CN102841771B - A kind of method of speech processing and voice processing apparatus - Google Patents
A kind of method of speech processing and voice processing apparatus Download PDFInfo
- Publication number
- CN102841771B CN102841771B CN201110168490.2A CN201110168490A CN102841771B CN 102841771 B CN102841771 B CN 102841771B CN 201110168490 A CN201110168490 A CN 201110168490A CN 102841771 B CN102841771 B CN 102841771B
- Authority
- CN
- China
- Prior art keywords
- state
- voice signal
- predetermined
- electronic equipment
- 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.)
- Active
Links
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention provides a kind of method of speech processing and voice processing apparatus, relate to phonetic entry technical field.Wherein said method of speech processing, is applied to an electronic equipment, and described electronic equipment at least has the first state and the second state, and described method of speech processing comprises: when described electronic equipment is in the first state, the first event detected; Judge described first event whether first predetermined condition; When described first event meets described first predetermined condition, described electronic equipment is switched to the second state from described first state; Judge described second state whether second predetermined condition; When described second state meets described second predetermined condition, gather voice signal; Resolve described voice signal.The present invention can improve the convenience of phonetic entry.
Description
Technical field
The present invention relates to phonetic entry technical field, be specifically related to a kind of method of speech processing and voice processing apparatus.
Background technology
Voice control function is all accomplished in a lot of handheld device, and the design original intention of voice control function is that conveniently user controls, and simplifies user operation, improves the convenience of equipment use.
The realization of voice control function, needs device start voice detection function, to identify the voice signal of input.Due to voice detection function relatively power consumption, if always in running order, then greatly can increase equipment power dissipation, and reduce the cruising time without external power supply equipment.
In order to overcome above problem, the use of voice control function of the prior art, needs by user as required, to enable voice detection function on one's own initiative.Such as, illustrate for phonetic dialing, user can start voice detection function by arranging interface, or starts voice detection function by specific physical button.Obviously, this processing mode, enables voice detection function with still needing user's special hand, and user needed to carry out manual operation with voice activated measuring ability before each phonetic entry, for certain user, not as good as the convenience that manually operation input is next always.Therefore, directly use physical button or touch-screen to carry out input of control commands compared to user, the improvement of above-mentioned processing mode to equipment use convenience is more limited.
Summary of the invention
Embodiment of the present invention technical matters to be solved is to provide a kind of method of speech processing and voice processing apparatus, in order to improve the convenience of phonetic entry.
For solving the problems of the technologies described above, the embodiment of the present invention provides scheme as follows:
A kind of method of speech processing, be applied to an electronic equipment, described electronic equipment at least has the first state and the second state, comprising:
When described electronic equipment is in the first state, the first event detected;
Judge described first event whether first predetermined condition;
When described first event meets described first predetermined condition, described electronic equipment is switched to the second state from described first state;
Judge described second state whether second predetermined condition;
When described second state meets described second predetermined condition, gather voice signal;
Resolve described voice signal.
Preferably, in said method,
After the described voice signal of described parsing, also comprise:
Obtain the analysis result of described voice signal;
Corresponding 3rd order is obtained according to described analysis result;
Perform described 3rd order.
Preferably, in said method,
After the described voice signal of described parsing, also comprise:
Obtain the analysis result of described voice signal;
When described analysis result cannot be ordered and gathers voice signal to stopping time corresponding or stop resolving voice signal with the 3rd.
Preferably, in said method,
Described collection voice signal comprises and gathers voice signal in the given time;
The voice signal that the described voice signal of described parsing comprises collecting in the described schedule time is resolved;
After the described voice signal of described parsing, also comprise:
Obtain the analysis result of the voice signal collected in the described schedule time;
When described analysis result cannot be ordered and gathers voice signal to stopping time corresponding or stop resolving voice signal with the 3rd.
Preferably, in said method,
Describedly judge whether second predetermined condition comprises described second state:
Determine the predetermined state selected in advance;
Judge whether described second state belongs to described predetermined state;
When described second state belongs to described predetermined state, judge that described second state meets described second predetermined condition.
Preferably, in said method,
Described the first event detected before also comprise:
Determine the third state of the first application program, the third state of described first application program is the state needing triggering voice signals collecting;
The described third state is added in described predetermined state.
Preferably, in said method,
Describedly judge whether second predetermined condition comprises described second state:
Determine registered in advance, for the predetermined message of triggering voice signals collecting;
Judge whether receive described predetermined message in said second condition;
When receiving described predetermined message, judge that described second state meets described second predetermined condition.
The embodiment of the present invention additionally provides a kind of voice processing apparatus, is applied to an electronic equipment, and described electronic equipment at least has the first state and the second state, comprising:
First detecting unit, for when described electronic equipment is in the first state, detects the first event;
First judging unit, for judging described first event whether first predetermined condition;
Switch unit, for when described first event meets described first predetermined condition, switches to the second state by described electronic equipment from described first state;
Second judging unit, for judging described second state whether second predetermined condition;
Collecting unit, for when described second state meets described second predetermined condition, gathers voice signal;
Resolution unit, for resolving described voice signal.
Preferably, also comprise in above-mentioned voice processing apparatus:
First obtains unit, for obtaining the analysis result of described voice signal;
Second obtains unit, for obtaining corresponding 3rd order according to described analysis result;
Performance element, for performing described 3rd order.
Preferably, in above-mentioned voice processing apparatus, also comprise:
3rd obtains unit, for obtaining the analysis result of described voice signal;
First control module, for ordering and gather voice signal to stopping time corresponding or stop resolving voice signal with the 3rd when described analysis result.
Preferably, in above-mentioned voice processing apparatus,
Described collecting unit is further used for gathering voice signal in the given time;
The voice signal that described resolution unit is further used for collecting in the described schedule time is resolved;
Described voice processing apparatus also comprises:
3rd obtains unit, for obtaining the analysis result of the voice signal collected in the described schedule time;
Second control module, for ordering and gather voice signal to stopping time corresponding or stop resolving voice signal with the 3rd when described analysis result.
Preferably, in above-mentioned voice processing apparatus, described second judging unit comprises:
First determining unit, for determining the predetermined state selected in advance;
3rd judging unit, for judging whether described second state belongs to described predetermined state;
First processing unit, for when described second state belongs to described predetermined state, judges that described second state meets described second predetermined condition.
Preferably, in above-mentioned voice processing apparatus, also comprise:
Second determining unit, for determining the third state of the first application program, the third state of described first application program is the state needing triggering voice signals collecting;
Second processing unit, for being added into the described third state in described predetermined state.
Preferably, in above-mentioned voice processing apparatus, described second judging unit comprises:
3rd determining unit, for determine registered in advance, for the predetermined message of triggering voice signals collecting;
4th judging unit, for judging whether receive described predetermined message in said second condition;
Second processing unit, for when receiving described predetermined message, judges that described second state meets described second predetermined condition.
As can be seen from the above, the method for speech processing that the embodiment of the present invention provides and voice processing apparatus,
As can be seen from above step, the present embodiment, when described second state meets described second predetermined condition, goes on one's own initiative to gather voice signal, and does not need user's manually deactivation voice detection function, thus can user friendly phonetic entry operation.
The present embodiment is in above-mentioned steps 15, can when described second state meet described second predetermined condition, do not start voice detection function, do not carry out the collection of voice signal, direct process ends, to avoid the waste of the equipment power dissipation that opening voice measuring ability causes under unexpected environment, thus save equipment power dissipation, the stand-by time of extension device.Can find out, the present embodiment can average out at phonetic entry convenience and reducing between power consumption, namely facilitates user speech input, again can not undue consumer device electric energy.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the method for speech processing described in the embodiment of the present invention;
Fig. 2 is the structural representation of the voice processing apparatus described in the embodiment of the present invention.
Embodiment
Embodiments provide a kind of method of speech processing, provide convenience to the phonetic entry of user, and equipment need not start voice detection function to gather voice signal, can save equipment power dissipation always.Below will the present invention is further illustrated by specific embodiment.
Method of speech processing described in the embodiment of the present invention, is applied to an electronic equipment, and described electronic equipment at least has the first state and the second state.
Here, the first state, the second state are all a kind of duties of electronic equipment.Such as, when electronic equipment is conversed, the state of this electronic equipment is talking state; When electronic equipment terminates call, its state is end of conversation state; Again such as, electronic equipment, in order to prevent false touch or illegal use, is provided with lock-out state, limits the input operation of keyboard or touch-screen under lock-out state, also limits the accessing operation to electronic equipment internal; After carrying out unlocking operation, electronic equipment enters released state, now removes above-mentioned restriction.
Please refer to Fig. 1, this method of speech processing comprises the following steps:
Step 11, when described electronic equipment is in the first state, detects the first event.
Step 12, judges described first event whether first predetermined condition.
Step 13, when described first event meets described first predetermined condition, switches to the second state by described electronic equipment from described first state.
Here, when electronic equipment detects the first event meeting predetermined first condition in a first state, then electronic equipment is switched to the second state from the first state.Such as, when electronic equipment is under talking state (the first state), detect that user have input an operational order (the first event), if this operational order is hangup command (meeting predetermined first condition), now will perform on-hook operation, the first equipment will be switched to end of conversation state from talking state.Again such as, when electronic equipment detects the operational order (the first event) that user inputs in the locked state, if the unlock command that this operational order coupling is preset, now the first equipment is switched to released state from lock-out state.
Here, the first event can be that electronic equipment side detects user operation, can also be to detect it is that system produces (not being the user operation of electronic equipment side).For call, trigger call state is switched to the first event of end of conversation state, can be the instruction of user's manual operation input kill-call, can also be the end call instruction that partner hangs up the generation of rear system.
Step 14, judges described second state whether second predetermined condition.
Step 15, when described second state meets described second predetermined condition, gathers voice signal.
Step 16, resolves described voice signal.
As can be seen from above step, the present embodiment, when described second state meets described second predetermined condition, goes on one's own initiative to gather voice signal, and does not need user's manually deactivation voice detection function, thus can user friendly phonetic entry operation.
The present embodiment is in above-mentioned steps 15, can when described second state meet described second predetermined condition, do not start voice detection function, do not carry out the collection of voice signal, direct process ends, to avoid the waste of the equipment power dissipation that opening voice measuring ability causes under unexpected environment, thus save equipment power dissipation, the stand-by time of extension device.Can find out, the present embodiment can average out at phonetic entry convenience and reducing between power consumption, namely facilitates user speech input, again can not undue consumer device electric energy.
In above-mentioned steps 14, judging the second state whether second predetermined condition, can be specifically judge whether the second state is the predetermined state selected in advance.That is, in the present embodiment in a kind of preferred implementation, certain or some state selected from the various states of electronic equipment in advance as predetermined state, and preserves the information of these predetermined states.Namely before step 11, determine the third state of the first application program, the third state of described first application program is the state needing triggering voice signals collecting, and the described third state is added in described predetermined state.Here the first application program is not application-specific, but under certain state of this first application program, usual user wishes to carry out phonetic entry, therefore this state of this application program is preserved as predetermined state.
Such as, statistics and analysis user uses the custom of electronic equipment in advance, selects the particular state that user can carry out voice operating usually and joins in described predetermined state.Such as, user is after a phone dialed by use electronic equipment, the demand then dialing next phone may also be had, conveniently by phonetic entry to dial next phone, in advance the end of conversation state of electronic equipment can be joined predetermined state to make user after end one call.Again such as, user is carrying out unlocking operation to electronic equipment and after lighting screen, may phonetic entry control command, therefore can be joined in predetermined state by the released state of electronic equipment in advance.Also such as, user operates in the graphical operation interface of electronic equipment, the main interface of return electron equipment or when logging in certain task interface, the demand of input voice control command may be had, therefore can in advance the main interfacial state of electronic equipment or specific task interface state be joined in predetermined state.
Then, judge in such a way in above-mentioned steps 14:
Step 141 ', determine the predetermined state selected in advance;
Step 142 ', judge whether described second state belongs to described predetermined state;
Step 143 ', when described second state belongs to described predetermined state, judge that described second state meets described second predetermined condition, and enter step 15;
Step 144 ', when described second state does not belong to described predetermined state, judge that described second state does not meet described second predetermined condition, now direct process ends.
The present embodiment gives another preferred implementation of above-mentioned steps 14 simultaneously.Such as, in Android operation system, realized the management notified by a kind of informing mechanism.Wherein message (intent) can illustrate the state of sender, and indicates the condition of recipient.What whom if the intent receiving Another Application is wanted in an application, need, to operating system registration recipient (receiver) information, to want to receive the intent of intent or the content sent to illustrate.Such operating system will know that this application program is wanted to receive which type of intent.The intent that any application program sends, can be taken over by the notice administrative mechanism functional module of Android operation system, then send to qualified receiver by it, starts subsequent operation.Such as, after device power-up has started, kernel (also can regard start-up routine as) will send a BOOT_COMPLETEintent, completes in order to indicate startup.Therefore, the present embodiment can in advance as required, select some predetermined messages (intent), described predetermined message refers to when receiving these message, state corresponding to this message normally user wishes to start phonetic entry measuring ability to gather the state of voice signal, that is, the function of this predetermined message is triggering voice signals collecting in the present embodiment.Such as, when receiving above-mentioned BOOT_COMPLETE, devices illustrated has started, and now user may wish to carry out phonetic entry operation.Then, judge in such a way in above-mentioned steps 14:
Step 141 ", determine registered in advance, for the predetermined message of triggering voice signals collecting;
Step 142 ", judge whether receive described predetermined message in said second condition;
Step 143 ", when receiving described predetermined message, judging that described second state meets described second predetermined condition, and entering step 15;
Step 144 ", when not receiving described predetermined message, judge that described second state does not meet described second predetermined condition, now direct process ends.
Here, if having received in the second condition registered in advance, for the predetermined message of triggering voice signals collecting, then can start voice detection function to gather voice signal; Otherwise, can direct process ends.
The present embodiment can also perform corresponding operation according to the voice signal of input further.Now, the present embodiment is after above-mentioned steps 16, further comprising the steps of:
Step 17, obtains the analysis result of described voice signal;
Step 18, obtains corresponding 3rd order according to described analysis result;
Step 19, performs described 3rd order.
In above-mentioned steps 17 ~ 19, according to analysis result, go to obtain the 3rd order corresponding to this analysis result, and then perform the 3rd order, to realize the phonetic entry of user, the executable order of the equipment that is converted to, completes corresponding function.Such as, according to a string phone numbers combination of user's input, resolve and obtain the order that is dialed corresponding telephone number, and perform the order of dialing this telephone number, to initiate audio call.Again such as, according to the phonetic entry at " the main interface " of user's input, resolve the order obtaining " returning to main interface ", and perform this order to return to main interface.
Certainly, when above-mentioned steps 15 gathers voice signal, user may not send voice signal, therefore the background sound in environment may only be collected in step 15, the analysis result obtained by parsing in step 16 may be an Indication message,, namely there is not significant input in the voice messaging that can not identify in the voice signal collected in order to instruction.Now, in step 18, the 3rd order obtained according to this analysis result may be the dummy instruction not performing any operation, and that is, when performing the 3rd order in step 19, owing to being a dummy instruction, therefore electronic equipment does not perform any operation.
In some cases, the voice signal of user's input may not be converted into the executable order of system, and in this case, the present embodiment can stop carrying out phonetic entry.Now, the present embodiment is after above-mentioned steps 16, further comprising the steps of:
Step 17 ', obtain the analysis result of described voice signal;
Step 18 ', when described analysis result cannot be ordered and gathers voice signal to stopping time corresponding or stop resolving voice signal with the 3rd.
By above step 17 ' ~ 18 ', thus the present embodiment on one's own initiative, in time can stop the parsing gathering voice signal or stopping voice signal, to save unnecessary operation and to save equipment power dissipation.
The present embodiment needs opening voice measuring ability when gathering voice signal in above-mentioned steps 15, this function expends the electric energy of equipment, consider saving equipment power dissipation, the present embodiment can arrange a timer, this timer is started, when this timer expiry overflows, if do not receive significant phonetic entry yet when starting to gather voice signal, then voice detection function can be stopped, the collection of conclusion tone signal.Now, in above-mentioned steps 15, described collection voice signal specifically comprises: gather voice signal in the given time; In above-mentioned steps 16, the voice signal that the described voice signal of described parsing comprises collecting in the described schedule time is resolved; After above-mentioned steps 16, can also comprise the following steps:
Step 17 ", obtain the analysis result of the voice signal collected in the described schedule time;
Step 18 ", when described analysis result cannot be ordered and gathers voice signal to stopping time corresponding or stop resolving voice signal with the 3rd.Here, analysis result cannot correspondingly with the 3rd order refer to, analysis result can not be converted into the executable order of equipment.
Here, preferably, the above-mentioned schedule time can be identical for switching time with the power consumption state preset.Here, power consumption state is the time arranged for the object reducing power consumption switching time.Do not having identifiable design to input, and when power consumption state arrives switching time, electronic equipment is switched to the second power consumption state from the first power consumption state, and the unit interval power consumption consumption of the first power consumption state is greater than the unit interval power consumption consumption of the second power consumption state.Here, identifiable design input comprises the input that voice or other input medias (as touch-screen, keyboard or various sensor) produce.When the above-mentioned schedule time is identical with the power consumption state switching time preset, can makes electronic equipment after the schedule time, enter the second power consumption state of low-power consumption.The reason that second power consumption state is low in energy consumption in the present embodiment comprises: voice collecting stops and/or speech recognition stops.Further, if when electronic equipment also comprises display unit and touch detection unit, said units can be closed in the lump to save power consumption, such as, will the display screen of electronic equipment be extinguished, thus display screen is switched to OFF state by illuminating state.
In above-mentioned steps 15, the present embodiment when gathering voice signal, electronic equipment display screen can also show a Status icons, in order to indicate voice detection function to work, with the state facilitating user to know current voice detection function.Certainly, the present embodiment can also provide of the prior art by physical button or started by touch sensing unit or close the implementation of voice detection function, independently can realize phonetic entry at any time to make user.
Based on above-described method of speech processing, the present embodiment additionally provides a kind of voice processing apparatus, is applied to an electronic equipment, and described electronic equipment at least has the first state and the second state.As shown in Figure 2, this voice processing apparatus comprises:
First detecting unit, for when described electronic equipment is in the first state, detects the first event;
First judging unit, for judging described first event whether first predetermined condition;
Switch unit, for when described first event meets described first predetermined condition, switches to the second state by described electronic equipment from described first state;
Second judging unit, for judging described second state whether second predetermined condition;
Collecting unit, for when described second state meets described second predetermined condition, gathers voice signal;
Resolution unit, for resolving described voice signal.
Preferably, this device can also comprise with lower unit, obtains corresponding order to resolve according to voice signal and performs:
First obtains unit, for obtaining the analysis result of described voice signal;
Second obtains unit, for obtaining corresponding 3rd order according to described analysis result;
Performance element, for performing described 3rd order.
Preferably, when analysis result cannot then stop voice signal input with any order to the present embodiment time corresponding, now this voice processing apparatus also comprises:
3rd obtains unit, for obtaining the analysis result of described voice signal;
First control module, for ordering and gather voice signal to stopping time corresponding or stop resolving voice signal with the 3rd when described analysis result.
Preferably, can also gather voice signal within a period of time of timer setting in the present embodiment, now, described collecting unit is further used for gathering voice signal in the given time; The voice signal that described resolution unit is further used for collecting in the described schedule time is resolved; Described voice processing apparatus also comprises:
3rd obtains unit, for obtaining the analysis result of the voice signal collected in the described schedule time;
Second control module, for ordering and gather voice signal to stopping time corresponding or stop resolving voice signal with the 3rd when described analysis result.
As a kind of preferred implementation of the second condition adjudgement, in the voice processing apparatus described in the present embodiment, described second judging unit comprises:
First determining unit, for determining the predetermined state selected in advance;
3rd judging unit, for judging whether described second state belongs to described predetermined state;
First processing unit, for when described second state belongs to described predetermined state, judges that described second state meets described second predetermined condition;
Second determining unit, for determining the third state of the first application program, the third state of described first application program is the state needing triggering voice signals collecting;
As the another kind of preferred implementation of the second condition adjudgement, in the voice processing apparatus described in the present embodiment, described second judging unit comprises:
3rd determining unit, for determine registered in advance, for the predetermined message of triggering voice signals collecting;
4th judging unit, for judging whether receive described predetermined message in said second condition;
Second processing unit, for when receiving described predetermined message, judges that described second state meets described second predetermined condition.
The above is only embodiments of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (14)
1. a method of speech processing, is applied to an electronic equipment, and described electronic equipment at least has the first state and the second state, it is characterized in that, comprising:
When described electronic equipment is in the first state, the first event detected, the first event is the user operation that electronic equipment side detects, or the event produced by electronic equipment that electronic equipment side detects;
Judge described first event whether first predetermined condition;
When described first event meets described first predetermined condition, described electronic equipment is switched to the second state from described first state; Described first state, the second state are all a kind of duties of electronic equipment, are from the various states of electronic equipment, to select certain or some states in advance as predetermined state, and preserve the information of these predetermined states;
Judge described second state whether second predetermined condition, comprising: judge whether described second state belongs to described predetermined state; When described second state belongs to described predetermined state, judge that described second state meets described second predetermined condition; Wherein, statistics and analysis user uses the custom of electronic equipment in advance, selects the predetermined state that user can carry out voice operating usually and joins in described predetermined state;
When described second state meets described second predetermined condition, gather voice signal;
Resolve described voice signal.
2. the method for claim 1, is characterized in that, after the described voice signal of described parsing, also comprises:
Obtain the analysis result of described voice signal;
Obtain should the order of analysis result according to described analysis result;
Perform the order of described analysis result.
3. the method for claim 1, is characterized in that, after the described voice signal of described parsing, also comprises:
Obtain the analysis result of described voice signal;
When described analysis result cannot with to should the order of analysis result realize gathering voice signal to stopping time corresponding or stopping resolving voice signal.
4. the method for claim 1, is characterized in that,
Described collection voice signal comprises and gathers voice signal in the given time;
The voice signal that the described voice signal of described parsing comprises collecting in the described schedule time is resolved;
After the described voice signal of described parsing, also comprise:
Obtain the analysis result of the voice signal collected in the described schedule time;
When described analysis result cannot be ordered and gathers voice signal to stopping time corresponding or stop resolving voice signal with the 3rd.
5. the method for claim 1, is characterized in that,
Describedly judge whether second predetermined condition comprises described second state:
Determine the predetermined state selected in advance;
Judge whether described second state belongs to described predetermined state;
When described second state belongs to described predetermined state, judge that described second state meets described second predetermined condition.
6. method as claimed in claim 5, is characterized in that,
Described the first event detected before also comprise:
Determine the third state of the first application program, the third state of described first application program is the state needing triggering voice signals collecting; The third state of described first application program is the state needing triggering voice signals collecting;
The described third state is added in described predetermined state.
7. the method for claim 1, is characterized in that,
Describedly judge whether second predetermined condition comprises described second state:
Determine registered in advance, for the predetermined message of triggering voice signals collecting;
Judge whether receive described predetermined message in said second condition;
When receiving described predetermined message, judge that described second state meets described second predetermined condition.
8. a voice processing apparatus, is applied to an electronic equipment, and described electronic equipment at least has the first state and the second state, it is characterized in that, comprising:
First detecting unit, for when described electronic equipment is in the first state, detects the first event, and the first event is the user operation that electronic equipment side detects, or the event produced by electronic equipment that electronic equipment side detects;
First judging unit, for judging described first event whether first predetermined condition;
Switch unit, for when described first event meets described first predetermined condition, switches to the second state by described electronic equipment from described first state; Described first state, the second state are all a kind of duties of electronic equipment, are from the various states of electronic equipment, to select certain or some states in advance as predetermined state, and preserve the information of these predetermined states;
Second judging unit, for judging described second state whether second predetermined condition, comprising: judge whether described second state belongs to described predetermined state; When described second state belongs to described predetermined state, judge that described second state meets described second predetermined condition; Wherein, statistics and analysis user uses the custom of electronic equipment in advance, selects the predetermined state that user can carry out voice operating usually and joins in described predetermined state;
Collecting unit, for when described second state meets described second predetermined condition, gathers voice signal;
Resolution unit, for resolving described voice signal.
9. voice processing apparatus as claimed in claim 8, is characterized in that, also comprise:
First obtains unit, for obtaining the analysis result of described voice signal;
Second obtains unit, for obtaining should the order of analysis result according to described analysis result;
Performance element, for performing the order of described analysis result.
10. voice processing apparatus as claimed in claim 8, is characterized in that, also comprise:
3rd obtains unit, for obtaining the analysis result of described voice signal;
First control module, for when described analysis result cannot with to should the order of analysis result realize gathering voice signal to stopping time corresponding or stopping resolving voice signal.
11. voice processing apparatus as claimed in claim 8, is characterized in that,
Described collecting unit is further used for gathering voice signal in the given time;
The voice signal that described resolution unit is further used for collecting in the described schedule time is resolved;
Described voice processing apparatus also comprises:
3rd obtains unit, for obtaining the analysis result of the voice signal collected in the described schedule time;
Second control module, for when described analysis result cannot with to should the order of analysis result realize gathering voice signal to stopping time corresponding or stopping resolving voice signal.
12. voice processing apparatus as claimed in claim 8, it is characterized in that, described second judging unit comprises:
First determining unit, for determining the predetermined state selected in advance;
3rd judging unit, for judging whether described second state belongs to described predetermined state;
First processing unit, for when described second state belongs to described predetermined state, judges that described second state meets described second predetermined condition.
13. voice processing apparatus as claimed in claim 12, is characterized in that, also comprise:
Second determining unit, for determining the third state of the first application program, the third state of described first application program is the state needing triggering voice signals collecting; The third state of described first application program is the state needing triggering voice signals collecting;
Second processing unit, for being added into the described third state in described predetermined state.
14. voice processing apparatus as claimed in claim 8, it is characterized in that, described second judging unit comprises:
3rd determining unit, for determine registered in advance, for the predetermined message of triggering voice signals collecting;
4th judging unit, for judging whether receive described predetermined message in said second condition;
Second processing unit, for when receiving described predetermined message, judges that described second state meets described second predetermined condition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110168490.2A CN102841771B (en) | 2011-06-21 | 2011-06-21 | A kind of method of speech processing and voice processing apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110168490.2A CN102841771B (en) | 2011-06-21 | 2011-06-21 | A kind of method of speech processing and voice processing apparatus |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102841771A CN102841771A (en) | 2012-12-26 |
CN102841771B true CN102841771B (en) | 2016-04-27 |
Family
ID=47369181
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110168490.2A Active CN102841771B (en) | 2011-06-21 | 2011-06-21 | A kind of method of speech processing and voice processing apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102841771B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9620144B2 (en) * | 2013-01-04 | 2017-04-11 | Kopin Corporation | Confirmation of speech commands for control of headset computers |
CN104424024B (en) * | 2013-08-19 | 2019-06-25 | 联想(北京)有限公司 | Information processing equipment and information processing method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100502415C (en) * | 2005-04-22 | 2009-06-17 | 英华达(上海)电子有限公司 | Voice automatic processing method of foreign communication event for mobile phone |
CN100396133C (en) * | 2006-02-06 | 2008-06-18 | 海信集团有限公司 | Mobile telephone with identity recognition and self-start by listening the environment and its implementation method |
WO2008084556A1 (en) * | 2007-01-12 | 2008-07-17 | Panasonic Corporation | Method of controlling voice recognition function of portable terminal, and wireless communication system |
-
2011
- 2011-06-21 CN CN201110168490.2A patent/CN102841771B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN102841771A (en) | 2012-12-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102833421B (en) | Mobile terminal and reminding method | |
CN103019521B (en) | A kind of mobile terminal puts out screen method and device | |
CN101287036B (en) | Method and device for preventing mobile phone from being woke-up in stand-by state | |
CN111629409B (en) | Call control method and device and electronic equipment | |
CN103246445B (en) | The changing method of application program and communication terminal | |
CN102981766B (en) | A kind of terminal Activiation method and terminal | |
KR101845877B1 (en) | Method and device for waking up mcu | |
CN100388213C (en) | Application programe switch-over method and system | |
CN103095915B (en) | A kind of method that prevents maloperation and mobile phone based on touch-screen mobile phone | |
CN101483683A (en) | Handhold apparatus and voice recognition method thereof | |
CN104660777A (en) | Touch screen cellphone and function setting method for physical buttons thereof | |
CN103150050A (en) | Touch screen terminal and working method thereof | |
CN103546635A (en) | Incoming-call processing method and incoming-call processing device | |
CN101370053B (en) | Mobile terminal and method for operating mobile terminal by headphone | |
CN103873660A (en) | Electronic device with incoming call processing function and incoming call processing method | |
CN103685693A (en) | Information processing method | |
CN101303831A (en) | Method for controlling backlight of electric display apparatus | |
CN102841771B (en) | A kind of method of speech processing and voice processing apparatus | |
CN101510915A (en) | Fast switching method for mobile phone software window | |
CN103401975A (en) | Fixed-number dialing method and system | |
CN103034318A (en) | Mobile terminal and key triggering method thereof | |
CN101695083A (en) | Method for notifying user of missed call or unread short message and cellphone using same | |
CN105721696A (en) | Mobile terminal information inputting method and device, and mobile terminal | |
CN105282298A (en) | Mobile phone screen-off method and device | |
CN101754445A (en) | Mobile device and operating method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |