CN105869635A - Speech recognition method and system - Google Patents
Speech recognition method and system Download PDFInfo
- Publication number
- CN105869635A CN105869635A CN201610142719.8A CN201610142719A CN105869635A CN 105869635 A CN105869635 A CN 105869635A CN 201610142719 A CN201610142719 A CN 201610142719A CN 105869635 A CN105869635 A CN 105869635A
- Authority
- CN
- China
- Prior art keywords
- printer
- control instruction
- voice
- unit
- command message
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004891 communication Methods 0.000 claims description 16
- 238000007639 printing Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000002093 peripheral effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
- Accessory Devices And Overall Control Thereof (AREA)
Abstract
The embodiment of the invention provides a speech recognition method and a speech recognition system, belonging to the technical field of speech recognition. The speech recognition method is applied to a speech recognition terminal, and the speech recognition terminal is connected with a printer. The speech recognition method comprises the following steps: receiving speech control information; detecting the state of the printer; searching for a linguistic model corresponding to the state of the printer, wherein a plurality of linguistic models are prestored in the speech recognition terminal, and correspond to the different states of the printer in a one-to-one correspondence manner; calling the found linguistic model, and carrying out recognition on the received speech control information by adopting the linguistic model, thus obtaining a control instruction corresponding to the speech control information; and sending the control instruction to the printer, so that the printer executes the control instruction. With the adoption of the speech recognition method and the speech recognition system, the customizability and the expandability of the speech recognition system are greatly improved.
Description
Technical field
The present invention relates to technical field of voice recognition, in particular to a kind of speech recognition
Method and system.
Background technology
Along with the development of speech recognition technology, the application of speech recognition system is more and more wider
General.Speech recognition of the prior art, can only identify the vocabulary specified.Wherein, voice is known
It is the most substantially a process based on language model computing, and the language model preset determines
Can identify which type of keyword.But the language model of traditional speech recognition system
Being fixing, all kinds of instructions all use same language model to be identified, and this seriously inhibits
The customizability of speech recognition system and extensibility.
Summary of the invention
The purpose of the embodiment of the present invention is to provide a kind of audio recognition method and system, it is intended to
It is effectively improved customizability and the extensibility of speech recognition system.
The embodiment of the present invention is achieved in that
First aspect, a kind of audio recognition method that the embodiment of the present invention provides, it is applied to language
Sound identification terminal, described voice recognition terminal connects printer, described audio recognition method
Including:
Receive Voice command message.
Detect the state of described printer.
Find out the language model corresponding with the state of described printer, described speech recognition
Terminal prestores multiple language model, the plurality of language model respectively with described printer
Different conditions one_to_one corresponding.
Call the described language model found out the described Voice command message received is carried out
Identify, obtain the control instruction corresponding with described Voice command message.
Described control instruction is sent to described printer, so that described printer performs described
Control instruction.
Preferably, described audio recognition method also includes:
Receiving the control instruction sent by described printer and perform feedback, described control instruction is held
Row feeds back the state of described printer after including performing described control instruction.
Switch to perform described control instruction after the corresponding language of the state of described printer
Speech model.
Preferably, the described step that described control instruction is sent to described printer includes:
Monitor whether the communication link between described voice recognition terminal and described printer connects
Logical, if do not connected, then described control instruction is cached, if connection, then by institute
State control instruction and be sent to described printer.
Preferably, described audio recognition method also includes:
Reception voice broadcast instructs.
Search the voice document corresponding with the instruction of described voice broadcast, to institute's voice file
Carrying out voice broadcast, it is right with the instruction of described voice broadcast to prestore in described voice recognition terminal
The voice document answered.
Preferably, the described language model the found out described voice to receiving is called described in
Control message to be identified, obtain the control instruction corresponding with described Voice command message
Step includes:
Call the described language model found out the described Voice command message received is carried out
Calculate, to obtain the characteristic parameter of described Voice command message, described characteristic parameter is carried out
It is converted to the control instruction corresponding with described Voice command message.
Second aspect, a kind of speech recognition system that the embodiment of the present invention provides, including voice
Identification terminal, described voice recognition terminal connects printer, described voice recognition terminal bag
Include:
First receives unit, is used for receiving Voice command message.
First detector unit, for detecting the state of described printer.
First searches unit, for finding out the language corresponding with the state of described printer
Model, prestores multiple language model, the plurality of language mould in described voice recognition terminal
Type respectively with the different conditions one_to_one corresponding of described printer.
Recognition unit, for calling the described language model found out institute's predicate to receiving
Sound control message is identified, and obtains the control instruction corresponding with described Voice command message.
