CN109688271A - The method, apparatus and terminal device of contact information input - Google Patents
The method, apparatus and terminal device of contact information input Download PDFInfo
- Publication number
- CN109688271A CN109688271A CN201910039493.2A CN201910039493A CN109688271A CN 109688271 A CN109688271 A CN 109688271A CN 201910039493 A CN201910039493 A CN 201910039493A CN 109688271 A CN109688271 A CN 109688271A
- Authority
- CN
- China
- Prior art keywords
- contact person
- phonetic
- voice messaging
- name
- contact
- 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 45
- 150000001875 compounds Chemical class 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000032258 transport Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
-
- 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
- G10L15/08—Speech classification or search
- G10L15/14—Speech classification or search using statistical models, e.g. Hidden Markov Models [HMMs]
- G10L15/142—Hidden Markov Models [HMMs]
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/12—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being prediction coefficients
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72433—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for voice messaging, e.g. dictaphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Probability & Statistics with Applications (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention is suitable for terminal device technical field, provides the method and terminal device of a kind of contact information input, which comprises the acquisition contact person's voice messaging instruction for listening to user's triggering receives contact person's voice messaging of user speech input；Contact person's voice messaging is converted into contact person's phonetic, contact person's phonetic is compared with the name pinyin prestored；If contact person's phonetic only fills the associated contact information of the name pinyin with successful match to corresponding contact information input frame with a name pinyin successful match.The present invention realizes contact information input by speech recognition, reduces user's operation, convenient and efficient.
Description
Technical field
The method, apparatus inputted the invention belongs to terminal device technical field more particularly to a kind of contact information and end
End equipment.
Background technique
Continuous with terminal device is popularized, and more and more things are dependent on terminal device to realize in people's lives.
It is usually first corresponding in contact information input frame by user in terminal device inputting contact information under the prior art
Location triggered address list control, terminal device load address book contact list, are subsequently used for the address book contact in load
Selection target contact person in list, the last selected target information in the contact details of object contact person, so that target be contacted
In the target information filling contact information input frame of people.
As it can be seen that existing mode user's operation is cumbersome, it is not convenient enough.
Summary of the invention
In view of this, the embodiment of the invention provides the method, apparatus and terminal device of a kind of input of contact information, with
The prior art is solved in terminal device inputting contact information, user's operation is cumbersome, not convenient and fast technical problem.
The first aspect of the embodiment of the present invention provides a kind of method of contact information input, comprising:
The acquisition contact person's voice messaging instruction for listening to user's triggering receives contact person's voice letter of user speech input
Breath；
Contact person's voice messaging is converted into contact person's phonetic, by contact person's phonetic and the name pinyin prestored
It is compared；
If contact person's phonetic only with a name pinyin successful match, by the name with successful match
The associated contact information of phonetic, filling to corresponding contact information input frame.
The second aspect of the embodiment of the present invention provides a kind of device of contact information input, comprising:
It monitors and receiving module, acquisition contact person's voice messaging for listening to user's triggering instructs, receive user's language
Contact person's voice messaging of sound input；
Conversion and comparison module, for contact person's voice messaging to be converted into contact person's phonetic, by the contact person
Phonetic is compared with the name pinyin prestored；
First filling module, if for contact person's phonetic only with a name pinyin successful match, it will be with
The associated contact information of the name pinyin of successful match, filling to corresponding contact information input frame.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory and processor, described to deposit
The computer program that can be run on the processor is stored in reservoir, when the processor executes the computer program,
Realize following steps:
The acquisition contact person's voice messaging instruction for listening to user's triggering receives contact person's voice letter of user speech input
Breath；
Contact person's voice messaging is converted into contact person's phonetic, by contact person's phonetic and the name pinyin prestored
It is compared；
If contact person's phonetic only with a name pinyin successful match, by the name with successful match
The associated contact information of phonetic, filling to corresponding contact information input frame.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor:
The acquisition contact person's voice messaging instruction for listening to user's triggering receives contact person's voice letter of user speech input
Breath；
Contact person's voice messaging is converted into contact person's phonetic, by contact person's phonetic and the name pinyin prestored
It is compared；
If contact person's phonetic only with a name pinyin successful match, by the name with successful match
The associated contact information of phonetic, filling to corresponding contact information input frame.
