CN103871409A - Voice identifying method, information processing method and electronic equipment - Google Patents

Voice identifying method, information processing method and electronic equipment Download PDF

Info

Publication number
CN103871409A
CN103871409A CN201210548625.2A CN201210548625A CN103871409A CN 103871409 A CN103871409 A CN 103871409A CN 201210548625 A CN201210548625 A CN 201210548625A CN 103871409 A CN103871409 A CN 103871409A
Authority
CN
China
Prior art keywords
use pattern
identification module
electronic equipment
sound identification
voice messaging
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
Application number
CN201210548625.2A
Other languages
Chinese (zh)
Other versions
CN103871409B (en
Inventor
戴海生
王天树
王茜莺
李向阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lenovo Beijing Ltd
Original Assignee
Lenovo Beijing Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lenovo Beijing Ltd filed Critical Lenovo Beijing Ltd
Priority to CN201210548625.2A priority Critical patent/CN103871409B/en
Priority to US14/079,219 priority patent/US9959865B2/en
Publication of CN103871409A publication Critical patent/CN103871409A/en
Application granted granted Critical
Publication of CN103871409B publication Critical patent/CN103871409B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Telephone Function (AREA)

Abstract

The invention discloses a voice identifying method, an information processing method and electronic equipment. The voice identifying method is applied to the electronic equipment, and the electronic equipment comprises at least two different voice identifying modules. The method comprises the following steps of obtaining to-be-identified voice information; obtaining the current mode of the electronic equipment as a first use mode; according to the corresponding relationship of the use mode and the voice identifying module, determining the voice identifying module corresponding to the first use mode as a first voice identifying module of the at least two different voice identifying modules; enabling the first voice identifying module to identify the to-be-identified voice information, and obtaining an identifying result.

Description

A kind of method of speech recognition, the method for information processing and electronic equipment
Technical field
The present invention relates to multimedia technology field, particularly a kind of method of method of speech recognition, information processing and electronic equipment.
Background technology
Along with the development of electronic equipment, its corresponding control mode is also more and more, such as: voice control, mouse control, touch screen control etc.Wherein, voice control mode, due to easy to operate and rapid, has been subject to increasing user's welcome.
In prior art; electronic equipment can comprise a speech recognition engine conventionally; wherein; described speech recognition engine has comprised the various speech recognition modelings that the voice messaging of user's input is identified; by described speech recognition engine, the voice messaging of user's input is identified, just can be obtained corresponding phonetic order or other voice messaging.
In the prior art, conventionally have following two kinds of speech recognition engines:
The first, hardware based speech recognition engine, this identification engine does not need system works can identify voice messaging, but owing to being confined to hardware technology, so its dictionary is limited, the voice messaging that can identify is less;
The second, based on the speech recognition engine of software, in this identification engine dictionary, word amount is abundant, can identify a large amount of voice messagings, but need to first start the system of electronic equipment, can identify.
Present inventor is realizing in the process of the embodiment of the present application technical scheme, at least finds to exist in prior art following technical matters:
Due in the prior art, if adopt the first scheme to carry out speech recognition, because dictionary is limited, so identification is not accurate enough; And if employing first scheme is identified, owing to need to starting the system of electronic equipment, so energy consumption is higher, thereby in prior art, exist the technical matters that can not reduce energy consumption in guaranteeing recognition accuracy.
Summary of the invention
The embodiment of the present invention provides a kind of method and electronic equipment of speech recognition, the technique effect that can not reduce energy consumption in guaranteeing recognition accuracy existing for solving prior art.
On the one hand, the application provides following technical scheme by an embodiment:
A kind of audio recognition method, is applied in an electronic equipment, includes at least two different sound identification modules in described electronic equipment, and described method comprises:
Obtain the first voice messaging to be identified;
The present mode that obtains described electronic equipment is the first use pattern;
Based on corresponding relation between use pattern and sound identification module, determine the sound identification module corresponding from described the first use pattern be described in the first sound identification module at least two different sound identification modules;
By described the first sound identification module, described voice messaging to be identified is identified, obtained a recognition result.
Optionally, before the present mode of the described electronic equipment of described acquisition is the first use pattern, described method also comprises:
When described electronic equipment is during in the second use pattern, detect and obtain the second voice messaging to be identified;
By the second sound identification module in described at least two different sound identification modules corresponding from described the second use pattern, described the second voice messaging to be identified is identified, to determine whether the existing described electronic equipment of control to enter the first steering order of described the first use pattern;
In the time there is described the first steering order, control described electronic equipment and enter described the first use pattern.
Optionally, after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, described method also comprises:
In the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
Optionally, described record described electronic equipment switch to from described the second use pattern described first use the first voice messaging that user inputs when pattern after, described method also comprises:
Described the first voice messaging is stored in to the internal memory of described electronic equipment.
Optionally, described acquisition first voice messaging to be identified, specifically comprises:
From described internal memory, read described the first voice messaging;
Obtaining in described the first voice messaging is still the first sub-voice messaging that is carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
Optionally, after the described electronic equipment of described control enters described the first use pattern, described method also comprises:
Judge whether to exist second steering order of opening described the first sound identification module;
After there is described the second steering order, execution step: based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module.
Optionally, after described definite sound identification module corresponding with described the first use pattern is the first sound identification module, described method also comprises:
Close described the second sound identification module.
Optionally, described the first sound identification module is: software sound identification module or hardware sound identification module; Described the second sound identification module is: hardware sound identification module;
Described the first use pattern is: the corresponding use pattern of open state; Described the second use pattern is shutdown/standby mode.
Optionally, described based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module, be specially:
In the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is software identification module;
In the time of the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determine that the sound identification module corresponding with described the first use pattern is hardware identification module.
On the other hand, the application provides following technical scheme by another embodiment:
A method for information processing, is applied in an electronic equipment, and described method comprises:
, detect and obtain the second voice messaging to be identified during in the second use pattern at described electronic equipment, wherein, described the second use pattern is described electronic equipment corresponding use pattern in the time of power down mode;
By described the second voice messaging information to be identified being identified with corresponding the second sound identification module of described the second use pattern, determine whether to exist the described electronic equipment of control to enter the first steering order of the first use pattern;
In the time there is described the first steering order, control described electronic equipment and enter described the first use pattern, wherein, described the first use pattern is described electronic equipment corresponding use pattern in the time of normal operating conditions.
Optionally, after the described electronic equipment of described control enters described the first use pattern, described method also comprises:
Determine corresponding the first sound identification module of described the first use pattern;
Obtain the first voice messaging to be identified;
Based on described the first sound identification module, described the first voice messaging to be identified is identified, to obtain at least one recognition result.
Optionally, described determine whether to exist control after described electronic equipment enters the first steering order of the first use pattern, described method also comprises:
In the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
Optionally, described in obtain the first voice messaging to be identified, be specially:
Obtaining in described the first voice messaging is still the first sub-voice messaging that was carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
On the other hand, the application provides following technical scheme by another embodiment:
A kind of electronic equipment, includes at least two different sound identification modules in described electronic equipment, described electronic equipment also comprises:
First obtains chip, for obtaining the first voice messaging to be identified;
Second obtains chip, is the first use pattern for obtaining the present mode of described electronic equipment;
First determines chip, for based on corresponding relation between use pattern and sound identification module, determine the sound identification module corresponding from described the first use pattern be described in the first sound identification module at least two different sound identification modules;
The 3rd obtains chip, for by described the first sound identification module, described voice messaging to be identified being identified, obtains a recognition result.
Optionally, described electronic equipment also comprises:
The first detection chip, before being the first use pattern at the present mode that obtains described electronic equipment, when described electronic equipment is during in the second use pattern, detect whether to exist by the second sound identification module in described at least two different sound identification modules corresponding from described the second use pattern and control described electronic equipment and enter the described first the first steering order that uses pattern;
The first control chip, in the time there is described the first steering order, controls described electronic equipment and enters described the first use pattern.
Optionally, described electronic equipment also comprises:
First records chip, for after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, in the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
Optionally, described electronic equipment also comprises:
Storage chip, for record described electronic equipment switch to from described the second use pattern described first use the first voice messaging that user inputs when pattern after, described the first voice messaging is stored in to the internal memory of described electronic equipment.
Optionally, described first obtains chip, specifically comprises:
Read sub-chip, for read described the first voice messaging from described internal memory;
Obtain sub-chip, for obtaining still the first sub-voice messaging for being carried out speech recognition by described the second sound identification module of described the first voice messaging, described the first sub-voice messaging is described the first voice messaging to be identified.
Optionally, described electronic equipment also comprises:
Judge chip: for after the described electronic equipment of control enters described the first use pattern, judge whether to exist second steering order of opening described the first sound identification module; And
After there is described the second steering order, execution step: based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module.
Optionally, described electronic equipment also comprises:
Close chip, for after definite sound identification module corresponding with described the first use pattern is the first sound identification module, close described the second sound identification module.
Optionally, described the first sound identification module is: software sound identification module or hardware sound identification module; Described the second sound identification module is: hardware sound identification module;
Described the first use pattern is: the corresponding use pattern of open state; Described the second use pattern is shutdown/standby mode.
Optionally, described first determines chip, specifically comprises:
The first true stator chip, for in the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is software identification module;
The second true stator chip, for when the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determines that the sound identification module corresponding with described the first use pattern is hardware identification module.
On the other hand, the application provides Europe following technical scheme by another embodiment:
A kind of electronic equipment, described method comprises:
A kind of electronic equipment, described electronic equipment comprises:
The second detection chip, for, detecting and obtain the second voice messaging to be identified during in the second use pattern at described electronic equipment, wherein, described the second use pattern is described electronic equipment corresponding use pattern in the time of power down mode;
Second determines chip, for by described the second voice messaging information to be identified being identified with corresponding the second sound identification module of described the second use pattern, determines whether to exist the described electronic equipment of control to enter the first steering order of the first use pattern;
The second control chip, in the time there is described the first steering order, controls described electronic equipment and enters described the first use pattern, and wherein, described the first use pattern is described electronic equipment corresponding use pattern in the time of normal operating conditions.
Optionally, described electronic equipment also comprises:
The 3rd determines chip, for after the described electronic equipment of control enters described the first use pattern, determines corresponding the first sound identification module of described the first use pattern;
Obtain chip, for obtaining the first voice messaging to be identified;
The 4th obtains chip, for based on described the first sound identification module, described the first voice messaging to be identified being identified, to obtain at least one recognition result.
Optionally, described electronic equipment also comprises:
Second records chip, for after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, in the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
Optionally, described in obtain chip, specifically for:
Obtaining in described the first voice messaging is still the first sub-voice messaging that was carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
The one or more technical schemes that provide in the embodiment of the present application, at least have following technique effect or advantage:
(1) due in the embodiment of the present application, adopt at least two different sound identification modules of electronic equipment setting, thereby the difference based on electronic equipment is used pattern, can adopt the technical scheme of different sound identification modules, so, at electronic equipment under the less use pattern of steering order, can adopt the speech recognition system that energy consumption is lower, only at electronic equipment under the more use pattern of steering order, just adopt the speech recognition system that energy consumption is higher, so solved the technical matters that can not improve recognition accuracy in prior art in reducing energy consumption, reach the technique effect that reduces energy consumption in guaranteeing recognition accuracy.
(2) due in the embodiment of the present application, when electronic equipment is in the second use pattern, such as: when shutdown/standby mode, can pass through the second sound identification module, such as: hardware identification module is identified steering order, enter described the first use pattern to control described electronic equipment, can realize speech recognition because hardware identification module does not need unlocking electronic equipment, so reached the technique effect of saving energy consumption.
(3) due in the embodiment of the present application, in the time that the described electronic equipment of control enters described the first use pattern, the first voice messaging that recording user is inputted, adopt the first speech recognition system at electronic equipment like this, such as: when software sound identification module, can call described the first voice messaging and then identification by described software sound identification module, and software sound identification module is compared to hardware sound identification module, its vocabulary is more, so reached the technique effect that improves recognition accuracy.
(4) due in the embodiment of the present application, after control electronic equipment enters described the first use pattern, first to judge whether to exist second steering order of opening the first sound identification module, in the time existing, just open described the first sound identification module, so reach the technique effect of saving energy consumption.
(5) due in the embodiment of the present application, in opening described the first sound identification module, close described the second sound identification module, so reached the technique effect of further reduction energy consumption.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the method for speech recognition in the embodiment of the present application one;
Fig. 2 controls described electronic equipment in the embodiment of the present application one method to enter the process flow diagram of the first use pattern;
Fig. 3 is the process flow diagram that judges whether to open described the first sound identification module in the embodiment of the present application one method;
Fig. 4 is the process flow diagram of the method for information processing in the embodiment of the present application four;
Fig. 5 is the processing flow chart after the first use pattern that enters in the method for the embodiment of the present application four directions;
Fig. 6 is the structural drawing of electronic equipment in the embodiment of the present application five;
Fig. 7 is the structural drawing of electronic equipment in the embodiment of the present application six.
Embodiment
The embodiment of the present invention provides a kind of method and electronic equipment of speech recognition, the technical matters that can not reduce energy consumption in guaranteeing recognition accuracy existing for solving prior art.
In the time that a voice messaging to be identified is identified, first determine the present mode of electronic equipment, such as: the use pattern, the power consumption that are greater than the first predetermined threshold value for power consumption are less than use pattern of the first predetermined threshold value etc.; Then the difference based on present mode, determine different sound identification modules, such as: in the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, determine that the sound identification module corresponding with described the first use pattern is software identification module, in this case, illustrate that electronic equipment is in normal operating conditions, its user's phonetic order is more, so adopt software identification module to identify, to improve recognition accuracy; In the time of the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determine that the sound identification module corresponding with described the first use pattern is hardware identification module, in this case, electronic equipment may be in standby mode/park mode etc., and in this case, electronic equipment only needs to carry out some and wakes instruction up, so, its corresponding vocabulary does not need too much, so adopt hardware identification module to identify it, and to save energy consumption.
Due to, while adopting such scheme to identify voice, at electronic equipment under the less use pattern of steering order, can adopt the speech recognition system that energy consumption is lower, only at electronic equipment under the more use pattern of steering order, just adopt the speech recognition system that energy consumption is higher, so, reach the technique effect in the situation decline low energy consumption of assurance recognition accuracy.
Embodiment mono-
The embodiment of the present application one provides a kind of method of speech recognition, application one electronic equipment, and described electronic equipment is for example: notebook computer, mobile phone, panel computer etc.
Described electronic equipment includes at least two different speech recognition systems, and wherein, described at least two different speech recognition systems are for example: hardware sound identification module, software sound identification module; Or, described at least two different speech recognition systems are: little vocabulary speech recognition system, major term table speech recognition system etc., be specially which kind of speech recognition system for described at least two different speech recognition systems, the embodiment of the present application is not restricted.
Please refer to Fig. 1, the method for described speech recognition comprises the steps:
Step S101: obtain the first voice messaging to be identified;
Step S102: the present mode that obtains described electronic equipment is the first use pattern;
Step S103: based on corresponding relation between use pattern and sound identification module, determine the sound identification module corresponding from described the first use pattern be described in the first sound identification module at least two different sound identification modules;
Step S104: by described the first sound identification module, described voice messaging to be identified is identified, obtained a recognition result.
In specific implementation process, obtaining based on step S101 present mode that voice messaging to be identified or step S102 obtain described electronic equipment is before the first use pattern, as Fig. 2, shown in described method also comprise the steps:
Step S201: when described electronic equipment is during in the second use pattern, detect and obtain the second voice messaging to be identified;
Step S202: by the second sound identification module in described at least two different sound identification modules corresponding from described the second use pattern, described the second voice messaging to be identified is identified, to determine whether the existing described electronic equipment of control to enter the first steering order of described the first use pattern;
Step S203: in the time there is described the first steering order, control described electronic equipment and enter described the first use pattern.
In specific implementation process, the second use pattern in step S201, be for example: shutdown mode, standby mode, in this case, described the second sound identification module is for example: hardware identification module, wherein, when described electronic equipment is during in shutdown mode or standby mode, microphone on described hardware identification module and electronic equipment is all still in running order, just can gather the voice messaging that user inputs the content that is stored in electronic equipment by described microphone.
Under normal conditions, the different phonetic identification module of electronic equipment can share microphone, that is to say no matter which kind of sound identification module electronic equipment adopts, can adopt same microphone to gather voice messaging, and the buffer memory of shared microphone, that is to say in the time that electronic equipment adopts the second sound identification module, the memory location of its voice messaging gathering and in the time that described electronic equipment adopts the first sound identification module, the memory location of its voice messaging gathering is identical.
Obtain described the second voice messaging to be identified based on step S201 after, just can be based on step S202, namely by described the second sound identification module, described the second voice messaging to be identified is identified, and then obtain some simple steering orders, such as: start-up command, wake instruction etc. up.
So, after the microphone of described electronic equipment detects voice messaging, just by described hardware identification engine, described voice messaging is identified, exist and start shooting or wake relevant voice messaging up determining whether, have relevant voice messaging, just produce a start-up command or wake instruction up, enter the first use pattern to control described electronic equipment, such as: the corresponding use pattern of open state, wherein, and such as: normally use pattern, power saving use pattern etc.
As seen from the above description, due in the embodiment of the present application, when electronic equipment is in the second use pattern, such as: when shutdown/standby mode, can pass through the second sound identification module, such as: hardware identification module is identified voice messaging, enters described the first use pattern to control described electronic equipment, because not needing unlocking electronic equipment, hardware identification module can realize speech recognition, so reached the technique effect of saving energy consumption.
After determining whether that based on step S202 the described electronic equipment of existence control enters the first steering order of the first use pattern, described method also comprises:
In the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
In specific implementation process; when user by electronic equipment described in voice messaging control after described the second use pattern switches to described the first use pattern; conventionally can wish electronic equipment execution certain operations, such as: open text editor, open music player, open web browser etc.
So user may be after by voice messaging control start, also can produce some other voice messagings, such as: " opening text editor ", " open music player ", " unlatching web browser " etc., wherein, due to described the second speech recognition system, such as: hardware sound identification module, the vocabulary comprising is less, may only comprise some and control start, the vocabulary waking up, and the vocabulary producing for above-mentioned user, can not identify, so described hardware identification module is in the time described start-up command/wake instruction up being detected, the first voice messaging of just can recording user inputting.
In specific implementation process, after obtaining described the first voice messaging, described the first voice messaging can be stored in to the internal memory of described electronic equipment, certainly, also can be stored in other position, for described which kind of reservoir that is stored in, the embodiment of the present application is not restricted.
As seen from the above description, due in the embodiment of the present application, in the time existing the described electronic equipment of control to enter the first steering order of the first use pattern, the first voice messaging that recording user is inputted, adopt the first speech recognition system at electronic equipment like this, such as: when software sound identification module, can call described the first voice messaging and then identification by described software sound identification module, and software sound identification module is compared to hardware sound identification module, its vocabulary is more, so reached the technique effect that improves recognition accuracy.
Wherein, in step S101, obtain the first voice messaging to be identified and may be divided into multiple situation, two kinds that enumerate below are wherein introduced, and certainly, in specific implementation process, are not limited to following two kinds of situations.
The first, specifically comprises the steps:
From described internal memory, read described the first voice messaging;
Obtaining in described the first voice messaging is still the first sub-voice messaging that is carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
In specific implementation process, due in the time that the described electronic equipment of control switches to the first use pattern from the second use pattern, the voice messaging of recording user, and be stored in internal memory, so can directly read described the first voice messaging in internal memory, as described voice messaging to be identified.Wherein, in the time that described the first voice messaging is stored in to internal memory, can record the time end point of the voice messaging of described the first voice messaging being identified by the second sound identification module, the voice messaging after this time point is the first sub-voice messaging for not identified by described the second sound identification module.
The second, directly by microphone Real-time Obtaining user's voice messaging.
In specific implementation process, may described the first voice messaging be not the voice messaging of user for described electronic equipment is controlled, or do not record described the first voice messaging, so directly catch real-time voice messaging by microphone, described electronic equipment is controlled.
Wherein, after described electronic equipment enters described the first use pattern, described electronic equipment can produce an information, for pointing out for not having the voice messaging that electronic equipment is controlled at present, and determines whether to need implementation record user's voice messaging.
For example, produce following information:
" the current voice messaging that electronic equipment is controlled that do not exist, please input corresponding voice messaging so that electronic equipment is controlled.”
Certainly, in specific implementation process, described information is not limited to above-mentioned information, is which kind of information for described information, and the embodiment of the present application is not restricted.
Wherein, in step S102, can adopt various ways to determine the first current use pattern of described electronic equipment, two kinds of modes enumerating below are wherein introduced, and certainly, in specific implementation process, are not limited to following two kinds of situations.
The first, determines the energy consumption of described electronic equipment, such as: if the energy consumption of described electronic equipment is less than a predetermined threshold value, the use pattern of determining described electronic equipment is used pattern for power saving; And if the energy consumption of described electronic equipment is greater than described predetermined threshold value, determine that the use pattern of described electronic equipment is normal use pattern etc.
The second, determine the application program in running status on described electronic equipment, such as: if described application program is simple games, image processing program, determine that it is controlled to needed control vocabulary is less, thereby can determine that it is little vocabulary and use pattern; And when described application program be complicated image processing program, text editor, determine that it is controlled to needed vocabulary is more, thereby determine that it is large vocabulary use pattern etc.
In specific implementation process, the mapping table of application program and speech recognition system can be set in described electronic equipment, determine the corresponding speech recognition system of application program based on mapping table; Or application program vocabulary used described in described electronic equipment direct-detection, the then vocabulary based on different, determines the corresponding different phonetic recognition system of different application programs.
In specific implementation process, control after described electronic equipment enters described the first use pattern based on step S102, as shown in Figure 3, described method also comprises the steps:
Step S301: judge whether to exist second steering order of opening described the first sound identification module;
Step S302: after there is described the second steering order, execution step: S103.
In specific implementation process, above-mentioned the second steering order can adopt any-mode to obtain, such as: when described the second speech recognition system is during in opening, catch user's voice messaging and analyze by described the second speech recognition system, comprise the result of voice analysis for controlling described the first sound identification module in definite voice messaging time, just perform step S103; Or the mode that can click by responding user a certain specific button triggers described the second steering order; Or can trigger described second steering order etc. by the slide on touch screen by response user.For in specific implementation process, adopt which kind of mode to trigger described the second steering order, the embodiment of the present application is not restricted.
As seen from the above description, due in the embodiment of the present application, after control electronic equipment enters described the first use pattern, first to judge whether to exist second steering order of opening the first sound identification module, in the time existing, just open described the first sound identification module, so reach the technique effect of saving energy consumption.
Wherein, in step S103, described based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module, specifically comprise:
In the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is software identification module;
In the time of the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determine that the sound identification module corresponding with described the first use pattern is hardware identification module.
In specific implementation process, when described electronic equipment enters described the first use pattern, such as: after the corresponding use pattern of open state, wherein, based on the corresponding different use patterns of open state, speech recognition system that may be corresponding different, suppose to exist following mapping table:
The first use pattern Speech recognition system
Power saving is used pattern Hardware sound identification module/little vocabulary software identification module
Normal use pattern Software sound identification module/large vocabulary software identification module
Wherein, use pattern because described electronic equipment adopts power saving, wish as can be seen here to save power consumption, so adopt the less sound identification module of vocabulary, such as: the software identification module of hardware sound identification module or little vocabulary, thereby save energy consumption; And when described electronic equipment employing normal mode of operation, that wishes to identify is more accurate, so adopt vocabulary more sound identification module, such as: the software sound identification module relative with hardware sound identification module, with little vocabulary software identification module with respect to large vocabulary software identification module.
In addition, in specific implementation process, the difference of the application program that also can use based on described electronic equipment, determines the first speech recognition system of its correspondence.
Such as: the application program using when described electronic equipment is comparatively simple application program, when namely the use pattern of described electronic equipment is little vocabulary use pattern, its corresponding steering order is less, and comparatively simple, such as: the first application program is Photo Browser, its corresponding steering order is less, such as: " upper one ", " next ", " dwindling ", " amplification " etc., in this case, adopt the sound identification module of hardware sound identification module or little vocabulary.
Be comparatively complicated application program and work as described the first application program, such as: text input application program, image are processed application program etc., because its corresponding steering order is more, when namely the use pattern of described electronic equipment is large vocabulary use pattern, adopt the more sound identification module of vocabulary, such as: the software sound identification module relative with hardware sound identification module, with little vocabulary software identification module with respect to large vocabulary software identification module etc., to reach identification more accurately.
In specific implementation process, described step S101 and step S102, step S103, its execution sequence is dividing of sequencing not, can first carry out by step S101, also can step S102 and step S103 first carry out, or both carry out simultaneously, and this embodiment of the present application is not restricted.
In specific implementation process, based on step S103, determine that the sound identification module corresponding with described the first use pattern is after the first sound identification module, described method also comprises:
Close described the second sound identification module.
In specific implementation process, if determining described the first speech recognition system in step S103 is software sound identification module, because the precision of its identification is higher, so do not need namely assisting of hardware sound identification module of described the second sound identification module, also can complete accurate identification, so in this case, close described the second sound identification module.
As seen from the above description, due in the embodiment of the present application, in opening described the first sound identification module, close described the second sound identification module, so reached the technique effect of further reduction energy consumption.
In step S104, when described voice messaging to be identified identification by described the first sound identification module, can obtain multiple recognition result, described recognition result is for example the steering order of application programs, such as: open PS image processing software, open music player; Be for example again the operation to file, such as: open C dish file, open WORD document of called after on desktop " application documents " etc.; For example some settings to electronic equipment again, such as: which kind of result is closed volume control button, changes desktop wallpaper etc., be for described recognition result, and the embodiment of the present application is not restricted.
Embodiment bis-
In order to make those skilled in the art can connect the specific implementation process of the method for the speech recognition of introducing in the embodiment of the present application one, in the present embodiment, will stand in the detailed annotation of user's side and introduce the specific implementation process of the method for this information processing.
In the present embodiment, take described electronic equipment as notebook computer, described the first sound identification module is: hardware sound identification module or software sound identification module, described the second sound identification module is that hardware sound identification module is that example is introduced.
In the T1 moment, described notebook computer is in off-mode, and wherein, the microphone of described notebook computer and hardware speech recognition system are in opening.
In the T2 moment, user A wishes to open described notebook computer and carries out some image processing, so user A produces following voice messaging " start ";
The processor of notebook computer detects with after user's above-mentioned voice messaging, and it is identified, and obtains start steering order, carries out open state so control described notebook computer; The processor of described notebook computer starts to record the voice messaging of described user A simultaneously, wherein be recorded to following the first voice messaging " open beautiful figure elegant; and open the jpg file of storage ' the bright moon when Qin ' by name on desktop ", and described the first voice messaging is stored in to internal memory.
In the T3 moment, described notebook computer enters opening, and, because the user who uses described notebook computer does not arrange its mode of operation, so it is normal use pattern, described notebook computer, after definite the first use pattern is normal use pattern, is just opened described software speech recognition system, closes described hardware speech recognition system simultaneously.
Meanwhile, described notebook computer is identified described the first voice messaging, obtains following phonetic control command:
" opening U.S. schemes elegant ", " bright moon .jpg while opening the Qin "
So the elegant program of the beautiful figure of processor control of described notebook computer, in open mode, is being controlled the elegant program of beautiful figure after open mode, bright moon .jpg open the Qin in the elegant program of U.S. figure time.
Embodiment tri-
The present embodiment will be take described electronic equipment as panel computer, and described the first speech recognition system is: little vocabulary software recognition system or large vocabulary software recognition system are that example is introduced.
In the T4 moment, user B uses described panel computer to play the game of Tetris, and wherein, Tetris only includes four steering orders such as " left side ", " right side " " acceleration " " rotation ";
The processor of described panel computer is after determining that the application program of being moved on described panel computer is Tetris, determine that described panel computer is that little vocabulary uses pattern, thereby the little vocabulary software recognition system of opening described panel computer, user's steering order is identified.
In the T5 moment, user B closes Russia Bricks Game, and open WORD and start to input document, after described panel computer detects that user opens WORD document, determine that its steering order is more, use pattern so determine that it is large vocabulary, thereby the large vocabulary software recognition system of opening described panel computer is identified to the voice messaging of user B.
Embodiment tetra-
Based on same inventive concept, the embodiment of the present application four provides a kind of method of information processing, is applied in an electronic equipment, and described electronic equipment is for example: panel computer, mobile phone, notebook computer etc.
Please refer to Fig. 4, the method for described information processing comprises the steps:
Step S401:, detect and obtain the second voice messaging to be identified during in the second use pattern at described electronic equipment, wherein, described the second use pattern is described electronic equipment corresponding use pattern in the time of power down mode;
Step S402: by described the second voice messaging information to be identified being identified with corresponding the second sound identification module of described the second use pattern, determine whether to exist the described electronic equipment of control to enter the first steering order of the first use pattern;
Step S403: in the time there is described the first steering order, control described electronic equipment and enter described the first use pattern, wherein, described the first use pattern is described electronic equipment corresponding use pattern in the time of normal operating conditions.
Wherein, in step S401, described the second use pattern can described electronic equipment corresponding any use pattern in the time of power saving shape, for example: shutdown mode, stand-by/sleep mode etc., the embodiment of the present application is not restricted.
In this case, the microphone of described electronic equipment is still in running order, the voice messaging can real time record user producing.
Wherein, in step S402, described the second sound identification module is for example: hardware identification module, when described electronic equipment is during in shutdown mode, standby mode or standby mode, described hardware identification module is still in running order, second voice messaging that just can obtain microphone by described hardware identification module is identified, and then obtains some simple steering orders, such as: start-up command, wake instruction etc. up.
Wherein, in step S403, described the first use pattern is described electronic equipment corresponding any use pattern in the time of normal operating conditions.
In specific implementation process, based on controlling in step S403 after described electronic equipment enters described the first use pattern, please refer to Fig. 5, described method also comprises the steps:
S501: determine corresponding the first sound identification module of described the first use pattern;
S502: obtain the first voice messaging to be identified;
S503: based on described the first sound identification module, described the first voice messaging to be identified is identified, to obtain at least one recognition result.
Wherein, in step S501, described the first use pattern corresponding use pattern when being normal work, so the first sound identification module is generally software identification module, certainly, in specific implementation process, can be after described electronic equipment switch to described the first use pattern, described electronic equipment is just opened described the first sound identification module automatically; Also can, after the operation that receives user, produce corresponding steering order, and then control described electronic equipment and open described the first sound identification module, this be opened in which kind of situation to described the first sound identification module, the embodiment of the present application is not restricted.
In specific implementation process, in step S502, described the first voice messaging to be identified can adopt various ways to obtain, and two kinds that enumerate below are wherein introduced.
The first, described determine whether to exist control after described electronic equipment enters the first steering order of the first use pattern, described method also comprises:
In the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
In this case, described in obtain the first voice messaging to be identified, be specially:
Obtaining in described the first voice messaging is still the first sub-voice messaging that was carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
In specific implementation process, after the first voice messaging of microphone recording user, can be stored in the internal memory of electronic equipment, after the first sound identification module is opened, can be directly in internal memory for described the first voice messaging.Wherein, in the time that described the first voice messaging is stored in to internal memory, can record the time end point of the voice messaging of described the first voice messaging being identified by the second sound identification module, the voice messaging after this time point is the first sub-voice messaging for not identified by described the second sound identification module.
As seen from the above description, due in the embodiment of the present application, in the time existing the described electronic equipment of control to enter the first steering order of the first use pattern, the first voice messaging that recording user is inputted, adopt the first speech recognition system at electronic equipment like this, such as: when software sound identification module, can call described the first voice messaging and then identification by described software sound identification module, and software sound identification module is compared to hardware sound identification module, its vocabulary is more, so reached the technique effect that improves recognition accuracy.
The second, after there is described the first steering order, does not record described the first voice messaging, so, after starting described the first sound identification module, by microphone Real-time Obtaining user's voice messaging.
In specific implementation process, may described the first voice messaging be not the voice messaging of user for described electronic equipment is controlled, or do not record described the first voice messaging, so directly catch the voice messaging that catches in real time user as described the first voice messaging to be identified by microphone.
Wherein, after described electronic equipment enters described the first use pattern, described electronic equipment can produce an information, for pointing out for not having the voice messaging that electronic equipment is controlled at present, and determines whether to need implementation record user's voice messaging.
Embodiment five
Based on same inventive concept, the embodiment of the present application four provides a kind of electronic equipment, and described electronic equipment is for example: notebook computer, mobile phone, panel computer etc.
In described electronic equipment, include at least two different sound identification modules, in specific implementation process, described at least two different speech recognition systems are for example: hardware sound identification module, software sound identification module; Or, described at least two different speech recognition systems are: little vocabulary speech recognition system, major term table speech recognition system etc., be specially which kind of speech recognition system for described at least two different speech recognition systems, the embodiment of the present application is not restricted.
Please refer to Fig. 6, described electronic equipment also comprises following structure:
First obtains chip 601, for obtaining a voice messaging to be identified;
Second obtains chip 602, is the first use pattern for obtaining the present mode of described electronic equipment;
Determine chip 603, for based on corresponding relation between use pattern and sound identification module, determine the sound identification module corresponding from described the first use pattern be described in the first sound identification module at least two different sound identification modules;
The 3rd obtains chip 604, for by described the first sound identification module, described voice messaging to be identified being identified, obtains a recognition result.
In specific implementation process, described electronic equipment also comprises following structure:
Detection chip, before being the first use pattern at the present mode that obtains described electronic equipment, when described electronic equipment is during in the second use pattern, detect whether to exist by the second sound identification module in described at least two different sound identification modules corresponding from described the second use pattern and control described electronic equipment and enter the described first the first steering order that uses pattern;
Control chip, in the time there is described the first steering order, controls described electronic equipment and enters described the first use pattern.
In specific implementation process, described the second use pattern, for example, be: shutdown mode, standby mode etc., in this case, described the second sound identification module is for example: hardware identification module.Wherein, when described electronic equipment is during in shutdown mode or standby mode, microphone on described hardware identification module and electronic equipment is all still in running order, can identify some simple voice messagings by described hardware identification module, and then produce some simple steering orders, thereby can detect user's voice messaging, to determine whether that controlling described electronic equipment enters described the first use pattern.
As seen from the above description, due in the embodiment of the present application, when electronic equipment is in the second use pattern, such as: when shutdown/standby mode, can pass through the second sound identification module, such as: hardware identification module is identified steering order, enters described the first use pattern to control described electronic equipment, because not needing unlocking electronic equipment, hardware identification module can realize speech recognition, so reached the technique effect of saving energy consumption.
In specific implementation process, described electronic equipment also comprises:
Record chip, for after the described electronic equipment of the described control of control enters described the first use pattern, record described electronic equipment and switch to described first from described the second use pattern and use the first voice messaging that user inputs when pattern, described the first voice messaging is described voice messaging to be identified.
In specific implementation process, described electronic equipment also comprises:
Storage chip, for record described electronic equipment switch to from described the second use pattern described first use the first voice messaging that user inputs when pattern after, described the first voice messaging is stored in to the internal memory of described electronic equipment.
As seen from the above description, due in the embodiment of the present application, set and enter described first and use when pattern controlling described electronics, the first voice messaging that recording user is inputted, adopt the first speech recognition system at electronic equipment like this, such as: when software sound identification module, can call described the first voice messaging and then identification by described software sound identification module, and software sound identification module is compared to hardware sound identification module, its vocabulary is more, so reached the technique effect that improves recognition accuracy.
In specific implementation process, described first obtains chip 601, can adopt various ways to obtain described the first voice messaging, and two kinds that enumerate below are wherein introduced, and certainly, in specific implementation process, are not limited to following two kinds of situations.
The first, described first obtains chip 601, specifically for:
From described internal memory, read described the first voice messaging.
The second, described first obtains chip 601, specifically for:
Directly by microphone Real-time Obtaining user's voice messaging.
In specific implementation process, described electronic equipment also comprises:
Judge chip: for after the described electronic equipment of control enters described the first use pattern, judge whether to exist second steering order of opening described the first sound identification module; And
After there is described the second steering order, execution step: based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module.
As seen from the above description, due in the embodiment of the present application, after control electronic equipment enters described the first use pattern, first to judge whether to exist second steering order of opening the first sound identification module, in the time existing, just open described the first sound identification module, so reach the technique effect of saving energy consumption.
In specific implementation process, described definite chip 604, specifically comprises:
The first true stator chip, for in the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is software identification module;
The second true stator chip, for when the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determines that the sound identification module corresponding with described the first use pattern is hardware identification module.
In specific implementation process, described electronic equipment also comprises:
Close chip, for after definite sound identification module corresponding with described the first use pattern is the first sound identification module, close described the second sound identification module.
As seen from the above description, due in the embodiment of the present application, in opening described the first sound identification module, close described the second sound identification module, so reached the technique effect of further reduction energy consumption.
The electronic equipment of introducing due to the present embodiment five, the electronic equipment adopting for implementing the method for the speech recognition in the embodiment of the present application one to three, so method of the speech recognition based on introducing in the embodiment of the present application one to three, the embodiment that those skilled in the art can understand electronic equipment in the embodiment of the present application five with and various version, so introduce no longer in detail for this electronic equipment at this.As long as those skilled in the art implement the electronic equipment that the method for speech recognition in the embodiment of the present application one to three adopts, all belong to the scope of the application institute wish protection.
Embodiment six
Based on same inventive concept, the embodiment of the present application six provides a kind of electronic equipment, and described electronic equipment is for example: notebook computer, panel computer, mobile phone etc.
Please refer to Fig. 7, described electronic equipment comprises following structure;
The second detection chip 701, for, detecting and obtain the second voice messaging to be identified during in the second use pattern at described electronic equipment, wherein, described the second use pattern is described electronic equipment corresponding use pattern in the time of power down mode;
Second determines chip 702, for by described the second voice messaging information to be identified being identified with corresponding the second sound identification module of described the second use pattern, determines whether to exist the described electronic equipment of control to enter the first steering order of the first use pattern;
The second control chip 703, in the time there is described the first steering order, controls described electronic equipment and enters described the first use pattern, and wherein, described the first use pattern is described electronic equipment corresponding use pattern in the time of normal operating conditions.
In specific implementation process, described electronic equipment also comprises:
The 3rd determines chip, for after the described electronic equipment of control enters described the first use pattern, determines corresponding the first sound identification module of described the first use pattern;
Obtain chip, for obtaining the first voice messaging to be identified;
The 4th obtains chip, for based on described the first sound identification module, described the first voice messaging to be identified being identified, to obtain at least one recognition result.
In specific implementation process, described in obtain chip and can adopt various ways to obtain described the first voice messaging to be identified, two kinds that enumerate below are wherein introduced, and certainly, in specific implementation process, are not limited to following two kinds of situations.
The first, described electronic equipment also comprises:
Second records chip, for after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, in the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
In this case, described in obtain chip, specifically for:
Obtaining in described the first voice messaging is still the first sub-voice messaging that was carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
As seen from the above description, due in the embodiment of the present application, in the time existing the described electronic equipment of control to enter the first steering order of the first use pattern, the first voice messaging that recording user is inputted, adopt the first speech recognition system at electronic equipment like this, such as: when software sound identification module, can call described the first voice messaging and then identification by described software sound identification module, and software sound identification module is compared to hardware sound identification module, its vocabulary is more, so reached the technique effect that improves recognition accuracy.
The second, described in obtain chip, specifically for:
Catch in real time user's voice messaging by microphone as described the first voice messaging to be identified.
The electronic equipment of introducing due to the present embodiment six, the electronic equipment adopting for implementing the method for the information processing in the embodiment of the present application four, so method of the information processing based on introducing in the embodiment of the present application four, the embodiment that those skilled in the art can understand electronic equipment in the embodiment of the present application six with and various version, so introduce no longer in detail for this electronic equipment at this.As long as those skilled in the art implement the electronic equipment that the method for information processing in the embodiment of the present application four adopts, all belong to the scope of the application institute wish protection.
One or more technical schemes that the application provides, at least have following technique effect or advantage:
(1) due in the embodiment of the present application, adopt at least two different sound identification modules of electronic equipment setting, thereby the difference based on electronic equipment is used pattern, can adopt the technical scheme of different sound identification modules, so, at electronic equipment under the less use pattern of steering order, can adopt the speech recognition system that energy consumption is lower, only at electronic equipment under the more use pattern of steering order, just adopt the speech recognition system that energy consumption is higher, so solved the technical matters that can not improve recognition accuracy in prior art in reducing energy consumption, reach the technique effect in the situation decline low energy consumption of assurance recognition accuracy.
(2) due in the embodiment of the present application, when electronic equipment is in the second use pattern, such as: when shutdown/standby mode, can pass through the second sound identification module, such as: hardware identification module is identified steering order, enter described the first use pattern to control described electronic equipment, can realize speech recognition because hardware identification module does not need unlocking electronic equipment, so reached the technique effect of saving energy consumption.
(3) due in the embodiment of the present application, set and enter described first and use when pattern controlling described electronics, the first voice messaging that recording user is inputted, adopt the first speech recognition system at electronic equipment like this, such as: when software sound identification module, can call described the first voice messaging and then identification by described software sound identification module, and software sound identification module is compared to hardware sound identification module, its vocabulary is more, so reached the technique effect that improves recognition accuracy.
(4) due in the embodiment of the present application, after control electronic equipment enters described the first use pattern, first to judge whether to exist second steering order of opening the first sound identification module, in the time existing, just open described the first sound identification module, so reach the technique effect of saving energy consumption.
(5) due in the embodiment of the present application, in opening described the first sound identification module, close described the second sound identification module, so reached the technique effect of further reduction energy consumption.
Although described the preferred embodiments of the present invention, once those skilled in the art obtain the basic creative concept of cicada, can make other change and modification to these embodiment.So claims are intended to be interpreted as comprising preferred embodiment and fall into all changes and the modification of the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.

Claims (26)

1. an audio recognition method, is applied in an electronic equipment, it is characterized in that, includes at least two different sound identification modules in described electronic equipment, and described method comprises:
Obtain the first voice messaging to be identified;
The present mode that obtains described electronic equipment is the first use pattern;
Based on corresponding relation between use pattern and sound identification module, determine the sound identification module corresponding from described the first use pattern be described in the first sound identification module at least two different sound identification modules;
By described the first sound identification module, described voice messaging to be identified is identified, obtained a recognition result.
2. the method for claim 1, is characterized in that, before the present mode of the described electronic equipment of described acquisition is the first use pattern, described method also comprises:
When described electronic equipment is during in the second use pattern, detect and obtain the second voice messaging to be identified;
By the second sound identification module in described at least two different sound identification modules corresponding from described the second use pattern, described the second voice messaging to be identified is identified, to determine whether the existing described electronic equipment of control to enter the first steering order of described the first use pattern;
In the time there is described the first steering order, control described electronic equipment and enter described the first use pattern.
3. method as claimed in claim 2, is characterized in that, after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, described method also comprises:
In the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
4. method as claimed in claim 3, is characterized in that, described record described electronic equipment switch to from described the second use pattern described first use the first voice messaging that user inputs when pattern after, described method also comprises:
Described the first voice messaging is stored in to the internal memory of described electronic equipment.
5. method as claimed in claim 4, is characterized in that, described acquisition first voice messaging to be identified, specifically comprises:
From described internal memory, read described the first voice messaging;
Obtaining in described the first voice messaging is still the first sub-voice messaging that is carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
6. method as claimed in claim 2, is characterized in that, after the described electronic equipment of described control enters described the first use pattern, described method also comprises:
Judge whether to exist second steering order of opening described the first sound identification module;
After there is described the second steering order, execution step: based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module.
7. method as claimed in claim 2, is characterized in that, after described definite sound identification module corresponding with described the first use pattern is the first sound identification module, described method also comprises:
Close described the second sound identification module.
8. the method as described in claim as arbitrary in claim 1-7, is characterized in that, described the first sound identification module is: software sound identification module or hardware sound identification module; Described the second sound identification module is: hardware sound identification module;
Described the first use pattern is: the corresponding use pattern of open state; Described the second use pattern is shutdown/standby mode.
9. the method as described in claim as arbitrary in claim 1-7, is characterized in that, described based on corresponding relation between use pattern and sound identification module, determines that the sound identification module corresponding with described the first use pattern is the first sound identification module, is specially:
In the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is software identification module;
In the time of the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determine that the sound identification module corresponding with described the first use pattern is hardware identification module.
10. a method for information processing, is applied in an electronic equipment, it is characterized in that, described method comprises:
, detect and obtain the second voice messaging to be identified during in the second use pattern at described electronic equipment, wherein, described the second use pattern is described electronic equipment corresponding use pattern in the time of power down mode;
By described the second voice messaging information to be identified being identified with corresponding the second sound identification module of described the second use pattern, determine whether to exist the described electronic equipment of control to enter the first steering order of the first use pattern;
In the time there is described the first steering order, control described electronic equipment and enter described the first use pattern, wherein, described the first use pattern is described electronic equipment corresponding use pattern in the time of normal operating conditions.
11. methods as claimed in claim 10, is characterized in that, after the described electronic equipment of described control enters described the first use pattern, described method also comprises:
Determine corresponding the first sound identification module of described the first use pattern;
Obtain the first voice messaging to be identified;
Based on described the first sound identification module, described the first voice messaging to be identified is identified, to obtain at least one recognition result.
12. methods as claimed in claim 11, is characterized in that, described determine whether to exist control after described electronic equipment enters the first steering order of the first use pattern, described method also comprises:
In the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
13. methods as claimed in claim 12, is characterized in that, described in obtain the first voice messaging to be identified, be specially:
Obtaining in described the first voice messaging is still the first sub-voice messaging that was carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
14. 1 kinds of electronic equipments, is characterized in that, include at least two different sound identification modules in described electronic equipment, and described electronic equipment also comprises:
First obtains chip, for obtaining the first voice messaging to be identified;
Second obtains chip, is the first use pattern for obtaining the present mode of described electronic equipment;
First determines chip, for based on corresponding relation between use pattern and sound identification module, determine the sound identification module corresponding from described the first use pattern be described in the first sound identification module at least two different sound identification modules;
The 3rd obtains chip, for by described the first sound identification module, described voice messaging to be identified being identified, obtains a recognition result.
15. electronic equipments as claimed in claim 14, is characterized in that, described electronic equipment also comprises:
The first detection chip, before being the first use pattern at the present mode that obtains described electronic equipment, when described electronic equipment is during in the second use pattern, detect whether to exist by the second sound identification module in described at least two different sound identification modules corresponding from described the second use pattern and control described electronic equipment and enter the described first the first steering order that uses pattern;
The first control chip, in the time there is described the first steering order, controls described electronic equipment and enters described the first use pattern.
16. electronic equipments as claimed in claim 15, is characterized in that, described electronic equipment also comprises:
First records chip, for after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, in the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
17. electronic equipments as claimed in claim 16, is characterized in that, described electronic equipment also comprises:
Storage chip, for record described electronic equipment switch to from described the second use pattern described first use the first voice messaging that user inputs when pattern after, described the first voice messaging is stored in to the internal memory of described electronic equipment.
18. electronic equipments as claimed in claim 17, is characterized in that, described first obtains chip, specifically comprises:
Read sub-chip, for read described the first voice messaging from described internal memory;
Obtain sub-chip, for obtaining still the first sub-voice messaging for being carried out speech recognition by described the second sound identification module of described the first voice messaging, described the first sub-voice messaging is described the first voice messaging to be identified.
19. electronic equipments as claimed in claim 15, is characterized in that, described electronic equipment also comprises:
Judge chip: for after the described electronic equipment of control enters described the first use pattern, judge whether to exist second steering order of opening described the first sound identification module; And
After there is described the second steering order, execution step: based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is the first sound identification module.
20. electronic equipments as claimed in claim 15, is characterized in that, described electronic equipment also comprises:
Close chip, for after definite sound identification module corresponding with described the first use pattern is the first sound identification module, close described the second sound identification module.
Electronic equipment as described in 21. claims as arbitrary in claim 14-20, is characterized in that, described the first sound identification module is: software sound identification module or hardware sound identification module; Described the second sound identification module is: hardware sound identification module;
Described the first use pattern is: the corresponding use pattern of open state; Described the second use pattern is shutdown/standby mode.
Electronic equipment as described in 22. claims as arbitrary in claim 14-20, is characterized in that, described first determines chip, specifically comprises:
The first true stator chip, for in the time that described the first use pattern is greater than the use pattern of the first predetermined threshold value for power consumption, based on corresponding relation between use pattern and sound identification module, determine that the sound identification module corresponding with described the first use pattern is software identification module;
The second true stator chip, for when the use pattern of described the first use pattern described first predetermined threshold value for power consumption is less than, determines that the sound identification module corresponding with described the first use pattern is hardware identification module.
23. 1 kinds of electronic equipments, is characterized in that, described electronic equipment comprises:
The second detection chip, for, detecting and obtain the second voice messaging to be identified during in the second use pattern at described electronic equipment, wherein, described the second use pattern is described electronic equipment corresponding use pattern in the time of power down mode;
Second determines chip, for by described the second voice messaging information to be identified being identified with corresponding the second sound identification module of described the second use pattern, determines whether to exist the described electronic equipment of control to enter the first steering order of the first use pattern;
The second control chip, in the time there is described the first steering order, controls described electronic equipment and enters described the first use pattern, and wherein, described the first use pattern is described electronic equipment corresponding use pattern in the time of normal operating conditions.
24. electronic equipments as claimed in claim 23, is characterized in that, described electronic equipment also comprises:
The 3rd determines chip, for after the described electronic equipment of control enters described the first use pattern, determines corresponding the first sound identification module of described the first use pattern;
Obtain chip, for obtaining the first voice messaging to be identified;
The 4th obtains chip, for based on described the first sound identification module, described the first voice messaging to be identified being identified, to obtain at least one recognition result.
25. electronic equipments as claimed in claim 24, is characterized in that, described electronic equipment also comprises:
Second records chip, for after determining whether that the described electronic equipment of existence control enters the first steering order of the first use pattern, in the time there is described the first steering order, be recorded in the first moment of producing described the first steering order to switching to the described first the first voice messaging that uses user's input between the second moment of pattern.
26. electronic equipments as claimed in claim 25, is characterized in that, described in obtain chip, specifically for:
Obtaining in described the first voice messaging is still the first sub-voice messaging that was carried out speech recognition by described the second sound identification module, and described the first sub-voice messaging is described the first voice messaging to be identified.
CN201210548625.2A 2012-11-13 2012-12-17 A kind of method of speech recognition, the method for information processing and electronic equipment Active CN103871409B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201210548625.2A CN103871409B (en) 2012-12-17 2012-12-17 A kind of method of speech recognition, the method for information processing and electronic equipment
US14/079,219 US9959865B2 (en) 2012-11-13 2013-11-13 Information processing method with voice recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210548625.2A CN103871409B (en) 2012-12-17 2012-12-17 A kind of method of speech recognition, the method for information processing and electronic equipment

Publications (2)

Publication Number Publication Date
CN103871409A true CN103871409A (en) 2014-06-18
CN103871409B CN103871409B (en) 2018-01-23

Family

ID=50909873

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210548625.2A Active CN103871409B (en) 2012-11-13 2012-12-17 A kind of method of speech recognition, the method for information processing and electronic equipment

Country Status (1)

Country Link
CN (1) CN103871409B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104282307A (en) * 2014-09-05 2015-01-14 中兴通讯股份有限公司 Method, device and terminal for awakening voice control system
CN104866274A (en) * 2014-12-01 2015-08-26 联想(北京)有限公司 Information processing method and electronic equipment
CN105005429A (en) * 2015-06-30 2015-10-28 广东欧珀移动通信有限公司 Method for showing picture through terminal and terminal
CN107112017A (en) * 2015-02-16 2017-08-29 三星电子株式会社 Operate the electronic equipment and method of speech identifying function
CN108093350A (en) * 2017-12-21 2018-05-29 广东小天才科技有限公司 Microphone control method and microphone
CN108847232A (en) * 2018-05-31 2018-11-20 联想(北京)有限公司 A kind of processing method and electronic equipment
WO2018233300A1 (en) * 2017-06-20 2018-12-27 京东方科技集团股份有限公司 Voice recognition method and voice recognition device
CN110770820A (en) * 2018-08-30 2020-02-07 深圳市大疆创新科技有限公司 Speech recognition method, apparatus, photographing system, and computer-readable storage medium
CN111369999A (en) * 2020-03-12 2020-07-03 北京百度网讯科技有限公司 Signal processing method and device and electronic equipment
CN112634879A (en) * 2020-12-18 2021-04-09 建信金融科技有限责任公司 Voice conference management method, device, equipment and medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020046023A1 (en) * 1995-08-18 2002-04-18 Kenichi Fujii Speech recognition system, speech recognition apparatus, and speech recognition method
CN1722230A (en) * 2004-07-12 2006-01-18 惠普开发有限公司 Allocation of speech recognition tasks and combination of results thereof
CN1723487A (en) * 2002-12-13 2006-01-18 摩托罗拉公司 Method and apparatus for selective speech recognition
CN101030130A (en) * 2006-03-02 2007-09-05 英华达（南京）科技有限公司 Manual device and method for inputting element by speech recognition
US20120179457A1 (en) * 2011-01-07 2012-07-12 Nuance Communications, Inc. Configurable speech recognition system using multiple recognizers

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020046023A1 (en) * 1995-08-18 2002-04-18 Kenichi Fujii Speech recognition system, speech recognition apparatus, and speech recognition method
CN1723487A (en) * 2002-12-13 2006-01-18 摩托罗拉公司 Method and apparatus for selective speech recognition
CN1722230A (en) * 2004-07-12 2006-01-18 惠普开发有限公司 Allocation of speech recognition tasks and combination of results thereof
CN101030130A (en) * 2006-03-02 2007-09-05 英华达（南京）科技有限公司 Manual device and method for inputting element by speech recognition
US20120179457A1 (en) * 2011-01-07 2012-07-12 Nuance Communications, Inc. Configurable speech recognition system using multiple recognizers

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104282307A (en) * 2014-09-05 2015-01-14 中兴通讯股份有限公司 Method, device and terminal for awakening voice control system
CN104866274A (en) * 2014-12-01 2015-08-26 联想(北京)有限公司 Information processing method and electronic equipment
CN104866274B (en) * 2014-12-01 2018-06-01 联想(北京)有限公司 Information processing method and electronic equipment
US10679628B2 (en) 2015-02-16 2020-06-09 Samsung Electronics Co., Ltd Electronic device and method of operating voice recognition function
CN107112017A (en) * 2015-02-16 2017-08-29 三星电子株式会社 Operate the electronic equipment and method of speech identifying function
US12027172B2 (en) 2015-02-16 2024-07-02 Samsung Electronics Co., Ltd Electronic device and method of operating voice recognition function
CN105005429A (en) * 2015-06-30 2015-10-28 广东欧珀移动通信有限公司 Method for showing picture through terminal and terminal
CN105005429B (en) * 2015-06-30 2018-12-11 广东欧珀移动通信有限公司 A kind of method and terminal of terminal display picture
WO2018233300A1 (en) * 2017-06-20 2018-12-27 京东方科技集团股份有限公司 Voice recognition method and voice recognition device
CN109102801A (en) * 2017-06-20 2018-12-28 京东方科技集团股份有限公司 Audio recognition method and speech recognition equipment
US11355124B2 (en) 2017-06-20 2022-06-07 Boe Technology Group Co., Ltd. Voice recognition method and voice recognition apparatus
CN108093350A (en) * 2017-12-21 2018-05-29 广东小天才科技有限公司 Microphone control method and microphone
CN108093350B (en) * 2017-12-21 2020-12-15 广东小天才科技有限公司 Microphone control method and microphone
CN108847232A (en) * 2018-05-31 2018-11-20 联想(北京)有限公司 A kind of processing method and electronic equipment
CN110770820A (en) * 2018-08-30 2020-02-07 深圳市大疆创新科技有限公司 Speech recognition method, apparatus, photographing system, and computer-readable storage medium
CN111369999A (en) * 2020-03-12 2020-07-03 北京百度网讯科技有限公司 Signal processing method and device and electronic equipment
CN111369999B (en) * 2020-03-12 2024-05-14 北京百度网讯科技有限公司 Signal processing method and device and electronic equipment
CN112634879A (en) * 2020-12-18 2021-04-09 建信金融科技有限责任公司 Voice conference management method, device, equipment and medium

Also Published As

Publication number Publication date
CN103871409B (en) 2018-01-23

Similar Documents

Publication Publication Date Title
CN103871409A (en) Voice identifying method, information processing method and electronic equipment
US11024332B2 (en) Cloud-based speech processing method and apparatus
US9959865B2 (en) Information processing method with voice recognition
CN103871401A (en) Method for voice recognition and electronic equipment
WO2012066557A1 (en) System and method for using information from intuitive multimodal interactions for media tagging
CN103699259B (en) A kind of method of cursor positioning, system and touch apparatus
CN103310785A (en) Electronic device and method for controlling power using voice recognition
CN103811003A (en) Voice recognition method and electronic equipment
WO2013185119A1 (en) Storing trace information
CN102073430B (en) Method for capacitive screen to automatically adjust induction value
US9588678B2 (en) Method of operating electronic handwriting and electronic device for supporting the same
CN111199733A (en) Multi-stage recognition voice awakening method and device, computer storage medium and equipment
CN112578967B (en) Chart information reading method and mobile terminal
US20200234707A1 (en) Voice interaction processing method and apparatus
CN103489444A (en) Speech recognition method and device
CN103543814A (en) Signal processing device and signal processing method
CN102609276A (en) Method for pre-loading common application program and electronic device thereof
CN102710846A (en) System and method for realizing electronic book page turning based on forced induction
CN102455887A (en) Input display apparatus and input display method
TW201445426A (en) A method for a handwriting signal starts program or an application
CN105760099A (en) Method and terminal for recording information
CN107005609A (en) The method and mobile terminal of mobile terminal are operated based on blowing action
CN209496342U (en) The adjustable mouse of wheel speeds
US20140180698A1 (en) Information processing apparatus, information processing method and storage medium
CN201577133U (en) Image pickup driving system and electronic device utilizing same

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