Transmitting element, for described control instruction is sent to described printer, so that described
Printer performs described control instruction.
Preferably, described voice recognition terminal also includes:
Second receives unit, performs anti-for receiving the control instruction sent by described printer
Feedback, described control instruction performs described printing after feedback includes performing described control instruction
The state of machine.
Switch unit, described printer after switching to and performing described control instruction
The language model that state is corresponding.
Preferably, described transmitting element is used for monitoring described voice recognition terminal and described printing
Whether the communication link between machine connects, if do not connected, then carries out described control instruction
Caching, if connection, is then sent to described printer by described control instruction.
Preferably, described voice recognition terminal also includes:
3rd receives unit, is used for receiving voice broadcast instruction.
Second searches unit, for searching the voice literary composition corresponding with the instruction of described voice broadcast
Part.
Report unit, for institute's voice file is carried out voice broadcast, described speech recognition
Terminal prestores the voice document corresponding with the instruction of described voice broadcast.
Preferably, described recognition unit is for calling the described language model found out to reception
To described Voice command message calculate, to obtain the feature of described Voice command message
Parameter, carries out being converted to corresponding with described Voice command message by described characteristic parameter
Control instruction.
The audio recognition method of embodiment of the present invention offer and system, by speech recognition eventually
End prestores multiple language model and multiple language model respectively with the different conditions one of printer
One is corresponding so that the voice that can call pointedly Yu send under printer different conditions
Control the language model corresponding to message and be controlled the identification of instruction, substantially increase voice
The customizability of identification system and extensibility.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below will be to embodiment
The accompanying drawing used required in is briefly described, it will be appreciated that the following drawings illustrate only
Certain embodiments of the present invention, therefore should not be viewed as the restriction to scope, for ability
From the point of view of the those of ordinary skill of territory, on the premise of not paying creative work, it is also possible to according to
These accompanying drawings obtain the accompanying drawing that other are relevant.
The voice recognition terminal that Fig. 1 provides for the embodiment of the present invention and printer interact
Schematic diagram.
The block diagram of the voice recognition terminal that Fig. 2 provides for the embodiment of the present invention.
The flow chart of the audio recognition method that Fig. 3 provides for the embodiment of the present invention.
The flow chart of the another kind of audio recognition method that Fig. 4 provides for the embodiment of the present invention.
The flow chart of the another kind of audio recognition method that Fig. 5 provides for the embodiment of the present invention.
The high-level schematic functional block diagram of the speech recognition system that Fig. 6 provides for the embodiment of the present invention.
Fig. 7 shows for the functional module of the another kind of speech recognition system that the embodiment of the present invention provides
It is intended to.
Fig. 8 shows for the functional module of the another kind of speech recognition system that the embodiment of the present invention provides
It is intended to.
Reference collects:
Voice recognition terminal 100；Printer 200；Memorizer 300；Storage control 400；
Processor 500；Peripheral Interface 600；Input-output unit 700；Audio unit 800；Aobvious
Show unit 900；First receives unit 101；First detector unit 102；First searches unit
103；Recognition unit 104；Transmitting element 105；Second receives unit 201；Switch unit
202；3rd receives unit 301；Second searches unit 302；Report unit 303.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below will
In conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, it is fully described by, it is clear that described embodiment is a part of embodiment of the present invention,
Rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under not making creative work premise, broadly falls into
The scope of protection of the invention.
It should also be noted that similar label and letter represent similar terms in following accompanying drawing, because of
This, be defined in the most a certain Xiang Yi accompanying drawing, then it is right to need not in accompanying drawing subsequently
It defines further and explains.Meanwhile, in describing the invention, term " first ",
" second " etc. are only used for distinguishing and describe, and it is not intended that indicate or hint relative importance.
As it is shown in figure 1, be the voice recognition terminal 100 that provides of present pre-ferred embodiments with
The schematic diagram that printer 200 interacts.Described voice recognition terminal 100 by network with
One or more printers 200 are communicatively coupled, to carry out data communication or mutual.
As in figure 2 it is shown, the side of a kind of described voice recognition terminal 100 of the present embodiment offer
Frame schematic diagram.Described voice recognition terminal 100 include memorizer 300, storage control 400,
Processor 500, Peripheral Interface 600, input-output unit 700, audio unit 800, aobvious
Show unit 900.
Described memorizer 300, storage control 400, processor 500, Peripheral Interface 600,
Input-output unit 700, audio unit 800, each element of display unit 900 are the most straight
Connect or be indirectly electrically connected with, to realize the transmission of data or mutual.Such as, these elements
Can realize being electrically connected with by one or more communication bus or holding wire each other.
