CN109828739A - The method and device of interactive voice based on voice label - Google Patents
The method and device of interactive voice based on voice label Download PDFInfo
- Publication number
- CN109828739A CN109828739A CN201910040369.8A CN201910040369A CN109828739A CN 109828739 A CN109828739 A CN 109828739A CN 201910040369 A CN201910040369 A CN 201910040369A CN 109828739 A CN109828739 A CN 109828739A
- Authority
- CN
- China
- Prior art keywords
- voice
- label
- app
- voice label
- interactive voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of methods of interactive voice based on voice label, include the following steps: A) the function packet that voice label defined and instructed calling is added in the APP upgrade package of mobile terminal；B) user first records voice label self to the operation object with sound self before operating to operation object, and automatically saves；C interactive voice operation) is carried out, the voice label of user oneself Record and Save is called, realizes relevant operation.The invention further relates to a kind of devices of method for realizing the above-mentioned interactive voice based on voice label, the method and device for implementing the interactive voice of the invention based on voice label, have the advantages that can improve and improve the experience of different user especially mandarin nonstandard group's interactive voice, development cost is low, low, effect of realizing difficulty preferably, can solve different regions and Different education levels group and use the problem that cannot identify or identify mistake in interactive voice.
Description
Technical field
The present invention relates to interactive voice field, in particular to the method and dress of a kind of interactive voice based on voice label
It sets.
Background technique
At present in artificial intelligent voice interactive product, since the levels of culture of people is different, birthplace is different, pronounces also each
It is not identical, when realizing the operation to same object for different sound, if the non-type group of mandarin, often goes out
Now due to user pronounce it is nonstandard, caused by instruction the problems such as can not identifying or identifying mistake, use can be largely effected in this way
Family also limits being widely used for interactive voice to the usage experience of interactive voice product.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the above drawbacks of the prior art, providing a kind of can improve and change
The nonstandard group's interactive voice of kind different user especially mandarin is experienced, development cost is low, it is low to realize difficulty, effect is preferable,
Can solve different regions and Different education levels group using cannot identify or identify in interactive voice mistake problem based on
The method and device of the interactive voice of voice label.
The technical solution adopted by the present invention to solve the technical problems is: constructing a kind of interactive voice based on voice label
Method, include the following steps:
A voice label) is added in the APP upgrade package of mobile terminal and defines and instruct the function packet called；
B) user first records language self to the operation object with sound self before operating to operation object
Phonetic symbol label, and automatically save；
C interactive voice operation) is carried out, the voice label of user oneself Record and Save is called, realizes relevant operation.
In the method for the interactive voice of the present invention based on voice label, the step B) further comprise:
B1) icon to the APP and internal submenu carry out tuning tag definition；
B2 voice label defined function) is activated by specific gesture to the operation object on the APP or APP, then
It clicks and records and automatically save.
In the method for the interactive voice of the present invention based on voice label, the operation object on the APP is at least
Including the icon or menu label on interface.
In the method for the interactive voice of the present invention based on voice label, the specific gesture is long-pressing or company
It hits.
In the method for the interactive voice of the present invention based on voice label, the voice label uses personal voice
As label.
The invention further relates to a kind of devices of method for realizing the above-mentioned interactive voice based on voice label, comprising:
Function adding unit: calling is defined and instructed for voice label to be added in the APP upgrade package of mobile terminal
Function packet.
Semantic label recording elements: for making user before operating to operation object, first with sound self to institute
The voice label of operation object recording self is stated, and is automatically saved；
Funcall unit: for calling the voice mark of user oneself recording with after function packet upgrading and after defining
Label realize relevant operation.
In device of the present invention, institute's semantic tags recording elements further comprise:
Tuning tag definition module: for the icon and internal submenu progress tuning tag definition to the APP；
Function activation module: for activating voice by the specific gesture to the operation object on the APP or APP
Then tag definition function is clicked and records and automatically save.
Function activation module: for activating voice by the specific gesture to the operation object on the APP or APP
Then tag definition function is clicked and records and automatically save.