In the embodiment of the present invention, by contact person's voice messaging of identification user speech input, contact person's phonetic is obtained, into
And contact person's phonetic is compared with the name pinyin prestored, when contact person's phonetic only with a name pinyin successful match
When, the contact information of successful match is filled to corresponding contact information input frame, to realize that voice inputs contact person
Information reduces user's operation, convenient and efficient.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of implementation flow chart of the method for contact information input provided in an embodiment of the present invention；
Fig. 2 is a kind of exemplary diagram of contact information input interface provided in an embodiment of the present invention；
Fig. 3 is the implementation flow chart of step 102 in a kind of method of contact information input provided in an embodiment of the present invention；
Fig. 4 is a kind of signal that contact information is filled in contact information input interface provided in an embodiment of the present invention
Figure；
Fig. 5 is the implementation flow chart of the method for another contact information input provided in an embodiment of the present invention；
Fig. 6 is the implementation process of step 501 in the method for another contact information input provided in an embodiment of the present invention
Figure；
Fig. 7 is provided in an embodiment of the present invention a kind of in contact information input interface load object contact person selection interface
Schematic diagram；
Fig. 8 is a kind of structural block diagram of the device of contact information input provided in an embodiment of the present invention；
Fig. 9 is the schematic diagram of terminal device provided in an embodiment of the present invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 shows the implementation process of the method for contact information input provided in an embodiment of the present invention, this method process
Including step S101 to S103.This method is applicable to carry out the situation of contact information input.This method is believed by contact person
The device of breath input executes, and the device of the contact information input is configured at terminal device, can be by software and/or hardware reality
It is existing.Terminal device includes intelligent mobile terminal etc..The specific implementation principle of each step is as follows.
S101 listens to acquisition contact person's voice messaging instruction of user's triggering, receives the contact person of user speech input
Voice messaging.
In the embodiment of the present invention, user is the user of terminal device.Terminal device includes but is not limited to portable terminal
Equipment.Terminal device includes the radio equipments such as microphone, and terminal device receives user speech by radio equipment.
In mountable any application on the terminal device, using including but not limited to browser, Email, loan
Using, shopping application or instant messaging application etc., when user being needed to fill in contact information, in contact information input interface
Contact information input frame corresponding position occur obtain contact person's voice messaging control, monitoring users by click the control touching
Acquisition contact person's voice messaging of hair instructs, to instruct the radio reception of starting terminal device according to acquisition contact person's voice messaging
Equipment receives contact person's voice messaging of user speech input.
It illustratively, be as shown in Fig. 2, in the contact information input interface 20 of smart phone loan application
Inputting contact information in contact information input frame 21, user can obtain contact person's voice messaging control 22 by clicking,
Triggering obtain contact person's voice messaging instruction, thus smart phone receive user speech input contact person's voice messaging after,
It is matched further according to contact person's voice messaging with the contact person in address list, the contact information of successful match is inserted into connection
In people's information input frame 21.It should be noted that as known to those skilled in the art, being merely illustrative description herein, cannot explain
For limitation of the present invention.
Contact person's voice messaging is converted into contact person's phonetic by S102, by contact person's phonetic and the people prestored
Name phonetic is compared.
In the embodiment of the present invention, after getting contact person's voice messaging by step 101, contact person's voice messaging is converted
At contact person's phonetic, contact person's phonetic is compared with the name pinyin prestored.Wherein, name pinyin is the connection of address list
The corresponding name pinyin of contact person, name pinyin are pre-stored in the memory of terminal device in list, thus need into
When row matching, by traversing all name pinyins prestored, comparison result is obtained.
It should be noted that in contacts list include contact person and with the associated contact information of each contact person.Connection
It is people's information include but is not limited to name, phone number, work base number, household fixed telephone number, mailbox number or Instant Messenger
Believe account etc..
Optionally, contact person's voice messaging is converted into contact person's phonetic in step 102, as shown in figure 3, including step
Rapid 301 to 302.
S301 extracts the acoustic feature vector of contact person's voice messaging.
Wherein, the acoustic feature vector be including at least linear prediction residue error and Mel frequency cepstrum coefficient this two
The feature vector of kind acoustic feature.
Acoustic feature selection is more, and quantity treating capacity is bigger, in the embodiment of the present invention while ensuring result precision,
Also calculating data volume is controlled, 2 kinds of acoustic features has been selected to constitute acoustic feature vector.Illustratively, connection human speech is extracted
2 kinds of acoustic features of message breath constitute acoustic feature vector: Mel frequency cepstrum coefficient (Mel Frequency Cepstral
Coefficients, MFCC) and linear prediction residue error (Linear Frequency Cepstral Coefficients,
LPCC).Wherein, MFCC can take multistage, such as 7 ranks, take CoTo C6。
S302 analyzes the acoustic feature vector using trained acoustic model, obtains contact person's phonetic.