Wherein, memorizer 300 may be, but not limited to, random access memory 300
(Random Access Memory, RAM), read only memory 300 (Read Only
Memory, ROM), programmable read only memory 300 (Programmable Read-Only
Memory, PROM), erasable read-only memory 300 (Erasable Programmable
Read-Only Memory, EPROM), electricallyerasable ROM (EEROM) 300 (Electric
Erasable Programmable Read-Only Memory, EEPROM) etc..Wherein,
Memorizer 300 is used for storing program, described processor 500 receive execution instruction after,
Perform described program, the language of the flow definition that aforementioned embodiment of the present invention any embodiment discloses
Method performed by sound identification terminal 100 can apply in processor 500, or by
Reason device 500 realizes.
Processor 500 is probably a kind of IC chip, has the disposal ability of signal.
Above-mentioned processor 500 can be general processor 500, including central processing unit
500 (Central Processing Unit is called for short CPU), network processing unit
500 (Network Processor is called for short NP) etc.；Can also is that digital signal processor
500 (DSP), special IC (ASIC), ready-made programmable gate array (FPGA) or its
His PLD, discrete gate or transistor logic, discrete hardware components.
Can realize or perform disclosed each method, step and the box in the embodiment of the present invention
Figure.General processor 500 can be that microprocessor 500 or this processor 500 can also
It it is the processor 500 etc. of any routine.
Described Peripheral Interface 600 various input/output devices are coupled to processor 500 and
Memorizer 300.In certain embodiments, Peripheral Interface 600, processor 500 and storage
Controller 400 can realize in one single chip.In some other example, they are permissible
Realized by independent chip respectively.
Input-output unit 700 is used for being supplied to user input data and realizes user and institute's predicate
Sound identification terminal 100 (or printer 200) mutual.Described input-output unit 700
May be, but not limited to, mouse and keyboard etc..
Audio unit 800 provides a user with audio interface, and it can include one or more Mike
Wind, one or more speaker and voicefrequency circuit.
Display unit 900 provides one between described server (or local terminal) and user
Individual interactive interface (such as user interface) or be used for showing that view data is to user's reference.
In the present embodiment, described display unit 900 can be liquid crystal display or touch control display.
If touch control display, it can be to support single-point and the capacitance type touch control screen of multi-point touch operation
Or resistance type touch control screen etc..Support that single-point and multi-point touch operation refer to that touch control display can be felt
Should to the touch control operation produced from one or more positions on this touch control display simultaneously,
And the touch control operation this sensed transfers to processor 500 to calculate and process.
As it is shown on figure 3, be the language being applied to shown in Fig. 2 of present pre-ferred embodiments offer
The flow chart of the audio recognition method of sound identification terminal 100.Described audio recognition method is applied
In voice recognition terminal 100, described voice recognition terminal 100 connects printer 200, institute
Predicate voice recognition method comprises the following steps.
S101: receive Voice command message.
Wherein, described voice recognition terminal 100 receives the Voice command message that user sends,
Described Voice command message includes the control content to described printer 200.
S102: detect the state of described printer 200.
Specifically, the status information being presently in is sent to institute's predicate by described printer 200
Sound identification terminal 100.The described voice recognition terminal 100 described status information to receiving
Carry out the state detecting to obtain described printer 200.
S103: find out the language model corresponding with the state of described printer 200, institute
Stating and prestore multiple language model in voice recognition terminal 100, the plurality of language model divides
The other different conditions one_to_one corresponding with described printer 200.
Specifically, described Voice command message is extracted by described voice recognition terminal 100,
Obtain the key word corresponding with described Voice command message.Described voice recognition terminal 100
The language mould corresponding with the state of described printer 200 is gone out according to described keyword lookup
Type.And in described voice recognition terminal 100, prestore multiple language model, described printing
The different conditions of machine 200 correspond to different described language models respectively.
S104: call the described language model found out and the described Voice command received is disappeared
Breath is identified, and obtains the control instruction corresponding with described Voice command message.
Specifically, prestore in the described language model found out and described printer 200
The corresponding control content of state.Described voice recognition terminal 100 is according to described language mould
The described Voice command message received is identified by the described control content in type, thus
Obtain the control instruction corresponding with described Voice command message.
S105: described control instruction is sent to described printer 200, so that described printing
Machine 200 performs described control instruction.
Wherein, the described control instruction obtained is sent to institute by described voice recognition terminal 100
Stating printer 200, described printer 200 just performs institute after receiving described control instruction
State control instruction.
During enforcement, the control instruction of described printer 200 includes printing, duplicates, suspends,
Stop, starting, delete and page turning.
As shown in Figure 4, described audio recognition method also includes:
S201: receive the control instruction sent by described printer 200 and perform feedback, described
Control instruction performs described printer 200 after feedback includes performing described control instruction
State.
Wherein, also can be by described control after described printer 200 performs described control instruction
Feedback of status after instruction execution gives described voice recognition terminal 100.Described speech recognition is eventually
The end 100 described control instruction of reception performs feedback, to guarantee accurately to obtain described printer 200
Current state.
S202: the state of described printer 200 after switching to and performing described control instruction
Corresponding language model.
Wherein, the execution that described voice recognition terminal 100 feeds back according to described printer 200
The status information of described control instruction, switches to described language model and described printer
The language model that 200 current states are corresponding, can either grasp described printer 200
Implementation status, again can be by the timely switching to language model, the quickly next language of response
Sound control message.
Further, the described step that described control instruction is sent to described printer 200
Including:
Monitor the communication link between described voice recognition terminal 100 and described printer 200
Whether connecting, if do not connected, then described control instruction being cached, if connection,
Then described control instruction is sent to described printer 200.
A communication chain is there is between described voice recognition terminal 100 and described printer 200
Road.The connection status of described communication link is examined by described voice recognition terminal 100 all the time
Survey.When described communication link is in the state not connected, described voice recognition terminal 100
Then described control instruction is cached.When described communication link is in connected state, institute
State voice recognition terminal 100 and directly control instruction is sent to described printer 200, when depositing
When the control instruction of caching, then the control instruction of caching is transmitted.
As it is shown in figure 5, described audio recognition method also includes:
S301: receive voice broadcast instruction.
During enforcement, described printer 200 can send the voice corresponding with oneself state and broadcast
Report instruction.Described voice recognition terminal 100 receives the instruction of described voice broadcast.At institute's predicate
Sound identification terminal 100 prestores the voice document corresponding with the instruction of described voice broadcast.Institute
State voice recognition terminal 100 to find out and described voice broadcast according to the instruction of described voice broadcast
Instruct corresponding voice document.Preferably trigger sound card to described voice literary composition by driver of sound card
Part is reported.
Further, the described language model found out institute's predicate to receiving is called described in
Sound control message is identified, and obtains the control instruction corresponding with described Voice command message
Step include:
Call the described language model found out the described Voice command message received is carried out
Calculate and identify, to obtain the characteristic parameter of described Voice command message, described feature being joined
Number carries out being converted to the control instruction corresponding with described Voice command message.
The most described voice recognition terminal 100 calls the described language model found out, according to
Described language model carries out the extraction of characteristic parameter to receiving described Voice command message, and
Change described characteristic parameter to obtain the control corresponding with described Voice command message
Instruction.
On the basis of the above, the embodiment of the present invention additionally provides a kind of speech recognition system, its
The technique effect realizing principle and generation is identical with preceding method embodiment, for briefly describing,
The not mentioned part of system embodiment part, refers to corresponding contents in preceding method embodiment.
As shown in Figure 6, a kind of speech recognition system that the embodiment of the present invention provides, including language
Sound identification terminal 100, described voice recognition terminal 100 connects printer 200.Institute's predicate
Sound identification terminal 100 includes first reception unit the 101, first detector unit 102, first looks into
Look for unit 103, recognition unit 104 and transmitting element 105.
Described first receives unit 101 for receiving the Voice command message that user sends, institute
State Voice command message and include the control content to described printer 200.About described first
The description receiving unit 101 specifically can be joined the description of step S101 in Fig. 3.That is,
Described step S101 can be received unit 101 by described first and perform.
Described first detector unit 102 is for carrying out the described Voice command message received
Detection, obtains the state of described printer 200 simultaneously according to described testing result.About institute
The description stating the first detector unit 102 specifically can be joined the description of step S102 in Fig. 3.
That is, described step S102 can be performed by described first detector unit 102.
Described first searches unit 103 for going out and described printing according to described keyword lookup
The language model that the state of machine 200 is corresponding.And it is pre-in described voice recognition terminal 100
Having multiple language model, the different conditions of described printer 200 correspond to different respectively
Described language model.Specifically can join Fig. 3 about the described first description searching unit 103
The description of middle step S103.That is, described step S103 can be searched single by described first
Unit 103 performs.
Described recognition unit 104 is for knowing the described Voice command message received
Not, thus obtain the control instruction corresponding with described Voice command message.Wherein, looking into
The described language model found out prestores the control corresponding with the state of described printer 200
Content processed.Description about described recognition unit 104 specifically can be joined step S104 in Fig. 3
Description.That is, described step S104 can be performed by described recognition unit 104.
Described transmitting element 105 is for being sent to described printing by the described control instruction obtained
Machine 200 so that described printer 200 just performs described after receiving described control instruction
Control instruction.Description about described transmitting element 105 specifically can be joined step in Fig. 3
The description of S105.That is, described step S105 can be held by described transmitting element 105
OK.
Further, as it is shown in fig. 7, described speech recognition system also includes the second reception list
Unit 201 and switch unit 202.
Specifically, described second reception unit 201 is used for receiving the execution of described control instruction instead
Feedback, to guarantee accurately to obtain the current state of described printer 200.Wherein, described printing
State after described control instruction also can be performed after performing described control instruction by machine 200 is anti-
Feed described voice recognition terminal 100.And described control instruction performs feedback and includes performing
The state of described printer 200 after described control instruction.
Described switch unit 202 is for switching to described language model and described printer
The language model that the state of 200 is corresponding.Wherein, described voice recognition terminal 100 basis
The status information performing described control instruction of described printer 200 feedback.
Further, described voice recognition terminal 100 also includes monitoring means.Described monitoring
Unit is for monitoring the communication between described voice recognition terminal 100 and described printer 200
Whether link connects, if do not connected, then caches described control instruction, if even
Logical, then described control instruction is sent to described printer 200.Wherein, at described voice
A communication link is there is between identification terminal 100 and described printer 200.Described voice is known
The connection status of described communication link is detected by other terminal 100 all the time.When described communication
When link is in the state not connected, described control is then referred to by described voice recognition terminal 100
Order caches.When described communication link is in connected state, described voice recognition terminal
Control instruction by the control instruction of caching or is directly sent to described printer by 100
200。
Further, as shown in Figure 8, described voice recognition terminal 100 also includes that the 3rd connects
Receive unit 301, second search unit 302 and report unit 303.
Specifically, described 3rd reception unit 301 receives the instruction of described voice broadcast.Wherein,
Described printer 200 will send the voice broadcast instruction corresponding with oneself state.And in institute
State and voice recognition terminal 100 prestores the voice literary composition corresponding with the instruction of described voice broadcast
Part.
Described second searches unit 302 for finding out and institute according to the instruction of described voice broadcast
State the voice document that voice broadcast instruction is corresponding.
The most described report unit 303 is for triggering sound card to described voice by driver of sound card
File is reported.
Further, described voice recognition terminal 100 also includes the second recognition unit.
Specifically, described second recognition unit for according to described language model to receiving
Described Voice command message carries out calculating to identify described Voice command message.Wherein, institute
State voice recognition terminal 100 and call the described language model found out, described in identifying
Voice command message carries out the extraction of characteristic parameter, and described characteristic parameter is changed with
Obtain the control instruction corresponding with described Voice command message.
The audio recognition method of embodiment of the present invention offer and system, by speech recognition eventually
End prestores multiple language model and multiple language model respectively with the different conditions of printer
One_to_one corresponding so that the language that can call pointedly Yu send under printer different conditions
Language model corresponding to sound control message is controlled the identification of instruction, substantially increases language
The customizability of sound identification system and extensibility.
It should be noted that in several embodiments provided herein, it should be understood that
Disclosed apparatus and method, can realize by another way.Device described above
Embodiment is only schematically, such as, the division of described unit, it is only a kind of logic
Function divides, and actual can have other dividing mode when realizing.
Those skilled in the art is it can be understood that arrive, for convenience and simplicity of description,
The device of foregoing description and the specific works process of unit, be referred to preceding method embodiment
In corresponding process, do not repeat them here.
In several embodiments provided herein, it should be understood that disclosed device
And method, can realize by another way.Device embodiment described above is only
Being schematic, such as, flow chart and block diagram in accompanying drawing show according to the present invention many
The device of individual embodiment, the architectural framework in the cards of method and computer program product,
Function and operation.In this, each square frame in flow chart or block diagram can represent one
A part for module, program segment or code, a part for described module, program segment or code
Comprise the executable instruction of one or more logic function for realizing regulation.Should also be as note
Meaning, at some as in the realization replaced, the function marked in square frame can also be with difference
The order marked in accompanying drawing occurs.Such as, two continuous print square frames can essentially base
Originally being performed in parallel, they can also perform sometimes in the opposite order, and this is according to involved
Depending on function.It is also noted that each square frame in block diagram and/or flow chart and frame
The combination of the square frame in figure and/or flow chart, can be with performing the function of regulation or the special of action
Hardware based system realize, or can be with specialized hardware and computer instruction
Combination realizes.
The described unit that illustrates as separating component can be or may not be and physically divide
Opening, the parts shown as unit can be or may not be physical location,
To be positioned at a place, or can also be distributed on multiple NE.Can be according to reality
The needing of border selects some or all of unit therein to realize the mesh of the present embodiment scheme
's.
It addition, each functional unit in each embodiment of the present invention can be integrated at one
Reason unit in, it is also possible to be that unit is individually physically present, it is also possible to two or two with
Upper unit is integrated in a unit.
If described function realizes and as independent product pin using the form of SFU software functional unit
When selling or use, can be stored in a computer read/write memory medium.Based on so
Understanding, the portion that prior art is contributed by technical scheme the most in other words
Divide or the part of this technical scheme can embody with the form of software product, this calculating
Machine software product is stored in a storage medium, including some instructions with so that a meter
Calculate machine equipment (can be personal computer, server, or the network equipment etc.) and perform basis
Invent all or part of step of method described in each embodiment.And aforesaid storage medium bag
Include: USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory),
Random access memory (RAM, Random Access Memory), magnetic disc or CD
Etc. the various media that can store program code.
It should be noted that in this article, the relational terms of such as first and second or the like
It is used merely to separate an entity or operation with another entity or operating space, and not
Necessarily require or imply these entities or operation between exist any this reality relation or
Person's order.And, term " includes ", " comprising " or its any other variant are intended to
Comprising of nonexcludability, so that include that the article of a series of key element or equipment not only wrap
Include those key elements, but also include other key elements being not expressly set out.There is no more limit
In the case of system, statement " including ... " key element limited, it is not excluded that including
The article of described key element or equipment there is also other identical element.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention
Being not limited thereto, any those familiar with the art is in the skill that the invention discloses
In the range of art, change can be readily occurred in or replace, all should contain in protection scope of the present invention
Within.Therefore, protection scope of the present invention should described be as the criterion with scope of the claims.
Claims (10)
1. an audio recognition method, is applied to voice recognition terminal, and described speech recognition is eventually
End connection has printer, it is characterised in that described audio recognition method includes:
Receive Voice command message；
Detect the state of described printer；
Find out the language model corresponding with the state of described printer, described speech recognition
Terminal prestores multiple language model, the plurality of language model respectively with described printer
Different conditions one_to_one corresponding；
Call the described language model found out the described Voice command message received is carried out
Identify, obtain the control instruction corresponding with described Voice command message；
Described control instruction is sent to described printer, so that described printer performs described
Control instruction.
Audio recognition method the most according to claim 1, it is characterised in that institute's predicate
Voice recognition method also includes:
Receiving the control instruction sent by described printer and perform feedback, described control instruction is held
Row feeds back the state of described printer after including performing described control instruction；
Switch to perform described control instruction after the corresponding language of the state of described printer
Speech model.
Audio recognition method the most according to claim 1, it is characterised in that described general
Described control instruction is sent to the step of described printer and includes:
Monitor whether the communication link between described voice recognition terminal and described printer connects
Logical, if do not connected, then described control instruction is cached, if connection, then by institute
State control instruction and be sent to described printer.
Audio recognition method the most according to claim 1, it is characterised in that institute's predicate
Voice recognition method also includes:
Reception voice broadcast instructs；
Search the voice document corresponding with the instruction of described voice broadcast, to institute's voice file
Carrying out voice broadcast, it is right with the instruction of described voice broadcast to prestore in described voice recognition terminal
The voice document answered.
Audio recognition method the most according to claim 1, it is characterised in that described tune
With the described language model found out, the described Voice command message received is identified,
The step obtaining the control instruction corresponding with described Voice command message includes:
Call the described language model found out the described Voice command message received is carried out
Calculate, to obtain the characteristic parameter of described Voice command message, described characteristic parameter is carried out
It is converted to the control instruction corresponding with described Voice command message.
6. a speech recognition system, including voice recognition terminal, described voice recognition terminal
Connect and have printer, it is characterised in that described voice recognition terminal includes:
First receives unit, is used for receiving Voice command message；
First detector unit, for detecting the state of described printer；
First searches unit, for finding out the language corresponding with the state of described printer
Model, prestores multiple language model, the plurality of language mould in described voice recognition terminal
Type respectively with the different conditions one_to_one corresponding of described printer；
Recognition unit, for calling the described language model found out institute's predicate to receiving
Sound control message is identified, and obtains the control instruction corresponding with described Voice command message；
Transmitting element, for described control instruction is sent to described printer, so that described
Printer performs described control instruction.
Speech recognition system the most according to claim 6, it is characterised in that institute's predicate
Sound identification terminal also includes:
Second receives unit, performs anti-for receiving the control instruction sent by described printer
Feedback, described control instruction performs described printing after feedback includes performing described control instruction
The state of machine；
Switch unit, described printer after switching to and performing described control instruction
The language model that state is corresponding.
Speech recognition system the most according to claim 6, it is characterised in that described
Send unit
For whether monitoring communication link between described voice recognition terminal and described printer
Connection, if do not connected, then caches described control instruction, if connection, then will
Described control instruction is sent to described printer.
Speech recognition system the most according to claim 6, it is characterised in that institute's predicate
Sound identification terminal also includes:
3rd receives unit, is used for receiving voice broadcast instruction；
Second searches unit, for searching the voice literary composition corresponding with the instruction of described voice broadcast
Part；
Report unit, for institute's voice file is carried out voice broadcast, described speech recognition
Terminal prestores the voice document corresponding with the instruction of described voice broadcast.
Speech recognition system the most according to claim 6, it is characterised in that described
Recognition unit, for calling the described language model found out institute's predicate to receiving
Sound control message calculates, to obtain the characteristic parameter of described Voice command message, by institute
State characteristic parameter to carry out being converted to the control instruction corresponding with described Voice command message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610142719.8A CN105869635B (en) | 2016-03-14 | 2016-03-14 | Voice recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610142719.8A CN105869635B (en) | 2016-03-14 | 2016-03-14 | Voice recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105869635A true CN105869635A (en) | 2016-08-17 |
| CN105869635B CN105869635B (en) | 2020-01-24 |
Family
ID=56624699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610142719.8A Expired - Fee Related CN105869635B (en) | 2016-03-14 | 2016-03-14 | Voice recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105869635B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122555A (en) * | 2017-12-18 | 2018-06-05 | 北京百度网讯科技有限公司 | The means of communication, speech recognition apparatus and terminal device |
| CN108897517A (en) * | 2018-06-27 | 2018-11-27 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN110770820A (en) * | 2018-08-30 | 2020-02-07 | 深圳市大疆创新科技有限公司 | Speech recognition method, apparatus, photographing system, and computer-readable storage medium |
| CN110808037A (en) * | 2019-11-14 | 2020-02-18 | 广东美的制冷设备有限公司 | Voice control method and device, household appliance and storage medium |
| CN110874195A (en) * | 2018-11-22 | 2020-03-10 | 哈尔滨安天科技集团股份有限公司 | Printing language identification method and device, electronic equipment and storage medium |
| CN111580760A (en) * | 2019-02-15 | 2020-08-25 | 精工爱普生株式会社 | Printing system, printing method, and information processing apparatus |
| CN113299283A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | Speech recognition method, system, device and medium |
| CN113434099A (en) * | 2021-07-23 | 2021-09-24 | 深圳市佳汇印刷有限公司 | Intelligent control system of digital printing machine |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1971500A (en) * | 2005-11-24 | 2007-05-30 | 富士施乐株式会社 | Printing apparatus and control method therefor, and printing system |
| US20080215329A1 (en) * | 2002-03-27 | 2008-09-04 | International Business Machines Corporation | Methods and Apparatus for Generating Dialog State Conditioned Language Models |
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| CN202798910U (en) * | 2012-09-20 | 2013-03-13 | 艾塔斯科技（镇江）有限公司 | Scanner capable of being controlled by speeches |
| CN103430232A (en) * | 2011-01-21 | 2013-12-04 | 谷歌公司 | Speech recognition using device docking context |
| CN203480601U (en) * | 2013-09-18 | 2014-03-12 | 杭州九聚科技有限公司 | Self-service equipment based on voice interaction |
| JP2015009630A (en) * | 2013-06-27 | 2015-01-19 | 庸 菊池 | Vehicle inspection recording unit |
| CN105022595A (en) * | 2015-07-01 | 2015-11-04 | 苏州奥莱维信息技术有限公司 | Speech printing method |
| CN105094717A (en) * | 2015-07-15 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Printing method, printing device and printer based on voice input |
-
2016
- 2016-03-14 CN CN201610142719.8A patent/CN105869635B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080215329A1 (en) * | 2002-03-27 | 2008-09-04 | International Business Machines Corporation | Methods and Apparatus for Generating Dialog State Conditioned Language Models |
| CN1971500A (en) * | 2005-11-24 | 2007-05-30 | 富士施乐株式会社 | Printing apparatus and control method therefor, and printing system |
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| CN103430232A (en) * | 2011-01-21 | 2013-12-04 | 谷歌公司 | Speech recognition using device docking context |
| CN202798910U (en) * | 2012-09-20 | 2013-03-13 | 艾塔斯科技（镇江）有限公司 | Scanner capable of being controlled by speeches |
| JP2015009630A (en) * | 2013-06-27 | 2015-01-19 | 庸 菊池 | Vehicle inspection recording unit |
| CN203480601U (en) * | 2013-09-18 | 2014-03-12 | 杭州九聚科技有限公司 | Self-service equipment based on voice interaction |
| CN105022595A (en) * | 2015-07-01 | 2015-11-04 | 苏州奥莱维信息技术有限公司 | Speech printing method |
| CN105094717A (en) * | 2015-07-15 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Printing method, printing device and printer based on voice input |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122555A (en) * | 2017-12-18 | 2018-06-05 | 北京百度网讯科技有限公司 | The means of communication, speech recognition apparatus and terminal device |
| CN108897517B (en) * | 2018-06-27 | 2021-09-14 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN108897517A (en) * | 2018-06-27 | 2018-11-27 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN110770820A (en) * | 2018-08-30 | 2020-02-07 | 深圳市大疆创新科技有限公司 | Speech recognition method, apparatus, photographing system, and computer-readable storage medium |
| WO2020042077A1 (en) * | 2018-08-30 | 2020-03-05 | 深圳市大疆创新科技有限公司 | Voice recognition method and apparatus, photography system, and computer readable storage medium |
| CN110874195A (en) * | 2018-11-22 | 2020-03-10 | 哈尔滨安天科技集团股份有限公司 | Printing language identification method and device, electronic equipment and storage medium |
| CN111580760A (en) * | 2019-02-15 | 2020-08-25 | 精工爱普生株式会社 | Printing system, printing method, and information processing apparatus |
| CN111580760B (en) * | 2019-02-15 | 2023-08-18 | 精工爱普生株式会社 | Printing system, printing method, and information processing apparatus |
| CN110808037A (en) * | 2019-11-14 | 2020-02-18 | 广东美的制冷设备有限公司 | Voice control method and device, household appliance and storage medium |
| CN110808037B (en) * | 2019-11-14 | 2021-12-21 | 广东美的制冷设备有限公司 | Voice control method and device, household appliance and storage medium |
| CN113299283B (en) * | 2021-04-28 | 2023-03-10 | 上海淇玥信息技术有限公司 | Speech recognition method, system, apparatus and medium |
| CN113299283A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | Speech recognition method, system, device and medium |
| CN113434099A (en) * | 2021-07-23 | 2021-09-24 | 深圳市佳汇印刷有限公司 | Intelligent control system of digital printing machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105869635B (en) | 2020-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105869635A (en) | Speech recognition method and system | |
| RU2767143C2 (en) | Decision-making control using machine learning in case of alerts coming from current control systems | |
| CN103064826B (en) | A kind of method, equipment and system for input of expressing one's feelings | |
| US9703624B2 (en) | Event correlation and calculation engine | |
| US20150347923A1 (en) | Error classification in a computing system | |
| CN105630685A (en) | Method and device for testing program interface | |
| CN108089977B (en) | Application program exception handling method and device and mobile terminal | |
| WO2011079776A1 (en) | Method and device for outputting web form data and form processing system | |
| US10175954B2 (en) | Method of processing big data, including arranging icons in a workflow GUI by a user, checking process availability and syntax, converting the workflow into execution code, monitoring the workflow, and displaying associated information | |
| CN105279435A (en) | Webpage vulnerability detecting method and webpage vulnerability detecting device | |
| KR102488582B1 (en) | Method and apparatus for verifying operation state of application | |
| CN104766008A (en) | Application program installation package safety detection method and server | |
| CN108574721B (en) | Login method, device, server, user terminal and readable storage medium | |
| CN111444080A (en) | Continuous testing method and device | |
| US20130221999A1 (en) | Testing system and method | |
| CN108595957A (en) | Main browser page altering detecting method, device and storage medium | |
| CN110276443A (en) | Model conversion consistency checking and analysis method, device and storage medium | |
| CN107967363B (en) | Data processing method and device and electronic equipment | |
| CN106791226A (en) | Call fault detection method and system | |
| CN103973870A (en) | Information processing device and information processing method | |
| CN105975389A (en) | Process data extraction method and apparatus | |
| JP5932721B2 (en) | Fault information management method, fault information management apparatus, and program | |
| CN105243315A (en) | Single picture verification code input method, apparatus and system | |
| CN105930224A (en) | Dump operation control method, device and terminal | |
| US20160253061A1 (en) | Evaluating user interface efficiency |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200124 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |