CN105072269A - Mobile terminal operation processing method and system based on voice recognition - Google Patents
Mobile terminal operation processing method and system based on voice recognition Download PDFInfo
- Publication number
- CN105072269A CN105072269A CN201510467241.1A CN201510467241A CN105072269A CN 105072269 A CN105072269 A CN 105072269A CN 201510467241 A CN201510467241 A CN 201510467241A CN 105072269 A CN105072269 A CN 105072269A
- Authority
- CN
- China
- Prior art keywords
- voltage
- mobile terminal
- voice
- preset group
- array
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Telephone Function (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a mobile terminal operation processing method and system based on voice recognition. The method comprises the steps of: starting a voice recognition function in a lock screen interface; when a voltage of voice input is detected to be higher than a first voltage threshold, starting voltage collection and periodically acquiring voltages at preset time intervals; storing the obtained voltages in an array according to the time sequence; if the obtained voltages are detected to be lower than a second voltage threshold, stopping obtaining voltages; carrying out voice recognition based on the array which is composed of the collected voltages; and searching for voice information which is set in advance to carry out corresponding operation for a mobile terminal and controlling the mobile terminal to carry out the corresponding operation. According to the method, a user can receive a call, and power off or unlock the mobile terminal just through voice input; in addition, different from existing voice recognition technologies, the voice recognition scheme of the mobile terminal operation processing method and system based on voice recognition is simpler, operation efficiency is increased, and convenience is provided for users.
Description
Technical field
The present invention relates to technical field of mobile terminals, particularly relate to a kind of mobile terminal operation processing method based on speech recognition and system.
Background technology
Along with the development of mobile communication and improving constantly of people's living standard, the use of various mobile terminals as mobile phone is more and more universal, and mobile phone has become indispensable means of communication in people's life.
In prior art, the function of mobile phone gets more and more, unblock is one of function that mobile terminal frequency of utilization is the highest, in the prior art, it is all adopt the operation such as key-press input, touch-screen input that mobile terminal unlocks, using these modes of operation to unlock needs to carry out certain input operation by finger, but user points be inconvenient to will to cause and unlocks difficult (having sticked foul as user points) sometimes.
Therefore, prior art has yet to be improved and developed.
Summary of the invention
The technical problem to be solved in the present invention is, for the above-mentioned defect of prior art, provides a kind of mobile terminal operation processing method based on speech recognition and system.Provide a kind of mobile terminal operation processing method based on speech recognition of fast and reliable, by method of the present invention, namely user only can need to be answered the call operation, power-off operation or unlocking mobile terminal by phonetic entry; In addition, different and existing speech recognition technology, the present invention is more simple for the identifying schemes of voice, improves operating efficiency, provides users with the convenient.
The technical scheme that technical solution problem of the present invention adopts is as follows:
Based on a mobile terminal operation processing method for speech recognition, wherein, comprising:
A, gather and store the voice messaging for carrying out corresponding operating to mobile terminal in advance;
B and pre-set one and start for starting the first voltage threshold VTH1 obtaining voice voltage signals, and if be arranged on start to obtain voltage after detect that voltage is lower than the second thresholding VTH2, stop obtaining voltage;
C, under locking screen interface, start speech identifying function; When the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with array voice [] coming;
If D, detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; And carry out speech recognition according to the array voice [] that the voltage collected is formed; According to the voice identified, search voice messaging mobile terminal being carried out to corresponding operating pre-set, control mobile terminal and perform corresponding operating.
The described mobile terminal operation processing method based on speech recognition, wherein, the corresponding operating in described steps A comprises: answer the call operation, power-off operation, unlocking operation.
The described mobile terminal operation processing method based on speech recognition, wherein, described steps A specifically comprises:
A1, when the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with preset group voice1 [] coming;
If A2, detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage;
In A3, the preset group voice1 [] that is made up of the voltage collected, ask poor by between adjacent voltage, adopt latter one to deduct and previously obtain a new preset group diff1 [];
A4, arrange new preset group diff1 [] and the instruction one_to_one corresponding carrying out corresponding operating for controlling mobile terminal;
Wherein, described preset group comprises: first preset group corresponding with operational order of answering the call, second preset group corresponding with power-off operation instruction, three preset group corresponding with unlocking operation instruction.
