CN104917904A - Voice information processing method and device and electronic device - Google Patents

Abstract

The invention provides a voice information processing method. When voice information does not need to be converted to be text information immediately, a user can control the electronic device to carry out voice information acquisition through a voice containing first command information; the electronic device only records the voice information but does not carry out conversion, and a first processing unit does not need to execute a voice-to-text action, so that power consumption, generated when converting the voice into texts, of the first processing unit is reduced; and when the voice information needs to be converted into text information immediately, the user can control the electronic device to begin to carry out voice information acquisition and awaken to the first processing unit to carry out voice recording and conversion through a voice containing second command information, thereby ensuring the need for converting the voice into texts immediately of the user. Whether to awaken the first processing unit to covert the collected voice information is controlled by the voice information of the user, and it is not necessary to carry out instant conversion on all collected voice information, so that power consumption of the electronic device is reduced, endurance time is prolonged, and user experience is improved.

Description

A kind of voice information processing method, device and electronic equipment

Technical field

The invention belongs to field of speech recognition, particularly relate to a kind of voice information processing method, device and electronic equipment.

Background technology

Along with the progress of electronic technology, speech recognition technology is developed rapidly, wherein, voice stenography as a kind of emerging shorthand way, because it has the favor that conveniently advantage is subject to more and more user.

When user needs electronic equipment (as mobile phone etc.) to take down in short-hand its voice, by clicking the button etc. arranged on mobile phone, activating microphone and starting to carry out typing to the voice of user, and immediately these voice being identified, speech conversion is become word.

In prior art, in this voice stenography process, be by the CPU(Central Processing Unit of mobile phone, central processing unit) control the process of recording and conversion, and CPU converts the speech into word immediately.

In some use scenes, do not need at any time the voice messaging of typing to be changed immediately, and in this case, still the mode of instant conversion is adopted in prior art, then need wake up process device at any time, make the waste that the power consumption of mobile phone is meaningless, cause the cruising time of mobile phone short, affect Consumer's Experience.

Summary of the invention

In view of this, the object of the present invention is to provide a kind of voice information processing method, to solve in prior art, the voice of all typings are changed immediately, cause the technical problem that mobile telephone power consumption is high.

A kind of voice information processing method, described method is applied to an electronic equipment, and described electronic equipment comprises voice collecting unit and the first processing unit, and described method comprises:

Obtain the voice messaging that described voice collecting unit gathers;

Identify that described voice messaging obtains voice identification result;

When institute's speech recognition result shows to comprise the first default command information in described voice messaging, from current time, record is carried out to the voice messaging gathered;

When described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Above-mentioned method, preferably, also comprises:

The running status of described first processing unit of real-time detection;

When detecting that described first processing unit switches to wake-up states by resting state, the described voice messaging of record being sent to the first processing unit and changing, being converted to Word message to make described first processing unit according to described voice messaging.

Above-mentioned method, preferably, when institute's speech recognition result shows to comprise the first default command information in described voice messaging, after recording, also comprises from current time to the voice messaging gathered:

Judge whether the recording status of described voice messaging meets and preset wake-up condition;

If met, generate wake-up signal and be sent to described first processing unit.

Above-mentioned method, preferably, whether the described recording status judging described voice messaging meets is preset wake-up condition and comprises:

Detect axle writing time of described voice messaging, judge whether length writing time of described voice messaging is greater than preset time threshold, if be greater than, met and preset wake-up condition.

Above-mentioned method, preferably, whether the described recording status judging described voice messaging meets is preset wake-up condition and comprises:

The memory space taken of voice messaging described in detection record, judges whether described memory space is greater than pre-set space threshold value, if be greater than, met and presets wake-up condition.

Above-mentioned method, preferably, described electronic equipment is also provided with Tip element, described in detect that described first processing unit switches to wake-up states by resting state after, the described described voice messaging by record is sent to before described first processing unit changes, and also comprises:

Generate inquiry message and be sent to described Tip element, whether described inquiry message is converted to Word message by the voice messaging of record for pointing out user;

When the feedback information of user being detected, judge whether described feedback information meets and confirm switch condition;

If met, perform the described described voice messaging by record and be sent to the first processing unit and carry out switch process.

A kind of speech information processing apparatus, described application of installation is in an electronic equipment, and described electronic equipment comprises voice collecting unit and the first processing unit, and described device comprises:

Acquiring unit, for obtaining the voice messaging that described voice collecting unit gathers;

Recognition unit, for identifying that described voice messaging obtains voice identification result;

Record cell, during for showing to comprise the first default command information in described voice messaging when institute's speech recognition result, carries out record to the voice messaging gathered from current time;

First wakeup unit, during for showing to comprise the second default command information in described voice messaging when described speech processes result, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Above-mentioned device, preferably, also comprises:

First detecting unit, for detecting the running status of described first processing unit in real time;

Notification unit, for when detecting that described first processing unit switches to wake-up states by resting state, notify that the described voice messaging of record is sent to the first processing unit and changes by described record cell, be converted to Word message to make described first processing unit according to described voice messaging.

Above-mentioned device, preferably, also comprises:

First judging unit, presets wake-up condition for judging whether the recording status of the described voice messaging of described record cell meets;

Second wakeup unit, when the recording status for the described voice messaging when described record cell meets default wake-up condition, generates wake-up signal and is sent to described first processing unit.

Above-mentioned device, preferably, described first judging unit comprises:

First detection sub-unit, for detecting axle writing time of described voice messaging;

First judgment sub-unit, for judging whether length writing time of described voice messaging is greater than preset time threshold according to axle described writing time, if being greater than, meeting and presetting wake-up condition and trigger the second wakeup unit.

Above-mentioned device, preferably, described first judging unit comprises:

Second detection sub-unit, for the memory space taken of voice messaging described in detection record;

Second judgment sub-unit, for judging whether the memory space taken of described voice messaging is greater than pre-set space threshold value, if being greater than, meeting default wake-up condition and triggering the second wakeup unit.

Above-mentioned device, preferably, described electronic equipment is also provided with Tip element, and described device also comprises:

Inquiry unit, is sent to described Tip element for generating inquiry message, and whether described inquiry message is converted to Word message by the voice messaging of record for pointing out user;

Second detecting unit, for detecting the feedback information of user;

Second judging unit, confirms switch condition for judging whether described feedback information meets;

If met, trigger described notification unit.

A kind of electronic equipment, comprising: the first processing unit, voice collecting unit and the speech information processing apparatus as described in above-mentioned any one.

A kind of voice information processing method provided by the invention, be applied to an electronic equipment, when not needing its voice messaging to be converted to immediately Word message, user starts to carry out voice messaging collection by the Voice command electronic equipment including the first default command information, an electronic equipment recording voice message and not changing, first processing unit does not need to perform speech conversion and becomes the action of word, reduce the first processing unit due to converting speech be the power consumption that word occurs.When its voice messaging is converted to Word message by needs immediately, user starts to carry out voice messaging collection by the Voice command electronic equipment including the second default command information and wakes the first processing unit up to carry out voice record and conversion, ensure that user is converted to the demand of word immediately for voice.In this method, whether wake the voice messaging of the first processing unit to this collection up and change, controlled, and need not change the voice messaging of all collections by the voice messaging of user, powder consumption of electronic equipment reduces, and cruising time extends, and improves Consumer's Experience.

Accompanying drawing explanation

In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.

Fig. 1 is the flow chart of a kind of voice information processing method embodiment 1 that the application provides;

Fig. 2 is the flow chart of a kind of voice information processing method embodiment 2 that the application provides;

Fig. 3 is the flow chart of a kind of voice information processing method embodiment 3 that the application provides;

Fig. 4 is the flow chart of a kind of voice information processing method embodiment 4 that the application provides;

Fig. 5 is the flow chart of a kind of voice information processing method embodiment 5 that the application provides;

Fig. 6 is the flow chart of a kind of voice information processing method embodiment 6 that the application provides;

Fig. 7 is the structural representation of a kind of speech information processing apparatus embodiment 1 that the application provides;

Fig. 8 is the structural representation of a kind of speech information processing apparatus embodiment 2 that the application provides;

Fig. 9 is the structural representation of a kind of speech information processing apparatus embodiment 3 that the application provides;

Figure 10 is the structural representation of a kind of speech information processing apparatus embodiment 4 that the application provides;

Figure 11 is the structural representation of a kind of speech information processing apparatus embodiment 5 that the application provides;

Figure 12 is the structural representation of a kind of speech information processing apparatus embodiment 6 that the application provides.

Embodiment

For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.

In order to more specifically emphasize the independence implemented, this specification relates to many unit or unit.For example, unit or unit can be realized by hardware circuit, and this hardware circuit comprises special VLSI circuit or gate array, such as logic chip, transistor, or other assembly.Unit or unit also can realize in programmable computer hardware, such as field effect programmable gate array, programmable logic array, programmable logic device etc.

Unit or unit also can realize in by the software performed by various forms of processor.Such as, computer instruction block that is that an executable code unit can comprise one or more entity or logic, this block may be formed as, such as, object, program or function.But the performed part of discriminating unit or unit does not need physically to put together, but can be made up of the different instruction being stored in diverse location, when combining in logic, forming unit or unit and the object reached required by this unit or unit.

In fact, executable code unit or unit can be a single instruction or multiple instruction, even can be distributed in the several different code section being arranged in different programs, and across several memory device.Similarly, operating data by identification and can be shown in this element or unit, and can implement in any suitable form and in any suitable data structure form inner tissue.Operating data can assemble single data set, maybe can be distributed in the different position with different memory devices, and is only present in a system or network in electronic signal mode at least in part.

" embodiment " mentioned by this specification or similar term represent characteristic, structure or the feature relevant with embodiment, are included at least one embodiment of the present invention.Therefore, this specification occur term " in one embodiment ", " in an embodiment " and similar term may but inevitablely all point to identical embodiment.

Moreover characteristic of the present invention, structure or feature can combine in one or more embodiments by any way.Below illustrate and will provide many specific details, the examples such as such as programming, software unit, user's selection, network trading, data base querying, database structure, hardware cell, hardware circuit, hardware chip, to provide the understanding to the embodiment of the present invention.But those of ordinary skill in the related art will find out the present invention, even without utilizing wherein one or more specific detail, or utilize other method, assembly, material etc. also can implement.On the other hand, be the present invention that avoids confusion, known structure, material or operation are not described in detail.

The flow chart of a kind of voice information processing method embodiment 1 that the application as shown in Figure 1 provides, described method can be applied to an electronic equipment, described electronic equipment can be the electronic equipments such as desktop computer, notebook, panel computer, mobile phone, intelligent television, intelligent watch, Wearable, and described electronic equipment comprises voice collecting unit and the first processing unit.This voice collecting unit is used for gathering the voice messaging in the external environment of electronic equipment, the voice that the voice messaging in this application in this external environment especially uses the user of this electronic equipment to send.First processing unit is used for being converted to Word message according to the control of user to the voice messaging received.

The method can adopt following steps to realize:

Step S101: obtain the voice messaging that described voice collecting unit gathers;

Wherein, this voice messaging is the voice that user sends.

Wherein, this voice collecting unit can be Real-time Collection voice messaging, and namely this voice collecting unit keeps operating state, and the voice that user in real sends.

Wherein, this voice messaging can be various language, as Chinese, English, French etc., also can be two kinds even voice messaging of multiple voice mixing.

Step S102: identify that described voice messaging obtains voice identification result;

Wherein, this voice messaging is identified, obtains voice identification result.

Wherein, this recognition result is preliminary identification, and better simply speech recognition engine can be adopted to identify, and according to the result that this identification obtains, and whether judge further in this voice messaging containing the first command information or the second command information.

In actual enforcement, also can directly this first command information or voice messaging corresponding to the second command information be mated with the voice messaging of this voice collecting unit collection, when the matching degree of the two meets default matching rate, the two can be considered as identical, in the voice messaging that namely described collecting unit gathers, contain this first command information or the second command information.

Step S103: when institute's speech recognition result shows to comprise the first default command information in described voice messaging, carries out record to the voice messaging gathered from current time;

Wherein, this first command information is beginning recording voice message, but without the need to being immediately converted to word content.

Concrete, this first command information for comprising the information such as " recording ", " promptly recording ", but can be not limited to this.

Concrete, when containing the first command information preset in this voice messaging, responding this first command information, from current time, record being carried out to the voice messaging of collecting unit collection.

Wherein, the position of this record can be the storage card in electronic equipment, or in flash memories flash.

Step S104: when described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message.

Wherein, the priority level of described second command information higher than described first command information, when showing in this speech processes result, not only comprised the first command information but also containing the second command information time, respond this second command information, generate wake-up signal.

Wherein, this second command information is start to record and the command information of converting speech information.

Concrete, this second command information for comprising the information such as " recording conversion ", " starting conversion ", but can be not limited to this.

Wherein, when including the second command information in this voice messaging, generate wake-up signal, and be sent to the first processing unit, after receiving this wake-up signal, switch to wake-up states with this first processing unit made, and the voice messaging of the voice collecting unit collection that current time starts is recorded and is converted to Word message.

It should be noted that, this wake-up signal be wake up the first processing unit enter record and converting speech information be the state of Word message, i.e. wake-up states.

Wherein, the resting state corresponding with this wake-up states, any operation can not carried out for this first processing unit, be in real resting state, other operations can be carried out for this first processing unit, but not carrying out recording also converting speech information is the operation of Word message, is in " resting state " changed for this voice messaging.

It should be noted that, when this first processing unit changes this voice messaging into Word message, this switching motion can be performed by this first processing unit, also this voice messaging can be uploaded in the Cloud Server be connected with this electronic equipment and change.

Wherein, when this voice messaging upload to change in Cloud Server time, be also provided with network element in this electronic equipment, by this network element, voice messaging uploaded in Cloud Server, and received the Word message be converted to by this network element, and in the electronic device user is shown.

A kind of voice information processing method that the present embodiment provides, when not needing its voice messaging to be converted to immediately Word message, user starts to carry out voice messaging collection by the Voice command electronic equipment including the first default command information, an electronic equipment recording voice message and not changing, first processing unit does not need to perform speech conversion and becomes the action of word, reduce the first processing unit due to converting speech be the power consumption that word occurs.When its voice messaging is converted to Word message by needs immediately, user starts to carry out voice messaging collection by the Voice command electronic equipment including the second default command information and wakes the first processing unit up to carry out voice record and conversion, ensure that user is converted to the demand of word immediately for voice.In this method, whether wake the voice messaging of the first processing unit to this collection up and change, controlled, and need not change the voice messaging of all collections by the voice messaging of user, powder consumption of electronic equipment reduces, and cruising time extends, and improves Consumer's Experience.

When this first processing unit is under other impacts operated, when switching to wake-up states by resting state, the voice messaging of record is changed.

The flow chart of a kind of voice information processing method embodiment 2 that the application as shown in Figure 2 provides, the method comprises the steps:

Step S201: obtain the voice messaging that described voice collecting unit gathers;

Step S202: identify that described voice messaging obtains voice identification result;

Step S203: when institute's speech recognition result shows to comprise the first default command information in described voice messaging, carries out record to the voice messaging gathered from current time;

Wherein, step S201-203 is consistent with the step S101-103 in embodiment 1, repeats no more in the present embodiment.

Step S204: the running status detecting described first processing unit in real time;

Wherein, during execution step S201-203, this first processing unit is in resting state, and when being in this resting state, this first processing unit does not carry out any operation.

Wherein, while starting to record the voice messaging gathered, detect the running status of this first processing unit in real time, the running status of this first processing unit is resting state.

Concrete, whether the data-interface by detecting this first processing unit has transfer of data to judge, if there is no transfer of data, then determine that this first processing unit is in resting state, when there is transfer of data in this data-interface, then can determine that this first processing unit switches to wake-up states by resting state.

In actual enforcement, when detecting the running status of this first processing unit, also the operating file detecting this first processing unit can be adopted, obtain the method for the process run time parameter in described operating file, judge can the running status of electronic equipment whether be just resting state according to the process run time parameter in this operating file, and determine according to this process run time parameter the time switching to wake-up states.

In actual enforcement, also can judge running status according to the voltage of this first processing unit, when this first processing unit is in resting state, its magnitude of voltage is in first voltage range, when the first processing unit is in wake-up states, its magnitude of voltage is in the second voltage range, and this second voltage range values is higher than the value of this first voltage range.

It should be noted that, this first processing unit switches to the condition of wake-up states to be that user operation makes this first processing unit bring into operation and executable operations by resting state.

Step S205: when detecting that described first processing unit switches to wake-up states by resting state, the described voice messaging of record is sent to the first processing unit change, is converted to Word message to make described first processing unit according to described voice messaging;

Wherein, when detecting that this first processing unit switches to wake-up states by resting state, this first processing unit starts normal operation, now, the voice messaging of record is sent in this first processing unit, to make this first processing unit, Word message is converted to this voice messaging.

Wherein, in this voicemail logging storage card in the electronic device or flash, from this memory location, voice messaging can be obtained, and be sent in the first processing unit and change.

In actual enforcement, also the recording address of this voice messaging can be sent to the first processing unit, indicate this first processing unit to obtain voice messaging according to this recording address from memory location, do not limit in the present embodiment.

Step S206: when described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message.

Wherein, the priority level of described second command information is higher than described first command information.

Wherein, step S206 is consistent with the step S104 in embodiment 1, repeats no more in the present embodiment.

It should be noted that, when this first processing unit changes this voice messaging into Word message, this switching motion can be performed by this first processing unit, also this voice messaging can be uploaded in the Cloud Server be connected with this electronic equipment and change.

Wherein, when this voice messaging upload to change in Cloud Server time, be also provided with network element in this electronic equipment, by this network element, voice messaging uploaded in Cloud Server, and received the Word message be converted to by this network element, and user is shown.

In the present embodiment, when entering wake-up states under the impact of the first processing unit in other factors, the voice messaging of record is sent to this first processing unit, just conversion is proceeded by this first processing unit, voice messaging is converted to Word message, make the voice messaging recorded also can be converted to Word message to store, while reducing powder consumption of electronic equipment, also ensure that the integrity degree that voice messaging is changed.

As shown in Figure 3, the flow chart of a kind of voice information processing method embodiment 3 that the application provides, the method realizes by following steps, comprising:

Step S301: obtain the voice messaging that described voice collecting unit gathers;

Step S302: identify that described voice messaging obtains voice identification result;

Step S303: when institute's speech recognition result shows to comprise the first default command information in described voice messaging, carries out record to the voice messaging gathered from current time;

Wherein, step S301-303 is consistent with the step S101-103 in embodiment 1, repeats no more in the present embodiment.

Step S304: judge whether the recording status of described voice messaging meets and preset wake-up condition; If met, generate wake-up signal and be sent to described first processing unit;

Wherein, this recording status comprises: writing time length, record data volume or record the space that this voice messaging takies.

Wherein, when the recording status of this voice messaging meets default wake-up condition, then generate wake-up signal and be sent to the first processing unit, switch to wake-up states with this first processing unit made according to this wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message.

It should be noted that, the voice messaging recorded in memory location is deleted, for record next time provides memory space.

Step S305: when described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Wherein, step S305 is consistent with the step S104 in embodiment 1, repeats no more in the present embodiment.

Wherein, judge whether the recording status of this voice messaging meets the wake-up condition preset and realize by various ways.

See the flow chart of a kind of voice information processing method embodiment 4 that the application shown in Fig. 4 provides, comprising:

Step S401: obtain the voice messaging that described voice collecting unit gathers;

Step S402: identify that described voice messaging obtains voice identification result;

Step S403: when institute's speech recognition result shows to comprise the first default command information in described voice messaging, carries out record to the voice messaging gathered from current time;

Wherein, step S401-403 is consistent with the step S101-103 in embodiment 1, repeats no more in the present embodiment.

Step S404: axle writing time detecting described voice messaging, judges whether length writing time of described voice messaging is greater than preset time threshold, if be greater than, met and presets wake-up condition, generates wake-up signal and is sent to described first processing unit;

Wherein, in the present embodiment, this wake-up condition preset is: length writing time of voice messaging is greater than default time threshold.

Wherein, the time span of this voice messaging is that the time shaft detecting this voicemail logging obtains, specifically, when recording this voice messaging, its time shaft synchronously changes growth, when the time that this time shaft represents meets default time threshold, then generate wake-up signal and be sent to the first processing unit to wake this first processing unit up.

It should be noted that, because in an electronic equipment, the form of recording voice message is default form, each record adopts identical form.The memory space that the voice messaging recording this form within the unit interval takies is fixed value, then according to obtaining recording the space size shared by this voice messaging the writing time of voice messaging.

Wherein, this time threshold preset correspond to the upper limit size in the space size of storage area in this electronic equipment or storage area.

Step S405: when described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Wherein, step S405 is consistent with the step S104 in embodiment 1, repeats no more in the present embodiment.

Wherein, judge whether the recording status of this voice messaging meets the wake-up condition preset and realize by various ways.

See the flow chart of a kind of voice information processing method embodiment 5 that the application shown in Fig. 5 provides, comprising:

Step S501: obtain the voice messaging that described voice collecting unit gathers;

Step S502: identify that described voice messaging obtains voice identification result;

Step S503: when institute's speech recognition result shows to comprise the first default command information in described voice messaging, carries out record to the voice messaging gathered from current time;

Wherein, step S501-503 is consistent with the step S101-103 in embodiment 1, repeats no more in the present embodiment.

Step S504: the memory space taken of voice messaging described in detection record, judges whether described memory space is greater than pre-set space threshold value, if be greater than, met and presets wake-up condition, generates wake-up signal and is sent to described first processing unit;

Wherein, in the present embodiment, this wake-up condition preset is: the memory space taken recording described voice messaging is greater than default capacity-threshold.

Wherein, when detecting that recording memory space that this voice messaging takies is greater than default time threshold, then generate wake-up signal and be sent to the first processing unit to wake this first processing unit up.

Wherein, this capacity-threshold preset correspond to the upper limit size in the space size of storage area in this electronic equipment or storage area.

When the memory space that recording voice message takies is greater than the higher limit of this storage area, needs that the voice messaging of this record is converted to Word message and store, with the space that this voice messaging is taken release, for record next time provides memory space.

Step S505: when described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Wherein, step S505 is consistent with the step S104 in embodiment 1, repeats no more in the present embodiment.

Wherein, in this electronic equipment, be also provided with Tip element, for showing inquiry message, to inquire whether user changes the voice messaging of record.

See the flow chart of a kind of voice information processing method embodiment 6 that the application shown in Fig. 6 provides, comprising:

Step S601: obtain the voice messaging that described voice collecting unit gathers;

Step S602: identify that described voice messaging obtains voice identification result;

Step S603: when institute's speech recognition result shows to comprise the first default command information in described voice messaging, carries out record to the voice messaging gathered from current time;

Step S604: the running status detecting described first processing unit in real time;

Wherein, step S601-604 is consistent with the step S201-204 in embodiment 2, repeats no more in the present embodiment.

Step S605: when detecting that described first processing unit switches to wake-up states by resting state, generate inquiry message and be sent to described Tip element, whether described inquiry message is converted to Word message by the voice messaging of record for pointing out user;

Wherein, during due to the voice messaging of record is converted to Word message, need to take this first processing unit, and when this first processing unit is switched to wake-up states by resting state, if it has other processes, and the urgency level of this process is higher than this voice messaging of conversion, then need first to process this process, and then change this voice messaging.

So, when detecting that the first processing unit switches to wake-up states by resting state, generating inquiry message, whether immediately the voice messaging of this record being converted to Word message with the demand estimation according to user.

Concrete, the mode of this inquiry message prompting can be show at the display unit of this electronic equipment, as " whether changing the voice messaging of record at once into Word message? " and corresponding option "Yes" and "No" etc.

Step S606: when the feedback information of user being detected, judges whether described feedback information meets and confirms switch condition; If met, perform step S607;

Wherein, this feedback information refers to the information that the feedback operation of user generates, and the feedback operation of user realizes by various ways.

Such as, when being provided with touch-screen in this electronic equipment, show the option tab of this inquiry message and correspondence thereof on the touchscreen, user selects an option tab in this touch-screen, the operation of this selection is as the input operation of user feedback, and electronic equipment receives the input operation of this user feedback by this touch-screen;

Such as, when adopting keyboard in this electronic equipment, the multiple matching results shown on the display screen, user selectes a selection key according to the operation at this keyboard, the operation should selected by keyboard also can be used as the input operation of user feedback, and electronic equipment receives the input operation of this user feedback by this key area;

Or when adopting mouse to select in this electronic equipment, the selection key adopting mouse to show on the display screen is selected, a selected selection key, the operation that this mouse is selected also can be used as the input operation of user feedback;

Or, user is selected by Voice command, as user inputs the voice signal of "Yes", makes electronic equipment obtain this voice signal, and identification is carried out to this voice signal draw and select "Yes" as feedback information, the input operation of user feedback also should be can be used as by the operation of voice selecting.

It should be noted that, when the feedback information received does not meet confirmation switch condition, then do not perform step S607, in concrete enforcement, also can generate the inquiry message whether retaining this voicemail logging, and according to the information of user feedback, perform and delete accordingly or retain this voice messaging.

Step S607: when described feedback information meets confirmation switch condition, the described voice messaging of record is sent to the first processing unit and changes, be converted to Word message to make described first processing unit according to described voice messaging;

Step S608: when described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Wherein, step S607-608 is consistent with the step S205-206 in embodiment 1, repeats no more in the present embodiment.

Corresponding with a kind of voice information processing method embodiment that above-mentioned the application provides, present invention also provides a kind of embodiment of speech information processing apparatus.

The structural representation of a kind of speech information processing apparatus embodiment 1 that the application as shown in Figure 7 provides, described device can be applied to an electronic equipment, described electronic equipment can be the electronic equipments such as desktop computer, notebook, panel computer, mobile phone, intelligent television, intelligent watch, Wearable, and described electronic equipment comprises voice collecting unit and the first processing unit.This voice collecting unit is used for gathering the voice messaging in the external environment of electronic equipment, the voice that the voice messaging in this application in this external environment especially uses the user of this electronic equipment to send.First processing unit is used for being converted to Word message according to the control of user to the voice messaging received.

This device can comprise: acquiring unit 701, recognition unit 702, record cell 703 and the first wakeup unit 704;

Acquiring unit 701, for obtaining the voice messaging that described voice collecting unit gathers;

Wherein, this voice messaging is the voice that user sends.

Wherein, voice collecting unit can be Real-time Collection voice messaging, and namely this voice collecting unit keeps operating state, and the voice that user in real sends, this acquiring unit 701 synchronously obtains the voice messaging that this voice collecting unit gathers.

Wherein, this voice messaging can be various language, as Chinese, English, French etc., also can be two kinds even voice messaging of multiple voice mixing.

Recognition unit 702, for identifying that described voice messaging obtains voice identification result;

Wherein, recognition unit 702 identifies this voice messaging, obtains voice identification result.

Wherein, this recognition result is preliminary identification, and better simply speech recognition engine can be adopted to identify, and according to the result that this identification obtains, and whether judge further in this voice messaging containing the first command information or the second command information.

In actual enforcement, also can directly this first command information or voice messaging corresponding to the second command information be mated with the voice messaging of this voice collecting unit collection, when the matching degree of the two meets default matching rate, the two can be considered as identical, in the voice messaging that namely described collecting unit gathers, contain this first command information or the second command information.

Record cell 703, during for showing to comprise the first default command information in described voice messaging when institute's speech recognition result, carries out record to the voice messaging gathered from current time;

Wherein, this first command information is beginning recording voice message, but without the need to being immediately converted to word content.

Concrete, this first command information for comprising the information such as " recording ", " promptly recording ", but can be not limited to this.

Concrete, when record cell 703 identification obtains containing the first command information preset in this voice messaging, respond this first command information, electronic equipment carries out record to the voice messaging of voice collecting unit collection from current time.

Wherein, the position of this record can be the storage card in electronic equipment, or in flash memories flash.

First wakeup unit 704, during for showing to comprise the second default command information in described voice messaging when described speech processes result, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

Wherein, the priority level of described second command information higher than described first command information, when showing in this speech processes result, not only comprised the first command information but also containing the second command information time, respond this second command information, generate wake-up signal.

Wherein, this second command information is start to record and the command information of converting speech information.

Concrete, this second command information for comprising the information such as " recording conversion ", " starting conversion ", but can be not limited to this.

Wherein, when including the second command information in this voice messaging, first wakeup unit 704 generates wake-up signal, and be sent to the first processing unit, after receiving this wake-up signal, switch to wake-up states with this first processing unit made, and the voice messaging of the voice collecting unit collection that current time starts is recorded and is converted to Word message.

It should be noted that, this wake-up signal be wake up the first processing unit enter record and converting speech information be the state of Word message, i.e. wake-up states.

Wherein, the resting state corresponding with this wake-up states, any operation can not carried out for this first processing unit, be in real resting state, other operations can be carried out for this first processing unit, but not carrying out recording also converting speech information is the operation of Word message, is in " resting state " changed for this voice messaging.

It should be noted that, when this first processing unit changes this voice messaging into Word message, this switching motion can be performed by this first processing unit, also this voice messaging can be uploaded in the Cloud Server be connected with this electronic equipment and change.

Wherein, when this voice messaging upload to change in Cloud Server time, be also provided with network element in this electronic equipment, by this network element, voice messaging uploaded in Cloud Server, and received the Word message be converted to by this network element, and in the electronic device user is shown.

A kind of speech information processing apparatus that the present embodiment provides, when not needing its voice messaging to be converted to immediately Word message, user starts to carry out voice messaging collection by the Voice command electronic equipment including the first default command information, an electronic equipment recording voice message and not changing, first processing unit does not need to perform speech conversion and becomes the action of word, reduce the first processing unit due to converting speech be the power consumption that word occurs.When its voice messaging is converted to Word message by needs immediately, user starts to carry out voice messaging collection by the Voice command electronic equipment including the second default command information and wakes the first processing unit up to carry out voice record and conversion, ensure that user is converted to the demand of word immediately for voice.In this device, whether wake the voice messaging of the first processing unit to this collection up and change, controlled, and need not change the voice messaging of all collections by the voice messaging of user, powder consumption of electronic equipment reduces, and cruising time extends, and improves Consumer's Experience.

When this first processing unit is under other impacts operated, when switching to wake-up states by resting state, the voice messaging of record is changed.

The structural representation of a kind of speech information processing apparatus embodiment 2 that the application as shown in Figure 8 provides, this device comprises:

Acquiring unit 801, recognition unit 802, record cell 803, first detecting unit 804, notification unit 805 and the first wakeup unit 806;

Wherein, this acquiring unit 801, recognition unit 802, record cell 803 are consistent with the function of corresponding construction in embodiment 1 with the function of the first wakeup unit 806, repeat no more in the present embodiment.

First detecting unit 804, for detecting the running status of described first processing unit in real time;

Wherein, when acquiring unit 801, recognition unit 802, record cell 803 and the first wakeup unit 806 executable operations, this first processing unit is in resting state, and when being in this resting state, this first processing unit does not carry out any operation.

Wherein, while record cell 803 starts to record the voice messaging gathered, the first detecting unit 804 detects the running status of this first processing unit in real time, and the running status of this first processing unit is resting state.

Concrete, whether the data-interface by detecting this first processing unit has transfer of data to judge, if there is no transfer of data, then determine that this first processing unit is in resting state, when there is transfer of data in this data-interface, then can determine that this first processing unit switches to wake-up states by resting state.

In actual enforcement, when detecting the running status of this first processing unit, also the operating file detecting this first processing unit can be adopted, obtain the method for the process run time parameter in described operating file, judge can the running status of electronic equipment whether be just resting state according to the process run time parameter in this operating file, and determine according to this process run time parameter the time switching to wake-up states.

In actual enforcement, also can judge running status according to the voltage of this first processing unit, when this first processing unit is in resting state, its magnitude of voltage is in first voltage range, when the first processing unit is in wake-up states, its magnitude of voltage is in the second voltage range, and this second voltage range values is higher than the value of this first voltage range.

It should be noted that, this first processing unit switches to the condition of wake-up states to be that user operation makes this first processing unit bring into operation and executable operations by resting state.

Notification unit 805, for when detecting that described first processing unit switches to wake-up states by resting state, notify that the described voice messaging of record is sent to the first processing unit and changes by described record cell, be converted to Word message to make described first processing unit according to described voice messaging.

Wherein, when detecting that this first processing unit switches to wake-up states by resting state, this first processing unit starts normal operation, now, notification unit 805 notifies that the voice messaging of record is sent in this first processing unit by this record cell 803, is converted to Word message to make this first processing unit to this voice messaging.

Wherein, in this voicemail logging storage card in the electronic device or flash, from this memory location, voice messaging can be obtained, and be sent in the first processing unit and change.

In actual enforcement, also the recording address of this voice messaging can be sent to the first processing unit, indicate this first processing unit to obtain voice messaging according to this recording address from memory location, do not limit in the present embodiment.

It should be noted that, when this first processing unit changes this voice messaging into Word message, this switching motion can be performed by this first processing unit, also this voice messaging can be uploaded in the Cloud Server be connected with this electronic equipment and change.

Wherein, when this voice messaging upload to change in Cloud Server time, be also provided with network element in this electronic equipment, by this network element, voice messaging uploaded in Cloud Server, and received the Word message be converted to by this network element, and user is shown.

In the present embodiment, when entering wake-up states under the impact of the first processing unit in other factors, the voice messaging of record is sent to this first processing unit, just conversion is proceeded by this first processing unit, voice messaging is converted to Word message, make the voice messaging recorded also can be converted to Word message to store, while reducing powder consumption of electronic equipment, also ensure that the integrity degree that voice messaging is changed.

The structural representation of a kind of speech information processing apparatus embodiment 3 that the application shown in Figure 9 provides, this device comprises: acquiring unit 901, recognition unit 902, record cell 903, first judging unit 904, second wakeup unit 905 and the first wakeup unit 906;

Wherein, this acquiring unit 901, recognition unit 902, record cell 903 are consistent with the function of corresponding construction in embodiment 1 with the function of the first wakeup unit 906, repeat no more in the present embodiment.

First judging unit 904, presets wake-up condition for judging whether the recording status of the described voice messaging of described record cell meets;

Second wakeup unit 905, when the recording status for the described voice messaging when described record cell meets default wake-up condition, generates wake-up signal and is sent to described first processing unit.

Wherein, this recording status comprises: writing time length, record data volume or record the space that this voice messaging takies.

Wherein, when the first judging unit 904 judges that the recording status of this voice messaging meets default wake-up condition, then the second wakeup unit 905 generates wake-up signal and is sent to the first processing unit, switch to wake-up states with this first processing unit made according to this wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message.

It should be noted that, the voice messaging recorded in memory location is deleted, for record next time provides memory space.

Wherein, judge whether the recording status of this voice messaging meets the wake-up condition preset and realize by various ways.

See the structural representation of a kind of speech information processing apparatus embodiment 4 that the application shown in Figure 10 provides, comprising: acquiring unit 1001, recognition unit 1002, record cell 1003, first judging unit 1004, second wakeup unit 1005 and the first wakeup unit 1006;

Wherein, this acquiring unit 1001, recognition unit 1002, record cell 1003, second wakeup unit 1005 are consistent with the function of corresponding construction in embodiment 3 with the function of the first wakeup unit 1006, repeat no more in the present embodiment.

Wherein, this first judging unit 1004 comprises: the first detection sub-unit 1007 and the first judgment sub-unit 1008.

First detection sub-unit 1007, for detecting axle writing time of described voice messaging;

First judgment sub-unit 1008, for judging whether length writing time of described voice messaging is greater than preset time threshold according to axle described writing time, if being greater than, meeting and presetting wake-up condition and trigger the second wakeup unit.

Wherein, in the present embodiment, this wake-up condition preset is: length writing time of voice messaging is greater than default time threshold.

Wherein, the time span of this voice messaging is that the time shaft that the first detection sub-unit 1007 detects this voicemail logging obtains, specifically, when recording this voice messaging, its time shaft synchronously changes growth, when the time that the first judgment sub-unit 1008 judges to obtain the representative of this time shaft meets default time threshold, then generate wake-up signal and be sent to the first processing unit to wake this first processing unit up.

It should be noted that, because in an electronic equipment, the form of recording voice message is default form, each record adopts identical form.The memory space that the voice messaging recording this form within the unit interval takies is fixed value, then according to obtaining recording the space size shared by this voice messaging the writing time of voice messaging.

Wherein, this time threshold preset correspond to the upper limit size in the space size of storage area in this electronic equipment or storage area.

Wherein, judge whether the recording status of this voice messaging meets the wake-up condition preset and realize by various ways.

See the structural representation of a kind of speech information processing apparatus embodiment 5 that the application shown in Figure 11 provides, comprising: acquiring unit 1101, recognition unit 1102, record cell 1103, first judging unit 1104, second wakeup unit 1105 and the first wakeup unit 1106;

Wherein, this acquiring unit 1101, recognition unit 1102, record cell 1103, second wakeup unit 1105 are consistent with the function of corresponding construction in embodiment 3 with the function of the first wakeup unit 1106, repeat no more in the present embodiment.

Wherein, this first judging unit 1104 comprises: the second detection sub-unit 1107 and the second judgment sub-unit 1108.

Second detection sub-unit 1107, for the memory space taken of voice messaging described in detection record;

Second judgment sub-unit 1108, for judging whether the memory space taken of described voice messaging is greater than pre-set space threshold value, if being greater than, meeting default wake-up condition and triggering the second wakeup unit.

Wherein, in the present embodiment, this wake-up condition preset is: the memory space taken recording described voice messaging is greater than default capacity-threshold.

Wherein, the memory space that second this voice messaging of detection sub-unit 1107 detection record takies, when the second judgment sub-unit 1108 judges that the memory space that this takies is greater than default time threshold, then generate wake-up signal and be sent to the first processing unit to wake this first processing unit up.

Wherein, this capacity-threshold preset correspond to the upper limit size in the space size of storage area in this electronic equipment or storage area.

When the memory space that recording voice message takies is greater than the higher limit of this storage area, needs that the voice messaging of this record is converted to Word message and store, with the space that this voice messaging is taken release, for record next time provides memory space.

Wherein, in this electronic equipment, be also provided with Tip element, for showing inquiry message, to inquire whether user changes the voice messaging of record.

See a kind of speech information processing apparatus embodiment 6 structural representation that the application shown in Figure 12 provides, comprising: acquiring unit 1201, recognition unit 1202, record cell 1203, first detecting unit 1204, inquiry unit 1205, second detecting unit 1206, second judging unit 1207, notification unit 1208 and the first wakeup unit 1209;

Wherein, this acquiring unit 1201, recognition unit 1202, record cell 1203, first detecting unit 1204 are consistent with the function of corresponding construction in embodiment 2 with the function of the first wakeup unit 1209, repeat no more in the present embodiment.

Inquiry unit 1205, for when detecting that described first processing unit switches to wake-up states by resting state, generate inquiry message and be sent to described Tip element, whether described inquiry message is converted to Word message by the voice messaging of record for pointing out user;

Wherein, during due to the voice messaging of record is converted to Word message, need to take this first processing unit, and when this first processing unit is switched to wake-up states by resting state, if it has other processes, and the urgency level of this process is higher than this voice messaging of conversion, then need first to process this process, and then change this voice messaging.

So when detection first detecting unit 1204 to the first processing unit is switched to wake-up states by resting state, inquiry unit 1205 generates inquiry message, whether immediately the voice messaging of this record is converted to Word message with the demand estimation according to user.

Concrete, the mode of this inquiry message prompting can be show at the display unit of this electronic equipment, as " whether changing the voice messaging of record at once into Word message? " and corresponding option "Yes" and "No" etc.

Second detecting unit 1206, for detecting the feedback information of user;

Second judging unit 1207, confirms switch condition for judging whether described feedback information meets; If met, trigger described notification unit 1208.

Wherein, this second detecting unit 1206 detects the feedback information of user, and this feedback information refers to the information that the feedback operation of user generates, and the feedback operation of user realizes by various ways.

Such as, when being provided with touch-screen in this electronic equipment, show the option tab of this inquiry message and correspondence thereof on the touchscreen, user selects an option tab in this touch-screen, the operation of this selection is as the input operation of user feedback, and electronic equipment receives the input operation of this user feedback by this touch-screen;

Such as, when adopting keyboard in this electronic equipment, the multiple matching results shown on the display screen, user selectes a selection key according to the operation at this keyboard, the operation should selected by keyboard also can be used as the input operation of user feedback, and electronic equipment receives the input operation of this user feedback by this key area;

Or when adopting mouse to select in this electronic equipment, the selection key adopting mouse to show on the display screen is selected, a selected selection key, the operation that this mouse is selected also can be used as the input operation of user feedback;

Or, user is selected by Voice command, as user inputs the voice signal of "Yes", makes electronic equipment obtain this voice signal, and identification is carried out to this voice signal draw and select "Yes" as feedback information, the input operation of user feedback also should be can be used as by the operation of voice selecting.

It should be noted that, when the second judging unit 1207 judges that the feedback information received does not meet confirmation switch condition, then not trigger notice unit, in concrete enforcement, also can generate the inquiry message whether retaining this voicemail logging, and according to the information of user feedback, perform and delete accordingly or retain this voice messaging.

Additionally provide a kind of electronic equipment in the application, this electronic equipment comprises the first processing unit, voice collecting unit and as the speech information processing apparatus in above-mentioned any embodiment.

Wherein, this information processor comprises: acquiring unit, recognition unit, record cell and the first wakeup unit, the function of this each component units of information processor is consistent with the function of corresponding construction in above-mentioned a kind of information processor embodiment, repeats no more in the present embodiment.

Preferably, this information processor also comprises: detecting unit and notification unit, and the function of this each component units of information processor is consistent with the function of corresponding construction in above-mentioned a kind of information processor embodiment, repeats no more in the present embodiment.

Preferably, this information processor also comprises: the first judging unit and the second wakeup unit, and the function of this each component units of information processor is consistent with the function of corresponding construction in above-mentioned a kind of information processor embodiment, repeats no more in the present embodiment.

Preferably, first judging unit of this information processor comprises: the first detection sub-unit and the first judgment sub-unit, the function of each component units of this information processor, subelement is consistent with the function of corresponding construction in above-mentioned a kind of information processor embodiment, repeats no more in the present embodiment.

Preferably, first judging unit of this information processor comprises: the second detection sub-unit and the second judgment sub-unit, the function of each component units of this information processor, subelement is consistent with the function of corresponding construction in above-mentioned a kind of information processor embodiment, repeats no more in the present embodiment.

Preferably, this electronic equipment is also provided with Tip element, this information processor also comprises: inquiry unit, detecting unit and the second judging unit, the function of this each component units of information processor is consistent with the function of corresponding construction in above-mentioned a kind of information processor embodiment, repeats no more in the present embodiment.

The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.

Claims (13)

1. a voice information processing method, is characterized in that, described method is applied to an electronic equipment, and described electronic equipment comprises voice collecting unit and the first processing unit, and described method comprises:

Obtain the voice messaging that described voice collecting unit gathers;

Identify that described voice messaging obtains voice identification result;

When institute's speech recognition result shows to comprise the first default command information in described voice messaging, from current time, record is carried out to the voice messaging gathered;

When described speech processes result shows to comprise the second default command information in described voice messaging, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

2. method according to claim 1, is characterized in that, also comprises:

The running status of described first processing unit of real-time detection;

When detecting that described first processing unit switches to wake-up states by resting state, the described voice messaging of record being sent to the first processing unit and changing, being converted to Word message to make described first processing unit according to described voice messaging.

3. method according to claim 1, is characterized in that, when institute's speech recognition result shows to comprise the first default command information in described voice messaging, after recording, also comprises from current time to the voice messaging gathered:

Judge whether the recording status of described voice messaging meets and preset wake-up condition;

If met, generate wake-up signal and be sent to described first processing unit.

4. method according to claim 3, is characterized in that, whether the described recording status judging described voice messaging meets is preset wake-up condition and comprise:

Detect axle writing time of described voice messaging, judge whether length writing time of described voice messaging is greater than preset time threshold, if be greater than, met and preset wake-up condition.

5. method according to claim 3, is characterized in that, whether the described recording status judging described voice messaging meets is preset wake-up condition and comprise:

The memory space taken of voice messaging described in detection record, judges whether described memory space is greater than pre-set space threshold value, if be greater than, met and presets wake-up condition.

6. method according to claim 2, it is characterized in that, described electronic equipment is also provided with Tip element, described detect that described first processing unit switches to wake-up states by resting state after, the described described voice messaging by record is sent to before described first processing unit changes, and also comprises:

Generate inquiry message and be sent to described Tip element, whether described inquiry message is converted to Word message by the voice messaging of record for pointing out user;

When the feedback information of user being detected, judge whether described feedback information meets and confirm switch condition;

If met, perform the described described voice messaging by record and be sent to the first processing unit and carry out switch process.

7. a speech information processing apparatus, is characterized in that, described application of installation is in an electronic equipment, and described electronic equipment comprises voice collecting unit and the first processing unit, and described device comprises:

Acquiring unit, for obtaining the voice messaging that described voice collecting unit gathers;

Recognition unit, for identifying that described voice messaging obtains voice identification result;

Record cell, during for showing to comprise the first default command information in described voice messaging when institute's speech recognition result, carries out record to the voice messaging gathered from current time;

First wakeup unit, during for showing to comprise the second default command information in described voice messaging when described speech processes result, generate wake-up signal and be sent to described first processing unit, to make described first processing unit switch to wake-up states according to described wake-up signal, and from current time, the voice messaging gathered is recorded and is converted to Word message;

Wherein, the priority level of described second command information is higher than described first command information.

8. device according to claim 7, is characterized in that, also comprises:

First detecting unit, for detecting the running status of described first processing unit in real time;

Notification unit, for when detecting that described first processing unit switches to wake-up states by resting state, notify that the described voice messaging of record is sent to the first processing unit and changes by described record cell, be converted to Word message to make described first processing unit according to described voice messaging.

9. device according to claim 7, is characterized in that, also comprises:

First judging unit, presets wake-up condition for judging whether the recording status of the described voice messaging of described record cell meets;

Second wakeup unit, when the recording status for the described voice messaging when described record cell meets default wake-up condition, generates wake-up signal and is sent to described first processing unit.

10. device according to claim 9, is characterized in that, described first judging unit comprises:

First detection sub-unit, for detecting axle writing time of described voice messaging;

First judgment sub-unit, for judging whether length writing time of described voice messaging is greater than preset time threshold according to axle described writing time, if being greater than, meeting and presetting wake-up condition and trigger the second wakeup unit.

11. devices according to claim 9, is characterized in that, described first judging unit comprises:

Second detection sub-unit, for the memory space taken of voice messaging described in detection record;

Second judgment sub-unit, for judging whether the memory space taken of described voice messaging is greater than pre-set space threshold value, if being greater than, meeting default wake-up condition and triggering the second wakeup unit.

12. devices according to claim 8, it is characterized in that, described electronic equipment is also provided with Tip element, described device also comprises:

Inquiry unit, is sent to described Tip element for generating inquiry message, and whether described inquiry message is converted to Word message by the voice messaging of record for pointing out user;

Second detecting unit, for detecting the feedback information of user;

Second judging unit, confirms switch condition for judging whether described feedback information meets;

If met, trigger described notification unit.

13. 1 kinds of electronic equipments, is characterized in that, comprising: the first processing unit, voice collecting unit and the speech information processing apparatus as described in any one of claim 7-12.