CN101572084A - Intelligent voice system and method thereof - Google Patents
Intelligent voice system and method thereof Download PDFInfo
- Publication number
- CN101572084A CN101572084A CNA2008100368215A CN200810036821A CN101572084A CN 101572084 A CN101572084 A CN 101572084A CN A2008100368215 A CNA2008100368215 A CN A2008100368215A CN 200810036821 A CN200810036821 A CN 200810036821A CN 101572084 A CN101572084 A CN 101572084A
- Authority
- CN
- China
- Prior art keywords
- voice
- voice signal
- intelligent
- signal
- module
- 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
Images
Abstract
The invention relates to an intelligent voice system and a method thereof. The system comprises a monitoring module, a distinguishing module and a function application module, wherein the monitoring module can monitor and receive an external voice signal; the distinguishing module is connected with the monitoring module so as to distinguish the voice signal received by the monitoring module; and the function application module is connected with the distinguishing module and can execute a relative function according to the distinguished voice signal. The method comprises the following steps: monitoring and receiving the external voice signal; distinguishing the received voice signal; executing the relative function according to the received voice signal; and realizing a more humanized and intelligent dialog between a person and the system.
Description
Technical field
The present invention relates to a kind of voice system and method, particularly relate to a kind of intelligent voice system and method.
Background technology
At present the voice command software that is provided with in some machinery and equipment all must be clicked hot key by the user and starts software, say order then, and the order kind is considerably less, can only user's input initiatively, there is not interactive sensation.
Such as, the hand-held GPS device that uses also rests on the manual input command stage mostly now, but the device of minority support voice input also can only be user's input initiatively, can not obtain the corresponding speech answering of machine.
Summary of the invention
Purpose of the present invention makes machinery and equipment carry out the intelligent voice system and the method for phonetic entry order for proposition is a kind of by man-machine conversation, has solved the problem that man-machine conversation has some setbacks.
Technical scheme of the present invention is: a kind of intelligent sound method, realize people and the more humane and intelligentized dialogue of machinery compartment, and steps of the method are:
(1) monitors and the reception external sound signal;
(2) the received voice signal of identification;
(3), carry out corresponding function according to the voice signal that is recognized.
The identification voice mode is in step (2), judges whether received voice signal is consistent with the speech data of being stored; As be consistent and then carry out next step and point out a voice messaging, the inconsistent voice signal that then feeds back to.
In step (3), comprise that also one searches the carried out functional steps relevant with voice signal, can search and the corresponding function of carrying out of voice signal.
In step (2), also comprise a voice signal switch process, but convert received voice signal to the machine identification signal.
This method can allow the user use machinery and equipment more easily by the setting of multiple voice and correlation function, and machinery and equipment is also had more cordial feeling.
The invention allows for a kind of intelligent voice system, realize people and the more humane and intelligentized dialogue of machinery compartment, this system comprises:
One monitors module, can monitor and receive external sound signal;
One recognition module, it connects this monitoring module, and the voice signal received to this monitoring module carries out identification;
One function application module, it connects this recognition module, can carry out corresponding function according to the voice signal that recognizes.
This recognition module also is provided with a units of speech data, voice data.
This recognition module, other has a speech conversion unit, can finish the mutual conversion between the cognizable bottom voice signal of advanced speech signal and machine.
This recognition module is provided with a judging unit, judges whether received voice signal has storage in native system; Also be provided with a voice feedback unit, the outside is given and voice signal, information indicating.
This function application module also is provided with a search unit, searches the corresponding function and the execution of the voice signal of identification.
Intelligent voice system of the present invention and method, the person of being easy to use reaches control to machinery and equipment by voice; Simultaneously, make interactive content abundanter, mode is easier, flexible; Make machinery and equipment have more hommization with intelligent.
Description of drawings
Fig. 1 is the inventive method schematic flow sheet.
Fig. 2 is the modular structure synoptic diagram of intelligent voice system of the present invention.
Embodiment
Below in conjunction with accompanying drawing in detail embodiments of the invention are described in detail.
Fig. 1 is the inventive method schematic flow sheet, and as shown in the figure, a kind of intelligent sound method realizes people and the more humane and intelligentized dialogue of machinery compartment, and the step of the method is:
Step 101: monitor and receive external sound signal, after machinery and equipment starts, enter into listening state automatically, monitor and the reception external sound signal, need not any hot key triggering; Also vice activation can be set, when only receiving a vice activation order, just other voice commands be handled;
Step 102: but convert received voice signal to the machine identification signal;
Step 103: judge whether received voice signal is consistent with the speech data of being stored, then carry out step 104 for "Yes" if be consistent; Then carry out step 105 as if inconsistent for "No";
Step 104:, carry out corresponding function according to received voice signal; After but identification is defined as recognition of speech signals, search and the corresponding function of carrying out of voice signal, and carry out corresponding function; The function that has only need be carried out voice dialogue, and the function that also has needs machine to carry out corresponding operating, and when executable operations the user is carried out speech answering;
Step 105: feed back to a voice signal.
Fig. 2 is the modular structure synoptic diagram of intelligent voice system of the present invention, and as shown in the figure, a kind of intelligent voice system is realized people and the more humane and intelligentized dialogue of machinery compartment, and this intelligent voice system uses said method, and this system comprises:
One monitors module 10, can monitor and receive external sound signal; This monitoring module 10 also can be provided with a vice activation unit 100, has only after a vice activation order that receives special setting, triggers this vice activation unit 100, and machine just can be carried out the corresponding operating of other voice commands.
One recognition module 20, it connects this monitoring module 10, and these monitoring module 10 received voice signals are carried out identification; Be provided with in this recognition module 20:
One speech conversion unit 201 at first, becomes the cognizable bottom voice signal of machine with the advanced speech conversion of signals that receives;
One judging unit 202 judges whether received voice signal has storage in native system, then call in this way and the corresponding executable function of this voice signal and carry out, as otherwise feed back a voice signal;
One units of speech data 203, voice data is a speech database, and the voice command that native system will use all is stored in this element; The speech data of storage is many more in this units of speech data 203, can make man-machine conversation smooth and easy more, makes the machinery and equipment that is mounted with native system have more hommization; Speech data in this units of speech data 203 all can be provided with by the user and be written into, and can insert the new speech data again, also can delete existing speech data.
Other has a voice feedback unit 204, and the outside is given and voice signal, information indicating; This voice feedback unit 204 is an external unit, and all external voice signals spread out of all thus, and the voice signal that is spread out of is by this speech conversion unit, converts the cognizable bottom layer signal of machine to the advanced speech signal.
One function application module 30, it connects this recognition module 20, can carry out corresponding function according to the voice signal that recognizes; This function application module 30 is provided with an associative cell 302, makes voice signal corresponding with corresponding function, and system receives this voice signal can carry out the realization corresponding function; This associative cell 302 can be provided with new incidence relation, also can adjust existing incidence relation.
This function application module 30 also is provided with a search unit 301, searches the corresponding function and the execution of the voice signal of identification, makes machine have more intellectuality.
Also have voice to insmod 40, its units of speech data 203 with recognition module 20 links, and new speech data is adjusted or be written into to the speech data of storing in this units of speech data 203.
Preferably, system of the present invention is inserted in the hand-held GPS device, after the GPS device is opened, used voice and the dialogue of GPS device as need, at first, need phonetic entry one vice activation order, trigger vice activation unit 100, man-machine conversation begins:
User: Mantas.
System: yes, Mr. worker, do I have anything to render you any further service? (system triggers vice activation unit 100, and the user is carried out voice feedback by feedback unit.)
The user: I want to go home.
System: good, just a moment,please, and I am just at programme path.(utilize 20 pairs of user voice signal that receive of recognition module to change and distinguish judgement, and search the corresponding function of carrying out of voice signal, and carry out this function by function application module 30.)
System: Mr. Wang, the Liang Tiaolu that goes home to have at present, one through the Nanjing Road, but comparatively traffic congestion is walked 2 loops for other one, can be than more than last 3 kilometers, but which bar free pathway be may I ask you and will be selected?
User: just select second.
System: good, just a moment,please, and I have planned, can keep straight on now, can turn right after 500 meters and go up the viaduct.
User: Mantas.
System: yes, Mr. Wang, do I have anything to render you any further service?
The user: I am good to be stranded!
System: sorry, I do not catch, can say once again?
The user: I really get well and am stranded!
System: sorry, I do not catch, can say once again?
……………………………
A user: shutdown!
System: OK is during shutdown is carried out.
From the above, intelligent voice system of the present invention and method are applied in the machinery and equipment, make machinery and equipment have more hommization, intellectuality, can allow the user by voice machinery and equipment be controlled, with the smooth and easy dialogue of machinery and equipment.
Claims (14)
1, a kind of intelligent sound method is characterized in that, the step of the method is:
(1) monitors and the reception external sound signal;
(2) the received voice signal of identification;
(3), carry out corresponding function according to the voice signal that is recognized.
2, intelligent sound method according to claim 1 is characterized in that, also comprises a voice signal switch process in this step 2, but converts received voice signal to the machine identification signal.
3, intelligent sound method according to claim 1 is characterized in that, comprises also in this step 3 that one searches the carried out functional steps relevant with voice signal.
4, intelligent sound method according to claim 2 is characterized in that, also comprises a step in this step 2: judge whether received voice signal is consistent with the speech data of being stored, as the execution in step 3 and point out a voice messaging of being consistent then; The inconsistent voice signal that then feeds back to.
5, intelligent sound method according to claim 1 is characterized in that, also comprises a vice activation step in this step 1, receives a special sound startup command, triggers reception and execution to other voice commands.
6, a kind of intelligent voice system is characterized in that, this system comprises:
One monitors module, can monitor and receive external sound signal;
One recognition module, it connects this monitoring module, and the voice signal received to this monitoring module carries out identification;
One function application module, it connects this recognition module, can carry out corresponding function according to the voice signal that recognizes.
7, intelligent voice system according to claim 6 is characterized in that, this recognition module also is provided with a units of speech data, voice data.
8, intelligent voice system according to claim 6 is characterized in that, this recognition module, and other has a speech conversion unit, can finish the mutual conversion between the cognizable bottom voice signal of advanced speech signal and machine.
9, intelligent voice system according to claim 6 is characterized in that, this function application module is provided with an associative cell, makes voice signal corresponding with corresponding function.
10, intelligent voice system according to claim 9 is characterized in that, this function application module also is provided with a search unit, searches the corresponding function and the execution of the voice signal of identification.
11, intelligent voice system according to claim 7 is characterized in that, this recognition module is provided with a judging unit, judges whether received voice signal has storage in native system.
12, intelligent voice system according to claim 8 is characterized in that, this recognition module also is provided with a voice feedback unit, and information indicating is done with voice signal in the outside.
13, intelligent voice system according to claim 6 is characterized in that, this monitors module, and a vice activation unit also can be set, and triggers this vice activation unit, and machine just can be carried out the corresponding operating of other voice commands.
14, intelligent voice system according to claim 8 is characterized in that, also has voice to insmod, and the units of speech data of itself and recognition module links, and new speech data is adjusted or be written into to the speech data of storing in this units of speech data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008100368215A CN101572084A (en) | 2008-04-29 | 2008-04-29 | Intelligent voice system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008100368215A CN101572084A (en) | 2008-04-29 | 2008-04-29 | Intelligent voice system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101572084A true CN101572084A (en) | 2009-11-04 |
Family
ID=41231417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2008100368215A Pending CN101572084A (en) | 2008-04-29 | 2008-04-29 | Intelligent voice system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101572084A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807395A (en) * | 2010-02-26 | 2010-08-18 | 中山大学 | Method for controlling intelligent terminal via voice |
| CN101826324A (en) * | 2010-02-26 | 2010-09-08 | 中山大学 | Intelligent terminal |
| CN102207844A (en) * | 2010-03-29 | 2011-10-05 | 索尼公司 | Information processing device, information processing method and program |
| CN104468961A (en) * | 2013-09-25 | 2015-03-25 | 北京新媒传信科技有限公司 | Method and device for prompting position of terminal |
| JP2018513431A (en) * | 2015-01-30 | 2018-05-24 | マイクロソフト テクノロジー ライセンシング，エルエルシー | Updating language understanding classifier model for digital personal assistant based on crowdsourcing |
-
2008
- 2008-04-29 CN CNA2008100368215A patent/CN101572084A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807395A (en) * | 2010-02-26 | 2010-08-18 | 中山大学 | Method for controlling intelligent terminal via voice |
| CN101826324A (en) * | 2010-02-26 | 2010-09-08 | 中山大学 | Intelligent terminal |
| CN102207844A (en) * | 2010-03-29 | 2011-10-05 | 索尼公司 | Information processing device, information processing method and program |
| CN102207844B (en) * | 2010-03-29 | 2016-01-20 | 索尼公司 | Messaging device and information processing method |
| CN104468961A (en) * | 2013-09-25 | 2015-03-25 | 北京新媒传信科技有限公司 | Method and device for prompting position of terminal |
| JP2018513431A (en) * | 2015-01-30 | 2018-05-24 | マイクロソフト テクノロジー ライセンシング，エルエルシー | Updating language understanding classifier model for digital personal assistant based on crowdsourcing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101557432B (en) | Mobile terminal and menu control method thereof | |
| CN109243444B (en) | Voice interaction method, device and computer-readable storage medium | |
| EP2854131A1 (en) | Vehicular device, server, and information processing method | |
| CN101572084A (en) | Intelligent voice system and method thereof | |
| CN101325756A (en) | Apparatus for identifying mobile phone voice and method for activating mobile phone voice identification | |
| EP2904486B1 (en) | Handsfree device with continuous keyword recognition | |
| CN104837010B (en) | Voice remote control testing method, device and system | |
| CN108108142A (en) | Voice information processing method, device, terminal device and storage medium | |
| WO2008083173A3 (en) | Local storage and use of search results for voice-enabled mobile communications devices | |
| KR20150022786A (en) | Embedded system for construction of small footprint speech recognition with user-definable constraints | |
| EP2747077A1 (en) | Voice recognition system, recognition dictionary logging system, and audio model identifier series generation device | |
| CN101902587A (en) | Voice-based television control system | |
| CN101521722A (en) | Speech recognition television and realization method thereof | |
| CN103514879A (en) | Local voice recognition method based on BP neural network | |
| CN101794126A (en) | Wireless intelligent home appliance voice control system | |
| CN103220423A (en) | Voice answering method and mobile terminal device | |
| CN102546953A (en) | System and method for full voice control of mobile terminal | |
| CN103209257B (en) | Method for controlling voice assistant through earphone | |
| EP3157003A1 (en) | Terminal control method and device, voice control device and terminal | |
| CN207938056U (en) | Addressable electronic gate enters system | |
| CN105635778A (en) | Voice interaction method and system of intelligent television | |
| CN107491286A (en) | Pronunciation inputting method, device, mobile terminal and the storage medium of mobile terminal | |
| CN102325218A (en) | Method and unit for changing dynamic application display effect of mobile phone by way of voice control | |
| CN109144458A (en) | For executing the electronic equipment for inputting corresponding operation with voice | |
| CN110047484A (en) | A kind of speech recognition exchange method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20091104 |