The described mobile terminal operation processing method based on speech recognition, wherein, the first voltage threshold VTH1 in described step B is greater than the second voltage threshold VTH2, and wherein the first voltage threshold VTH1 is 0.8mV, and the second voltage threshold VTH2 is 0.5mV;
In described step C every one predetermined period of time obtain voltage be per interval (1/6000) second cycle obtain voltage.
The described mobile terminal operation processing method based on speech recognition, wherein, recognition methods in described step D specifically comprises: ask poor to adjacent two voltages collected, therefore for collected array voice [], identify by following flow process:
In D1, the array voice [] that is made up of the voltage collected, ask poor by between adjacent voltage, adopt latter one to deduct and previously obtain a new array diff [];
D2, new array diff [] is inputted with the operating mobile terminal instruction preset the array that voice form one to one compare successively, if all identical, perform corresponding operation, otherwise operation failure.
The described mobile terminal operation processing method based on speech recognition, wherein, described step D2 also comprises:
The first preset group that D21, the input voice that operate of new array diff [] and the correct unblock preset being answered the call are formed compares, if all identical, unlocks and the operation that receives calls, otherwise operation failure of answering the call;
D22, new array diff [] to be compared successively with the second preset group that the input voice of correct power-off operation preset are formed, if all identical, carry out power-off operation, otherwise power-off operation failure;
D22, new array diff [] to be compared with the 3rd preset group that the input voice of correct unblock preset are formed, if all identical, unlock successfully, otherwise unlock unsuccessfully.
Based on a mobile terminal operational processes system for speech recognition, wherein, comprising:
Gather memory module in advance, for gathering in advance and storing the voice messaging for carrying out corresponding operating to mobile terminal;
Pre-set module, for and pre-set one and start for starting the first voltage threshold VTH1 obtaining voice voltage signals, and if be arranged on start to obtain voltage after detect that voltage is lower than the second thresholding VTH2, stop obtaining voltage;
Voltage acquisition module, for starting speech identifying function under locking screen interface; When the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with array voice [] coming;
Speech recognition and operation control module, if for detecting that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; And carry out speech recognition according to the array voice [] that the voltage collected is formed; And according to the voice identified, search voice messaging mobile terminal being carried out to corresponding operating pre-set, control mobile terminal and perform corresponding operating.
The described mobile terminal operational processes system based on speech recognition, wherein, the described memory module that gathers in advance comprises:
First acquiring unit, for when the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, starts to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with preset group voice1 [] coming;
Second acquisition unit, if for detecting that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stops obtaining voltage;
Computing unit, in the preset group voice1 [] that is made up of the voltage collected, asks poor by between adjacent voltage, adopts latter one to deduct and previously obtain a new preset group diff1 [];
Setting unit, for arranging new preset group diff1 [] and the instruction one_to_one corresponding carrying out corresponding operating for controlling mobile terminal;
Wherein, described corresponding operating comprises: answer the call operation, power-off operation, unlocking operation; Described preset group comprises: first preset group corresponding with operational order of answering the call, second preset group corresponding with power-off operation instruction, three preset group corresponding with unlocking operation instruction;
Described first voltage threshold VTH1 is greater than the second voltage threshold VTH2, and wherein the first voltage threshold VTH1 is 0.8mV, and the second voltage threshold VTH2 is 0.5mV;
Described every one predetermined period of time obtain voltage be per interval (1/6000) second cycle obtain voltage.
The described mobile terminal operation processing method based on speech recognition, wherein, described sound identification module comprises:
Array asks poor unit, in the array voice [] that is made up of the voltage collected, asks poor by between adjacent voltage, adopts latter one to deduct and previously obtain a new array diff [];
Operation control unit, compares successively for new array diff [] is inputted with the operating mobile terminal instruction preset the array that voice form one to one, if all identical, performs corresponding operation, otherwise operation failure.
The described mobile terminal operational processes system based on speech recognition, wherein, described operation control unit comprises:
The first preset group that first operation controls subelement, the input voice that operate for new array diff [] and default correct unblock being answered the call are formed compares, if all identical, unlocks and the operation that receives calls, otherwise operation failure of answering the call;
Second operation controlling subelement, for being compared successively with the second preset group that the input voice of the correct power-off operation preset are formed by new array diff [], if all identical, carrying out power-off operation, otherwise power-off operation failure;
3rd operation controls subelement, for being compared with the 3rd preset group that the input voice of the correct unblock preset are formed by new array diff [], if all identical, unlocking successfully, otherwise unlocking unsuccessfully.
Mobile terminal operation processing method based on speech recognition provided by the present invention and system, compared with the voice prestored owing to have employed the voice inputted by user, if identical, trigger corresponding function; Put as user preset answer the call, the speech recognition array of shut down, unlock three functions that can trigger and correspondence thereof, trigger when the array detecting that the voice signal that user inputs is changed is identical with above function and perform corresponding function, by method of the present invention, namely user only can need to be answered the call operation, power-off operation or unlocking mobile terminal by phonetic entry; In addition, different and existing speech recognition technology, the present invention is more simple for the identifying schemes of voice, improves operating efficiency, provides users with the convenient.
Accompanying drawing explanation
Fig. 1 is the flow chart of the preferred embodiment of the mobile terminal operation processing method that the present invention is based on speech recognition.
Fig. 2 pre-sets in the inventive method embodiment to trigger the corresponding flow chart of execution one operation.
Fig. 3 is that the speech recognition of the inventive method embodiment controls details flow chart with operation.
Fig. 4 is the flow chart of the preferred embodiment of the mobile terminal operation processing method that the present invention is based on speech recognition.
Embodiment
For making object of the present invention, technical scheme and advantage clearly, clearly, developing simultaneously referring to accompanying drawing, the present invention is described in more detail for embodiment.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
Refer to Fig. 1, Fig. 1 is the flow chart of the preferred embodiment of the mobile terminal operation processing method that the present invention is based on speech recognition.A kind of mobile terminal operation processing method based on speech recognition shown in Fig. 1, comprises the following steps:
Step S100, gather and store the voice messaging for carrying out corresponding operating to mobile terminal in advance.
Corresponding operating described in the present invention comprises: answer the call operation, power-off operation, unlocking operation.
The present invention in the specific implementation, gather in advance and store the voice messaging for answer the call to mobile terminal operation, power-off operation, unlocking operation, such as, voice messaging " unblock " voice of unlocking operation, the voice messaging of operation of answering the call " receives calls " voice messaging " shutdown " voice of voice, power-off operation.
When default voice messaging, specifically comprise:
Such as, when presetting voice messaging " unblock " voice of unlocking operation, when the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with preset group voice1 [] coming; If detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; In the preset group voice1 [] be made up of the voltage collected, ask poor by between adjacent voltage, adopt latter one to deduct and previously obtain a new preset group diff1 []; Arrange new preset group diff1 [] and the instruction one_to_one corresponding carrying out corresponding operating for controlling mobile terminal; Wherein, described preset group comprises: first preset group corresponding with operational order of answering the call, second preset group corresponding with power-off operation instruction, three preset group corresponding with unlocking operation instruction.
Step S200 and pre-set one and start for starting the first voltage threshold VTH1 obtaining voice voltage signals, and if be arranged on start to obtain voltage after detect that voltage is lower than the second thresholding VTH2, stop obtaining voltage.
Wherein, described first voltage threshold VTH1 is greater than the second voltage threshold VTH2, and preferably, described first voltage threshold VTH1 is 0.8mV, and the second voltage threshold VTH2 is 0.5mV.
Step S300, under locking screen interface, start speech identifying function; When the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with array voice [] coming.
Such as every one predetermined period of time obtain voltage be per interval (1/6000) second cycle obtain voltage.
If step S400, detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; And carry out speech recognition according to the array voice [] that the voltage collected is formed; According to the voice identified, search voice messaging mobile terminal being carried out to corresponding operating pre-set, control mobile terminal and perform corresponding operating.
In the specific implementation: adjacent two voltages collected are asked poor, therefore for collected array voice [], identifies by following flow process:
In D1, the array voice [] that is made up of the voltage collected, ask poor by between adjacent voltage, adopt latter one to deduct and previously obtain a new array diff [];
D2, new array diff [] is inputted with the operating mobile terminal instruction preset the array that voice form one to one compare successively, if all identical, perform corresponding operation, otherwise operation failure.
The described mobile terminal operation processing method based on speech recognition, wherein, described step D2 also comprises:
The first preset group that D21, the input voice that operate of new array diff [] and the correct unblock preset being answered the call are formed compares, if all identical, unlocks and the operation that receives calls, otherwise operation failure of answering the call;
D22, new array diff [] to be compared successively with the second preset group that the input voice of correct power-off operation preset are formed, if all identical, carry out power-off operation, otherwise power-off operation failure;
D22, new array diff [] to be compared with the 3rd preset group that the input voice of correct unblock preset are formed, if all identical, unlock successfully, otherwise unlock unsuccessfully.
Such as, when receiving user speech information for " unblock " voice, controlling mobile terminal and performing unlocking operation; Perform for " receiving calls " voice then control mobile terminal operation of answering the call when receiving user speech information; When the voice messaging receiving user is " shutdown " voice, then control mobile terminal and perform power-off operation.
In order to be described in further details the present invention, reoffer an embodiment herein, the voice that the device of this embodiment can be inputted by user are compared with the voice prestored, if identical, trigger corresponding function; Put as user preset answer the call, the speech recognition array of shut down, unlock three functions that can trigger and correspondence thereof, trigger when the array detecting that the voice signal that user inputs is changed is identical with above function and perform corresponding function.
Said method comprising the steps of:
In this embody rule embodiment user sound by microphone the voltage signal changed out; Then array in chronological sequence formed for the voltage got is carried out data processing; Particularly, if in chronological sequence the formed array of the voltage that gets of voltage acquisition module is that voice [], voice [0] represent the voltage adopted at first, the less expression acquisition time of small tenon more early; The process that data processing module is done will poor (latter one deducts previous) be asked between adjacent voltage to obtain a new array diff [] by this array, i.e. diff [i]=voice [i+1]-voice [i], i be 0,1,2,3,
Consider that the frequency range of people's sounding is at 300Hz ~ 3000Hz, according to nyquist sampling law sample frequency for namely the twice (being 6000Hz) being sampled signal frequency (herein for 3000Hz) maximum can reduce according to the discrete signal sampled the signal be sampled herein, therefore the time-out time of this timer is (1/6000) second.
Also arrange in this specific embodiment: the first voltage threshold VTH1 being set, namely only having when detecting that the voltage of phonetic entry obtains voltage higher than just starting during VTH1; If detect that after starting to obtain voltage voltage is lower than the second voltage threshold VTH2, stop obtaining voltage; Wherein, VTH1 is greater than VTH2, and preferably, VTH1 is 0.8mV, VTH2 is 0.5mV.
As shown in Figure 2, pre-set the array triggering input voice corresponding to execution one operation and form, comprise following flow process:
S1, prompting user input voice; The threshold voltage arranging interrupt module is VTH1, and only has when detecting that voltage performs S2 higher than during VTH1;
S2, the threshold voltage arranging interrupt module are VTH2, and only have when detecting that voltage performs S5 lower than during VTH2; Start timer, variable k is set to 0;
S3, judge that whether timer is overtime, if time-out, perform S4, otherwise continue wait timeout;
S4, voltage acquisition module obtain voltage and are saved in array voice [k]; K=k+1 afterwards; Perform S3 afterwards;
If S5, detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage, stop timer, by data processing module, array voice [] is processed; Specifically be treated to and will between adjacent voltage, ask poor (latter one deducts previous) to obtain a new array diff [] by this array, be i.e. diff [i]=voice [i+1]-voice [i], i be 0,1,2,3,
S6, preservation array diff [].
As shown in Figure 3, for the speech recognition based on above embodiment controls details flow process with operation, comprise the following steps:
S101, under locking screen interface, the threshold voltage arranging interrupt module is VTH1, and only has when detecting that voltage performs S102 higher than during VTH1;
S102, the threshold voltage arranging interrupt module are VTH2, and only have when detecting that voltage performs S105 lower than during VTH2; Start timer, variable k is set to 0;
S103, judge that whether timer is overtime, if time-out, perform S104, otherwise continue wait timeout;
S104, voltage acquisition module obtain voltage and are saved in voice [k]; K=k+1 afterwards; Perform S103 afterwards;
S105, stopping timer, processed array voice [] by data processing module; Specifically be treated to and will between adjacent voltage, ask poor (latter one deducts previous) to obtain a new array diff [] by this array, be i.e. diff [i]=voice [i+1]-voice [i], i be 0,1,2,3,
S106, to be compared this array diff [] by comparison module and whether pre-set the array arranged in module consistent, if consistent, trigger to perform pre-seting operation corresponding in module; If inconsistent, perform S102.
Therefore the invention provides a kind of mobile terminal operation processing method based on speech recognition of fast and reliable, by method of the present invention, namely user only can need to be answered the call operation, power-off operation or unlocking mobile terminal by phonetic entry; In addition, different and existing speech recognition technology, the present invention is more simple for the identifying schemes of voice, improves operating efficiency, provides users with the convenient.
Based on said method embodiment, present invention also offers a kind of mobile terminal operational processes system based on speech recognition, as shown in Figure 4, comprising:
Gather memory module 410 in advance, for gathering in advance and storing the voice messaging for carrying out corresponding operating to mobile terminal; As detailed above.
Pre-set module 420, for and pre-set one and start for starting the first voltage threshold VTH1 obtaining voice voltage signals, and if be arranged on start to obtain voltage after detect that voltage is lower than the second thresholding VTH2, stop obtaining voltage; As detailed above.
Voltage acquisition module 430, for starting speech identifying function under locking screen interface; When the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with array voice [] coming; As detailed above.
Speech recognition and operation control module 440, if for detecting that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; And carry out speech recognition according to the array voice [] that the voltage collected is formed; And according to the voice identified, search voice messaging mobile terminal being carried out to corresponding operating pre-set, control mobile terminal and perform corresponding operating; As detailed above.
Further, the described mobile terminal operational processes system based on speech recognition, wherein, the described memory module that gathers in advance comprises:
First acquiring unit, for when the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, starts to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with preset group voice1 [] coming; As detailed above.
Second acquisition unit, if for detecting that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stops obtaining voltage; As detailed above.
Computing unit, in the preset group voice1 [] that is made up of the voltage collected, asks poor by between adjacent voltage, adopts latter one to deduct and previously obtain a new preset group diff1 []; As detailed above.
Setting unit, for arranging new preset group diff1 [] and the instruction one_to_one corresponding carrying out corresponding operating for controlling mobile terminal; As detailed above.
Wherein, described corresponding operating comprises: answer the call operation, power-off operation, unlocking operation; Described preset group comprises: first preset group corresponding with operational order of answering the call, second preset group corresponding with power-off operation instruction, three preset group corresponding with unlocking operation instruction; As detailed above.
Described first voltage threshold VTH1 is greater than the second voltage threshold VTH2, and wherein the first voltage threshold VTH1 is 0.8mV, and the second voltage threshold VTH2 is 0.5mV;
Described every one predetermined period of time obtain voltage be per interval (1/6000) second cycle obtain voltage.
Further, the described mobile terminal operational processes system based on speech recognition, wherein, described sound identification module comprises:
Array asks poor unit, in the array voice [] that is made up of the voltage collected, asks poor by between adjacent voltage, adopts latter one to deduct and previously obtain a new array diff []; As detailed above.
Operation control unit, compares successively for new array diff [] is inputted with the operating mobile terminal instruction preset the array that voice form one to one, if all identical, performs corresponding operation, otherwise operation failure; As detailed above.
Further, the described mobile terminal operational processes system based on speech recognition, wherein, described operation control unit comprises:
The first preset group that first operation controls subelement, the input voice that operate for new array diff [] and default correct unblock being answered the call are formed compares, if all identical, unlocks and the operation that receives calls, otherwise operation failure of answering the call; As detailed above.
Second operation controlling subelement, for being compared successively with the second preset group that the input voice of the correct power-off operation preset are formed by new array diff [], if all identical, carrying out power-off operation, otherwise power-off operation failure; As detailed above.
3rd operation controls subelement, for being compared with the 3rd preset group that the input voice of the correct unblock preset are formed by new array diff [], if all identical, unlocking successfully, otherwise unlocking unsuccessfully; As detailed above.
In sum, the mobile terminal operation processing method based on speech recognition provided by the present invention and system, compared with the voice prestored owing to have employed the voice inputted by user, if identical, trigger corresponding function; Put as user preset answer the call, the speech recognition array of shut down, unlock three functions that can trigger and correspondence thereof, trigger when the array detecting that the voice signal that user inputs is changed is identical with above function and perform corresponding function, by method of the present invention, namely user only can need to be answered the call operation, power-off operation or unlocking mobile terminal by phonetic entry; In addition, different and existing speech recognition technology, the present invention is more simple for the identifying schemes of voice, improves operating efficiency, provides users with the convenient.
Should be understood that, application of the present invention is not limited to above-mentioned citing, for those of ordinary skills, can be improved according to the above description or convert, and all these improve and convert the protection range that all should belong to claims of the present invention.
Claims (10)
1., based on a mobile terminal operation processing method for speech recognition, it is characterized in that, comprising:
A, gather and store the voice messaging for carrying out corresponding operating to mobile terminal in advance;
B and pre-set one and start for starting the first voltage threshold VTH1 obtaining voice voltage signals, and if be arranged on start to obtain voltage after detect that voltage is lower than the second thresholding VTH2, stop obtaining voltage;
C, under locking screen interface, start speech identifying function; When the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with array voice [] coming;
If D, detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; And carry out speech recognition according to the array voice [] that the voltage collected is formed; According to the voice identified, search voice messaging mobile terminal being carried out to corresponding operating pre-set, control mobile terminal and perform corresponding operating.
2. the mobile terminal operation processing method based on speech recognition according to claim 1, it is characterized in that, the corresponding operating in described steps A comprises: answer the call operation, power-off operation, unlocking operation.
3. the mobile terminal operation processing method based on speech recognition according to claim 1, it is characterized in that, described steps A specifically comprises:
A1, when the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with preset group voice1 [] coming;
If A2, detect that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage;
In A3, the preset group voice1 [] that is made up of the voltage collected, ask poor by between adjacent voltage, adopt latter one to deduct and previously obtain a new preset group diff1 [];
A4, arrange new preset group diff1 [] and the instruction one_to_one corresponding carrying out corresponding operating for controlling mobile terminal;
Wherein, described preset group comprises: first preset group corresponding with operational order of answering the call, second preset group corresponding with power-off operation instruction, three preset group corresponding with unlocking operation instruction.
4. the mobile terminal operation processing method based on speech recognition according to claim 1, it is characterized in that, the first voltage threshold VTH1 in described step B is greater than the second voltage threshold VTH2, and wherein the first voltage threshold VTH1 is 0.8mV, and the second voltage threshold VTH2 is 0.5mV;
In described step C every one predetermined period of time obtain voltage be per interval (1/6000) second cycle obtain voltage.
5. the mobile terminal operation processing method based on speech recognition according to claim 1, it is characterized in that, recognition methods in described step D specifically comprises: ask poor to adjacent two voltages collected, therefore for collected array voice [], identify by following flow process:
In D1, the array voice [] that is made up of the voltage collected, ask poor by between adjacent voltage, adopt latter one to deduct and previously obtain a new array diff [];
D2, new array diff [] is inputted with the operating mobile terminal instruction preset the array that voice form one to one compare successively, if all identical, perform corresponding operation, otherwise operation failure.
6. the mobile terminal operation processing method based on speech recognition according to claim 1, it is characterized in that, described step D2 also comprises:
The first preset group that D21, the input voice that operate of new array diff [] and the correct unblock preset being answered the call are formed compares, if all identical, unlocks and the operation that receives calls, otherwise operation failure of answering the call;
D22, new array diff [] to be compared successively with the second preset group that the input voice of correct power-off operation preset are formed, if all identical, carry out power-off operation, otherwise power-off operation failure;
D22, new array diff [] to be compared with the 3rd preset group that the input voice of correct unblock preset are formed, if all identical, unlock successfully, otherwise unlock unsuccessfully.
7., based on a mobile terminal operational processes system for speech recognition, it is characterized in that, comprising:
Gather memory module in advance, for gathering in advance and storing the voice messaging for carrying out corresponding operating to mobile terminal;
Pre-set module, for and pre-set one and start for starting the first voltage threshold VTH1 obtaining voice voltage signals, and if be arranged on start to obtain voltage after detect that voltage is lower than the second thresholding VTH2, stop obtaining voltage;
Voltage acquisition module, for starting speech identifying function under locking screen interface; When the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, start to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with array voice [] coming;
Speech recognition and operation control module, if for detecting that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stop obtaining voltage; And carry out speech recognition according to the array voice [] that the voltage collected is formed; And according to the voice identified, search voice messaging mobile terminal being carried out to corresponding operating pre-set, control mobile terminal and perform corresponding operating.
8. according to claim 7 based on the mobile terminal operational processes system of speech recognition, it is characterized in that, the described memory module that gathers in advance comprises:
First acquiring unit, for when the voltage of phonetic entry being detected higher than the first voltage threshold VTH1, starts to gather voltage, to obtain voltage every a predetermined period of time; And these voltages obtained in chronological sequence sequentially are preserved; The voltage sampled is preserved with preset group voice1 [] coming;
Second acquisition unit, if for detecting that after starting to obtain voltage the voltage of acquisition is lower than the second voltage threshold VTH2, stops obtaining voltage;
Computing unit, in the preset group voice1 [] that is made up of the voltage collected, asks poor by between adjacent voltage, adopts latter one to deduct and previously obtain a new preset group diff1 [];
Setting unit, for arranging new preset group diff1 [] and the instruction one_to_one corresponding carrying out corresponding operating for controlling mobile terminal;
Wherein, described corresponding operating comprises: answer the call operation, power-off operation, unlocking operation; Described preset group comprises: first preset group corresponding with operational order of answering the call, second preset group corresponding with power-off operation instruction, three preset group corresponding with unlocking operation instruction;
Described first voltage threshold VTH1 is greater than the second voltage threshold VTH2, and wherein the first voltage threshold VTH1 is 0.8mV, and the second voltage threshold VTH2 is 0.5mV;
Described every one predetermined period of time obtain voltage be per interval (1/6000) second cycle obtain voltage.
9., according to claim 7 based on the mobile terminal operational processes system of speech recognition, it is characterized in that, described sound identification module comprises:
Array asks poor unit, in the array voice [] that is made up of the voltage collected, asks poor by between adjacent voltage, adopts latter one to deduct and previously obtain a new array diff [];
Operation control unit, compares successively for new array diff [] is inputted with the operating mobile terminal instruction preset the array that voice form one to one, if all identical, performs corresponding operation, otherwise operation failure.
10., according to claim 7 based on the mobile terminal operational processes system of speech recognition, it is characterized in that, described operation control unit comprises:
The first preset group that first operation controls subelement, the input voice that operate for new array diff [] and default correct unblock being answered the call are formed compares, if all identical, unlocks and the operation that receives calls, otherwise operation failure of answering the call;
Second operation controlling subelement, for being compared successively with the second preset group that the input voice of the correct power-off operation preset are formed by new array diff [], if all identical, carrying out power-off operation, otherwise power-off operation failure;
3rd operation controls subelement, for being compared with the 3rd preset group that the input voice of the correct unblock preset are formed by new array diff [], if all identical, unlocking successfully, otherwise unlocking unsuccessfully.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510467241.1A CN105072269B (en) | 2015-08-03 | 2015-08-03 | A kind of mobile terminal operation processing method and system based on speech recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510467241.1A CN105072269B (en) | 2015-08-03 | 2015-08-03 | A kind of mobile terminal operation processing method and system based on speech recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105072269A true CN105072269A (en) | 2015-11-18 |
| CN105072269B CN105072269B (en) | 2018-04-10 |
Family
ID=54501544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510467241.1A Active CN105072269B (en) | 2015-08-03 | 2015-08-03 | A kind of mobile terminal operation processing method and system based on speech recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105072269B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050182631A1 (en) * | 2004-02-13 | 2005-08-18 | In-Seok Lee | Voice message recording and playing method using voice recognition |
| JP2009094813A (en) * | 2007-10-09 | 2009-04-30 | Digital Technologies Corp | Telephone call recording device |
| CN103636183A (en) * | 2012-11-20 | 2014-03-12 | 华为终端有限公司 | Method and mobile device of voice response |
| CN104144102A (en) * | 2013-05-13 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method for activating voice intercom function of instant messaging application software and mobile terminal |
| CN104219388A (en) * | 2014-08-28 | 2014-12-17 | 小米科技有限责任公司 | Voice control method and device |
| US8990079B1 (en) * | 2013-12-15 | 2015-03-24 | Zanavox | Automatic calibration of command-detection thresholds |
-
2015
- 2015-08-03 CN CN201510467241.1A patent/CN105072269B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050182631A1 (en) * | 2004-02-13 | 2005-08-18 | In-Seok Lee | Voice message recording and playing method using voice recognition |
| JP2009094813A (en) * | 2007-10-09 | 2009-04-30 | Digital Technologies Corp | Telephone call recording device |
| CN103636183A (en) * | 2012-11-20 | 2014-03-12 | 华为终端有限公司 | Method and mobile device of voice response |
| CN104144102A (en) * | 2013-05-13 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method for activating voice intercom function of instant messaging application software and mobile terminal |
| US8990079B1 (en) * | 2013-12-15 | 2015-03-24 | Zanavox | Automatic calibration of command-detection thresholds |
| CN104219388A (en) * | 2014-08-28 | 2014-12-17 | 小米科技有限责任公司 | Voice control method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105072269B (en) | 2018-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105425941B (en) | A kind of method and device preventing application program in error starting mobile terminal | |
| US7483692B2 (en) | System and method of predicting user input to a mobile terminal | |
| CN104991721B (en) | A kind of fingerprint operating method and device | |
| CN104850222B (en) | A kind of instruction identification method and electric terminal | |
| CN109313903A (en) | Voice user interface | |
| EP2849041A1 (en) | Wakeup method and system for touch terminal and touch terminal | |
| CN105100461B (en) | Mobile terminal and method for realizing automatic answering | |
| WO2016070533A1 (en) | Method, system for processing fingerprint input information and mobile terminal | |
| CN108665889B (en) | Voice signal endpoint detection method, device, equipment and storage medium | |
| CN102135800A (en) | Electronic equipment and function control method thereof | |
| CN105159734A (en) | Fast application starting method and device | |
| CN110825446A (en) | Parameter configuration method and device, storage medium and electronic equipment | |
| CN107491286A (en) | Pronunciation inputting method, device, mobile terminal and the storage medium of mobile terminal | |
| CN104883444B (en) | One kind call quick application process, system and mobile terminal | |
| US8311577B2 (en) | Proactive control of mobile communications devices | |
| CN104298911A (en) | Fingerprint identification and authentication circuit of mobile terminal | |
| CN105069404A (en) | Method and system for processing fingerprint information | |
| CN103365400A (en) | Method and device for feedback of gesture recognizing operations | |
| CN106027739A (en) | Incoming call processing method and device, and terminal | |
| CN107621921B (en) | Application program starting method and mobile device | |
| CN105657161A (en) | Incoming call processing method and device | |
| CN106570373A (en) | Startup and shutdown method of terminal equipment and terminal equipment | |
| CN105577934A (en) | Call processing method and system | |
| CN108986809B (en) | Portable equipment and awakening method and device thereof | |
| CN112434268A (en) | Shared electronic equipment management method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |