
The effect of several waves, in this way, processing is overlapped after duplicate sound wave being postponed half of vibration period, with voice data
Obtain vehicle sounds data relevant to vehicle.
In above-described embodiment, by replicating other sound waves in addition to the sound wave of rule vibration, duplicate sound wave is obtained, then will answer
It is overlapped processing after half of vibration period of acoustical impedance processed, with voice data, can accurately and rapidly obtain filtering out noise
The vehicle sounds data of data.
In one embodiment, which further includes the steps that vehicle trouble is removed, and the step is specific
It include: that vehicle trouble messages are shown by mobile terminal;At position corresponding with the vehicle trouble messages of displaying, vehicle is shown
Fault clearance prompt information;Detection acts on the trigger action that shown vehicle trouble removes prompt information;It is touched when detecting
When hair operation, corresponding vehicle trouble clearance order is sent to vehicle;The vehicle trouble clearance order of transmission is used to indicate vehicle
Execute repair action.
It in one embodiment, can be after mobile terminal has determined vehicle trouble messages corresponding with current vehicle
Vehicle trouble messages are shown in the page.Meanwhile (for example, the positions such as lower section or right side) show vehicle around vehicle trouble messages
Fault clearance prompt information.When the user clicks or the corresponding vehicle trouble of pressing removes prompt information, mobile terminal can pass through
It is connected to the network to the onboard system of vehicle and sends vehicle trouble clearance order.The onboard system of vehicle receives vehicle trouble removing
Corresponding repair action can be performed after instruction.
For example, when the vehicle trouble messages that mobile terminal determines be seat position not just.Correspondingly, vehicle trouble removing mentions
Show information for adjustment seat.After vehicle trouble removes prompt information when the user clicks, mobile terminal can send to onboard system and adjust
The instruction of bed rearrangement chair sets back and sets correspondingly, onboard system can control seat.
In above-described embodiment, by detecting the trigger action for acting on vehicle trouble and removing prompt information, to be sent out to vehicle
Vehicle trouble clearance order is sent, for simple vehicle trouble, vehicle can be controlled by vehicle trouble clearance order and carried out automatically
It repairs, it is convenient and efficient.
In one embodiment, which further includes the steps that voice broadcast reparation is suggested, the step
It specifically includes: when user inquires that reparation relevant to vehicle trouble messages is suggested, acquiring user voice data;It obtains to user
Voice data carries out the obtained text of speech recognition;Word segmentation processing is carried out to text, obtains keyword word set;It is determining and crucial
Reparation suggestion corresponding to the matched vehicle trouble messages of word word set;By way of voice broadcast, output, which is repaired, to be suggested.
Wherein, speech recognition is that voice data is identified as to the process of text.Participle is will be with sentence or natural paragraph etc.
The text that form is presented is divided into the process of word one by one.
In one embodiment, when user inquires that reparation relevant to vehicle trouble messages is suggested, mobile terminal can lead to
It crosses voice collection device and records user voice data.Mobile terminal can carry out speech recognition to user voice data in local to obtain
User voice data can also be sent to server by the text after to identification, and server is by machine learning model to user's language
Sound data carry out speech recognition, obtain corresponding text and feed back to mobile terminal.
Further, segmentation methods can be used in mobile terminal or participle model segments text, after obtaining participle
Word.Word after participle is gone after stop words to polymerize composition keyword word set again.Wherein, stop words (Stop Words) refers specifically to
It is some using very extensive word, auxiliary words of mood, polite formula word, preposition or conjunction etc..
Wherein, there are many segmentation methods, for example, the segmentation methods based on string matching, the participle based on semantic analysis
Algorithm or the segmentation methods based on statistics etc..It is segmentation methods based on string matching such as Forward Maximum Method algorithm, reverse
Maximum matching algorithm, minimum segmentation algorithm or self-reinforcing in double directions.Participle model is trained to can be used to segment
Machine learning model, participle model specifically can be hidden Markov model or CRF (conditional random field
Algorithm, condition random field algorithm) model etc..
Further, mobile terminal can be stored in advance keyword set, vehicle trouble messages and repair the pass between suggesting
Join table.After mobile terminal has determined keyword word set, most matched vehicle can be successively looked into from contingency table by keyword word set
Fault message.And then determine that reparation corresponding with vehicle trouble messages is suggested again.Mobile terminal can pass through the side of voice broadcast
Formula, output, which is repaired, to be suggested.
In above-described embodiment, by acquiring user voice data, obtains and user voice data is carried out obtained by speech recognition
The text arrived.The keyword word set in text is determined again, and then determines that reparation corresponding with the vehicle trouble that user inquires is built
View, more intelligently can rapidly analyze user demand, and give suggestion.
As shown in figure 3, in a specific embodiment, the vehicle trouble recognition methods the following steps are included:
S302 acquires the voice data of vehicle in the process of moving by mobile terminal.
S304 parses voice data, determines the first sound wave for meeting default regular vibration condition in voice data.
S306 obtains the second sound wave in voice data in addition to the first sound wave.
S308, the second sound wave of duplication obtain duplicate sound wave.
S310 is overlapped processing after duplicate sound wave is postponed half of vibration period, with voice data, obtains and vehicle phase
The vehicle sounds data of pass.
S312 carries out digitized processing to vehicle sounds data, obtains vehicle audio corresponding with vehicle sounds data
Data.
S314 shows vehicle data input interface by mobile terminal.
S316 shows candidate vehicle model information in information of vehicles input interface.
S318, what detection acted on candidate vehicle model information chooses operation.
S320, when detect choose operation when, obtain to choose and operate acted on vehicle model information.
S322 determines corresponding vehicle trouble identification model according to vehicle model information.
Vehicle audio data are input in vehicle trouble identification model by S324, are exported by vehicle trouble identification model
Fault category corresponding with vehicle audio data.
S326 determines vehicle trouble messages corresponding with fault category.
S328 shows vehicle trouble messages by mobile terminal.
S330 shows vehicle fault clearance prompt information at position corresponding with the vehicle trouble messages of displaying.
S332, detection act on the trigger action that shown vehicle trouble removes prompt information.
S334 sends corresponding vehicle trouble clearance order to vehicle when detecting trigger action;The vehicle event of transmission
Barrier clearance order is used to indicate vehicle and executes repair action.
S336 acquires user voice data when user inquires that reparation relevant to vehicle trouble messages is suggested.
S338 is obtained and is carried out the obtained text of speech recognition to user voice data.
S340 carries out word segmentation processing to text, obtains keyword word set.
S342, determination and reparation suggestion corresponding to the matched vehicle trouble messages of keyword word set.
S344, by way of voice broadcast, output, which is repaired, to be suggested.
Above-mentioned vehicle trouble recognition methods acquires vehicle voice data in the process of moving by mobile terminal, to adopting
The voice data of collection is filtered processing, obtains vehicle sounds data relevant to vehicle, can filter out noise data in this way,
Improve the accuracy of vehicle trouble identification.Digitized processing is carried out to vehicle sounds data again, obtains corresponding vehicle audio number
According to.And then vehicle event corresponding with current vehicle can be accurately determined according to vehicle audio data and vehicle model information
Hinder information.In this way, by mobile terminal acquire voice data can realize quickly, accurately, easily determine current vehicle
Fault message is not limited by place and personnel, substantially increases the recognition efficiency of vehicle trouble, is brought for the trip of people
It is convenient.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of vehicle trouble identification device 400, comprising: acquisition module
401, filter processing module 402, digital processing module 403, acquisition module 404 and determining module 405, in which:
Acquisition module 401, for acquiring the voice data of vehicle in the process of moving by mobile terminal.
Filter processing module 402 obtains vehicle relevant to vehicle for being filtered processing to the voice data of acquisition
Voice data.
Digital processing module 403 obtains and vehicle sounds data for carrying out digitized processing to vehicle sounds data
Corresponding vehicle audio data.
Module 404 is obtained, for obtaining the vehicle model information of vehicle.
Determining module 405, for according to vehicle audio data and vehicle model information, determination to be corresponding with current vehicle
Vehicle trouble messages.
In one embodiment, acquisition module 401 is also used to parse voice data, determines and meets default rule in voice data
Restrain the first sound wave of vibration condition;Obtain the second sound wave in voice data in addition to the first sound wave;The second sound wave is replicated to be answered
Sound wave processed;It is overlapped processing after duplicate sound wave is postponed half of vibration period, with voice data, obtains vehicle relevant to vehicle
Voice data.
In one embodiment, module 404 is obtained to be also used to show vehicle data input interface by mobile terminal;In vehicle
Candidate vehicle model information is shown in data input interface;What detection acted on candidate vehicle model information chooses operation;When
Detect that when choosing operation, acquisition, which is chosen, operates acted on vehicle model information.
In one embodiment, determining module 405 is also used to determine that corresponding vehicle trouble is known according to vehicle model information
Other model;Vehicle audio data are input in vehicle trouble identification model, are exported by vehicle trouble identification model and vehicle
The corresponding fault category of audio data;Determine vehicle trouble messages corresponding with fault category.
In one embodiment, vehicle trouble identification device 400 further includes display module 406, detection module 407, sends
Module 408, in which:
Display module 406, for showing vehicle trouble messages by mobile terminal.
Display module 406 is also used at position corresponding with the vehicle trouble messages of displaying, shows vehicle fault clearance
Prompt information.
Detection module 407, for detecting the trigger action for acting on shown vehicle trouble and removing prompt information.
Sending module 408, for sending corresponding vehicle trouble clearance order to vehicle when detecting trigger action;
The vehicle trouble clearance order of transmission is used to indicate vehicle and executes repair action.
As shown in figure 5, in one embodiment, vehicle trouble identification device 400 further includes that word segmentation module 409 and voice are broadcast
Report module 410, in which:
Acquisition module 401 is also used to acquire user's language when user inquires that reparation relevant to vehicle trouble messages is suggested
Sound data.
Module 404 is obtained to be also used to obtain to the user voice data progress obtained text of speech recognition.
Word segmentation module 409 obtains keyword word set for carrying out word segmentation processing to text.
Determining module 405 is also used to reparation suggestion corresponding to the determining and matched vehicle trouble messages of keyword word set.
Voice broadcast module 410, for by way of voice broadcast, suggestion to be repaired in output.
Above-mentioned vehicle trouble identification device acquires vehicle voice data in the process of moving by mobile terminal, to adopting
The voice data of collection is filtered processing, obtains vehicle sounds data relevant to vehicle, can filter out noise data in this way,
Improve the accuracy of vehicle trouble identification.Digitized processing is carried out to vehicle sounds data again, obtains corresponding vehicle audio number
According to.And then vehicle event corresponding with current vehicle can be accurately determined according to vehicle audio data and vehicle model information
Hinder information.In this way, by mobile terminal acquire voice data can realize quickly, accurately, easily determine current vehicle
Fault message is not limited by place and personnel, substantially increases the recognition efficiency of vehicle trouble, is brought for the trip of people
It is convenient.
Specific about vehicle trouble identification device limits the limit that may refer to above for vehicle trouble recognition methods
Fixed, details are not described herein.Modules in above-mentioned vehicle trouble identification device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen, input unit and voice collection device.Wherein, the processor of the computer equipment is for providing calculating and control ability.It should
The memory of computer equipment includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operation
System and computer program.The built-in storage is that the operation of the operating system and computer program in non-volatile memory medium mentions
For environment.The network interface of the computer equipment is used to communicate with external terminal by network connection.The computer program quilt
To realize a kind of vehicle trouble recognition methods when processor executes.The display screen of the computer equipment can be liquid crystal display or
Person's electric ink display screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible to count
Key, trace ball or the Trackpad being arranged on machine equipment shell are calculated, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, memory is stored with meter
Calculation machine program, when computer program is executed by processor, so that the step of processor executes above-mentioned vehicle trouble recognition methods.This
The step of locating vehicle trouble recognition methods can be the step in the vehicle trouble recognition methods of above-mentioned each embodiment.
In one embodiment, a kind of computer readable storage medium is provided, computer program, computer journey are stored with
When sequence is executed by processor, so that the step of processor executes above-mentioned vehicle trouble recognition methods.Vehicle trouble identification side herein
The step of method, can be the step in the vehicle trouble recognition methods of above-mentioned each embodiment.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of vehicle trouble recognition methods is applied to mobile terminal, which comprises
The voice data of vehicle in the process of moving is acquired by mobile terminal;
Processing is filtered to the voice data of acquisition, obtains vehicle sounds data relevant to the vehicle;
Digitized processing is carried out to the vehicle sounds data, obtains vehicle audio number corresponding with the vehicle sounds data
According to;
Obtain the vehicle model information of the vehicle;
According to the vehicle audio data and the vehicle model information, vehicle trouble letter corresponding with current vehicle is determined
Breath.
2. being obtained the method according to claim 1, wherein the voice data of described pair of acquisition is filtered processing
To vehicle sounds data relevant to the vehicle, comprising:
The voice data is parsed, determines the first sound wave for meeting default regular vibration condition in the voice data;
Obtain the second sound wave in the voice data in addition to first sound wave;
It replicates second sound wave and obtains duplicate sound wave;
It is overlapped processing after the duplicate sound wave is postponed half of vibration period, with the voice data, is obtained and the vehicle
Relevant vehicle sounds data.
3. the method according to claim 1, wherein the vehicle model information for obtaining the vehicle includes:
Vehicle data input interface is shown by the mobile terminal;
Candidate vehicle model information is shown in the information of vehicles input interface;
What detection acted on the candidate vehicle model information chooses operation;
When detect it is described choose operation when, choose described in acquisition and operate acted on vehicle model information.
4. the method according to claim 1, wherein described according to the vehicle audio data and the vehicle type
Number information determines vehicle trouble messages corresponding with current vehicle, comprising:
Corresponding vehicle trouble identification model is determined according to the vehicle model information;
The vehicle audio data are input in the vehicle trouble identification model, it is defeated by the vehicle trouble identification model
Fault category corresponding with the vehicle audio data out;
Determine vehicle trouble messages corresponding with the fault category.
5. method according to any one of claims 1 to 4, which is characterized in that the method also includes:
The vehicle trouble messages are shown by the mobile terminal;
At position corresponding with the vehicle trouble messages of displaying, vehicle fault clearance prompt information is shown;
Detection acts on the trigger action that shown vehicle trouble removes prompt information;
When detecting the trigger action, Xiang Suoshu vehicle sends corresponding vehicle trouble clearance order;The vehicle sent
Fault clearance instruction is used to indicate the vehicle and executes repair action.
6. method according to any one of claims 1 to 4, which is characterized in that the method also includes:
When user inquires that reparation relevant to the vehicle trouble messages is suggested, user voice data is acquired;
It obtains and the obtained text of speech recognition is carried out to the user voice data;
Word segmentation processing is carried out to the text, obtains keyword word set;
Reparation suggestion corresponding to the determining and matched vehicle trouble messages of keyword word set;
By way of voice broadcast, exports the reparation and suggest.
7. a kind of vehicle trouble identification device, which is characterized in that described device includes:
Acquisition module, for acquiring the voice data of vehicle in the process of moving by mobile terminal;
Filter processing module obtains vehicle sound relevant to the vehicle for being filtered processing to the voice data of acquisition
Sound data;
Digital processing module obtains and the vehicle sounds number for carrying out digitized processing to the vehicle sounds data
According to corresponding vehicle audio data;
Module is obtained, for obtaining the vehicle model information of the vehicle;
Determining module, for according to the vehicle audio data and the vehicle model information, determination to be corresponding with current vehicle
Vehicle trouble messages.
8. device according to claim 7, which is characterized in that the filter processing module is also used to parse the sound number
According to determining the first sound wave for meeting default regular vibration condition in the voice data;It obtains in the voice data except described
The second sound wave outside first sound wave;It replicates second sound wave and obtains duplicate sound wave;The duplicate sound wave is postponed into half of vibration
It is overlapped processing after period, with the voice data, obtains vehicle sounds data relevant to the vehicle.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910003470.6A CN109785460A (en) | 2019-01-03 | 2019-01-03 | Vehicle trouble recognition methods, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910003470.6A CN109785460A (en) | 2019-01-03 | 2019-01-03 | Vehicle trouble recognition methods, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109785460A true CN109785460A (en) | 2019-05-21 |
Family
ID=66499869
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910003470.6A Pending CN109785460A (en) | 2019-01-03 | 2019-01-03 | Vehicle trouble recognition methods, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109785460A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110457394A (en) * | 2019-08-14 | 2019-11-15 | 浙江大搜车软件技术有限公司 | Vehicle information management method, apparatus, computer equipment and storage medium |
CN112306034A (en) * | 2019-08-02 | 2021-02-02 | 深圳市道通科技股份有限公司 | Automobile maintenance method, device and system |
CN113945393A (en) * | 2021-10-19 | 2022-01-18 | 上海仙塔智能科技有限公司 | Vehicle safety early warning method and device, electronic equipment and storage medium |
CN114279717A (en) * | 2021-11-18 | 2022-04-05 | 珠海零边界集成电路有限公司 | Vehicle fault detection method and device, electronic equipment and storage medium |
CN114842868A (en) * | 2021-02-02 | 2022-08-02 | 北京福田康明斯发动机有限公司 | Method and system for identifying abnormal noise source, electronic device and storage medium |
CN115185216A (en) * | 2022-07-18 | 2022-10-14 | 江苏东久机械有限公司 | Agricultural machinery intelligence control unit |
CN115295009A (en) * | 2022-10-08 | 2022-11-04 | 深圳市轩宇车鼎科技有限公司 | Independent data-based self-elimination data instant analysis automobile diagnosis system |
CN116304863A (en) * | 2023-02-08 | 2023-06-23 | 北京北明数科信息技术有限公司 | Multi-data-fusion vehicle fault monitoring and early warning method, equipment and medium |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10144076A1 (en) * | 2001-09-07 | 2003-03-27 | Daimler Chrysler Ag | Method for early recognition and prediction of unit damage or wear in machine plant, particularly mobile plant, based on vibration analysis with suppression of interference frequencies to improve the reliability of diagnosis |
CN101063629A (en) * | 2006-04-25 | 2007-10-31 | 汤京乐 | Judging functional failure of electromechanical by speech recognition technology |
CN101782464A (en) * | 2010-03-03 | 2010-07-21 | 罗新宇 | Method and instrument thereof for acoustic diagnosis of automobile engine |
CN101848288A (en) * | 2010-04-19 | 2010-09-29 | 北京东微世纪科技有限公司 | Simulation noise reduction system and method for microphone |
CN201622112U (en) * | 2010-03-03 | 2010-11-03 | 罗新宇 | Automobile engine acoustics diagnosis instrument |
CN101983513A (en) * | 2008-07-30 | 2011-03-02 | 雅马哈株式会社 | Audio signal processing device, audio signal processing system, and audio signal processing method |
CN102385381A (en) * | 2011-09-30 | 2012-03-21 | 中联重科股份有限公司 | Fault early warning prompt system of operating equipment |
CN103575536A (en) * | 2012-07-23 | 2014-02-12 | 上海博泰悦臻电子设备制造有限公司 | Device and method for identifying vehicle failure |
JP2016090461A (en) * | 2014-11-07 | 2016-05-23 | 公益財団法人鉄道総合技術研究所 | Construction method for abnormality diagnostic functional model for sound of monitored object, and construction system therefor |
WO2016083687A1 (en) * | 2014-11-26 | 2016-06-02 | Peugeot Citroen Automobiles Sa | Diagnostics device for a motor vehicle |
CN205406087U (en) * | 2016-02-29 | 2016-07-27 | 武汉大学 | System of making an uproar that goes that can be used to automobile engine failure recognition |
CN106596123A (en) * | 2016-11-22 | 2017-04-26 | 东软集团股份有限公司 | Device fault diagnosis method, device fault diagnosis device, and device fault diagnosis system |
CN107458383A (en) * | 2016-06-03 | 2017-12-12 | 法拉第未来公司 | Use the vehicle trouble automatic detection of audio signal |
CN107521500A (en) * | 2017-09-05 | 2017-12-29 | 百度在线网络技术(北京)有限公司 | Information acquisition method and device |
CN107945576A (en) * | 2017-12-25 | 2018-04-20 | 重庆冀繁科技发展有限公司 | Vehicle trouble monitoring method |
CN108512716A (en) * | 2018-02-07 | 2018-09-07 | 深圳壹账通智能科技有限公司 | Method, system, computer equipment and the storage medium of reporting equipment information |
CN108958227A (en) * | 2018-08-09 | 2018-12-07 | 北京智行者科技有限公司 | Car fault diagnosis method |
CN108985466A (en) * | 2018-06-19 | 2018-12-11 | 深圳市元征科技股份有限公司 | A kind of vehicle maintenance method, apparatus and server |
CN109019349A (en) * | 2018-06-19 | 2018-12-18 | 上海振华重工(集团)股份有限公司 | fault detection method, detector, computer storage medium and crane |
-
2019
- 2019-01-03 CN CN201910003470.6A patent/CN109785460A/en active Pending
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10144076A1 (en) * | 2001-09-07 | 2003-03-27 | Daimler Chrysler Ag | Method for early recognition and prediction of unit damage or wear in machine plant, particularly mobile plant, based on vibration analysis with suppression of interference frequencies to improve the reliability of diagnosis |
CN101063629A (en) * | 2006-04-25 | 2007-10-31 | 汤京乐 | Judging functional failure of electromechanical by speech recognition technology |
CN101983513A (en) * | 2008-07-30 | 2011-03-02 | 雅马哈株式会社 | Audio signal processing device, audio signal processing system, and audio signal processing method |
CN101782464A (en) * | 2010-03-03 | 2010-07-21 | 罗新宇 | Method and instrument thereof for acoustic diagnosis of automobile engine |
CN201622112U (en) * | 2010-03-03 | 2010-11-03 | 罗新宇 | Automobile engine acoustics diagnosis instrument |
CN101848288A (en) * | 2010-04-19 | 2010-09-29 | 北京东微世纪科技有限公司 | Simulation noise reduction system and method for microphone |
CN102385381A (en) * | 2011-09-30 | 2012-03-21 | 中联重科股份有限公司 | Fault early warning prompt system of operating equipment |
CN103575536A (en) * | 2012-07-23 | 2014-02-12 | 上海博泰悦臻电子设备制造有限公司 | Device and method for identifying vehicle failure |
JP2016090461A (en) * | 2014-11-07 | 2016-05-23 | 公益財団法人鉄道総合技術研究所 | Construction method for abnormality diagnostic functional model for sound of monitored object, and construction system therefor |
WO2016083687A1 (en) * | 2014-11-26 | 2016-06-02 | Peugeot Citroen Automobiles Sa | Diagnostics device for a motor vehicle |
CN205406087U (en) * | 2016-02-29 | 2016-07-27 | 武汉大学 | System of making an uproar that goes that can be used to automobile engine failure recognition |
CN107458383A (en) * | 2016-06-03 | 2017-12-12 | 法拉第未来公司 | Use the vehicle trouble automatic detection of audio signal |
CN106596123A (en) * | 2016-11-22 | 2017-04-26 | 东软集团股份有限公司 | Device fault diagnosis method, device fault diagnosis device, and device fault diagnosis system |
CN107521500A (en) * | 2017-09-05 | 2017-12-29 | 百度在线网络技术(北京)有限公司 | Information acquisition method and device |
CN107945576A (en) * | 2017-12-25 | 2018-04-20 | 重庆冀繁科技发展有限公司 | Vehicle trouble monitoring method |
CN108512716A (en) * | 2018-02-07 | 2018-09-07 | 深圳壹账通智能科技有限公司 | Method, system, computer equipment and the storage medium of reporting equipment information |
CN108985466A (en) * | 2018-06-19 | 2018-12-11 | 深圳市元征科技股份有限公司 | A kind of vehicle maintenance method, apparatus and server |
CN109019349A (en) * | 2018-06-19 | 2018-12-18 | 上海振华重工(集团)股份有限公司 | fault detection method, detector, computer storage medium and crane |
CN108958227A (en) * | 2018-08-09 | 2018-12-07 | 北京智行者科技有限公司 | Car fault diagnosis method |
Non-Patent Citations (1)
Title |
---|
唐浩等: "基于支持向量机的发动机故障诊断", 《西安交通大学学报》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112306034A (en) * | 2019-08-02 | 2021-02-02 | 深圳市道通科技股份有限公司 | Automobile maintenance method, device and system |
WO2021023097A1 (en) * | 2019-08-02 | 2021-02-11 | 深圳市道通科技股份有限公司 | Automobile maintenance method and apparatus, and system therefor |
CN110457394A (en) * | 2019-08-14 | 2019-11-15 | 浙江大搜车软件技术有限公司 | Vehicle information management method, apparatus, computer equipment and storage medium |
CN114842868A (en) * | 2021-02-02 | 2022-08-02 | 北京福田康明斯发动机有限公司 | Method and system for identifying abnormal noise source, electronic device and storage medium |
CN113945393A (en) * | 2021-10-19 | 2022-01-18 | 上海仙塔智能科技有限公司 | Vehicle safety early warning method and device, electronic equipment and storage medium |
CN114279717A (en) * | 2021-11-18 | 2022-04-05 | 珠海零边界集成电路有限公司 | Vehicle fault detection method and device, electronic equipment and storage medium |
CN115185216A (en) * | 2022-07-18 | 2022-10-14 | 江苏东久机械有限公司 | Agricultural machinery intelligence control unit |
CN115295009A (en) * | 2022-10-08 | 2022-11-04 | 深圳市轩宇车鼎科技有限公司 | Independent data-based self-elimination data instant analysis automobile diagnosis system |
CN116304863A (en) * | 2023-02-08 | 2023-06-23 | 北京北明数科信息技术有限公司 | Multi-data-fusion vehicle fault monitoring and early warning method, equipment and medium |
CN116304863B (en) * | 2023-02-08 | 2024-06-11 | 北京北明数科信息技术有限公司 | Multi-data-fusion vehicle fault monitoring and early warning method, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109785460A (en) | Vehicle trouble recognition methods, device, computer equipment and storage medium | |
KR102272622B1 (en) | Deep learning based abnormal symptom detection system using mechanical sound of mechanical equipment | |
US8784311B2 (en) | Systems and methods of screening for medical states using speech and other vocal behaviors | |
US9579056B2 (en) | Screening for neurological disease using speech articulation characteristics | |
JP3940383B2 (en) | How to determine speech recognition accuracy | |
US20040015350A1 (en) | Determining speech recognition accuracy | |
CN109326305B (en) | Method and system for batch testing of speech recognition and text synthesis | |
JP2007004001A (en) | Operator answering ability diagnosing device, operator answering ability diagnosing program, and program storage medium | |
US6876964B1 (en) | Apparatus for detecting fatigue and doze by voice, and recording medium | |
WO2019119279A1 (en) | Method and apparatus for emotion recognition from speech | |
WO2006109268A1 (en) | Automated speech disorder detection method and apparatus | |
Enzinger et al. | Empirical test of the performance of an acoustic-phonetic approach to forensic voice comparison under conditions similar to those of a real case | |
JP2004534326A (en) | Method of providing settlement information and method and apparatus for dictation | |
CN112562724A (en) | Speech quality evaluation model, training evaluation method, system, device, and medium | |
Gong et al. | Vocalsound: A dataset for improving human vocal sounds recognition | |
CN116665845A (en) | User emotion self-testing system based on multi-mode data | |
CN114373452A (en) | Voice abnormity identification and evaluation method and system based on deep learning | |
JP2010160788A (en) | Method, system, and computer program for dynamically improving performance of interactive voice response system using complex event processor | |
CN110322587B (en) | Evaluation recording method, device and equipment in driving process and storage medium | |
ES2233350T3 (en) | METHODS AND APPLIANCES TO TEST THE INTEGRITY OF THE USER INTERFACE IN VOCALLY ACTIVATED DEVICES. | |
Toivanen et al. | Emotions in [a]: a perceptual and acoustic study | |
CN116013371A (en) | Neurodegenerative disease monitoring method, system, device and storage medium | |
Maniak et al. | Automated sound signalling device quality assurance tool for embedded industrial control applications | |
Dineley et al. | Towards robust paralinguistic assessment for real-world mobile health (mHealth) monitoring: an initial study of reverberation effects on speech | |
CN108762230A (en) | One kind being based on Embedded Portable automobile failure diagnosis device and method |
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: 20190521 |