Wherein, acoustic model can be hidden Markov model (Hidden Markov Model, HMM).Using training
Acoustic model analyze the acoustic feature vector, contact person's phonetic can be obtained.
Further, before S301 further include: carry out pretreated step to connection human speech message breath.Wherein pre-process
Including mute excision and framing.By being pre-processed to connection human speech message breath, on the one hand less data volume treating capacity, separately
On the one hand the precision of speech recognition result is also improved.
Wherein, in the embodiment of the present invention, using voice activity detection (Voice Activity Detection, VAD) skill
Art realizes end-point detection, mute to eliminate.
Framing is carried out using mobile window function, is existed between each frame overlapping.Illustratively, it is moved with frame length 25ms, frame
10ms sub-frame processing voice signal obtains N frame subsignal, i.e., the length of every frame is 25 milliseconds, has 25-10=15 between every two frame
Millisecond overlaps.Or 10ms sub-frame processing voice signal is moved with frame length 20ms, frame and obtains N frame subsignal, i.e., the length of every frame is
20 milliseconds, there is 20-10=10 milliseconds overlapping between every two frame.
If being pre-processed and then being identified pretreated contact person's voice messaging to connection human speech message breath to obtain
To contact person's phonetic.At this point, correspondingly, step 301 includes: to extract the sub- acoustic feature vector of every frame contact person voice messaging,
The son of all frames is learned into combination of eigenvectors into acoustic feature matrix.
Correspondingly, step 302 includes: to analyze the acoustic feature matrix using trained acoustic model, contacted
People's phonetic.
S103, if contact person's phonetic only with a name pinyin successful match, by the institute with successful match
State the associated contact information of name pinyin, filling to corresponding contact information input frame.
In the embodiment of the present invention, if contact person's phonetic only with a name pinyin successful match, at this point, the people of successful match
The associated artificial object contact person of connection of name phonetic, it is determined that object contact person, by the associated contact information of object contact person
It fills to corresponding contact information input frame.
Wherein, by by the keyword of the associated every contact information of object contact person and contact information input frame
Keyword is matched, and does not need user and execute operation to fill name, phone, still in contact information filling frame to determine
The contact information of successful match can be filled into corresponding contact information input frame, further be mentioned by mailbox number etc.
Intelligent level has been supplied, user's operation is reduced, has improved user experience.
Illustratively, continue example shown in Fig. 2, smart phone is in the contact person's voice messaging for receiving user speech input
Afterwards, contact person's voice messaging is converted into contact person's phonetic " zhangsan ", multiple name pinyins with contact person in address list
Be compared respectively, contact person's phonetic only with name pinyin " zhangsan " successful match.It will be with the successful people of unique match
Name phonetic " zhangsan " associated contact information " name: Zhang San；Cell-phone number: 1XXXXXXXXXXX, identification card number:
XXXXXXXXXXXXXXXXXX " is filled respectively into corresponding contact information input frame 21, as shown in figure 4, contact person is believed
Name " Zhang San " filling in breath fills " 1XXXXXXXXXXX " in contact information extremely to " name of contact person " input frame
" contact person's cell-phone number " input frame；By identification card number " XXXXXXXXXXXXXXXXXX " filling in contact information to " connection
People's identification card number " input frame.
In the embodiment of the present invention, by obtaining contact person's voice messaging of user speech input, contact person's phonetic is identified
It is compared with the name pinyin prestored, obtains object contact person, to filling the contact information of object contact person to connection
It is to obtain the instruction of contact person's voice messaging in addition to needing user to trigger, subsequent process does not need user hand in people's information input frame
Dynamic operation, improves intelligent level, reduces the cumbersome operation of user, efficiently convenient.
On the basis of embodiment shown in Fig. 1, optionally, by contact person's phonetic and the name prestored in step 102
After phonetic is compared, as shown in figure 5, further including step 501 to 504.
S501 believes contact person's voice if contact person's phonetic and multiple name pinyin successful match
Breath is converted into toned contact person's phonetic.
Contact person's phonetic is compared with the name pinyin prestored in a step 102, the name prestored is traversed and spells
Sound obtains comparison result.Since there are many word in Chinese with identical phonetic, thus the corresponding name pinyin of different contact persons can
Can there is a situation where it is identical, at this point, there are multiple with the name pinyin of contact person's phonetic successful match.In order to further obtain standard
Contact person's voice messaging is converted further into toned contact person's phonetic in the embodiment of the present invention by standby matching result.
Optionally, contact person's voice messaging is converted into toned contact person's phonetic in step 501, such as Fig. 6 institute
Show, including step 601 is to 605.A kind of more accurate voice recognition mode is realized by step 601 to 605.
S601 extracts the acoustic feature vector of contact person's voice messaging.
S602 analyzes the acoustic feature vector using trained acoustic model, obtains contact person's phonetic.
Wherein, step 601 is to 602 identical as step 301 and 302, and details are not described herein again.
It should be noted that in other embodiments of the present invention, step 301 and 302 obtained connections can be directly used
People's phonetic as a result, at this point, not needing to repeat execution 601 and 602.
S603 intercepts the simple or compound vowel of a Chinese syllable sound bite of simple or compound vowel of a Chinese syllable in corresponding relationship people's phonetic in contact person's voice messaging.
Wherein, since simple or compound vowel of a Chinese syllable just has tone, in embodiments of the present invention, identify contact person's voice messaging pair
After the contact person's phonetic answered, the simple or compound vowel of a Chinese syllable sound bite of simple or compound vowel of a Chinese syllable in contact person's voice messaging is intercepted, to be contacted based on this
The tone of people's phonetic.
S604 extracts the fundamental frequency of the simple or compound vowel of a Chinese syllable sound bite.
S605 determines the corresponding tone of simple or compound vowel of a Chinese syllable sound bite according to the track of the fundamental frequency.
Wherein, by preset sample mode, the fundamental frequency of simple or compound vowel of a Chinese syllable sound bite is extracted, to pass through several sampled points
Set obtains the track of fundamental frequency, and then the tone of simple or compound vowel of a Chinese syllable is determined by track.The present invention is not specifically limited sample mode.
Specifically, step 605 includes: to obtain geometric locus according to the track of the fundamental frequency, and it is bent to calculate separately the track
The similarity value of line and each desired guiding trajectory curve determines that the corresponding tone of the smallest desired guiding trajectory curve of similarity value is described
The corresponding tone of simple or compound vowel of a Chinese syllable sound bite.
In the embodiment of the present invention, it is fitted to obtain geometric locus by the fundamental frequency of several sampled points.Desired guiding trajectory curve is
Five kinds of different tones, including a sound (tone level), two sound (rising tone), three sound (upper sound), the four tones of standard Chinese pronunciation (falling tone) He Wusheng (softly), point
Not corresponding pitch contour curve, to pass through following formula:
Calculate separately the similarity value C of geometric locus y=f (x) Yu each desired guiding trajectory curve Y=F (X).
Wherein,
Geometric locus y=f (x) is (y1,y2,y3,......,yi)=f (x1,x2,x3,......,xi)；Desired guiding trajectory is bent
Line Y=F (X) is (Y1,Y2,Y3,......,Yi)=f (X1,X2,X3,......,Xi)；I value is 1 to n；I and n is positive whole
Number.
In other embodiments of the present invention, desired guiding trajectory curve can also be four kinds of different tones, including a sound (sound
It is flat), two sound (rising tone), three sound (upper sound) and the four tones of standard Chinese pronunciation (falling tone), corresponding pitch contour curve.
Toned contact person's phonetic is compared S502 with the toned name pinyin prestored.
In the embodiment of the present invention, after getting toned contact person's voice by step 501, by toned contact person
Phonetic is compared with the toned name pinyin prestored.Wherein, toned name pinyin is that the contact person of address list arranges
The corresponding toned name pinyin of contact person, toned name pinyin are pre-stored in the memory of terminal device in table,
To by traversing all toned name pinyins prestored, obtain comparison result when being matched.
It should be noted that in contacts list include contact person and with the associated contact information of each contact person.Connection
It is people's information include but is not limited to name, phone number, work base number, household fixed telephone number, mailbox number or Instant Messenger
Believe account etc..
S503, if toned contact person's phonetic only with a toned name pinyin successful match, will be with matching
The successful toned associated contact information of name pinyin, filling to corresponding contact information input frame.
S504 shows and matches if toned contact person's phonetic and multiple toned name pinyin successful match
Successful multiple toned associated name of contact persons of name pinyin；If listening to user's triggering selection name of contact person thing
Part, the name of contact person that user is selected will be filled out as object contact person with the associated contact information of the object contact person
It is charged to corresponding contact information input frame.
In embodiments of the present invention, if toned contact person's phonetic and multiple toned name pinyin successful match,
Then show multiple toned associated name of contact persons of name pinyin with successful match, for selection by the user.When listening to
User's triggering selection name of contact person event, at this point, user has selected target connection from the name of contact person of multiple successful match
It is people, then fills the associated contact information of object contact person to corresponding contact information input frame.
Wherein, it selects name of contact person event for the event of user selected target contact person, is usually executed by user default
Operation triggering.Predetermined registration operation includes mouse action or touch operation, such as is clicked and selected on touching curtain by mouse or finger
Control, or picture closed figure chooses object contact person etc. on touching curtain by mouse or finger.
Illustratively, when contact person's phonetic " zhangsan " is matched with multiple name pinyins " zhangsan " in address list
Success, then be converted into toned contact person's phonetic for contact person's voice messagingAgain by toned connection
People's phonetic is matched with toned name pinyin.
If toned contact person's phoneticOnly with a toned name pinyin?
With success, then by the toned name pinyin corresponding contact information " name: Zhang San of successful match；Phone:
1XXXXXXXXXXX, identification card number: XXXXXXXXXXXXXXXXXX " is inserted in corresponding contact information input frame, continues to join
As shown in Figure 4.
If toned contact person's phoneticWith multiple toned name pinyinsMatching
Success, then as shown in fig. 7, load object contact person selection interface 71, object contact person selection interface 71 show successful match
The corresponding name of contact person " Zhang San " of toned name pinyin and " three ", for selection by the user.
If user has selected object contact person " Zhang San " in object contact person selection interface 71, object contact person " is opened
Three " corresponding object contact person information " names: Zhang San；Phone: 1XXXXXXXXXXX, identification card number:
XXXXXXXXXXXXXXXXXX " is inserted in corresponding contact information input frame, with continued reference to shown in Fig. 4.
It should be noted that if contact person's phonetic then prompts user's language again not with any one name pinyin successful match
Sound inputs contact person's voice messaging, continues to execute the step process for the method that contact person inputs in the embodiment of the present invention.In addition, if
Toned contact person's phonetic with any one toned name pinyin successful match, does not then prompt user's voice input connection again
It is people's voice messaging, continues to execute the step process for the method that contact person inputs in the embodiment of the present invention.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Corresponding to the method for the input of contact information described in foregoing embodiments, Fig. 8 shows offer of the embodiment of the present invention
The structural block diagram of device of contact information input illustrate only portion relevant to the embodiment of the present invention for ease of description
Point.
Referring to Fig. 8, the device of contact information input includes:
It monitors and receiving module 81, acquisition contact person's voice messaging for listening to user's triggering instructs, receive user
Contact person's voice messaging of voice input；
Conversion and comparison module 82, for contact person's voice messaging to be converted into contact person's phonetic, by the connection
People's phonetic is compared with the name pinyin prestored；
First filling module 83, if for contact person's phonetic only with a name pinyin successful match, it will
With the associated contact information of the name pinyin of successful match, filling to corresponding contact information input frame.
Optionally, the device of contact information input further include:
Second conversion module, if for contact person's phonetic and multiple name pinyin successful match, it will be described
Contact person's voice messaging is converted into toned contact person's phonetic；
Second comparison module, for comparing toned contact person's phonetic with the toned name pinyin prestored
It is right；
Second filling module, if only being matched into a toned name pinyin for toned contact person's phonetic
Function is filled defeated to corresponding contact information then by the associated contact information of toned name pinyin with successful match
Enter frame；
Third fills module, if for toned contact person's phonetic and multiple toned name pinyin successful match,
Then show multiple toned associated name of contact persons of name pinyin with successful match；If listening to user's triggering selection connection
It is people's name event, the name of contact person that user is selected, will be associated with the object contact person as object contact person
It is that people's information is filled to corresponding contact information input frame.
Optionally, the conversion and comparison module 82, are specifically used for:
Extract the acoustic feature vector of contact person's voice messaging；
The acoustic feature vector is analyzed using trained acoustic model, obtains contact person's phonetic.
Optionally, second conversion module, is specifically used for:
The acoustic feature vector of contact person's voice messaging is extracted,
The acoustic feature vector is analyzed using trained acoustic model, obtains contact person's phonetic；
Intercept the simple or compound vowel of a Chinese syllable sound bite of simple or compound vowel of a Chinese syllable in corresponding relationship people's phonetic in contact person's voice messaging；
Extract the fundamental frequency of the simple or compound vowel of a Chinese syllable sound bite；
The corresponding tone of simple or compound vowel of a Chinese syllable sound bite is determined according to the track of the fundamental frequency.
Optionally, the track according to the fundamental frequency determines the corresponding tone of simple or compound vowel of a Chinese syllable sound bite, comprising:
Geometric locus is obtained according to the track of the fundamental frequency, calculates separately the geometric locus and each desired guiding trajectory curve
Similarity value, determine the corresponding tone of the smallest desired guiding trajectory curve of similarity value be the corresponding sound of the simple or compound vowel of a Chinese syllable sound bite
It adjusts.
Optionally, the similarity value for calculating separately the geometric locus Yu each desired guiding trajectory curve, comprising:
Pass through formulaCalculate separately geometric locus y=f (x) and each
The similarity value C of desired guiding trajectory curve Y=F (X)；
Wherein,
Geometric locus y=f (x) is (y1,y2,y3,......,yi)=f (x1,x2,x3,......,xi)；Desired guiding trajectory is bent
Line Y=F (X) is (Y1,Y2,Y3,......,Yi)=f (X1,X2,X3,......,Xi)；I value is 1 to n；I and n is positive whole
Number.
Fig. 9 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 9, the terminal of the embodiment is set
Standby 9 include: processor 90, memory 91 and are stored in the meter that can be run in the memory 91 and on the processor 90
Calculation machine program 92, such as the program of contact information input.The processor 90 is realized when executing the computer program 92
State the step in the embodiment of the method for contact information input, such as step S101 to S103 shown in FIG. 1.Alternatively, the place
Reason device 90 realizes the function of each module in above-mentioned each Installation practice, such as mould shown in Fig. 8 when executing the computer program 92
The function of block 81 to 83.
Illustratively, the computer program 92 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 91, and are executed by the processor 90, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 92 in the terminal device 9 is described.
The terminal device 9 can be PC or portable intelligent device etc..The terminal device 9 may include, but
It is not limited only to, processor 90, memory 91.It will be understood by those skilled in the art that Fig. 9 is only the example of terminal device 9, and
Do not constitute the restriction to terminal device 9, may include than illustrating more or fewer components, perhaps combine certain components or
Different components, such as the terminal device can also include input-output equipment, network access equipment, bus etc..
Alleged processor 90 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 91 can be the internal storage unit of the terminal device 9, such as the hard disk or interior of terminal device 9
It deposits.The memory 91 is also possible to the External memory equipment of the terminal device 9, such as be equipped on the terminal device 9
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 91 can also both include the storage inside list of the terminal device 5
Member also includes External memory equipment.The memory 91 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 91 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of method of contact information input characterized by comprising
The acquisition contact person's voice messaging instruction for listening to user's triggering, receives contact person's voice messaging of user speech input；
Contact person's voice messaging is converted into contact person's phonetic, contact person's phonetic is carried out with the name pinyin prestored
It compares；
If contact person's phonetic only with a name pinyin successful match, by the name pinyin with successful match
Associated contact information, filling to corresponding contact information input frame.
2. the method as described in claim 1, which is characterized in that it is described by contact person's phonetic and the name pinyin that prestores into
After row compares, further includes:
If contact person's phonetic and multiple name pinyin successful match, are converted into band for contact person's voice messaging
Contact person's phonetic of tone；
Toned contact person's phonetic is compared with the toned name pinyin prestored；
If toned contact person's phonetic only with a toned name pinyin successful match, by with successful match band sound
The associated contact information of the name pinyin of tune, filling to corresponding contact information input frame；
If toned contact person's phonetic and multiple toned name pinyin successful match, show multiple with successful match
The toned associated name of contact person of name pinyin；If listening to user's triggering selection name of contact person event, user is selected
The name of contact person selected will be filled with the associated contact information of the object contact person to corresponding as object contact person
It is people's information input frame.
3. the method as described in claim 1, which is characterized in that described that contact person's voice messaging is converted into contact person's spelling
Sound, comprising:
Extract the acoustic feature vector of contact person's voice messaging；
The acoustic feature vector is analyzed using trained acoustic model, obtains contact person's phonetic.
4. method according to claim 2, which is characterized in that it is described contact person's voice messaging is converted into it is toned
It is people's phonetic, comprising:
The acoustic feature vector of contact person's voice messaging is extracted,
The acoustic feature vector is analyzed using trained acoustic model, obtains contact person's phonetic；
Intercept the simple or compound vowel of a Chinese syllable sound bite of simple or compound vowel of a Chinese syllable in corresponding relationship people's phonetic in contact person's voice messaging；
Extract the fundamental frequency of the simple or compound vowel of a Chinese syllable sound bite；
The corresponding tone of simple or compound vowel of a Chinese syllable sound bite is determined according to the track of the fundamental frequency.
5. method as claimed in claim 4, which is characterized in that the track according to the fundamental frequency determines simple or compound vowel of a Chinese syllable sound bite
Corresponding tone, comprising:
Geometric locus is obtained according to the track of the fundamental frequency, calculates separately the phase of the geometric locus with each desired guiding trajectory curve
Like angle value, determine that the corresponding tone of the smallest desired guiding trajectory curve of similarity value is the corresponding tone of the simple or compound vowel of a Chinese syllable sound bite.
6. method as claimed in claim 5, which is characterized in that described to calculate separately the geometric locus and each desired guiding trajectory
The similarity value of curve, comprising:
Pass through formulaIt calculates separately geometric locus y=f (x) and each presets
The similarity value C of geometric locus Y=F (X)；
Wherein,
Geometric locus y=f (x) is (y1,y2,y3,......,yi)=f (x1,x2,x3,......,xi)；Desired guiding trajectory curve Y=
F (X) is (Y1,Y2,Y3,......,Yi)=f (X1,X2,X3,......,Xi)；I value is 1 to n；I and n is positive integer.
7. the method as claimed in claim 3 or 4, which is characterized in that the acoustic feature vector is including at least linear prediction
The feature vector of both acoustic features of cepstrum coefficient and Mel frequency cepstrum coefficient.
8. a kind of device of contact information input characterized by comprising
It monitors and receiving module, acquisition contact person's voice messaging for listening to user's triggering instructs, it is defeated to receive user speech
The contact person's voice messaging entered；
Conversion and comparison module, for contact person's voice messaging to be converted into contact person's phonetic, by contact person's phonetic
It is compared with the name pinyin prestored；
First filling module, if for contact person's phonetic only with a name pinyin successful match, it will be with matching
The successful associated contact information of name pinyin, filling to corresponding contact information input frame.
9. a kind of terminal device, including memory and processor, it is stored with and can transports on the processor in the memory
Capable computer program, which is characterized in that when the processor executes the computer program, realize such as claim 1 to 7 times
The step of one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 7 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910039493.2A CN109688271A (en) | 2019-01-16 | 2019-01-16 | The method, apparatus and terminal device of contact information input |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910039493.2A CN109688271A (en) | 2019-01-16 | 2019-01-16 | The method, apparatus and terminal device of contact information input |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109688271A true CN109688271A (en) | 2019-04-26 |
Family
ID=66192458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910039493.2A Pending CN109688271A (en) | 2019-01-16 | 2019-01-16 | The method, apparatus and terminal device of contact information input |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109688271A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364212A (en) * | 2020-11-04 | 2021-02-12 | 北京致远互联软件股份有限公司 | Voice name recognition method based on approximate voice recognition |
| CN113241078A (en) * | 2021-05-10 | 2021-08-10 | 杭州魔点科技有限公司 | Attendance machine-based voice recognition method and system |
| CN113593569A (en) * | 2021-07-27 | 2021-11-02 | 德邦物流股份有限公司 | Electronic bill generation method and device, electronic equipment and storage medium |
| CN116010562A (en) * | 2023-03-28 | 2023-04-25 | 之江实验室 | Name matching method, device, equipment and medium based on multiple data sources |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102164205A (en) * | 2011-03-02 | 2011-08-24 | 宇龙计算机通信科技(深圳)有限公司 | Quick input method of contact person information and mobile terminal |
| CN102263855A (en) * | 2011-06-03 | 2011-11-30 | 宇龙计算机通信科技(深圳)有限公司 | Method, system, mobile terminal and browser for inputting contact information |
| CN105607799A (en) * | 2015-12-15 | 2016-05-25 | 深圳市永兴元科技有限公司 | Data processing method and apparatus |
| CN107016994A (en) * | 2016-01-27 | 2017-08-04 | 阿里巴巴集团控股有限公司 | The method and device of speech recognition |
| CN107357772A (en) * | 2017-07-04 | 2017-11-17 | 贵州小爱机器人科技有限公司 | List filling method, device and computer equipment |
| US20180109675A1 (en) * | 2016-09-15 | 2018-04-19 | International Business Machines Corporation | Multi-dimensional auditory notification composition based on sender categorizations |
| CN108595141A (en) * | 2018-03-22 | 2018-09-28 | 珠海市魅族科技有限公司 | Pronunciation inputting method and device, computer installation and computer readable storage medium |
| CN108881383A (en) * | 2018-05-07 | 2018-11-23 | 深圳壹账通智能科技有限公司 | Address book data processing method, device, computer equipment and storage medium |
| CN108874872A (en) * | 2018-04-26 | 2018-11-23 | 深圳市艾塔文化科技有限公司 | A kind of speech recognition string processing comparison method based on phonetic |
-
2019
- 2019-01-16 CN CN201910039493.2A patent/CN109688271A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102164205A (en) * | 2011-03-02 | 2011-08-24 | 宇龙计算机通信科技(深圳)有限公司 | Quick input method of contact person information and mobile terminal |
| CN102263855A (en) * | 2011-06-03 | 2011-11-30 | 宇龙计算机通信科技(深圳)有限公司 | Method, system, mobile terminal and browser for inputting contact information |
| CN105607799A (en) * | 2015-12-15 | 2016-05-25 | 深圳市永兴元科技有限公司 | Data processing method and apparatus |
| CN107016994A (en) * | 2016-01-27 | 2017-08-04 | 阿里巴巴集团控股有限公司 | The method and device of speech recognition |
| US20180109675A1 (en) * | 2016-09-15 | 2018-04-19 | International Business Machines Corporation | Multi-dimensional auditory notification composition based on sender categorizations |
| CN107357772A (en) * | 2017-07-04 | 2017-11-17 | 贵州小爱机器人科技有限公司 | List filling method, device and computer equipment |
| CN108595141A (en) * | 2018-03-22 | 2018-09-28 | 珠海市魅族科技有限公司 | Pronunciation inputting method and device, computer installation and computer readable storage medium |
| CN108874872A (en) * | 2018-04-26 | 2018-11-23 | 深圳市艾塔文化科技有限公司 | A kind of speech recognition string processing comparison method based on phonetic |
| CN108881383A (en) * | 2018-05-07 | 2018-11-23 | 深圳壹账通智能科技有限公司 | Address book data processing method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 白俊贤: "大词汇量语音匹配方法研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364212A (en) * | 2020-11-04 | 2021-02-12 | 北京致远互联软件股份有限公司 | Voice name recognition method based on approximate voice recognition |
| CN113241078A (en) * | 2021-05-10 | 2021-08-10 | 杭州魔点科技有限公司 | Attendance machine-based voice recognition method and system |
| CN113593569A (en) * | 2021-07-27 | 2021-11-02 | 德邦物流股份有限公司 | Electronic bill generation method and device, electronic equipment and storage medium |
| CN116010562A (en) * | 2023-03-28 | 2023-04-25 | 之江实验室 | Name matching method, device, equipment and medium based on multiple data sources |
| CN116010562B (en) * | 2023-03-28 | 2023-07-07 | 之江实验室 | Name matching method, device, equipment and medium based on multiple data sources |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11887582B2 (en) | Training and testing utterance-based frameworks | |
| WO2021093449A1 (en) | Wakeup word detection method and apparatus employing artificial intelligence, device, and medium | |
| US11900948B1 (en) | Automatic speaker identification using speech recognition features | |
| CN110310623B (en) | Sample generation method, model training method, device, medium, and electronic apparatus | |
| CN107644638B (en) | Audio recognition method, device, terminal and computer readable storage medium | |
| KR102369416B1 (en) | Speech signal recognition system recognizing speech signal of a plurality of users by using personalization layer corresponding to each of the plurality of users | |
| CN109688271A (en) | The method, apparatus and terminal device of contact information input | |
| US10504505B2 (en) | System and method for speech personalization by need | |
| US20180012593A1 (en) | Keyword detection modeling using contextual information | |
| US10811005B2 (en) | Adapting voice input processing based on voice input characteristics | |
| WO2017112466A1 (en) | Multi-speaker speech separation | |
| CN111341325A (en) | Voiceprint recognition method and device, storage medium and electronic device | |
| CN110364143A (en) | Voice awakening method, device and its intelligent electronic device | |
| US8600744B2 (en) | System and method for improving robustness of speech recognition using vocal tract length normalization codebooks | |
| CN113129867B (en) | Training method of voice recognition model, voice recognition method, device and equipment | |
| US11341954B2 (en) | Training keyword spotters | |
| CN104361896B (en) | Voice quality assessment equipment, method and system | |
| CN110047484A (en) | A kind of speech recognition exchange method, system, equipment and storage medium | |
| CN113314119A (en) | Voice recognition intelligent household control method and device | |
| KR20190074508A (en) | Method for crowdsourcing data of chat model for chatbot | |
| CN113053362A (en) | Method, device, equipment and computer readable medium for speech recognition | |
| JP2003163951A (en) | Sound signal recognition system, conversation control system using the sound signal recognition method, and conversation control method | |
| CN113421573B (en) | Identity recognition model training method, identity recognition method and device | |
| KR100622019B1 (en) | Voice interface system and method | |
| Gorniak et al. | Augmenting user interfaces with adaptive speech commands |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |
|
| RJ01 | Rejection of invention patent application after publication |