In device of the present invention, the operation object on the APP includes at least icon or menu mark on interface
Label.
In device of the present invention, the specific gesture is long-pressing or double hit.
In device of the present invention, the voice label is using personal voice as label.
The method and device for implementing the interactive voice of the invention based on voice label, have the advantages that due to
The function packet called is defined and instructed equipped with voice label is added in the APP upgrade package of mobile terminal；User is to operation pair
Before being operated, voice label self first is recorded to operation object with sound self, and automatically save；Carry out voice friendship
Interoperability calls the voice label of user oneself Record and Save to realize relevant operation；By being to operate by personal sound
Object make a label that can be understood or use self, that is, made marks i.e. voice label, can be improved with personal voice
And improve the experience of different user especially mandarin nonstandard group's interactive voice, development cost is low, low, effect of realizing difficulty compared with
Well, different regions and Different education levels group be can solve and use the problem that cannot identify or identify mistake in interactive voice.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is that the present invention is based on the processes of method in method and device one embodiment of the interactive voice of voice label
Figure；
Fig. 2 is that user is before operating operation object in the embodiment, first with sound self to operation object
Record voice label self, and the specific flow chart automatically saved；
Fig. 3 is the structural schematic diagram of device in the embodiment.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It, should the language based on voice label in the method and device embodiment the present invention is based on the interactive voice of voice label
The flow chart of the method for sound interaction is as shown in Figure 1.In Fig. 1, the method for being somebody's turn to do the interactive voice based on voice label includes following step
It is rapid:
Voice label is added in the APP upgrade package of mobile terminal and defines and instruct the function packet called: this step by step S01
In rapid, voice label is added in the APP upgrade package of mobile terminal and defines and instruct the function packet called, makes the mobile terminal
There is APP voice label to define and instruct calling function.The APP can be the APP for interactive voice.It is noted that
In the present embodiment, mobile terminal can be smart phone or tablet computer etc., in practical applications, user can according to oneself
Hobby selection uses smart phone or tablet computer etc..
It is noted that above-mentioned APP is shown in the form of icon in the terminal.
Step S02 user first records self operation object with sound self before operating to operation object
Voice label, and automatically save: in this step, user is before operating operation object, first with the sound of oneself to behaviour
Make the voice label of object recording self, and the voice label of recording is automatically saved.Since the levels of culture of people is different,
Birthplace is different, pronounces also different, to realize the operation to same object for different sound, the best way is to use
The sound of this people is that the object to be operated makees a label that can be understood or use self, this is made marks with personal voice
Method is exactly voice label, and in other words, which, as label, is specifically such as about voice label using personal voice
What what was recorded, it is subsequent to will be described in detail.
Step S03 carries out interactive voice operation, calls the voice label of user oneself Record and Save, realizes related behaviour
Make: in this step, carrying out interactive voice operation, the sound that user says oneself Record and Save can call corresponding voice
Label realizes relevant operation.Specifically, user says content identical with the voice label recorded, so that it may directly wake up
Into voice operating mode, such user can be directly entered relevant operation using the voice label defined, eliminate people
Work operates the trouble of mobile terminal, especially uses the elderly or action inconvenient people more convenient.
The method of interactive voice based on voice label of the invention can improve and improve different user especially mandarin
Nonstandard group's interactive voice experience, development cost is low, it is low to realize difficulty, effect is preferable, can solve different regions and not identical text
Change level group and uses the problem that cannot identify or identify mistake in interactive voice.
For the present embodiment, above-mentioned steps S02 can also be refined further, and the flow chart after refinement is as shown in Figure 2.
In Fig. 2, step S02 further comprises:
Step S21 carries out tuning tag definition to the icon of APP and internal submenu: in this step, in APP upgrade package
Voice label definition and instruction calling function packet is added, so that it may which it is fixed that icon and internal submenu to APP carry out tuning label
Justice.
Step S22 activates voice label defined function by specific gesture to the operation object on APP or APP, then
It clicks and records and automatically save: in this step, voice label being activated by specific gesture to the operation object on APP or APP
Then defined function clicks Record and Save, which is long-pressing or double hit.It is noted that in the present embodiment,
Setting comprising long setting and double hit number temporally in voice label defined function packet, above-mentioned length temporally with double hit number
Any definition can be carried out according to the actual situation, such as: length temporally can be 2s, 3s etc., and double hit number can be 2 times, 3 times
Deng.It can be seen that being in fact exactly to activate voice label by long-pressing or double hit to the operation object on APP or APP in this step
Then defined function is clicked and records and automatically save.
Specifically, user will pop up the icon of microphone, user by the icon of long-pressing APP or the icon of double hit APP
The icon for pinning microphone, loquiturs and is recorded, such as: user says " opening wechat " or " opening Taobao ", then starts
It is recorded, after the completion of recording, hand is unclamped to the icon of microphone, then automatically saves the content of recording, the content of the recording is just
It is voice label, records after saving, recording process can be exited.When next time enters the APP, it can directly voice wake up, utilize
The voice label defined enters relevant operation, that is, user will say content same as the voice label defined, ability
Voice operating mode is waken up, such as: when the voice label defined is " opening wechat " or " opening Taobao ", said for voice
" open wechat " out or " opening Taobao ", then the APP can directly open wechat or Taobao, not need user's hands-on
APP。
Several submenus are equipped in the APP just not have to again submenu if the mandarin standard of comparison of user
Recorded speech label can directly carry out voice operating mode.If the mandarin of user it is nonstandard (such as some the elderlys only
Can speak a dialect, will not speak standard Chinese pronunciation), then the recording of voice label is also carried out to submenu, it can be to the operation object on APP
Activate voice label defined function by long-pressing or double hit, then click Record and Save, specific recording process be directed to
The recording process of the voice label of the icon of APP is identical.
It is noted that the operation object in the method for the interactive voice of the invention based on voice label, on APP
Including at least the icon or menu label etc. on interface, such as wechat, Taobao etc..
The present embodiment further relates to a kind of device of method for realizing the above-mentioned interactive voice based on voice label, the device
Structural schematic diagram is as shown in Figure 3.In Fig. 3, which includes function adding unit 1, semantic label recording elements 2 and funcall
Unit 3；Wherein, function adding unit 1 is used to that voice label definition to be added in the APP upgrade package of mobile terminal and instruction is called
Function packet；The APP can be the APP for interactive voice.It is noted that mobile terminal can be in the present embodiment
Smart phone or tablet computer etc., in practical applications, user can be selected using smart phone or be put down according to the hobby of oneself
Plate computer etc..It is noted that above-mentioned APP is shown in the form of icon in the terminal.
Semantic label recording elements 2 are for making user before operating to operation object, first with sound self to behaviour
Make the voice label of object recording self, and automatically saves；Since the levels of culture of people is different, birthplace is different, pronounces also each
It is not identical, the operation to same object to be realized for different sound, it is to grasp that the best way, which is with the sound of this people,
The object of work makees a label that can be understood or use self, this is exactly voice label with the method that personal voice makes marks,
In other words, the voice label using personal voice as label, specifically how to be recorded about voice label, rear extended meeting into
Row detailed description.
Funcall unit 3 is for calling the voice mark of user oneself Record and Save after being upgraded and defined with function packet
Label realize relevant operation.Specifically, user says content identical with the voice label recorded, so that it may directly wake up and enter
Voice operating mode, such user can be directly entered relevant operation using the voice label defined, eliminate artificial behaviour
Make the trouble of mobile terminal, especially the elderly or action inconvenient people is used more convenient.
The device of the invention can improve and improve the nonstandard group's interactive voice experience of different user especially mandarin, open
Send out at low cost, realization difficulty is low, effect is preferable, can solve different regions and Different education levels group uses in interactive voice not
It can identify or identify the problem of mistake.
In the present embodiment, which further comprises tuning tag definition module 21 and function activation
Module 22；Wherein, since voice label definition and instruction calling function packet being added in APP upgrade package, so that it may to the figure of APP
Mark and internal submenu carry out tuning tag definition, may be used for using tuning tag definition module 21 to the icon of APP and
Internal submenu carries out tuning tag definition.
Function activation module 22 is used for the operation object on APP or APP by activating voice mark by specific gesture
Defined function is signed, is then clicked and is recorded and automatically save.The specific gesture is long-pressing or double hit, it is worth mentioning at this point that, this reality
Apply in example, the setting comprising long setting and double hit number temporally in voice label defined function packet, above-mentioned length temporally and
Double hit number can carry out any definition according to the actual situation, such as: long temporally to can be 2s, 3s etc., double hit number can be with
It is 2 times, 3 inferior.It can be seen that the effect of the function activation module 22 is exactly to pass through to the operation object on APP or APP in fact
Long-pressing or double hit activate voice label defined function, then click and record and automatically save.
Specifically, user will pop up the icon of microphone, user by the icon of long-pressing APP or the icon of double hit APP
The icon for pinning microphone, loquiturs and is recorded, such as: user says " opening wechat " or " opening Taobao ", then starts
It is recorded, after the completion of recording, hand is unclamped to the icon of microphone, then automatically saves the content of recording, the content of the recording is just
It is voice label, records after saving, recording process can be exited.When next time enters the APP, it can directly voice wake up, utilize
The voice label defined enters relevant operation, that is, user will say content same as the voice label defined, ability
Voice operating mode is waken up, such as: when the voice label defined is " opening wechat " or " opening Taobao ", said for voice
" open wechat " out or " opening Taobao ", then the APP can directly open wechat or Taobao, not need user's hands-on
APP。
Several submenus are equipped in the APP, if the mandarin standard of comparison of the user of recorded speech label, antithetical phrase
Menu does not just have to recorded speech label again, can directly carry out voice operating mode.If the user's of recorded speech label
Mandarin is nonstandard (for example some the elderlys can only speak a dialect, and will not speak standard Chinese pronunciation), then also to carry out voice mark to submenu
The recording of label can activate voice label defined function by long-pressing or double hit to the operation object on APP, then click recording
And save, the recording process of specific recording process and the voice label of the icon for APP is identical.
It is noted that in the apparatus of the present, the operation object on APP includes at least icon or dish on interface
Single label etc., such as wechat, Taobao etc..
In short, the present invention makes interactive voice product in Different education levels, different pronunciation user groups, can effectively use
Sound self issues the instruction that can be identified to product.In addition, the existing cell phone application developed based on Android and ios platform is basic
It is not present or the not design of interactive voice, only needs through the invention in subsequent addition voice label function during upgrading, just
User may be implemented in addition to clicking screen, related APP software is operated with sound self, user's body can be substantially improved
It tests, improves user to the degree of adhesion and satisfaction of product.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of method of the interactive voice based on voice label, which comprises the steps of:
A voice label) is added in the APP upgrade package of mobile terminal and defines and instruct the function packet called；
B) user first records voice mark self to the operation object with sound self before operating to operation object
Label, and automatically save；
C interactive voice operation) is carried out, the voice label of user oneself Record and Save is called, realizes relevant operation.
2. the method for the interactive voice according to claim 1 based on voice label, which is characterized in that the step B) into
One step includes:
B1) icon to the APP and internal submenu carry out tuning tag definition；
B2 voice label defined function) is activated by specific gesture to the operation object on the APP or APP, is then clicked
It records and automatically saves.
3. the method for the interactive voice according to claim 2 based on voice label, which is characterized in that on the APP
Operation object includes at least the icon or menu label on interface.
4. the method for the interactive voice according to claim 2 or 3 based on voice label, which is characterized in that described specific
Gesture be long-pressing or double hit.
5. the method for the interactive voice according to claim 1 based on voice label, which is characterized in that the voice label
Using personal voice as label.
6. a kind of device for realizing the method for the interactive voice based on voice label as described in claim 1, which is characterized in that
Include:
Function adding unit: the function of calling is defined and instructed for voice label to be added in the APP upgrade package of mobile terminal
Packet；
Semantic label recording elements: for making user before operating to operation object, first with sound self to the behaviour
Make the voice label of object recording self, and automatically saves；
Funcall unit: after being upgraded and being defined with the function packet, the voice label for calling user oneself to record is realized
Relevant operation.
7. device according to claim 6, which is characterized in that institute's semantic tags recording elements further comprise:
Tuning tag definition module: for the icon and internal submenu progress tuning tag definition to the APP；
Function activation module: for activating voice label by the specific gesture to the operation object on the APP or APP
Then defined function is clicked and records and automatically save.
8. device according to claim 7, which is characterized in that the operation object on the APP includes at least on interface
Icon or menu label.
9. device according to claim 7 or 8, which is characterized in that the specific gesture is long-pressing or double hit.
10. device according to claim 9, which is characterized in that the voice label is using personal voice as label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910040369.8A CN109828739A (en) | 2019-01-16 | 2019-01-16 | The method and device of interactive voice based on voice label |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910040369.8A CN109828739A (en) | 2019-01-16 | 2019-01-16 | The method and device of interactive voice based on voice label |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109828739A true CN109828739A (en) | 2019-05-31 |
Family
ID=66860260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910040369.8A Pending CN109828739A (en) | 2019-01-16 | 2019-01-16 | The method and device of interactive voice based on voice label |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109828739A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113035171A (en) * | 2021-03-05 | 2021-06-25 | 随锐科技集团股份有限公司 | Voice recognition processing method and system |
-
2019
- 2019-01-16 CN CN201910040369.8A patent/CN109828739A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113035171A (en) * | 2021-03-05 | 2021-06-25 | 随锐科技集团股份有限公司 | Voice recognition processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2710984C2 (en) | Performing task without monitor in digital personal assistant | |
| CN111261144B (en) | Voice recognition method, device, terminal and storage medium | |
| US8606576B1 (en) | Communication log with extracted keywords from speech-to-text processing | |
| CN105940446B (en) | Method for machine-to-human interaction, computer storage medium, and humanoid robot | |
| CN105074817A (en) | Systems and methods for switching processing modes using gestures | |
| CN109448460A (en) | Recitation detection method and user equipment | |
| CN106898349A (en) | A kind of Voice command computer method and intelligent sound assistant system | |
| US10540451B2 (en) | Assisted language learning | |
| CN107403623A (en) | Store method, terminal, Cloud Server and the readable storage medium storing program for executing of recording substance | |
| CN109545197A (en) | Voice instruction identification method and device and intelligent terminal | |
| CN108694947A (en) | Sound control method, device, storage medium and electronic equipment | |
| CN105679119A (en) | Scanning dictation method | |
| CN110033769A (en) | A kind of typing method of speech processing, terminal and computer readable storage medium | |
| CN107291704A (en) | Treating method and apparatus, the device for processing | |
| CN106228047B (en) | A kind of application icon processing method and terminal device | |
| CN103177724A (en) | Method, device and terminal for text operating controlled by voice | |
| CN109828739A (en) | The method and device of interactive voice based on voice label | |
| CN102546901A (en) | Information processing method capable of realizing forcible word memorization by aid of cell phone | |
| CN111199724A (en) | Information processing method and device and computer readable storage medium | |
| US9881611B2 (en) | System and method for providing voice communication from textual and pre-recorded responses | |
| CN108597499A (en) | Method of speech processing and voice processing apparatus | |
| Tomko et al. | Towards efficient human machine speech communication: The speech graffiti project | |
| RU2344492C2 (en) | Dynamic support of pronunciation for training in recognition of japanese and chinese speech | |
| CN106897275A (en) | A kind of dialect real-time translation system | |
| US20200111478A1 (en) | Retraining voice model for trigger phrase using training data collected during usage |
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 |