CN108986811A - Voice recognition detection method, device and equipment - Google Patents
Voice recognition detection method, device and equipment Download PDFInfo
- Publication number
- CN108986811A CN108986811A CN201811009582.4A CN201811009582A CN108986811A CN 108986811 A CN108986811 A CN 108986811A CN 201811009582 A CN201811009582 A CN 201811009582A CN 108986811 A CN108986811 A CN 108986811A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- audio
- speech recognition
- information
- frequency information
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims description 22
- 238000012795 verification Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 6
- 230000015572 biosynthetic process Effects 0.000 description 5
- 238000003786 synthesis reaction Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007639 printing Methods 0.000 description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229910052710 silicon Inorganic materials 0.000 description 2
- 239000010703 silicon Substances 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a detection method, a device and equipment for voice recognition, which relate to the technical field of vehicle voice recognition, and the method comprises the following steps: after the vehicle is connected with a vehicle to be detected, acquiring vehicle type information of the vehicle; judging the voice configuration state of the vehicle according to the vehicle type information; sending audio information to a voice recognition server according to the determined voice configuration state; and receiving a detection result which is sent by the voice recognition server and used for carrying out voice recognition on the audio information. According to the invention, the preset vehicle type information is obtained according to the vehicle type information, so that the detection efficiency is improved; the voice recognition server for voice recognition detection can be judged and the audio information is sent for detection through the determined voice configuration state, then the detection result sent by the voice recognition server for voice recognition of the audio information is received, and the efficiency and the accuracy of voice recognition can be judged according to the detection result.
Description
Technical field
The present invention relates to the technical fields of vehicle audio identification, and in particular to a kind of detection method of speech recognition, device
And equipment.
Background technique
With the development of science and technology the continuous iteration of computer intelligence algorithm, speech recognition technology from consumption electronic product not
It is disconnected to be generalized to auto industry field, vehicle-mounted information and entertainment system integrated speech identifying system, to help driver to solve to drive a vehicle
The puzzlement being manually operated, such as making and receiving calls, Navigation Control and regulation skylight are inconvenient in journey, are brought more quick and safety
Operating method.
Under normal circumstances, according to voice principle, audio user is input to system, and system needs audio file being converted to text
Then this format text and local or cloud database is compared, determine the intention of user, then carries out control and holds
Row, and implementing result is broadcasted in a manner of voice.According to voice vehicle control function, vehicle-mounted information and entertainment system needs
It is dealt into middle layer and bottom after receiving application layer voice request, is sent to Full Vehicle System in the form of automobile bus signal, with
The components such as control air-conditioning, skylight are acted.But the speech recognition for being commonly provided with car networking includes that local and two sets of cloud is drawn
It holds up, the speech engine that do not network only includes local engine, and different types of engine, which is checked and accepted, needs largely manually macrocyclic test
It receives, in artificial recording, due to artificial otherness, everyone tone color of speaking, tone, loudness of a sound, word speed is different, and
Live mouth exhales the personnel of tissue to read aloud and inevitably generates mistake, the mood of the effect tested person personnel of pronunciation, volume and clarity
Directly affect, and the environment of factory testing cannot cover common noise scenarios, thus the test of offline voice frequency link and
Basic voice wake-up rate discrimination becomes a difficult point.And.The detection of speech recognition vehicle control needs manually to go to record
Sound determines whether to control success by the breakdown action of the movement of vehicle air conditioning, skylight, and the function of being controlled vehicle is more, directly
Connect the efficiency for influencing offline detection.
Therefore, detection method, device and the equipment of a kind of speech recognition are needed, it is offline can quickly to detect speech recognition
Accuracy, strong interference immunity reduce cost, improve detection efficiency.
Summary of the invention
The embodiment of the invention provides a kind of detection method of speech recognition, device and equipment, to solve artificial detection
The problem that time-consuming, interference is big, detection efficiency is low.
In order to solve the above technical problems, the embodiment of the invention provides a kind of detection methods of speech recognition, comprising:
After connecting with vehicle to be detected, the vehicle model information of vehicle is obtained；
According to the vehicle model information, the voice configuration status of vehicle is judged；
According to determining voice configuration status, audio-frequency information is sent to speech recognition server；
Receive the speech recognition server transmission carries out the testing result after speech recognition to the audio-frequency information.
