CN108621981A - Speech recognition system based on seat and its recognition methods - Google Patents
Speech recognition system based on seat and its recognition methods Download PDFInfo
- Publication number
- CN108621981A CN108621981A CN201810293765.7A CN201810293765A CN108621981A CN 108621981 A CN108621981 A CN 108621981A CN 201810293765 A CN201810293765 A CN 201810293765A CN 108621981 A CN108621981 A CN 108621981A
- Authority
- CN
- China
- Prior art keywords
- pickup unit
- phonetic order
- vehicle
- unit
- seat
- 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
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 claims description 34
- 239000000203 mixture Substances 0.000 claims description 2
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 abstract 1
- 238000012544 monitoring process Methods 0.000 description 26
- 230000001276 controlling effect Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 14
- 230000005236 sound signal Effects 0.000 description 14
- 230000000875 corresponding effect Effects 0.000 description 12
- 230000009471 action Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011022 operating instruction Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001143 conditioned effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
- B60R16/0373—Voice control
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention discloses one speech recognition system and its recognition methods based on pedestal, the wherein described speech recognition system includes a control unit and a collecting unit, the wherein described collecting unit includes at least two pickup units, pickup unit described in wherein at least one is arranged at the middle control flow of a vehicle or is neighboringly set to the middle control flow, in addition the pickup unit is arranged at the seat of the vehicle, wherein each pickup unit is communicatively connected in a network respectively in described control unit, the wherein each pickup unit of described control unit control acquires the phonetic order for controlling the vehicle in a manner of co-operating, in this way, it is capable of providing the efficiency and accuracy of speech recognition.
Description
Technical field
The present invention relates to vehicle audios to identify field, further relate to a speech recognition system based on seat and its
Recognition methods, the speech recognition system and its recognition methods based on seat include one first pickup unit and one second pickup
Unit, and first pickup unit and second pickup unit are located at control flow and vehicle driver's seat in vehicle respectively
Chair, first pickup unit and second pickup unit cooperate, and improve the efficiency of vehicle audio identification.
Background technology
With the development of science and technology, more and more scientific and technological achievements are gradually walked out laboratory and are come into our life, vehicle
It is exactly one in these numerous technologies to carry speech control system.Vehicle-mounted voice control system is widely used in vehicle,
To allow user to control vehicle in a manner of voice control, that is, user, which only needs to send out specific sound, can complete pair
The control of vehicle, making specific action without user can make vehicle complete specific function, greatly side
The user of vehicle to the control of vehicle and ensure that the safeties of driving conditions.
For example, when vehicle driver wants to open vehicle window, traditional way is that driver needs to touch vehicle window control
Button processed controls the folding of vehicle window with this.But with the application of vehicle audio control system, vehicle driver only needs to send out
Go out to open the phonetic order of vehicle window, vehicle audio control system can be controlled vehicle window accordingly according to the phonetic order
System touches vehicle window control button, to facilitate control of the vehicle driver to vehicle without user with hand.
On the other hand, vehicle driver is a generally acknowledged job more dry as dust, in very long driving procedure,
Driver often likes playing some music, increases the enjoyment in vehicle travel process with this.If vehicle driver is in vehicle
Traveling during want play music, traditional way is the switch of the in-vehicle player on vehicle to be touched, with this come
It opens in-vehicle player and plays music.And when driver touches in-vehicle player switch, the sight of driver inevitably can
The of short duration travel direction for leaving vehicle looks for the position of in-vehicle player switch, and in this course, if vehicle institute
Emergency situations occur on the route of traveling, vehicle driver is difficult timely and effectively to make a response, and greatly increases accident
Probability.
And by vehicle-mounted voice control system, vehicle driver wants in driving procedure can not when playing music
It needs directly to touch in-vehicle player switch, it is only necessary to send out phonetic control command, vehicle-mounted voice control system can be according to institute
It states voice control instruction unpack in-vehicle player and plays music, greatly liberated traditional in-vehicle player to vehicle driver's
Limitation enables vehicle driver to be absorbed in the driving of vehicle, reduces the probability that accident occurs, improves the security performance of vehicle.
But conventional truck speech control system has great limitation, because conventional truck speech control system
Sound pick up equipment (device of the voice for receiving user) is generally placed near the middle control flow of vehicle, residing for vehicle
External environment and/or when more noisy interior environment, the sound pick up equipment that is arranged in vehicle near control flow
It is difficult to accurately receive corresponding phonetic order in a noisy environment, result in vehicle audio control system can not basis
Phonetic order generates corresponding action message or is possible to will produce the action message of mistake, and strong influence people are to vehicle
Control ability, so that the driving experience of vehicle is had a greatly reduced quality.
For example, when the phonetic order that vehicle driver sends out during driving vehicle is to play music still to work as vehicle
Personnel in are relatively more, when environment inside car is more noisy, then the sound that interior other staff send out will be to vehicle
Speech control system generates interference, causes vehicle audio control system that can not quickly recognize vehicle in a noisy environment
The phonetic order that driver sends out can not timely and effectively make a response according to the phonetic order of driver.
In addition, vehicle audio control system is also possible to that the phonetic order of mistake, and root can be recognized in a noisy environment
The action message that mistake is generated according to the phonetic order of the mistake recognized, for example, vehicle audio control system may be noisy
Environment in the phonetic order for playing music is identified as to open the phonetic order of car door, and by vehicle during vehicle travels
Car door opening, cause great security risk to the driving procedure of vehicle.
The sound pick up equipment of the vehicle-mounted speech control system of tradition is arranged at the middle control flow of vehicle, to that can obtain preferably
Radio reception effect, vehicle driver must be close in vehicle control flow sounding nearby, and it is very inconvenient to use, Er Qiecun
In security risk.Also, be arranged at the sound pick up equipment of middle control flow the passenger of pickup vehicle heel row phonetic order
When, due to longer, the phonetic order that heel row passenger is sent out meeting when in reaching vehicle near control flow of distance
Become very faint, vehicle-mounted sound pick up equipment often can not quickly and accurately pick up these phonetic orders, can not root
Corresponding action is generated according to these phonetic orders.
Therefore, the audio identification efficiency for how further increasing vehicle audio control system becomes and is controlled for vehicle audio
System future development needs the critical issue solved.
Invention content
It is an object of the present invention to provide one speech recognition system and its recognition methods based on seat, with traditional vehicle
Speech recognition system is carried to compare, the speech recognition system of the invention has higher audio identification efficiency and accuracy, with
The phonetic order for enabling the speech recognition system quickly and accurately to identify that user sends out.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, with tradition
Vehicle-mounted voice identifying system is compared, and the speech recognition system of the invention has higher audio identification efficiency and accuracy,
It is effective that the user of vehicle is avoided to repeat to send out phonetic order.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, with tradition
Vehicle-mounted voice identifying system is compared, and the speech recognition system of the invention has higher audio identification efficiency and accuracy,
The phonetic order that user sends out can be accurately obtained in relatively noisy environment.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
State speech recognition system include at least one first pickup unit and at least one second pickup unit, and first pickup unit with
Second pickup unit is located at the middle control flow of vehicle and the chair headrest of vehicle, first pickup unit and institute respectively
The collaborative work of the second pickup unit is stated, the efficiency of vehicle audio identification is improved.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
Second phonetic order of the first phonetic order and second pickup unit acquisition of stating the acquisition of the first pickup unit can be mutual
It corrects, to improve the accuracy and efficiency that the speech recognition system identifies phonetic order.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
The pickup unit stated in the first pickup unit and second pickup unit is main pickup unit, another pickup unit is
Auxiliary pickup unit, wherein the voice that the phonetic order of auxiliary pickup unit acquisition can be used for correcting main pickup unit acquisition refers to
It enables, to improve the accuracy and efficiency that the speech recognition system identifies phonetic order.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
It states the first pickup unit and second pickup unit can be converted between main pickup unit and auxiliary pickup unit.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
It states the first pickup unit and second pickup unit forms a radio reception field, when the phonetic order that user sends out is transmitted to institute
When stating radio reception field, it can be acquired by first pickup unit and second pickup unit.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
The chair headrest that the second pickup unit is adjustably set to the vehicle is stated, for example, the direction of second pickup unit
Can be adjusted so that with the change of the face orientation of user enables second pickup unit to acquire with more preferably
The phonetic order of effect, to improve the accuracy and efficiency that the speech recognition system identifies phonetic order.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
The chair headrest that the second pickup unit is adjustably set to the vehicle is stated, to make first pickup unit and described
The radio reception field that second pickup unit is formed is dynamic radio reception field.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
The chair headrest that the second pickup unit is arranged at the vehicle is stated, radio reception is carried out in a manner of close to sound sender, into one
Step improves the efficiency of speech recognition.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
Working condition can be adjusted according to the state of user by stating speech recognition system, for obtaining more efficient radio reception effect.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, wherein institute
It includes a position sensor to state speech recognition system, and the position sensor can judge the position shape of phonetic order sender
State, and the working condition of first pickup unit and second pickup unit is adjusted according to the location status, for obtaining
Obtain more efficient radio reception effect.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, into one
Step includes a noise reduction unit, and the noise reduction unit is able to acquired in first pickup unit and second pickup unit
Phonetic order carries out noise reduction process, keeps the phonetic order more clear.
It is another object of the present invention to provide one speech recognition system and its recognition methods based on seat, into one
Step includes a processing module, wherein first pickup unit and second pickup unit receive what user was sent out simultaneously
Phonetic order, the phonetic order that the processing module is received according to first pickup unit and second pickup unit
Status information, and corresponding action message is generated according to the phonetic order information.
One side under this invention, the present invention provide a speech recognition system based on seat comprising:
One control unit;With
One collecting unit, wherein the collecting unit includes at least two pickup units, pickup list described in wherein at least one
Member is arranged at the middle control flow of a vehicle or is neighboringly set to the middle control flow, the pickup unit quilt in addition
It is set to the seat of the vehicle, wherein each pickup unit is communicatively connected in a network respectively in described control unit,
Described in each pickup unit of control unit control the voice for controlling the vehicle is acquired in a manner of co-operating
Instruction.
According to one embodiment of present invention, it is arranged at the middle control flow of the vehicle or is neighboringly arranged
It is one first pickup unit in the pickup unit of the middle control flow, the pickup unit for being arranged at the seat is
One second pickup unit, wherein first pickup unit is used for acquiring one first phonetic order, second pickup unit
In one second phonetic order of acquisition, the wherein sound quality of described control unit first phonetic order and second voice
The sound quality of instruction, with according to a preferable phonetic order of sound quality in first phonetic order and second phonetic order
A third phonetic order is generated, for controlling the vehicle.
According to one embodiment of present invention, it is arranged at the middle control flow of the vehicle or is neighboringly arranged
It is one first pickup unit in the pickup unit of the middle control flow, the pickup unit for being arranged at the seat is
One second pickup unit, wherein first pickup unit is used for acquiring one first phonetic order, second pickup unit
In acquiring one second phonetic order, first phonetic order and second phonetic order are superimposed by wherein described control unit
To generate a third phonetic order, for controlling the vehicle.
According to one embodiment of present invention, it is arranged at the middle control flow of the vehicle or is neighboringly arranged
It is one first pickup unit in the pickup unit of the middle control flow, the pickup unit for being arranged at the seat is
One second pickup unit, wherein first pickup unit is used for acquiring one first phonetic order, second pickup unit
In acquiring one second phonetic order, wherein described control unit carries out first phonetic order and second phonetic order
Difference set processing is to generate a third phonetic order, for controlling the vehicle.
According to one embodiment of present invention, it is arranged at the middle control flow of the vehicle or is neighboringly arranged
It is one first pickup unit in the pickup unit of the middle control flow, the pickup unit for being arranged at the seat is
One second pickup unit, wherein first pickup unit is used for acquiring one first phonetic order, second pickup unit
In acquiring one second phonetic order, wherein described control unit can intercept the preferable piece of sound quality in first phonetic order
The preferable segment of sound quality in section and second phonetic order is to generate a third phonetic order, for controlling the vehicle.
According to one embodiment of present invention, described control unit first phonetic order and second voice
The foundation condition of instruction is:The condition group of the size of sound, the frequency of sound, the size of background sound composition.
Other side under this invention, the present invention further provides an audio recognition methods based on seat, wherein institute
Predicate voice recognition method includes the following steps:
(a) by the way that at least one first pickup unit is arranged near the middle control flow of a vehicle or the middle control flow
With the mode of at least seat setting at least one second pickup unit in the vehicle, formed in the seating space of the vehicle
One radio reception field;With
(b) it is issued in the seating space of the vehicle when for controlling the phonetic order of the vehicle and is transmitted to institute
When stating radio reception field, controls first pickup unit and second pickup unit acquires the voice in a manner of co-operating
Instruction.
According to one embodiment of present invention, in the step (a), second pickup unit is adjustably arranged
In the seat, to make the radio reception field that first pickup unit and second pickup unit are formed be that a dynamic is received
Sound field.
According to one embodiment of present invention, in the step (a), a setting at least third pickup unit is at least one
A seat, to form the radio reception field by the third pickup unit and second pickup unit.
According to one embodiment of present invention, in the above-mentioned methods, second pickup unit is adjustably set to
The seat, to make the radio reception field that second pickup unit and the third pickup unit are formed be a dynamic radio reception
.
According to one embodiment of present invention, in the above-mentioned methods, the third pickup unit is adjustably set to
The seat, to make the radio reception field that second pickup unit and the third pickup unit are formed be a dynamic radio reception
.
According to one embodiment of present invention, in the above-mentioned methods, the third pickup unit is adjustably set to
The seat, to which the radio reception field for making second pickup unit and the third pickup unit be formed is received for the dynamic
Sound field.
According to one embodiment of present invention, in the step (b), further comprise step:Compare described the first ten
The sound quality of one first phonetic order of sound unit acquisition and one second phonetic order of second pickup unit acquisition, according to institute
The preferable phonetic order of a sound quality stated in the first phonetic order and second phonetic order generates a third phonetic order,
For controlling the vehicle.
According to one embodiment of present invention, in the step (b), further comprise step:It is superimposed described the first ten
Sound unit acquisition one first phonetic order and second pickup unit acquisition one second phonetic order and generate a third
Phonetic order, for controlling the vehicle.
According to one embodiment of present invention, in the step (b), further comprise step:Difference set processing described the
One pickup unit acquisition one first phonetic order and second pickup unit acquisition one second phonetic order and generate one
Third phonetic order, for controlling the vehicle.
According to one embodiment of present invention, in the step (b), further comprise step:Intercept first language
Sound instruction in the preferable segment of sound quality and second phonetic order in the preferable segment of sound quality and generate a third voice
Instruction, for controlling the vehicle.
Other side under this invention, the present invention further provides an audio recognition methods, wherein the speech recognition
Method includes the following steps:
(A) a radio reception field is formed in the seating space of a vehicle;
(B) when the phonetic order of the vehicle described in the desired control propagates to the radio reception field, the phonetic order is used for
Form one first pickup unit and the acquisition of one second pickup unit of the radio reception field;And
(C) one acquired according to one first phonetic order of first pickup unit acquisition and second pickup unit
Second phonetic order generates the third phonetic order for controlling the vehicle.
According to one embodiment of present invention, in the step (A), the radio reception field is a dynamic radio reception field.
According to one embodiment of present invention, in the step (A), the control flow or described in the one of the vehicle
First pickup unit is set near middle control flow, and the second pickup list is set in an at least seat for the vehicle
Member, to form the radio reception field by first pickup unit and second pickup unit.
According to one embodiment of present invention, in the step (A), the control flow or described in the one of the vehicle
First pickup unit is set near middle control flow, and is arranged by adjustable described in an at least seat for the vehicle
Second pickup unit, to form dynamic radio reception field by first pickup unit and second pickup unit.
Other side under this invention, the present invention further provides a seat can radio reception vehicle comprising:
One vehicle body;
An at least seat, wherein each seat is arranged at the vehicle body respectively;And
One collecting unit, wherein the collecting unit includes an at least pickup unit, pickup list described in wherein at least one
Member is arranged at the seat.
According to one embodiment of present invention, control flow during the vehicle further comprises one, wherein the middle control flow
It is arranged at the vehicle body, wherein the collecting unit includes at least two pickup units, and one described is picked up
Sound unit is arranged at the middle control flow or is neighboringly set to the middle control flow, the pickup unit quilt in addition
It is set to the seat.
According to one embodiment of present invention, the collecting unit includes two pickup units, a pickup
Unit is defined as one first pickup unit, another described pickup unit is defined as one second pickup unit, wherein described
First pickup unit is arranged at the middle control flow or is neighboringly set to the middle control flow, the second pickup list
Member is arranged at the seat.
According to one embodiment of present invention, the collecting unit includes three pickup units, a pickup
Unit is defined as one first pickup unit, and a pickup unit is defined as one second pickup unit, described in another
Pickup unit is defined as a third pickup unit, wherein first pickup unit be arranged at the middle control flow or by
It is neighboringly set to the middle control flow, second pickup unit and the third pickup unit are arranged at the seat respectively
Chair, and second pickup unit is towards the front of the vehicle body and the third pickup unit towards the vehicle
The rear portion of ontology.
According to one embodiment of present invention, first pickup unit and second pickup unit cooperate and
The seating space of the vehicle body forms a dynamic radio reception field.
According to one embodiment of present invention, first pickup unit and second pickup unit cooperate and
The seating space of the vehicle body forms a dynamic radio reception field.
According to one embodiment of present invention, second pickup unit and the third pickup unit cooperate and
The seating space of the vehicle body forms dynamic radio reception field.
According to one embodiment of present invention, second radio unit is adjustably set to the seat.
According to one embodiment of present invention, at least one of second pickup unit and the third pickup unit
Pickup unit is adjustably set to the seat.
According to one embodiment of present invention, the seat includes the front-seat driving for being arranged at the vehicle body
Seat and an assistant driver seat and be arranged at the vehicle body heel row first seat of heel row, ranked second seat after one
Seat is ranked third after chair and one, wherein second pickup unit includes at least two sound pick up equipments, wherein the driver seat,
The assistant driver seat, the first seat of the heel row, it is described after ranked second seat and it is described after ranked third in seat at least two
A seat is equipped at least one sound pick up equipment respectively.
According to one embodiment of present invention, the seat includes the front-seat driving for being arranged at the vehicle body
Seat and an assistant driver seat and be arranged at the vehicle body heel row first seat of heel row, ranked second seat after one
Seat is ranked third after chair and one, wherein second pickup unit includes at least two sound pick up equipments, wherein the driver seat,
The assistant driver seat, the first seat of the heel row, it is described after ranked second seat and it is described after ranked third in seat at least two
A seat is equipped at least one sound pick up equipment respectively.
According to one embodiment of present invention, the third pickup unit includes an at least audio signal reception device, wherein described drive
It sails at least one of seat and the assistant driver seat seat and is equipped at least one audio signal reception device.
According to one embodiment of present invention, the pickup unit is arranged at the chair headrest of the seat.
Description of the drawings
Figure 1A is the schematic diagram of a state of a vehicle of one first preferred embodiment under this invention.
Figure 1B is the schematic diagram of another state of the vehicle of above-mentioned preferred embodiment under this invention.
Fig. 1 C are the schematic diagrames of another state of the vehicle of above-mentioned preferred embodiment under this invention.
Fig. 2 is the entire block diagram structure of the speech recognition system based on seat of above-mentioned preferred embodiment according to the present invention
Schematic diagram.
Fig. 3 is the flow diagram of the audio recognition method based on seat of above-mentioned preferred embodiment according to the present invention.
Fig. 4 is the entire block diagram knot of the speech recognition system based on seat of one second preferred embodiment according to the present invention
Structure schematic diagram.
Fig. 5 is the flow diagram of the audio recognition method based on seat of above-mentioned preferred embodiment according to the present invention.
Fig. 6 is the entire block diagram knot of the speech recognition system based on seat of third preferred embodiment according to the present invention
Structure schematic diagram.
Fig. 7 is the flow diagram of the audio recognition method based on seat of above-mentioned preferred embodiment according to the present invention.
Fig. 8 is the entire block diagram knot of the speech recognition system based on seat of one the 4th preferred embodiment according to the present invention
Structure schematic diagram.
Fig. 9 is the flow chart of an audio recognition method according to a preferred embodiment of the present invention.
Figure 10 is the flow chart of an audio recognition method of another preferred embodiment according to the present invention.
Specific implementation mode
It is described below for disclosing the present invention so that those skilled in the art can realize the present invention.It is excellent in being described below
Embodiment is selected to be only used as illustrating, it may occur to persons skilled in the art that other obvious modifications.It defines in the following description
The present invention basic principle can be applied to other embodiments, deformation scheme, improvement project, equivalent program and do not carry on the back
Other technologies scheme from the spirit and scope of the present invention.
It will be understood by those skilled in the art that the present invention exposure in, term " longitudinal direction ", " transverse direction ", "upper",
The orientation or position of the instructions such as "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside"
Relationship is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of description of the present invention and simplification of the description, rather than
Indicate or imply that signified device or element must have a particular orientation, with specific azimuth configuration and operation, therefore above-mentioned
Term is not considered as limiting the invention.
It is understood that term " one " is interpreted as " at least one " or " one or more ", i.e., in one embodiment,
The quantity of one element can be one, and in a further embodiment, the quantity of the element can be multiple, and term " one " is no
It can be interpreted as the limitation to quantity.
With reference to the attached drawing 1A to Fig. 1 C of the Figure of description of the present invention, the one of a preferred embodiment under this invention is based on seat
The speech recognition system 100 of chair is disclosed for and is set forth in following description, wherein the speech recognition system 100 is applicable in
In an at least vehicle 200, so that the driver and/or 200 passenger of the vehicle that receive the vehicle 200 send out at least
One phonetic order 300, and the vehicle 200 is controlled according to the phonetic order 300.The vehicle 200 includes a vehicle body
201, control flow 203 at least in a seat 202 and one, wherein the seat 202 and the middle control flow 203 are set respectively
In the vehicle body 201, and the seat 202 and the middle control flow 203 are respectively positioned on the seating sky of the vehicle 200
Between, the seat 202 allows user to take, such as user can be driven by way of riding on the seat 202
The vehicle 200 or user can take the vehicle 200 by way of riding on the seat 202, in described
The permission user of control flow 203 checks and controls the state of the vehicle 200.Compared with the vehicle-mounted speech recognition system of tradition, this
The position that the speech recognition system 100 of invention passes through a chair headrest 2020 of the seat 202 in the vehicle 200
Sound pick up equipment is set, the phonetic order 300 is received in a manner of close to the position of phonetic order sender, and then described in raising
300 identified efficiency of phonetic order, accuracy and success rate.For example, when user rides in the seat of the vehicle 200
When on chair 202, the mouth of user is filled close to the pickup for the chair headrest 2020 for being arranged at the seat 202
It sets, to when user sends out the phonetic order 300, be arranged at the chair headrest 2020 of the seat 202
The sound pick up equipment can receive the phonetic order 300 in the position of the mouth close to user, to be conducive to improve institute
State 300 identified efficiency of phonetic order and success rate.
A better embodiment of refer to the attached drawing 1A to Fig. 2, the speech recognition system 100 provided by the present invention exist
It is expanded on further in following description, wherein the speech recognition system 100 includes that a collecting unit 10 and one control is single
Member 20, the collecting unit 10 and described control unit 20 are mutually communicatively coupled, wherein the collecting unit 10 is able to
The phonetic order 300 is acquired, and the phonetic order 300 is sent to described control unit 20, described control unit 20
The vehicle 200 is controlled according to the phonetic order 300.That is, working as the phonetic order of vehicle 200 described in desired control
300 be issued after can be acquired by the collecting unit 10, described control unit 20 is subsequently can be to the control instruction 300
Handle and the vehicle 200 is controlled according to the control instruction 300.
The collecting unit 10 further comprises at least one first pickup unit 11 and at least one second pickup unit 12,
Described in the first pickup unit 11 and second pickup unit 12 be arranged at the middle control flow of the vehicle 200 respectively
203 or be arranged near the middle control flow 203 and the vehicle 200 described in seat 202 the chair headrest
2020 position, when vehicle occupant person sends out the phonetic order 300 of vehicle 200 described in desired control in vehicle,
The acquisition to the phonetic order 300 is completed in first pickup unit 11 and second pickup unit 12 collaborative work.
That is when the passenger in the seating space of the vehicle 200 sends out the phonetic order 300, be arranged at it is described in
It control flow 203 or first pickup unit 11 that is arranged near the middle control flow 203 and is arranged at described
Second pickup unit 12 of the chair headrest 2020 of seat 202 can acquire the voice that user sends out and refer to
Enable 300.Subsequently, what the phonetic order 300 and second pickup unit 12 that first pickup unit 11 acquires acquired
The phonetic order 300 can mutually be corrected by user, and the phonetic order is identified to improve the speech recognition system 100
300 efficiency and accuracy, to improve the user experience of user and ensure the safety of driving conditions.
Refer to the attached drawing 1A to Fig. 2, first pickup unit 11 and second pickup unit 12 can cooperate and
A radio reception field 500 is formed, wherein when the user in the seating space positioned at the vehicle 200 sends out the phonetic order 300, and
When the phonetic order 300 is transmitted to the radio reception field 500, the phonetic order 300 can be used for forming the radio reception
First pickup unit 11 of field 500 and second pickup unit 12 acquisition.Preferably, the radio reception field 500 is one
Dynamic radio reception field, wherein the state of the radio reception field 500 can change with the change of the posture of user.Specifically,
The direction of second pickup unit 12 is adjusted, such as the direction of second pickup unit 12 can be always towards use
The facial direction of person, to the radio reception field 500 for making first pickup unit 11 and second pickup unit 12 be formed
For dynamic radio reception field, and because second pickup unit 12 direction can always towards the facial direction of user, from
And second pickup unit 12 can acquire the phonetic order 300 that user sends out in high quality.
In addition, a pickup unit in first pickup unit 11 and second pickup unit 12 is main pickup list
Member, pickup unit supplemented by another pickup unit, and first pickup unit 11 and second pickup unit 12 can
As the variation of the posture of user is converted between main pickup unit and auxiliary pickup unit.Preferably, the first pickup list
Member 11 and second pickup unit 12 in main pickup unit and auxiliary can be picked up according to the distance between user and pickup unit
It is converted between sound unit.For example, when user is closer apart from first pickup unit 11, first pickup unit 11 can
To be main pickup unit, and second pickup unit 12 is auxiliary pickup unit;When user is apart from second pickup unit
12 it is closer when, first pickup unit 11 can be auxiliary pickup unit, and second pickup unit 12 is main pickup unit.
Optionally, first pickup unit 11 and second pickup unit 12 can according to user face orientation in main pickup
It is converted between unit and auxiliary pickup unit.For example, when user face orientation described in the first pickup unit 11 or close to
When towards first pickup unit 11, first pickup unit 11 is main radio unit, and second pickup unit 12
Supplemented by pickup unit;The second pickup unit 12 described in the face orientation of user or close to towards the second pickup list
When member 12, second pickup unit 12 is main radio unit 12, and pickup unit supplemented by first pickup unit 11.
Further, refer to the attached drawing 1A to Fig. 1 C, the quantity of the seat 202 of the vehicle 200 can there are five, wherein
These described seats 202 are defined as a driver seat 2021, a copilot in the speech recognition system 100 of the present invention
Seat 2025 is ranked third after ranked second seat 2024 and one after seat 2022, first seat of heel row 2023, one, wherein described
Driver seat 2021 changes the front row that an assistant driver seat 2022 is located at the vehicle body 201, ranked first after described
Seat 2023, it is described after ranked second seat 2024 and it is described after ranked third seat 2025 mutually adjacently be located at the vehicle body
201 heel row.Second pickup unit 12 include at least one first sound pick up equipment 121, at least one second sound pick up equipment 122,
An at least third sound pick up equipment 123, at least one the 4th sound pick up equipment 124 and at least one the 5th sound pick up equipment 125, wherein described
First sound pick up equipment 121 is arranged at the driver seat 2021, second sound pick up equipment 122 is arranged at the copilot
Seat 2022, the third sound pick up equipment 123 are arranged at the first seat of the heel row 123,124 quilt of the 4th sound pick up equipment
Be set to it is described after ranked second seat 124, the 5th sound pick up equipment 125 be arranged at it is described after ranked third seat 125.
It should be noted that illustrated in the present embodiment with the vehicle 200 with two rows of totally five seats, still,
It will be appreciated by those ordinary people skilled in the art that the speech recognition system 100 provided by the present invention not only can be by
Suitable for the vehicle 200 with two rows of totally five seats, the vehicle 200 for having there are one seat is can be applicable to,
The vehicle 200 of two seats, even with multiple rows of seat the vehicle 200, the seat of the vehicle 200 it is specific
Quantity and set-up mode are not construed as limiting the invention.
In the speech recognition system 100 of the present invention, second pickup unit 12 is set to the vehicle 200
The seat 202 the chair headrest 2020 position mode, when the personnel in the seating space of the vehicle 200 send out
It is described since second pickup unit 12 is close to the position of phonetic order sender when the phonetic order 300
Collecting unit 10 can accurately collect the phonetic order that phonetic order sender is sent out.Such as described in being sent out as driver
When phonetic order 300, first sound pick up equipment for being arranged at the driver seat 2021 of second pickup unit 12
121 can close to driver station acquisition described in phonetic orders 300, meanwhile, be arranged at the vehicle 200 it is described in
First pickup unit 11 near control flow 203 can also acquire the phonetic order 300 that driver sends out.It is preferred that
The direction on ground, first sound pick up equipment 121 is adjusted, that is, first sound pick up equipment 121 is adjustably set to institute
Driver seat 2021 is stated, to which when the face orientation sounding of driver changes, the direction of first sound pick up equipment 121 can
It is conditioned, so that first sound pick up equipment 121 can be always towards the face of driver or close to towards driver's
Face, to acquire the phonetic order 300 that driver sends out.
For example, when the body of the driver of the vehicle 200 is close to 2021 sitting of the driver seat and sends out described
When phonetic order 300, first sound pick up equipment of the chair headrest 2020 of the driver seat 2021 is set
The position that 121 driver apart from the vehicle 200 sends out the phonetic order 300 is closer to, first sound pick up equipment
The phonetic order 300 that 121 drivers that can accurately collect the vehicle 200 are sent out.
When the chair headrest 2020 sitting of the body far from the driver seat 2021 of the driver of the vehicle 200
And when sending out the phonetic order 300, then relatively close first pickup unit of the driver of the vehicle 200 11
Position, first pickup unit 11 can accurately collect the phonetic order that the driver of the vehicle 200 is sent out.
In addition, when being seated at the passenger of heel row of the vehicle 200 and sending out the phonetic order 300, due to
The position of the chair headrest 2020 of the seat 202 is equipped with the pickup unit 12, and is located at the chair headrest 2020
The pickup unit 12 of position sends out the position of the phonetic order 300 close to passenger, and the pickup unit 12 can
The phonetic order 300 that the heel row passenger of the vehicle 200 is sent out is acquired well.
In the position of the chair headrest 2020 of the seat 202 of the vehicle 200, second pickup unit 12 is set,
Radio reception is carried out by the position sent out close to phonetic order, solves the vehicle-mounted speech recognition system of tradition well only in the car
It is difficult that control flow is nearby arranged audio signal reception device radio reception, the inaccurate problem of radio reception, is conducive to improve the phonetic order 300 and be known
Other efficiency and accuracy.
Also, first pickup unit 11 and second pickup unit 12 are in the seat 202 of the vehicle 200
The radio reception field 500 is formed between the middle control flow 203, when passenger is seated at the seat 202 of the vehicle 200
When, passenger is in first pickup unit 11 and second pickup unit 12 is formed by the radio reception field
In 500, the phonetic order 300 that passenger is sent out can be good in the radio reception field 500 by acquisition list
First radio unit 11 and second radio unit 12 of member 10 are acquired.
Further, described control unit 20 includes a voice receiving unit 21, wherein the institute of the collecting unit 10
It states the first pickup unit 11 and second pickup unit 12 is communicatively connected in a network respectively in the voice receiving unit 21, from
And the voice receiving unit 21 is able to receive the voice of first pickup unit 11 acquisition of the collecting unit 10
The phonetic order 300 of instruction 300 and second pickup unit 12 acquisition.
It should be pointed out that when the passenger of the vehicle 200 sends out the phonetic order 300, described
One pickup unit 11 and second pickup unit 12 distinguish phonetic order 300 described in respective individual reception, and by described first
The phonetic order that pickup unit 11 is acquired is named as one first phonetic order 301, and second pickup unit 12 is acquired
Phonetic order be named as one second phonetic order 302, and the voice receiving unit 21 is able to respectively from first pickup
Unit 11 and second pickup unit 12 receive first phonetic order 301 and second phonetic order 302.
Preferably, the voice receiving unit 21 is connected to 11 He of the first pickup unit by way of wired connection
Second pickup unit 12, certainly, it will be appreciated by those ordinary people skilled in the art that the voice receiving unit 21 can
It is connected to first pickup unit 11 and second pickup unit 12 in a manner of by wireless connection, is such as but not limited to
The mode of the wireless connections such as bluetooth connection, WiFi connections.
Described control unit 20 further comprises that a comparison unit 22, the comparison unit 22 are able to from the phonetic incepting
Unit 21 receives first phonetic order 301 and second phonetic order 302, and the comparison unit 22 can to from
First phonetic order 301 that first pickup unit 11 receives and received from second pickup unit 12 described the
Two phonetic orders 302 are handled.
In a preferable examples of the speech recognition system 100 of the present invention, the comparison unit 22 is compared
The quality of the voice of first phonetic order 301 and second phonetic order 302, by the preferable phonetic order of sound quality
Retain, gives up the poor phonetic order of sound quality.The comparison unit 22 judges that the standard of voice quality quality includes but not limited to
The size of sound, the frequency of sound, size of background sound etc..Voice quality judges that the method for quality can be for described first
Several identical timing nodes are chosen in phonetic order 301 and second phonetic order 302 to be compared.
For example, the comparison unit 22 show that the voice quality of first phonetic order 301 is preferable by comparing
In the voice quality of second phonetic order 302, then first phonetic order 301 is passed into next unit, it will be described
Second phonetic order 301 is given up.
It should be pointed out that the speech recognition system 100 provided by the present invention further has identification specific people
The function of phonetic order, if for example, the vehicle 200 for being equipped with the speech recognition system 100 of the present invention is returned
Mr. Wang is all, and the raw tone stored in the speech recognition system 100 based on seat is also the language that Mr. Wang sends out
Sound instructs, then when Lee sends out phonetic order, the speech recognition system 100 based on seat will not then identify,
The vehicle 200 will not be controlled to occur to act accordingly.
That is, before using the speech recognition system 100 based on seat provided by the present invention, need pre-
Raw tone instruction is first inputted, the collecting unit 10 is able to acquire the raw tone instruction, and will be collected described
Raw tone instruction, which is transmitted in the voice receiving unit 21, to be stored.
Described control unit 20 further comprises that a judging unit 23, the judging unit 23 are able to from the comparison unit
22 receive through treated the phonetic order 300 of the comparison unit 22, and the phonetic order 300 is described with being stored in
Voice receiving unit 21 raw tone instruction whether belong to the same sender, if the phonetic order 300 with it is described original
Phonetic order belongs to the same sender, then the phonetic order 300 is transmitted to next unit, if being not belonging to same send out
Person does not act then.
Described control unit 20 further comprises that a processing unit 24, the processing unit 24 are able to from the judging unit
23 receive the phonetic order, and control vehicle according to the phonetic order 300 and execute corresponding action.
Both may be used it will be appreciated by those ordinary people skilled in the art that the processing unit 24 controls the action that vehicle executes
To be to drive relevant, for example, overtaking other vehicles, stopping, change lane etc., it can also be unrelated with driving, for example play music, beat
Open or be closed vehicle window, adjustment seat etc..
In another preferable examples of the speech recognition system 100 of the present invention, the comparison unit 22 can be right
From first phonetic order 301 of first pickup unit 11 reception and from described in second pickup unit 12 reception
Second phonetic order 302 is modified, to improve the sound quality of the collected phonetic order of the collecting unit 10 300.Example
Such as, in a specific example of the speech recognition system 100 of the present invention, the comparison unit 22 can be to described the
One phonetic order 301 and second phonetic order 302 are overlapped processing, to correct first phonetic order 301 and institute
State the second phonetic order 302.For example, in another specific example of the speech recognition system 100 of the present invention, it is described
Comparison unit 22 can carry out difference set processing to first phonetic order 301 and second phonetic order 302, to correct
State the first phonetic order 301 and second phonetic order 302.Specifically, the comparison unit 22 can be to described first
It is instruction sound which sound phonetic order 301 and second phonetic order 302, which are compared to determine, which sound is background
Sound, then the comparison unit 22 can change the phonetic order 300 by way of removing background sound.
Such as Fig. 3, according to another aspect of the present invention, the present invention further provides an audio recognition methods based on seat
300, wherein the audio recognition method 300 includes the following steps:
Step 301:Respectively one first phonetic order 301 and one second pickup unit 12 are acquired from one first pickup unit 11
One second phonetic order 302 is acquired, wherein first pickup unit 11 is arranged at the middle control flow of the vehicle 200
It 203 or is arranged near the middle control flow 203, second pickup unit 12 is arranged at the vehicle 200
The chair headrest 2020 of the seat 202;With
Step 302:Compare the voice quality of first phonetic order 301 and second phonetic order 302, and by sound
The preferable phonetic order 300 of matter is transmitted to a control unit 20.
As Figure 1A, Figure 1B, Fig. 1 C and Fig. 4 disclose the speech recognition system 100 provided by the present invention based on seat
Second preferred embodiment, wherein the speech recognition system 100 includes a collecting unit 10 and a control unit 20, the acquisition
Unit 10 and described control unit 20 are mutually communicatively coupled.The collecting unit 10 is able to acquire on the vehicle 200
At least phonetic order 300 that sends out of personnel, and the phonetic order 300 is transmitted to described control unit 20, the control
Unit 20 processed, which is able to control the vehicle 200 according to the phonetic order 300, generates corresponding action.
The collecting unit 10 includes being arranged at the middle control flow 203 of the vehicle 200 or being arranged at institute
It states at least one first pickup unit 11 near control flow 203 and is arranged at the seat 202 of the vehicle 200
At least one second pickup unit 12 of the chair headrest 2020.First pickup unit 11 and second pickup unit 12
It cooperates and forms the radio reception field 500 in the seating space of the vehicle 200, for collecting multiplying in the vehicle 100
Sit the phonetic order 300 that the passenger in space is sent out.
Described control unit 20 includes a voice receiving unit 21, a judging unit 23 and a processing unit 24, described
Voice receiving unit 21, the judging unit 23 and the processing unit 24 are mutually communicatively coupled, and the voice
Receiving unit 21 is communicatively connected in a network first pickup unit 11 and the second pickup list in the collecting unit 10
Member 12.The voice receiving unit 21 is able to receive one first phonetic order, 301 He that first pickup unit 11 is acquired
One second phonetic order 302 that second pickup unit 12 is acquired.The judging unit 23 is able to judge that the voice refers to
Enable 300 and one raw tone instruction whether belong to the same sender.The processing unit 24 is able to according to the phonetic order
300, which control the vehicle 200, generates corresponding action.
The speech recognition system 100 of this preferred embodiment and the speech recognition system of the first preferred embodiment
It is in place of 100 difference, described control unit 20 further comprises that an integral unit 27, the integral unit 27 are able to from institute
It states voice receiving unit 21 and receives first phonetic order 301 and second phonetic order 302, and first language
The quality of the voice quality of sound instruction 301 and second phonetic order 302, and intercept first phonetic order 301 and neutralize
Quality preferably partly forms complete third phonetic order 303 in second phonetic order 302, for controlling the vehicle
200.
For example, the passenger when the vehicle 200 is seated at the seat 202 of the vehicle 200, and send out
During the phonetic order 300 of vehicle 200 described in desired control, the passenger in the seating space of the vehicle 200
Position be possible to change.For example, the front half section time for sending out the phonetic order 300 in passenger may
Front can be faced, the latter half for sending out the phonetic order 300 may be towards rear, that is, passenger is sent out in front
Go out the front half section content of the phonetic order 300, and the second half section content of the phonetic order 300 is sent out at rear, this will
Lead to first pickup unit 11 and second pickup unit during passenger sends out the phonetic order 300
The quality of 12 phonetic orders 300 acquired in section in different times is different.If this when is only with described
The phonetic order that first pickup unit 11 and second pickup unit 12 are acquired is handled and is judged, it is likely that is merely able to
The phonetic order of half is received, phonetic order or the identification phonetic order of mistake can not be correctly identified, give passenger
Cause great inconvenience.
And in this preferable example of the speech recognition system 100 in the present invention, the integral unit 27 can
The phonetic order that first pickup unit 11 and second pickup unit 12 are acquired is integrated, it is complete to generate one
Whole quality being capable of the identified third phonetic order 303.
The judging unit 23 is able to receive the third phonetic order 303 from the integral unit 27, and by described
Three phonetic orders 303 are compared with raw tone instruction, when the judgement third phonetic order 303 and the original finger
When system being enabled to be sent out by unified sender, then the third phonetic order 303 is transmitted to the processing unit 24, the processing is single
Member 24 is able to be acted according to 303 generation of third phonetic order, controls the vehicle 200 and generates corresponding action, works as judgement
When the third phonetic order 303 instructs system sent out by different senders from raw tone, then not by the third voice
Instruction 303 is transmitted to the processing unit 24, and the vehicle 200 does not generate action yet.
Such as Fig. 5, according to another aspect of the present invention, the present invention further provides an audio recognition methods based on seat
500, wherein the audio recognition method 500 includes the following steps:
Step 501:Respectively one first phonetic order 301 and one second pickup unit 12 are acquired from one first pickup unit 11
One second phonetic order 302 is acquired, wherein first pickup unit 11 is arranged at the middle control flow of the vehicle 200
It 203 or is arranged near the middle control flow 203, second pickup unit 12 is arranged at the vehicle 200
The chair headrest 2020 of the seat 202;With
Step 502:First phonetic order 301 and second phonetic order 302 are integrated, a third is generated
Phonetic order 303, for controlling the vehicle 200.
Wherein, further comprise the steps in the step 202:
Compare the voice quality of first phonetic order 301 and second phonetic order 302, and extracts described first
The preferable segment of quality forms the third phonetic order 303 in phonetic order 301 and second phonetic order 302.
Such as attached drawing 1A, Figure 1B, Fig. 1 C and Fig. 6, the third of the speech recognition system 100 provided by the present invention based on seat
Preferred embodiment is set forth, wherein the speech recognition system 100 includes a collecting unit 10 and a control unit 20, it is described to adopt
Collection unit 10 and described control unit 20 are mutually communicatively coupled, and the collecting unit 10 is able to acquire the vehicle 200
On at least phonetic order 300 that sends out of personnel, and the phonetic order 300 is transmitted to described control unit 20, it is described
Control unit 20, which is able to control the vehicle 200 according to the phonetic order 300, generates corresponding action.
The collecting unit 10 includes being arranged at middle control flow 203 described in the vehicle 200 or being arranged at described
The institute of at least one first pickup unit 11 and the seat 202 for being arranged at the vehicle 200 near middle control flow 203
State at least one second pickup unit 12 of chair headrest 2020.First pickup unit 11 and 12 phase of the second pickup unit
Mutually coordinate and form a radio reception field 500 in the seating space of the vehicle 200, for collecting the seating sky in the vehicle 200
Between the voice will woods 300 that sends out of passenger.
Described control unit 20 includes a voice receiving unit 21, a judging unit 23 and a processing unit 24, described
Voice receiving unit 21, the judging unit 23 and the processing unit 24 are mutually communicatively coupled, and the voice
Receiving unit 21 is communicatively connected in a network first pickup unit 11 and the second pickup list in the collecting unit 10
Member 12.The voice receiving unit 21 is able to receive the first phonetic order 301 and institute that first pickup unit 11 is acquired
State the second phonetic order 302 that the second pickup unit 12 is acquired.The judging unit 23 is able to judge the phonetic order 300
Whether belong to the same sender with raw tone instruction.The processing unit 24 is able to be controlled according to the phonetic order 300
It makes the vehicle 200 and generates corresponding action.
It is in place of the speech recognition system 100 of this preferred embodiment and the difference of preceding two preferred embodiment, it is described
Control unit 20 further comprises a sitting posture monitoring unit 25 and an Audio Processing Unit 26, and 25 quilt of sitting posture monitoring unit
What can be worked is connected to the collecting unit 10, and the sitting posture monitoring unit 25 is able to monitor the seat of the vehicle 200
The sitting posture of 202 upper passenger, and then control the work shape of first pickup unit 11 and second pickup unit 12
State, and then make first pickup unit 11 and 12 coordinated of the second pickup unit, it completes to the phonetic order 300
Acquisition.
For example, the passenger when the vehicle 200 is sat against the backrest of the seat 202 of the vehicle 200
Immediately, the sitting posture monitoring unit 25 is able to the shape for monitoring passenger against 202 sitting of the seat of the vehicle 200
State, and control second pickup unit 12 of the chair headrest 2020 for the seat 202 for being set to the vehicle 200
The sound that main acquisition passenger is sent out, and be one first phonetic order 301 by collected voice command, it controls simultaneously
The first pickup unit 11 acquisition background sound being set near the middle control flow of the vehicle 200, and by collected sound
Sound is named as one second phonetic order 302.
The voice receiving unit 21 receives institute from first pickup unit 11 and second pickup unit 12 respectively
The first phonetic order 301 and second phonetic order 302 are stated, and the phonetic order is sent to the Audio Processing Unit
26。
The Audio Processing Unit 26 is able to according to described in rejecting on the basis of the background sound in second phonetic order 302
Background sound in first phonetic order 301 generates a third phonetic order 303.
It is understood that due to the third phonetic order 303 be rejected it is acquired after background sound,
In the third phonetic order 303, the phonetic order 300 that passenger is sent out is more clear, the background being subject to
The interference of sound is reduced, and can improve 300 identified efficiency of the phonetic order and accuracy that passenger is sent out.
Likewise, when the sitting posture monitoring unit 25 monitors passenger far from vehicle backrest sitting, controllably set up
Second pickup unit 12 for being placed in the chair headrest 2020 of the seat 202 of the vehicle 200 mainly acquires background sound,
And by collected voice command be first phonetic order 301, while control is set to the middle control of the vehicle 200
The sound that first pickup unit 11 acquisition passenger near system screen 203 is sent out, and collected sound is ordered
Entitled second phonetic order 302.The Audio Processing Unit 26 is able to pick on the basis of the background sound in the first phonetic order 301
Except the background sound in second phonetic order 302, the third phonetic order 303 is generated.
The sitting posture monitoring unit 25 further comprises a monitoring modular 251 and an analysis and Control module 252, the monitoring
Module 251 and the analysis and Control module 252 are mutually communicatively coupled, the first pickup list of the collecting unit 10
Member 11 and second pickup unit 12 are controllably connected to the analysis and Control module 252 respectively, wherein the monitoring
Module 251 is able to the sitting posture state of monitoring passenger, and generates a status information, and the analysis and Control module 252 is connect
It receives the status information, and first pickup unit 11 and second pickup unit 12 is controlled according to the status information
Working condition.
Preferably, the monitoring unit 251 is implemented as imaging sensor, and described image sensor is able to acquisition rider
State pictorial information of the member relative to the seat 202 of the vehicle 200, the analysis and Control module 252 are able to receive institute
Pictorial information is stated, and analyzes the state of passenger according to the pictorial information, and then controls 11 He of the first pickup unit
The working condition of second pickup unit 12.Optionally, the monitoring unit 251 can also be communicatively connected in a network in described
Imaging sensor.
For example, when the state of the collected passenger of described image sensor institute is against the vehicle 200
When the backrest sitting of the seat 202, the analysis and Control module 252 controls second pickup unit 12 and acquires passenger
The phonetic order 300 sent out controls first pickup unit 11 and acquires background sound in the vehicle 200.Work as institute
State imaging sensor collected passenger state be the seat 202 far from the vehicle 200 backrest sitting
When, the analysis and Control module 252 controls second pickup unit 12 and acquires background sound in the vehicle 200, controls institute
State the phonetic order 300 that the first pickup unit 11 acquisition passenger is sent out.
Certainly, it will be appreciated by those skilled in the art that, the monitoring unit 252 can also be implemented as one group of pressure
Sensor, and the pressure sensor may be placed at the seat 202 of the vehicle 200 backrest and/or cushion it is more
A position, the pressure sensor are able to collected pressure being sent to the analysis and Control module 252, the analysis and Control
Module 252 is able to the state letter by bus for the Pressure Analysis passenger born according to the pressure sensor for being set to each point
Breath, and control the working condition of first pickup unit 11 and second pickup unit 12.Optionally, the monitoring unit
252 can also be communicatively connected in a network in the pressure sensor.
For example, when the pressure sensor of the backrest for the seat 202 for being set to the vehicle 200 does not collect
Pressure and the pressure sensor for being set to the cushion of the seat 202 of the vehicle 200 collects larger pressure, then judge
The backrest sitting of the seat 202 of the passenger far from the vehicle 200, then the analysis and Control module 252 control described
Second pickup unit 12 acquires the background sound in the vehicle 200, controls first pickup unit 11 and acquires passenger institute
The phonetic order 300 sent out.When the pressure sensor acquisition of the backrest for the seat 202 for being set to the vehicle 200
When to larger pressure, then it can determine that backrest sitting of the passenger close to the seat 202 of the vehicle 200, then it is described
Analysis and Control module 252 controls second pickup unit 12 and acquires the phonetic order 300 that passenger is sent out, control
Background sound in first pickup unit, 11 collection vehicle.
Certainly, it will be appreciated by those skilled in the art that, the monitoring unit 251 can be implemented as Distance-sensing
Device, the range sensor may be placed at the position of the backrest of the seat 202 of the vehicle 200, the analysis and Control
It controls the position of the passenger that module 252 is acquired according to the range sensor seat 202 of the vehicle 200 relatively
Make the working condition of first pickup unit 11 and second pickup unit 12.
For example, when the collected passenger of the range sensor is close to the seat 202 of the vehicle 200
Backrest sitting when, then the analysis and Control module 252, which controls second pickup unit 12 and acquires passenger, is sent out
The phonetic order 300 gone out controls first pickup unit 11 and acquires background sound in the vehicle 200.When it is described away from
When the backrest sitting of the seat 202 of the passenger collected from sensor far from the vehicle 200, then described point
Analysis control module 252 controls second pickup unit 12 and acquires background sound in the vehicle 200, controls first pickup
Unit 11 acquires the phonetic order 300 that passenger is sent out.
The judging unit 23 is able to receive the third phonetic order 303 from the Audio Processing Unit 26, and compares
Whether the third phonetic order 303 belongs to same sender with raw tone instruction, will if belonging to same sender
The third phonetic order 303 is transmitted to the processing unit 24, and the processing unit 24 is according to the third phonetic order 303
Control vehicle 200 executes corresponding action.If it is determined that the third phonetic order 303 is not belonging to together with raw tone instruction
The third phonetic order 303 is not then transmitted to the processing unit 24 by one sender, and the vehicle 200 does not execute accordingly yet
Action.
It is noted that also would know that the passenger of the vehicle 200 in institute by the sitting posture monitoring unit 25
The substantially seat position in vehicle 200 is stated, the phonetic order that neighbouring pickup unit acquisition passenger is sent out then is controlled,
Control the pickup unit acquisition background sound near other seats.
For example, when vehicle occupant person is located at driver seat 2021 of the vehicle 200, the sitting posture prison
The monitoring unit 251 for surveying unit 25 can be according to one or more in imaging sensor, pressure sensor or range sensor
The mode of combination knows that passenger is located at the driver seat 2021 of the vehicle 200, and passenger is then located at institute
It states the driver seat 2021 of vehicle 200 this information and is sent to the analysis and Control module 252, the analysis and Control module
252 the second pickup unit 12 acquisitions for being controlled near the driver seat 2021 for being located at the vehicle 200 are ridden
The acquisition background sound of the pickup unit near non-driver seat is located in the phonetic order 300 that member is sent out, control.
Such as Fig. 7, according to another aspect of the present invention, the present invention further provides an audio recognition methods based on seat
700, wherein the audio recognition method 700 includes the following steps:
Step 701:Monitor the state of passenger;
Step 702:According to the sitting posture of passenger control be arranged at the vehicle 200 the middle control flow 203 or
Person is arranged at one first pickup unit 11 near the middle control flow 203 and is arranged at the described of the vehicle 200
The working condition of one second pickup unit 12 of chair headrest 2020, and control first pickup unit 11 and acquire one first language
Sound instruction 301 and second pickup unit 12 acquire one second phonetic order 302;And
Step 703:According to first phonetic order 301 and second phonetic order 302, background sound is rejected, is generated
One third phonetic order 303, for controlling the vehicle 200.
Wherein, in the step 302, when passenger is close to the backrest sitting of the seat 202 of the vehicle 200
When, second pickup unit 12 acquires the sound that passenger is sent out, and first pickup unit 11 acquires background sound.When multiplying
When the backrest sitting of the seat 202 of the vehicle personnel far from the vehicle 200, second pickup unit 12 acquires background
Sound, first pickup unit 11 acquire the sound that passenger is sent out.
Such as Figure 1A, Figure 1B, Fig. 1 C and Fig. 8, the speech recognition system 100 provided by the present invention based on seat the 4th compared with
Good embodiment is set forth, wherein the speech recognition system 100 includes a collecting unit 10 and a control unit 20, the acquisition
Unit 10 and described control unit 20 are mutually communicatively coupled.The collecting unit 10 is able to acquire on the vehicle 200
At least phonetic order 300 that sends out of personnel, and the phonetic order 300 is transmitted to described control unit 20, the control
Unit 20 processed, which is able to control the vehicle 200 according to the phonetic order 300, generates corresponding action.
The collecting unit 10 includes being arranged at the middle control flow 203 of the vehicle 200 or being arranged at institute
It states at least one first pickup unit 11 near the middle control flow 203 of vehicle 200 and is arranged at the vehicle 200
At least one second pickup unit 12 of the chair headrest 2020 of the seat 202.First pickup unit 11 and described
Second pickup unit 12 cooperates and forms a radio reception field 500 in the seating space of the vehicle 200, for acquiring described
The phonetic order 300 that the passenger in the seating space of vehicle 200 is sent out.
Such as Figure 1A to Fig. 1 C, second pickup unit 12 further comprises the institute for being arranged at the driver seat 2021
It states first sound pick up equipment 121 of chair headrest 2020, be arranged at the chair headrest of the assistant driver seat 2022
2020 second sound pick up equipment 122, be arranged at the first seat of the heel row 2023 the chair headrest 2020 institute
State third sound pick up equipment 123, be arranged at it is described after ranked second seat 2024 the chair headrest 2020 the described 40th
Mixer 124 and be arranged at it is described after ranked third seat 2025 the chair headrest 2020 the 5th sound pick up equipment
125。
It should be noted that illustrated in the present embodiment with the vehicle 200 with two rows of totally five seats, still,
It will be appreciated by those ordinary people skilled in the art that the speech recognition system 100 provided by the present invention based on seat is not only
It can be applied to the vehicle 200 with two rows of totally five seats, can be applicable to tool, there are one the vehicles of seat
200, the vehicle 200 of two seats, the even vehicle 200 with multiple rows of seat, the seat of the vehicle 200
Quantity and set-up mode be not construed as limiting the invention.
Described control unit 20 includes a voice receiving unit 21, an Audio Processing Unit 26, at a judging unit 23, one
Unit 24 and a sitting posture monitoring unit 25 are managed, wherein the voice receiving unit 21, the Audio Processing Unit 26, described sentencing
Disconnected unit 23, the processing unit 24 and the sitting posture monitoring unit 25 are mutually communicatively coupled, and the acquisition
First pickup unit 11 and second pickup unit 12 of unit 10 are communicatively connected in a network are connect in the voice respectively
Receive unit 21.The voice receiving unit 21 is able to receive one first phonetic order that first pickup unit 11 is acquired
301 and one second phonetic order 302 that is acquired of second pickup unit 12.The Audio Processing Unit 26 is able to integrate institute
The first phonetic order 301 and second phonetic order 302 are stated, and a third phonetic order 303 is generated after rejecting background sound, with
For controlling the vehicle 200.The judging unit 23 is able to judge whether the phonetic order 300 belongs to raw tone instruction
In the same sender.The processing unit 24, which is able to control the vehicle 200 according to the phonetic order 300, to be generated accordingly
Action.The sitting posture monitoring unit 22 is able to the sitting posture state of monitoring passenger, and according to the sitting posture state control of passenger
The working condition for making first pickup unit 11 and second pickup unit 12 makes first pickup unit 11 and described
Second pickup unit 12, which cooperates, completes radio reception work.
It is in place of the speech recognition system 100 of this preferred embodiment and the difference of third preferred embodiment, wherein
The collecting unit 10 further comprises that a third pickup unit 13, the third pickup unit 13 include being arranged at the vehicle
One first audio signal reception device 131 at the back of 200 driver seat 2021 and the pair for being arranged at the vehicle 200
One second audio signal reception device 132 at the back of driver seat 2022.
It should be noted that only just there is the seat citing of two rows of five seats in the preferred embodiment, certainly, this
The those skilled in the art in field are it is understood that the speech recognition system 100 provided by the present invention based on seat can be fitted
For the vehicle with more numbers of rows and the seat of quantity, correspondingly, the audio signal reception device included by the third pickup unit 13
Number can also be increased, the present invention is not limited by the number of rows and seat number of the specific seat of vehicle.
It will be appreciated by those skilled in the art that when passenger be located at the back seat of the vehicle 200 when
Wait, passenger and first pickup unit 11 that is arranged near the middle control flow 203 of the vehicle 200 it
Between distance it is larger, be arranged at first pickup unit 11 near the middle control flow 203 of the vehicle 200 very
Hardly possible accurately collects the phonetic order that back seat passenger is sent out.
By the way that first audio signal reception device 131 is set in the back of the driver seat 2021 and by second radio reception
Device 132 makes the third pickup unit 13 close to positioned at back seat in the mode of the back of the assistant driver seat 2022
Passenger, carry out radio reception in a manner of close, and then improve the institute's predicate sent out positioned at the passenger of vehicle heel row
Sound instructs 300 identified efficiency.
When passenger is located at the back seat of the vehicle 200, the sitting posture monitoring unit 25 is monitored first
It is described to be located at the specific seat of vehicle heel row to passenger, it then controls and is arranged at described the of the chair headrest 2020
Two pickup units 12 and the third pickup unit 13 work, with by making second pickup unit 12 and the third pickup
The mode that unit 13 forms the radio reception field 500 acquires the phonetic order 300 of passenger, meanwhile, control is set to institute
It states first pickup unit 11 near the middle control flow 203 of vehicle 200 and is set to other seats of the vehicle 200
Second pickup unit 12 of chair acquires background sound.
For example, when passenger is located at the first seat of the heel row 2023 of the vehicle 200, then the detection is single
Member 25 is able to know passenger according to one or more combinations in image acquisition device, pressure sensor or range sensor
Positioned at the first seat of the heel row 2023 of the vehicle 200, then control be set to the vehicle 200 it is described after ranked first
The third sound pick up equipment 123 of the chair headrest 2020 of seat 2023 is driven with the described of the vehicle 200 is arranged at
The phonetic order 300 of the first audio signal reception device 131 acquisition passenger of the back of seat 2021 is sailed, while control is set
It is placed in first pickup unit 11 of the middle control flow 203 of the vehicle 200, first sound pick up equipment 121, described
Second sound pick up equipment 122, the 4th sound pick up equipment 124, the 5th sound pick up equipment 125 and second audio signal reception device
Background sound in 132 collection vehicles.
Further, the sitting posture monitoring unit 25 is able to further to monitor passenger ranked first seat in the rear
Specific sitting posture when 2023 sitting, and then control the work shape of the third sound pick up equipment 123 and first audio signal reception device 131
State.
For example, when passenger abuts the back sitting of the first seat of the heel row 2023, then rider
Member is controlled the third sound pick up equipment 123 and adopts close to the third sound pick up equipment 123, at this time the sitting posture monitoring unit 25
The phonetic order 300 that collection passenger is sent out, and control first audio signal reception device 131 and acquire background sound.When by bus
When back sitting of the personnel far from the first seat of the heel row 2023, then passenger is close to first audio signal reception device
131, at this time the sitting posture monitoring unit 25 be controlled first audio signal reception device 131 acquire passenger sent out it is described
Phonetic order 300, and control the third sound pick up equipment 123 and acquire background sound.
The Audio Processing Unit 26 is able to receive the phonetic order 300 that the third sound pick up equipment 123 is acquired
With the collected phonetic orders 300 of the institute of first audio signal reception device 131, and background is rejected from the phonetic order 300
Sound obtains the third phonetic order 303.
It is noted that when vehicle occupant person is located at the driver seat 2021 of the vehicle 200, institute
It states sitting posture detection unit 25 and is controlled first sound pick up equipment 121 and first pickup unit 11 acquisition passenger institute
The phonetic order 300 sent out, and control the background sound of 13 collection vehicle of third pickup unit.It should be pointed out that
Since the third pickup unit 13 is close to the back seat of the vehicle 200, the third pickup unit 13 can be better
Acquire the background sound in the vehicle 200, the speech processing module 22 to the phonetic order 303 handled when
It waits, can reject background sound is more abundant, correspondingly, the phonetic order 300 that passenger is sent out can become
It is more clear, phonetic recognization rate and accuracy higher.
Refer to the attached drawing 9, other side under this invention, the present invention further provides a speech recognition sides based on seat
Method 900, wherein the audio recognition method 900 includes the following steps:
Step 901, by being arranged at least near the middle control flow 203 of a vehicle 200 or the middle control flow 203
One first pickup unit 11 and the vehicle 200 an at least seat 202 be arranged at least one second pickup unit 12 mode,
A radio reception field 500 is formed in the seating space of the vehicle 200;With
Step 902, when the phonetic order for controlling the vehicle 200 is issued in the seating space of the vehicle 200
And when being transmitted to the radio reception field 500, first pickup unit 11 and second pickup unit 12 are controlled mutually to assist
The mode of work acquires the phonetic order.
Refer to the attached drawing 10, other side under this invention, the present invention further provides an audio recognition method 1000,
Described in audio recognition method 1000 include the following steps:
Step 1001, a radio reception field 500 is formed in the seating space of a vehicle 200;
Step 1002, it is described when the phonetic order 300 of the vehicle 200 described in the desired control propagates to the radio reception field 500
Phonetic order 300 is used to form one first pickup unit 11 and the acquisition of one second pickup unit 12 of the radio reception field 500;With
And
Step 1003, according to one first phonetic order 301 of first pickup unit 11 acquisition and second pickup
One second phonetic order 302 that unit 12 acquires generates the third phonetic order 303 for controlling the vehicle 200.
Preferably, in the step (A), the radio reception field 500 is a dynamic radio reception field.Specifically, in the step
Suddenly in (A), first pickup is set near control flow 203 or the middle control flow 203 in the one of the vehicle 200
Unit 11, and the vehicle 200 the setting of an at least seat 202 by adjustable second pickup unit 12, with by
First pickup unit 11 and second pickup unit 12 form dynamic radio reception field.
Further, in the step (A), control flow 203 or the middle control flow in the one of the vehicle 200
First pickup unit 11 is set near 203, and is arranged described the second ten in an at least seat 202 for the vehicle 200
Sound unit 12, to form the radio reception field 500 by first pickup unit 11 and second pickup unit 12.
It should be understood by those skilled in the art that the embodiment of the present invention shown in foregoing description and attached drawing is only used as illustrating
And it is not intended to limit the present invention.The purpose of the present invention has been fully and effectively achieved.The function and structural principle of the present invention exists
It shows and illustrates in embodiment, under without departing from the principle, embodiments of the present invention can have any deformation or modification.
Claims (20)
1. the speech recognition system based on seat, which is characterized in that including:
One control unit;With
One collecting unit, wherein the collecting unit includes at least two pickup units, pickup unit quilt described in wherein at least one
It is set to the middle control flow of a vehicle or is neighboringly set to the middle control flow, the pickup unit in addition is set
In the seat of the vehicle, wherein each pickup unit is communicatively connected in a network respectively in described control unit, wherein institute
It states each pickup unit of control unit control and acquires phonetic order for controlling the vehicle in a manner of co-operating.
2. speech recognition system according to claim 1, wherein be arranged at the vehicle the middle control flow or
The pickup unit for being neighboringly set to the middle control flow is one first pickup unit, is arranged at the institute of the seat
It is one second pickup unit to state pickup unit, wherein first pickup unit is for acquiring one first phonetic order, described the
Two pickup units for acquire one second phonetic order, wherein the sound quality of described control unit first phonetic order and
The sound quality of second phonetic order, with according to a sound quality in first phonetic order and second phonetic order compared with
Good phonetic order generates a third phonetic order, for controlling the vehicle.
3. speech recognition system according to claim 1, wherein be arranged at the vehicle the middle control flow or
The pickup unit for being neighboringly set to the middle control flow is one first pickup unit, is arranged at the institute of the seat
It is one second pickup unit to state pickup unit, wherein first pickup unit is for acquiring one first phonetic order, described the
Two pickup units are for acquiring one second phonetic order, wherein described control unit by first phonetic order and described second
Phonetic order is superimposed to generate a third phonetic order, for controlling the vehicle.
4. speech recognition system according to claim 1, wherein be arranged at the vehicle the middle control flow or
The pickup unit for being neighboringly set to the middle control flow is one first pickup unit, is arranged at the institute of the seat
It is one second pickup unit to state pickup unit, wherein first pickup unit is for acquiring one first phonetic order, described the
Two pickup units are for acquiring one second phonetic order, wherein described control unit by first phonetic order and described second
Phonetic order carries out difference set processing to generate a third phonetic order, for controlling the vehicle.
5. speech recognition system according to claim 1, wherein be arranged at the vehicle the middle control flow or
The pickup unit for being neighboringly set to the middle control flow is one first pickup unit, is arranged at the institute of the seat
It is one second pickup unit to state pickup unit, wherein first pickup unit is for acquiring one first phonetic order, described the
Two pickup units can be intercepted for acquiring one second phonetic order, wherein described control unit in first phonetic order
The preferable segment of sound quality in the preferable segment of sound quality and second phonetic order is to generate a third phonetic order, for control
Make the vehicle.
6. speech recognition system according to claim 2, wherein described control unit first phonetic order and
The foundation condition of second phonetic order is:The condition group of the size of sound, the frequency of sound, the size of background sound composition.
7. the audio recognition method based on seat, which is characterized in that the audio recognition method includes the following steps:
(a) by be arranged near the middle control flow of a vehicle or the middle control flow at least one first pickup unit and
The mode of at least seat setting at least one second pickup unit of the vehicle, forms one in the seating space of the vehicle and receives
Sound field;With
(b) it is issued in the seating space of the vehicle when for controlling the phonetic order of the vehicle and is transmitted to the receipts
When sound field, controls first pickup unit and second pickup unit is acquired the voice in a manner of co-operating and referred to
It enables.
8. audio recognition method according to claim 7, wherein in the step (a), the second pickup unit quilt
It is adjustably set to the seat, to the radio reception for making first pickup unit and second pickup unit be formed
Field is a dynamic radio reception field.
9. an at least third pickup is arranged wherein in the step (a) in audio recognition method according to claim 7
Unit is at least one seat, to form the radio reception by the third pickup unit and second pickup unit
.
10. audio recognition method according to claim 9, wherein in the above-mentioned methods, the second pickup unit quilt can
It is adjustably set to the seat, to the radio reception field for making second pickup unit and the third pickup unit be formed
For a dynamic radio reception field.
11. audio recognition method according to claim 9, wherein in the above-mentioned methods, the third pickup unit quilt can
It is adjustably set to the seat, to the radio reception field for making second pickup unit and the third pickup unit be formed
For a dynamic radio reception field.
12. audio recognition method according to claim 10, wherein in the above-mentioned methods, the third pickup unit quilt can
It is adjustably set to the seat, to the radio reception field for making second pickup unit and the third pickup unit be formed
For dynamic radio reception field.
13. further being wrapped wherein in the step (b) according to any audio recognition method in claim 7 to 12
Include step:Compare the one second of one first phonetic order and second pickup unit acquisition that first pickup unit acquires
The sound quality of phonetic order refers to according to a preferable voice of sound quality in first phonetic order and second phonetic order
It enables and generates a third phonetic order, for controlling the vehicle.
14. further being wrapped wherein in the step (b) according to any audio recognition method in claim 7 to 12
Include step:It is superimposed the one second of one first phonetic order and second pickup unit acquisition that first pickup unit acquires
Phonetic order and generate a third phonetic order, for controlling the vehicle.
15. further being wrapped wherein in the step (b) according to any audio recognition method in claim 7 to 12
Include step:Difference set handles the one of one first phonetic order that first pickup unit acquires and second pickup unit acquisition
Second phonetic order and generate a third phonetic order, for controlling the vehicle.
16. further being wrapped wherein in the step (b) according to any audio recognition method in claim 7 to 12
Include step:The sound quality intercepted in the preferable segment of sound quality and second phonetic order in first phonetic order is preferable
Segment and generate a third phonetic order, for controlling the vehicle.
17. an audio recognition method, which is characterized in that the audio recognition method includes the following steps:
(A) a radio reception field is formed in the seating space of a vehicle;
(B) when the phonetic order of the vehicle described in the desired control propagates to the radio reception field, the phonetic order is used to form
One first pickup unit of the radio reception field and the acquisition of one second pickup unit;And
(C) one second acquired according to one first phonetic order of first pickup unit acquisition and second pickup unit
Phonetic order generates the third phonetic order for controlling the vehicle.
18. audio recognition method according to claim 17, wherein in the step (A), the radio reception field is one dynamic
State radio reception field.
19. audio recognition method according to claim 17, wherein in the step (A), in the one of the vehicle
First pickup unit is set near control flow or the middle control flow, and is arranged in an at least seat for the vehicle
Second pickup unit, to form the radio reception field by first pickup unit and second pickup unit.
20. audio recognition method according to claim 18, wherein in the step (A), in the one of the vehicle
First pickup unit is set near control flow or the middle control flow, and is arranged in an at least seat for the vehicle
It is described dynamic to be formed by first pickup unit and second pickup unit by adjustable second pickup unit
State radio reception field.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810293765.7A CN108621981A (en) | 2018-03-30 | 2018-03-30 | Speech recognition system based on seat and its recognition methods |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810293765.7A CN108621981A (en) | 2018-03-30 | 2018-03-30 | Speech recognition system based on seat and its recognition methods |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108621981A true CN108621981A (en) | 2018-10-09 |
Family
ID=63704729
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810293765.7A Pending CN108621981A (en) | 2018-03-30 | 2018-03-30 | Speech recognition system based on seat and its recognition methods |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108621981A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493865A (en) * | 2018-10-17 | 2019-03-19 | 北京车和家信息技术有限公司 | Signal processing method, terminal and vehicle |
CN110556108A (en) * | 2019-09-05 | 2019-12-10 | 上海擎感智能科技有限公司 | Method, system, medium and vehicle-mounted terminal for starting equipment in vehicle without key |
CN111516618A (en) * | 2019-02-05 | 2020-08-11 | 李尔公司 | Electrical assembly |
WO2021217572A1 (en) * | 2020-04-30 | 2021-11-04 | 华为技术有限公司 | In-vehicle user positioning method, on-board interaction method, on-board device, and vehicle |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090055170A1 (en) * | 2005-08-11 | 2009-02-26 | Katsumasa Nagahama | Sound Source Separation Device, Speech Recognition Device, Mobile Telephone, Sound Source Separation Method, and Program |
US20090055180A1 (en) * | 2007-08-23 | 2009-02-26 | Coon Bradley S | System and method for optimizing speech recognition in a vehicle |
CN102498709A (en) * | 2009-05-14 | 2012-06-13 | 鹦鹉股份有限公司 | Method for selecting one of two or more microphones for a speech-processing system such as a hands-free telephone device operating in a noisy environment |
WO2012165657A1 (en) * | 2011-06-03 | 2012-12-06 | 日本電気株式会社 | Speech processing system, speech processing device, speech processing method, and program therefor |
CN103678456A (en) * | 2012-09-11 | 2014-03-26 | 通用汽车环球科技运作有限责任公司 | Voice stamp-driven in-vehicle functions |
CN104572258A (en) * | 2013-10-18 | 2015-04-29 | 通用汽车环球科技运作有限责任公司 | Methods and apparatus for processing multiple audio streams at vehicle onboard computer system |
CN105913844A (en) * | 2016-04-22 | 2016-08-31 | 乐视控股(北京)有限公司 | Vehicle-mounted voice acquisition method and device |
CN105957523A (en) * | 2016-04-22 | 2016-09-21 | 乐视控股(北京)有限公司 | Vehicular system control method and device |
JP2017047784A (en) * | 2015-09-02 | 2017-03-09 | アルパイン株式会社 | Voice input device |
CN206124669U (en) * | 2016-09-14 | 2017-04-26 | 北京汽车股份有限公司 | Car and air conditioner control system thereof |
CN106828102A (en) * | 2016-11-25 | 2017-06-13 | 未来汽车科技(深圳)有限公司 | Automobile instrument panel and control method |
CN107465986A (en) * | 2016-06-03 | 2017-12-12 | 法拉第未来公司 | The method and apparatus of audio for being detected and being isolated in vehicle using multiple microphones |
CN206781656U (en) * | 2017-05-22 | 2017-12-22 | 延锋安道拓座椅有限公司 | Motor-vehicle seat system with bluetooth conversation and acoustic function |
CN107554456A (en) * | 2017-08-31 | 2018-01-09 | 上海博泰悦臻网络技术服务有限公司 | Vehicle-mounted voice control system and its control method |
CN107863106A (en) * | 2017-12-12 | 2018-03-30 | 长沙联远电子科技有限公司 | Voice identification control method and device |
-
2018
- 2018-03-30 CN CN201810293765.7A patent/CN108621981A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090055170A1 (en) * | 2005-08-11 | 2009-02-26 | Katsumasa Nagahama | Sound Source Separation Device, Speech Recognition Device, Mobile Telephone, Sound Source Separation Method, and Program |
US20090055180A1 (en) * | 2007-08-23 | 2009-02-26 | Coon Bradley S | System and method for optimizing speech recognition in a vehicle |
CN102498709A (en) * | 2009-05-14 | 2012-06-13 | 鹦鹉股份有限公司 | Method for selecting one of two or more microphones for a speech-processing system such as a hands-free telephone device operating in a noisy environment |
WO2012165657A1 (en) * | 2011-06-03 | 2012-12-06 | 日本電気株式会社 | Speech processing system, speech processing device, speech processing method, and program therefor |
CN103678456A (en) * | 2012-09-11 | 2014-03-26 | 通用汽车环球科技运作有限责任公司 | Voice stamp-driven in-vehicle functions |
CN104572258A (en) * | 2013-10-18 | 2015-04-29 | 通用汽车环球科技运作有限责任公司 | Methods and apparatus for processing multiple audio streams at vehicle onboard computer system |
JP2017047784A (en) * | 2015-09-02 | 2017-03-09 | アルパイン株式会社 | Voice input device |
CN105913844A (en) * | 2016-04-22 | 2016-08-31 | 乐视控股(北京)有限公司 | Vehicle-mounted voice acquisition method and device |
CN105957523A (en) * | 2016-04-22 | 2016-09-21 | 乐视控股(北京)有限公司 | Vehicular system control method and device |
CN107465986A (en) * | 2016-06-03 | 2017-12-12 | 法拉第未来公司 | The method and apparatus of audio for being detected and being isolated in vehicle using multiple microphones |
CN206124669U (en) * | 2016-09-14 | 2017-04-26 | 北京汽车股份有限公司 | Car and air conditioner control system thereof |
CN106828102A (en) * | 2016-11-25 | 2017-06-13 | 未来汽车科技(深圳)有限公司 | Automobile instrument panel and control method |
CN206781656U (en) * | 2017-05-22 | 2017-12-22 | 延锋安道拓座椅有限公司 | Motor-vehicle seat system with bluetooth conversation and acoustic function |
CN107554456A (en) * | 2017-08-31 | 2018-01-09 | 上海博泰悦臻网络技术服务有限公司 | Vehicle-mounted voice control system and its control method |
CN107863106A (en) * | 2017-12-12 | 2018-03-30 | 长沙联远电子科技有限公司 | Voice identification control method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493865A (en) * | 2018-10-17 | 2019-03-19 | 北京车和家信息技术有限公司 | Signal processing method, terminal and vehicle |
CN111516618A (en) * | 2019-02-05 | 2020-08-11 | 李尔公司 | Electrical assembly |
CN110556108A (en) * | 2019-09-05 | 2019-12-10 | 上海擎感智能科技有限公司 | Method, system, medium and vehicle-mounted terminal for starting equipment in vehicle without key |
WO2021217572A1 (en) * | 2020-04-30 | 2021-11-04 | 华为技术有限公司 | In-vehicle user positioning method, on-board interaction method, on-board device, and vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108621981A (en) | Speech recognition system based on seat and its recognition methods | |
CN107650862A (en) | A kind of automotive keyless entering system and control method based on smart mobile phone close to perception | |
CN105835804A (en) | Method and apparatus for monitoring a rear passenger seating area of a vehicle | |
WO2017183372A1 (en) | Vehicle interior conversion assist device | |
CN105128764A (en) | Automobile audio control method and system | |
CN106611602A (en) | Vehicle sound collection apparatus and sound collection method | |
DE102018126721A1 (en) | SYSTEMS AND METHODS OF DELIVERING DISCREET AUTONOMOUS VEHICLE OWN NOTIFICATIONS | |
CN107010073A (en) | System and method based on the occupancy condition in data aggregate automatic detection vehicle | |
CN110789477B (en) | Control method and device for test driving vehicle, cloud platform and vehicle-mounted intelligent equipment | |
JP2018027731A (en) | On-vehicle device, control method of on-vehicle device, and content providing system | |
CN107351853A (en) | A kind of active noise reduction seat suitable for high ferro business class | |
JP2021066275A (en) | Vehicle control device | |
CN102651215B (en) | Noise producing device of automobile engine and control method thereof | |
CN112735408A (en) | Voice control system and control method for automobile seat | |
CN208498402U (en) | Seat can radio reception vehicle | |
JP5687889B2 (en) | Vehicle interior monitoring device | |
CN107958573A (en) | A kind of traffic control method being applied in intelligent vehicle | |
CN107776545A (en) | Open method, opening device and the automobile of automobile body components | |
CN109177822A (en) | A kind of operator seat facility adjusting method and system | |
CN108099785A (en) | A kind of traffic control method applied in intelligent vehicle | |
WO2019061502A1 (en) | Vehicle suspension adjustment method and system, and adjustable suspended vehicle | |
CN108674344A (en) | Speech processing system based on steering wheel and its application | |
CN107933425A (en) | A kind of in-car life-detection system based on technology of Internet of things | |
CN107231442A (en) | Multi-functional unperturbed calling system and its control method | |
CN107921918A (en) | The adjust automatically set into vehicle vehicle in front |
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 |