Preferably, described according to the vehicle model information, judge that the voice configuration status of vehicle includes:
The vehicle model information and default vehicle model information are subjected to consistency desired result；
When passed the verification, obtain in the default vehicle model information with consistent first parameter configuration of the vehicle model information；
According to first parameter configuration, the voice configuration status of vehicle is judged.
Preferably, after described by the vehicle model information and default vehicle model information progress consistency desired result, the method
Further include:
When verification does not pass through, the second parameter configuration is obtained；
Preferably, described according to determining voice configuration status when the speech recognition server is vehicle, know to voice
Other server sends audio-frequency information
When determining voice configuration status is local voice configuration status, the first text information is obtained；
According to first text information, the first audio-frequency information in audio-frequency information is obtained；
First audio-frequency information is sent to the vehicle.
Preferably, described according to determining voice configuration status when the speech recognition server is cloud server, to
Speech recognition server sends audio-frequency information
When determining voice configuration status is cloud voice configuration status, the second text information is obtained；
According to second text information, the second audio-frequency information in audio-frequency information is obtained；
The second audio-frequency information is sent to the cloud server.
The embodiment of the invention also provides a kind of detection devices of speech recognition, comprising:
Module is obtained, for obtaining the vehicle model information of vehicle after connecting with vehicle to be detected；
Judgment module, for judging the voice configuration status of vehicle according to the vehicle model information；
Speech processing module, for sending audio-frequency information to speech recognition server according to determining voice configuration status；
First communication module carries out voice knowledge to the audio-frequency information for receive that the speech recognition server sends
Testing result after not.
Preferably, the judgment module includes:
Verification unit, for the vehicle model information and default vehicle model information to be carried out consistency desired result；
First parameter configuration unit, for when passed the verification, obtaining in the default vehicle model information and believing with the vehicle
Cease consistent first parameter configuration；
Judging unit, for judging the voice configuration status of vehicle according to first parameter configuration.
Preferably, the judgment module further include:
Second parameter configuration unit, for obtaining the second parameter configuration when verification does not pass through.
Preferably, when the speech recognition server is vehicle, the speech processing module includes:
First words art Database Unit, for obtaining the when determining voice configuration status is local voice configuration status
One text information；
First audio synthesizer unit, for according to first text information, obtaining the first audio letter in audio-frequency information
Breath；
First audio output unit, for sending first audio-frequency information to the vehicle.
Preferably, when the speech recognition server is cloud server, the speech processing module includes:
Second words art Database Unit, for obtaining the when determining voice configuration status is cloud voice configuration status
Two text informations；
Second audio synthesizer unit, for according to second text information, obtaining the second audio letter in audio-frequency information
Breath；
Second audio output unit, for sending the second audio-frequency information to the cloud server.
The embodiment of the invention also provides a kind of detection devices of speech recognition, comprising: memory, processor and is stored in
On memory and the computer program that can run on a processor, the processor are realized as above when executing the computer program
Step in the detection method of the speech recognition.
Compared with prior art, detection method, device and the equipment of a kind of speech recognition provided in an embodiment of the present invention, until
It has the advantages that less
By judging the voice configuration status of vehicle according to vehicle model information, available preset vehicle model information is mentioned
The efficiency of high detection；By audio-frequency information being sent to speech recognition server, according to determination according to determining voice configuration status
Voice configuration status, it can be determined that carry out the speech recognition server of speech recognition detection and send audio-frequency information and being examined
It surveys, then receive the speech recognition server transmission carries out the testing result after speech recognition to the audio-frequency information, can
To judge the efficiency and accuracy of speech recognition according to testing result.
Detailed description of the invention
Fig. 1 is the flow chart of detection method provided in an embodiment of the present invention；
Fig. 2 is the specific flow chart of detection method provided in an embodiment of the present invention；
Fig. 3 is the specific flow chart of detection method provided in an embodiment of the present invention；
Fig. 4 is the specific flow chart of detection method provided in an embodiment of the present invention；
Fig. 5 is the structural block diagram of detection device provided in an embodiment of the present invention；
Fig. 6 is the structural block diagram of detection device provided in an embodiment of the present invention；
Fig. 7 is the structural block diagram of detection device provided in an embodiment of the present invention；
Description of symbols:
1- obtains module, 2- judgment module, 21- verification unit, the first parameter configuration unit of 22-, 23- judging unit, 24-
Second parameter configuration unit, 3- speech processing module, 31- first talk about art Database Unit, the first audio synthesizer unit of 32-, 33-
First audio output unit, 34- second talk about art Database Unit, the second audio synthesizer unit of 35-, 36- the second audio output list
Member, the first communication module of 4-.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.In the following description, such as specific configuration is provided and the specific detail of component is only
In order to help comprehensive understanding the embodiment of the present invention.It therefore, it will be apparent to those skilled in the art that can be to reality described herein
Example is applied to make various changes and modifications without departing from scope and spirit of the present invention.In addition, for clarity and brevity, it is omitted pair
The description of known function and construction.
It should be understood that " one embodiment " or " embodiment " that specification is mentioned in the whole text mean it is related with embodiment
A particular feature, structure, or characteristic is included at least one embodiment of the present invention.Therefore, occur everywhere in the whole instruction
" in one embodiment " or " in one embodiment " not necessarily refer to identical embodiment.In addition, these specific features, knot
Structure or characteristic can combine in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be appreciated that the size of the serial number of following each processes is not meant to execute suitable
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the implementation without coping with the embodiment of the present invention
Process constitutes any restriction.
The embodiment of the invention provides a kind of detection methods of speech recognition, as shown in Figure 1, comprising:
Step S1 obtains the vehicle model information of vehicle after connecting with vehicle to be detected；
Step S2 judges the voice configuration status of vehicle according to the vehicle model information；
Step S3 sends audio-frequency information to speech recognition server according to determining voice configuration status；
Step S4, receive the speech recognition server transmission carries out the detection after speech recognition to the audio-frequency information
As a result.
The above embodiment of the present invention, it is available pre- by judging the voice configuration status of vehicle according to vehicle model information
The vehicle model information first set improves the efficiency of detection；By being sent out to speech recognition server according to determining voice configuration status
Audio-frequency information is sent, according to determining voice configuration status, it can be determined that carry out the speech recognition server of speech recognition detection simultaneously
It sends audio-frequency information to be detected, then receive the speech recognition server transmission carries out voice knowledge to the audio-frequency information
Testing result after not can judge the efficiency and accuracy of speech recognition according to testing result.Wherein, the speech recognition clothes
Business device includes vehicle and/or cloud server；The vehicle includes vehicle-mounted information and entertainment system, the vehicle-mounted information and entertainment system
It include: speech recognition system and the second communication module.
Illustrate the specific implementation process of above scheme below with reference to detailed process:
As shown in Fig. 2, the step S2 includes:
The vehicle model information and default vehicle model information are carried out consistency desired result by step S21；Wherein, vehicle model information is preset
Including multiple vehicle model informations, the default vehicle model information is the parameter information of preset different automobile types；When the default vehicle is believed
When being preset with the vehicle model information in breath, passes through for verification, then enter step S22；When there is no institute in the default vehicle model information
When stating vehicle model information, does not pass through for verification, then enter step S23.
Step S22 is obtained in the default vehicle model information and is joined with the vehicle model information consistent first when passed the verification
Number configuration；Wherein, first parameter configuration includes: type (including electret, silicon Mike etc.), the enunciator's information of microphone
(including wind is made an uproar, road for (including male, female, old man, children etc.), word speed (including quick, middling speed, at a slow speed etc.), loudness of a sound, distance, noise
Dry, tire is made an uproar) etc..Wherein, word speed set can according to be greater than the first word speed be it is quick, greater than the second word speed and be less than or wait
It is middling speed in the first word speed, is method setting at a slow speed less than or equal to the second word speed.
Step S23 obtains the second parameter configuration when verification does not pass through.Wherein, second parameter configuration is default vehicle
When the vehicle model information being not present in type information, what operator was artificially arranged, it can be selected according to the essential information of vehicle
Select the parameter that configuration meets vehicle needs.
Step S24 judges the voice configuration shape of vehicle according to first parameter configuration and second parameter configuration
State.Wherein, the voice configuration status includes: local voice configuration status and/or cloud voice configuration status.Judge vehicle
Voice configuration status is according to first parameter configuration, second parameter configuration and the on-vehicle information joy being integrated on vehicle
The determined property of speech SDK in music system obtains.
As shown in figure 3, the step S3 includes: when the speech recognition server is vehicle
Step S311 obtains the first text information when determining voice configuration status is local voice configuration status；Its
In, it include: the words art text collection such as local navigation, local music, radio, phone in the text information, it can also basis
Art text collection if actual set is different.
Step S312 obtains the first audio-frequency information in audio-frequency information according to first text information；Wherein, described
First audio-frequency information is the audio that processing synthesis is carried out according to first text information.
Step S313 sends first audio-frequency information to the vehicle.Wherein, the mode of transmission can be to pass through loudspeaking
Device carries out voice broadcasting, and the speech recognition system of the vehicle passes through the content that the voice received plays and carries out speech recognition.
As shown in figure 3, the step S3 includes: when the speech recognition server is cloud server
Step S321 obtains the second text information when determining voice configuration status is cloud voice configuration status；It is described
Second text information may include: the words art text collection such as Weather information, Flight Information, stock information, can also be according to reality
Art text collection if setting is different.
Step S322 obtains the second audio-frequency information in audio-frequency information according to second text information；Wherein, described
Second audio-frequency information is the audio that processing synthesis is carried out according to second text information.
Step S323 sends the second audio-frequency information to the cloud server.Wherein, second audio-frequency information is to pass through
The second communication module of the vehicle is sent to the cloud server.
As shown in figure 4, when the speech recognition server is vehicle and cloud server, it is described to be matched according to determining voice
State is set, sending audio-frequency information (i.e. step S3) to speech recognition server includes:
Step S331 obtains the when determining that voice configuration status is local voice configuration and when cloud voice configuration status
One text information and the second text information；
Step S332 obtains the first audio-frequency information in audio-frequency information according to first text information, meanwhile, according to
Second text information obtains the second audio-frequency information in audio-frequency information；
Step S333 sends first audio-frequency information to the vehicle, and sends the second sound to the cloud server
Frequency information.
Wherein, the step of when speech recognition server is vehicle and cloud server, is equivalent to while including determining
The step of voice configuration status is local voice configuration status and determines when voice configuration status is cloud voice configuration status.
In the step S4, comprising:
Receive the vehicle transmission carries out the first testing result after speech recognition to first audio-frequency information；With/
Or
Receive the second detection knot carried out after speech recognition to second audio-frequency information that the cloud server is sent
Fruit.
Wherein it is possible to the first testing result and/or the second testing result are printed, according to printing as a result, can be with
Judge whether speech recognition is correct, and the text information that can not be identified, in this, as the result of speech recognition detection.
The embodiment of the invention also provides a kind of detection devices of speech recognition, as shown in Figure 5, comprising:
Module 1 is obtained, for obtaining the vehicle model information of vehicle after connecting with vehicle to be detected；
Judgment module 2, for judging the voice configuration status of vehicle according to the vehicle model information；
Speech processing module 3, for sending audio letter to speech recognition server according to determining voice configuration status
Breath；
First communication module 4 carries out voice to the audio-frequency information for receive that the speech recognition server sends
Testing result after identification.
The above embodiment of the present invention, it is available pre- by judging the voice configuration status of vehicle according to vehicle model information
The vehicle model information first set improves the efficiency of detection；By being sent out to speech recognition server according to determining voice configuration status
Audio-frequency information is sent, according to determining voice configuration status, it can be determined that carry out the speech recognition server of speech recognition detection simultaneously
It sends audio-frequency information to be detected, then receive the speech recognition server transmission carries out voice knowledge to the audio-frequency information
Testing result after not can judge the efficiency and accuracy of speech recognition according to testing result.Wherein, the speech recognition clothes
Business device includes vehicle and/or cloud server；Wherein, the vehicle includes vehicle-mounted information and entertainment system, the on-vehicle information joy
Music system includes: speech recognition system and the second communication module；First communication module 4 is by communicating mould with the second of vehicle
Block connection, connection type can connect for mobile network's connection, wireless network connection, bluetooth connection with controller LAN.
In a specific embodiment of the invention, as shown in fig. 6, the judgment module 2 includes:
Verification unit 21, for the vehicle model information and default vehicle model information to be carried out consistency desired result；Wherein, vehicle is preset
Type information includes multiple vehicle model informations, and the default vehicle model information is the parameter information of preset different automobile types.
First parameter configuration unit 22, for when passed the verification, obtain in the default vehicle model information with the vehicle
Consistent first parameter configuration of information；Wherein, first parameter configuration includes: type (including the electret, silicon wheat of microphone
Gram etc.), enunciator's information (including male, female, old man, children etc.), word speed (including quick, middling speed, at a slow speed etc.), loudness of a sound, distance,
Noise (including wind is made an uproar, road is dry, tire is made an uproar) etc..Wherein, word speed set can according to be greater than the first word speed be it is quick, greater than the
Two word speeds and be less than or equal to the first word speed be middling speed, less than or equal to the second word speed be at a slow speed method setting.
Judging unit 23, for judging the voice configuration status of vehicle according to first parameter configuration.Wherein, described
Voice configuration status includes: local voice configuration status and/or cloud voice configuration status.Judge the voice configuration status of vehicle
It is according to the language in first parameter configuration, second parameter configuration and the vehicle-mounted information and entertainment system that is integrated on vehicle
The determined property of sound development kit obtains.
In a specific embodiment of the invention, as shown in fig. 6, the judgment module 2 further include:
Second parameter configuration unit 24, for obtaining the second parameter configuration when verification does not pass through.Wherein, described second
When is the vehicle model information is not present in default vehicle model information in parameter configuration, what operator was artificially arranged, it can be according to vehicle
Essential information carry out option and installment and meet the parameters of vehicle needs.
In a specific embodiment of the invention, as shown in fig. 7, when the speech recognition server is vehicle, the voice
Processing module 3 includes:
First words art Database Unit 31, for obtaining when determining voice configuration status is local voice configuration status
First text information；It wherein, include: the words art text such as local navigation, local music, radio, phone in the text information
Set, can also according to actual set it is different if art text collection.
First audio synthesizer unit 32, for obtaining the first audio in audio-frequency information according to first text information
Information；Wherein, wherein first audio-frequency information is the audio that processing synthesis is carried out according to first text information, described
Speech synthesis unit can form for digital audio processing chip.
First audio output unit 33, for sending first audio-frequency information to the vehicle.Wherein, the mode of transmission
It can be to carry out voice broadcasting by loudspeaker, the speech recognition system of the vehicle passes through the content that the voice received plays
Carry out speech recognition.
In a specific embodiment of the invention, when the speech recognition server is cloud server, the speech processes
Module 3 includes:
Second words art Database Unit 34, for obtaining when determining voice configuration status is cloud voice configuration status
Second text information；Second text information may include: the words art text set such as Weather information, Flight Information, stock information
Close, can also according to actual set it is different if art text collection.
Second audio synthesizer unit 35, for obtaining the second audio in audio-frequency information according to second text information
Information；Wherein, second audio-frequency information is the audio that processing synthesis is carried out according to second text information.
Second audio output unit 36, for sending the second audio-frequency information to the cloud server.Wherein, described second
Audio-frequency information is to be sent by the second communication module of the vehicle to the cloud server.
In a specific embodiment of the invention, first communication module 4 includes:
Receive the vehicle transmission carries out the first testing result after speech recognition to first audio-frequency information；With/
Or
Receive the second detection knot carried out after speech recognition to second audio-frequency information that the cloud server is sent
Fruit.
Wherein, the detection device of the speech recognition can also carry out communication connection, the on-vehicle information amusement with computer
System can carry out system upgrade by the detection device of the speech recognition, and the detection device of the speech recognition can be with
First testing result and/or the second testing result are printed by computer and printer, according to printing as a result, can sentence
Conclusion sound identifies whether correctly, and the text information that can not be identified, in this, as the result of speech recognition detection.Its
In, the communication connection can be mobile network's connection, wireless network connection and bluetooth connection；Also, pass through controller local
Net is attached with on-board automatic diagnosis system, can be with quick obtaining by the database of vehicle model information and default vehicle model information
The signal log of vehicle voice control, detection structure printing when can quasi- clock synchronization, with voice software log joint-detection.
In a specific embodiment of the invention, the detection device of the speech recognition can be placed in where the driver
On position, which is equipped with encapsulating structure, the acquisition module 1, judgment module 2, speech processing module 3 and the first communication module
4 are set in the encapsulating structure；The encapsulating structure can be designed with the morphosis of drive simulating person, in the encapsulation
Headrest positions in structure close to the driver's seat are equipped with microphone and loudspeaker, and the loudspeaker is for playing voice, institute
Microphone is stated for receiving voice.Wherein, the position on the encapsulating structure close to the headrest is also provided with fixing bundle band,
For being bonded the encapsulating structure with headrest fixation.Vehicle-mounted information and entertainment system on the vehicle is set to the headrest
On, all seats of full vehicle, flexible Application single microphone and multi-microphone can be simulated.
It should be noted that the embodiment of the device is device corresponding with the embodiment of the above method, the above method
Embodiment in all implementations suitable for the embodiment of the device, can also reach identical technical effect.
The embodiment of the invention also provides a kind of detection devices of speech recognition, comprising: memory, processor and is stored in
On memory and the computer program that can run on a processor, the processor are realized as above when executing the computer program
Either step in the detection method of the speech recognition.
The embodiment of the present invention, it is available to preset by judging the voice configuration status of vehicle according to vehicle model information
Vehicle model information, improve the efficiency of detection；By sending audio to speech recognition server according to determining voice configuration status
Information, according to determining voice configuration status, it can be determined that carry out the speech recognition server of speech recognition detection and send sound
Frequency information is detected, after then receive that the speech recognition server sends carries out speech recognition to the audio-frequency information
Testing result can judge the efficiency and accuracy of speech recognition according to testing result.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, several improvements and modifications can also be made, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (11)
1. a kind of detection method of speech recognition characterized by comprising
After connecting with vehicle to be detected, the vehicle model information of vehicle is obtained；
According to the vehicle model information, the voice configuration status of vehicle is judged；
According to determining voice configuration status, audio-frequency information is sent to speech recognition server；
Receive the speech recognition server transmission carries out the testing result after speech recognition to the audio-frequency information.
2. the detection method of speech recognition as described in claim 1, which is characterized in that it is described according to the vehicle model information, sentence
The voice configuration status of disconnected vehicle includes:
The vehicle model information and default vehicle model information are subjected to consistency desired result；
When passed the verification, obtain in the default vehicle model information with consistent first parameter configuration of the vehicle model information；
According to first parameter configuration, the voice configuration status of vehicle is judged.
3. the detection method of speech recognition as claimed in claim 2, which is characterized in that described by the vehicle model information and pre-
After if vehicle model information carries out consistency desired result, the method also includes:
When verification does not pass through, the second parameter configuration is obtained.
4. the detection method of speech recognition as described in claim 1, which is characterized in that the speech recognition server is vehicle
When, described according to determining voice configuration status, sending audio-frequency information to speech recognition server includes:
When determining voice configuration status is local voice configuration status, the first text information is obtained；
According to first text information, the first audio-frequency information in audio-frequency information is obtained；
First audio-frequency information is sent to the vehicle.
5. the detection method of speech recognition as described in claim 1, which is characterized in that the speech recognition server is cloud
When server, described according to determining voice configuration status, sending audio-frequency information to speech recognition server includes:
When determining voice configuration status is cloud voice configuration status, the second text information is obtained；
According to second text information, the second audio-frequency information in audio-frequency information is obtained；
The second audio-frequency information is sent to the cloud server.
6. a kind of detection device of speech recognition characterized by comprising
Module is obtained, for obtaining the vehicle model information of vehicle after connecting with vehicle to be detected；
Judgment module, for judging the voice configuration status of vehicle according to the vehicle model information；
Speech processing module, for sending audio-frequency information to speech recognition server according to determining voice configuration status；
First communication module, after carrying out speech recognition to the audio-frequency information for receive that the speech recognition server sends
Testing result.
7. the detection device of speech recognition as claimed in claim 6, which is characterized in that the judgment module includes:
Verification unit, for the vehicle model information and default vehicle model information to be carried out consistency desired result；
First parameter configuration unit, for when passed the verification, obtain in the default vehicle model information with the vehicle model information one
The first parameter configuration caused；
Judging unit, for judging the voice configuration status of vehicle according to first parameter configuration.
8. the detection device of speech recognition as claimed in claim 7, which is characterized in that the judgment module further include:
Second parameter configuration unit, for obtaining the second parameter configuration when verification does not pass through.
9. the detection device of speech recognition as claimed in claim 6, which is characterized in that the speech recognition server is vehicle
When, the speech processing module includes:
First words art Database Unit, for when determining voice configuration status is local voice configuration status, obtaining the first text
This information；
First audio synthesizer unit, for obtaining the first audio-frequency information in audio-frequency information according to first text information；
First audio output unit, for sending first audio-frequency information to the vehicle.
10. the detection device of speech recognition as claimed in claim 6, which is characterized in that the speech recognition server is cloud
When holding server, the speech processing module includes:
Second words art Database Unit, for when determining voice configuration status is cloud voice configuration status, obtaining the second text
This information；
Second audio synthesizer unit, for obtaining the second audio-frequency information in audio-frequency information according to second text information；
Second audio output unit, for sending the second audio-frequency information to the cloud server.
11. a kind of detection device of speech recognition characterized by comprising memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, the processor realize such as Claims 1 to 5 when executing the computer program
Step in the detection method of described in any item speech recognitions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009582.4A CN108986811B (en) | 2018-08-31 | 2018-08-31 | Voice recognition detection method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009582.4A CN108986811B (en) | 2018-08-31 | 2018-08-31 | Voice recognition detection method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108986811A true CN108986811A (en) | 2018-12-11 |
| CN108986811B CN108986811B (en) | 2021-05-28 |
Family
ID=64547736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811009582.4A Active CN108986811B (en) | 2018-08-31 | 2018-08-31 | Voice recognition detection method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108986811B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523990A (en) * | 2019-01-21 | 2019-03-26 | 未来电视有限公司 | Speech detection method and device |
| CN114401346A (en) * | 2022-01-13 | 2022-04-26 | 平安普惠企业管理有限公司 | Response method, device, equipment and medium based on artificial intelligence |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1619643A (en) * | 2003-09-04 | 2005-05-25 | 株式会社东芝 | Voice recognition estimating apparatus and method |
| CN1726532A (en) * | 2002-12-20 | 2006-01-25 | 国际商业机器公司 | Sensor based speech recognizer selection, adaptation and combination |
| JP2009265307A (en) * | 2008-04-24 | 2009-11-12 | Toyota Motor Corp | Speech recognition device and vehicle system using the same |
| CN103247291A (en) * | 2013-05-07 | 2013-08-14 | 华为终端有限公司 | Updating method, device, and system of voice recognition device |
| CN103617795A (en) * | 2013-10-31 | 2014-03-05 | 广东好帮手电子科技股份有限公司 | A vehicle-mounted voice recognition control method and a vehicle-mounted voice recognition control system |
| CN103839549A (en) * | 2012-11-22 | 2014-06-04 | 腾讯科技（深圳）有限公司 | Voice instruction control method and system |
| CN104535071A (en) * | 2014-12-05 | 2015-04-22 | 百度在线网络技术（北京）有限公司 | Voice navigation method and device |
| CN106043150A (en) * | 2016-08-04 | 2016-10-26 | 歌尔科技有限公司 | Vehicle-mounted projection system with speech recognition function |
| CN106057196A (en) * | 2016-07-08 | 2016-10-26 | 成都之达科技有限公司 | Vehicular voice data analysis identification method |
| CN106601244A (en) * | 2016-12-08 | 2017-04-26 | 深圳市元征科技股份有限公司 | Voice control method and system for vehicle diagnosis client |
| CN106992009A (en) * | 2017-05-03 | 2017-07-28 | 深圳车盒子科技有限公司 | Vehicle-mounted voice exchange method, system and computer-readable recording medium |
| CN107660303A (en) * | 2015-06-26 | 2018-02-02 | 英特尔公司 | The language model of local speech recognition system is changed using remote source |
| CN108091341A (en) * | 2017-11-28 | 2018-05-29 | 湖南海翼电子商务股份有限公司 | Audio signal processing method and vehicle electronic device |
-
2018
- 2018-08-31 CN CN201811009582.4A patent/CN108986811B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1726532A (en) * | 2002-12-20 | 2006-01-25 | 国际商业机器公司 | Sensor based speech recognizer selection, adaptation and combination |
| CN1619643A (en) * | 2003-09-04 | 2005-05-25 | 株式会社东芝 | Voice recognition estimating apparatus and method |
| JP2009265307A (en) * | 2008-04-24 | 2009-11-12 | Toyota Motor Corp | Speech recognition device and vehicle system using the same |
| CN103839549A (en) * | 2012-11-22 | 2014-06-04 | 腾讯科技（深圳）有限公司 | Voice instruction control method and system |
| CN103247291A (en) * | 2013-05-07 | 2013-08-14 | 华为终端有限公司 | Updating method, device, and system of voice recognition device |
| CN103617795A (en) * | 2013-10-31 | 2014-03-05 | 广东好帮手电子科技股份有限公司 | A vehicle-mounted voice recognition control method and a vehicle-mounted voice recognition control system |
| CN104535071A (en) * | 2014-12-05 | 2015-04-22 | 百度在线网络技术（北京）有限公司 | Voice navigation method and device |
| CN107660303A (en) * | 2015-06-26 | 2018-02-02 | 英特尔公司 | The language model of local speech recognition system is changed using remote source |
| CN106057196A (en) * | 2016-07-08 | 2016-10-26 | 成都之达科技有限公司 | Vehicular voice data analysis identification method |
| CN106043150A (en) * | 2016-08-04 | 2016-10-26 | 歌尔科技有限公司 | Vehicle-mounted projection system with speech recognition function |
| CN106601244A (en) * | 2016-12-08 | 2017-04-26 | 深圳市元征科技股份有限公司 | Voice control method and system for vehicle diagnosis client |
| CN106992009A (en) * | 2017-05-03 | 2017-07-28 | 深圳车盒子科技有限公司 | Vehicle-mounted voice exchange method, system and computer-readable recording medium |
| CN108091341A (en) * | 2017-11-28 | 2018-05-29 | 湖南海翼电子商务股份有限公司 | Audio signal processing method and vehicle electronic device |
Non-Patent Citations (2)
| Title |
|---|
| XUE FENG ET AL.: "On Using heterogeneous data for vehicle-based speech recognition: A DNN-based approach", 《2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)》 * |
| 何升帆: "基于智能移动终端的语音车载信息系统的设计研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523990A (en) * | 2019-01-21 | 2019-03-26 | 未来电视有限公司 | Speech detection method and device |
| CN109523990B (en) * | 2019-01-21 | 2021-11-05 | 未来电视有限公司 | Voice detection method and device |
| CN114401346A (en) * | 2022-01-13 | 2022-04-26 | 平安普惠企业管理有限公司 | Response method, device, equipment and medium based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108986811B (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1941079B (en) | Speech recognition method and system | |
| CN109671424B (en) | Responsive activation of vehicle features | |
| CN109785828A (en) | Spatial term based on user speech style | |
| CN110491414A (en) | Use the adjustable automatic speech recognition for monitoring time-out of dynamic | |
| CN107656465A (en) | Expansible Vehicular system | |
| US20160039356A1 (en) | Establishing microphone zones in a vehicle | |
| US10431221B2 (en) | Apparatus for selecting at least one task based on voice command, vehicle including the same, and method thereof | |
| CN107791984A (en) | Method and apparatus for the detection of automotive occupant position | |
| US11928390B2 (en) | Systems and methods for providing a personalized virtual personal assistant | |
| CN105005276B (en) | Operator's method supported is provided using vehicle telematics service system | |
| CN105632521B (en) | A kind of random source of sound automatic sound control device based on automobile | |
| CN107097718A (en) | Active speech synthesizing device and the vehicles | |
| CN109712615A (en) | System and method for detecting the prompt in dialogic voice | |
| CN107093427A (en) | The automatic speech recognition of not smooth language | |
| CN103151037A (en) | Correcting unintelligible synthesized speech | |
| CN108447488A (en) | Enhance voice recognition tasks to complete | |
| CN110865788B (en) | Vehicle communication system and method of operating a vehicle communication system | |
| CN108986811A (en) | Voice recognition detection method, device and equipment | |
| CN107444318A (en) | Automobile rear end door control method and system | |
| CN113270095B (en) | Voice processing method, device, storage medium and electronic equipment | |
| CN113409798A (en) | Method, device and equipment for generating noise-containing voice data in vehicle | |
| CN105551484A (en) | Selective noise suppression during automatic speech recognition | |
| CN116259320A (en) | Voice-based vehicle control method and device, storage medium, and electronic device | |
| CN111661065B (en) | Agent device, method for controlling agent device, and storage medium | |
| CN109215648A (en) | Vehicle-mounted voice identifying system 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |