CN105788598A - Speech processing method and electronic device - Google Patents
Speech processing method and electronic device Download PDFInfo
- Publication number
- CN105788598A CN105788598A CN201410804192.1A CN201410804192A CN105788598A CN 105788598 A CN105788598 A CN 105788598A CN 201410804192 A CN201410804192 A CN 201410804192A CN 105788598 A CN105788598 A CN 105788598A
- Authority
- CN
- China
- Prior art keywords
- electronic equipment
- information
- environment
- data message
- 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
Links
Landscapes
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a speech processing method and an electronic device. The method includes the following steps that: first information associated with an electronic device is obtained, wherein the first information is used for characterizing the current environment of the electronic device; the current environment of the electronic device is determined as a first environment according to the first information; speech information inputted by a user is obtained; target data information associated with the first environment is determined from pre-stored data information; matching is performed on the speech information based on the target data information, and a matching result is obtained; and the electronic device is controlled to carry out actions corresponding to the matching result. According to the speech processing method and the electronic device of the invention, the speech information inputted by the user and the current environment of the electronic device are used in combination so as to determine speed information which may appear in the current environment most possibly, and therefore, the correct rate of speech information identification can be improved, and time for speech information matching can be decreased.
Description
Technical field
The present invention relates to voice processing technology field, more particularly to a kind of method of speech processing and electronic equipment.
Background technology
Along with popularizing of electronic equipment, the function of electronic equipment is also more and more abundanter, and supports that the electronic equipment of speech identifying function also obtains the favor of user gradually.
Wherein, electronic equipment can perform corresponding action according to the voice messaging of user's input.Concrete, electronic equipment needs first the voice messaging of user's input to be carried out semantics recognition or voice match, and when the semanteme that user states is unclear or in electronic equipment, the phonetic order of storage is more, it is easy to make electronic equipment mistake occur in identifying voice messaging process or take the too much time in coupling voice messaging process.
Summary of the invention
In view of this, the present invention provides a kind of method of speech processing and electronic equipment, mistake occurs or takies the technical problem of too much time in coupling voice messaging process solving electronic equipment in prior art in identifying voice messaging process.
For achieving the above object, the present invention provides following technical scheme:
A kind of method of speech processing, is applied in electronic equipment, and the method includes:
Obtain the first information relevant to described electronic equipment；Wherein, the described first information is used for characterizing described electronic equipment and is presently in environment；
Determining that described electronic equipment is presently in environment based on the described first information is first environment；
Obtain the voice messaging of user's input；
The data message of pre-stored is determined the target data information relevant to described first environment；
Based on described target data information, described voice messaging is mated, obtain matching result；
Control described electronic equipment and perform the action corresponding with described matching result.
Preferably, the described first information is specially geographical location information, and described to determine that described electronic equipment is presently in environment based on the described first information be first environment, particularly as follows:
Determine the first environment for described electronic equipment corresponding with described geographical location information.
Preferably, the first information that described acquisition is relevant to described electronic equipment, including:
Obtain the focus mark of the wireless network focus being connected with described electronic equipment；
The geographical location information that described electronic equipment is presently in is determined according to described focus mark；
Or, described electronic equipment specifically includes locating module；
The first information that described acquisition is relevant to described electronic equipment includes:
Described locating module is utilized to obtain the geographical location information that described electronic equipment is presently in.
Preferably, described electronic equipment includes sensing module, the first information that described acquisition is relevant to described electronic equipment, including:
Described sensing module is utilized to obtain the first parameter for described electronic equipment；
The first information relevant to described electronic equipment is determined based on described first parameter；
Wherein, the described first information is used for characterizing described electronic equipment and is presently in state, and the state of described electronic equipment includes resting state and kinestate.
Preferably, the data message of described pre-stored comprises the corresponding relation put in order of first environment and a plurality of data message；
Described in the data message of pre-stored, determine the target data information relevant to described first environment, including:
Described data message is determined putting in order of a plurality of data message corresponding with described first environment；
Described based on described target data information, described voice messaging is mated, obtain matching result, including:
Put in order according to determined, successively described voice messaging and described data message are contrasted, it is determined that matching degree；
Described matching degree and preset matching degree are compared, when determining that described matching degree is spent more than preset matching, stops subsequent contrast；
Determine that described matching degree is the target data information corresponding with described voice messaging more than the data message of preset matching degree；
The described electronic equipment of described control performs the action corresponding with described matching result, particularly as follows:
Control described electronic equipment and perform the action corresponding more than the target data information of preset matching degree with matching degree.
Preferably, the data message of described pre-stored includes the corresponding relation of first environment and data message；
Described based on described target data information, described voice messaging is mated, obtain matching result, including:
Utilize speech recognition algorithm that described voice messaging is identified, obtain identification information；
Utilize described data message that described identification information is corrected, it is determined that the identification information after correction；
The described electronic equipment of described control performs the action corresponding with described matching result, particularly as follows:
Control described electronic equipment and perform the action corresponding with the identification information after described correction.
A kind of electronic equipment, including:
First acquiring unit, for obtaining the first information relevant to described electronic equipment；Wherein, the described first information is used for characterizing described electronic equipment and is presently in environment；
First determines unit, is first environment for determining that described electronic equipment is presently in environment based on the described first information；
Second acquisition unit, for obtaining the voice messaging of user's input；
Second determines unit, for determining the target data information relevant to described first environment in the data message of pre-stored；
Coupling acquiring unit, for described voice messaging being mated based on described target data information, obtains matching result；
First control unit, performs the action corresponding with described matching result for controlling described electronic equipment.
Preferably, the described first information is specially geographical location information, and described first determines that unit is specifically for determining the first environment for described electronic equipment corresponding with described geographical location information.
Preferably, described first acquiring unit, including:
First acquisition module, for obtaining the focus mark of the wireless network focus being connected with described electronic equipment；
First determines module, for determining, according to described focus mark, the geographical location information that described electronic equipment is presently in；
Or, described electronic equipment specifically includes locating module；
Described first acquiring unit obtains, specifically for utilizing described locating module, the geographical location information that described electronic equipment is presently in.
Preferably, described electronic equipment includes sensing module, described first acquiring unit, including:
Second acquisition module, for utilizing described sensing module to obtain the first parameter for described electronic equipment；
Second determines module, for determining the first information relevant to described electronic equipment based on described first parameter；
Wherein, the described first information is used for characterizing described electronic equipment and is presently in state, and the state of described electronic equipment includes resting state and kinestate.
Preferably, the data message of described pre-stored comprises the corresponding relation put in order of first environment and a plurality of data message；
Described second determines that unit specifically for determining putting in order of a plurality of data message corresponding with described first environment in described data message；
Accordingly, described coupling acquiring unit includes
Module is determined in contrast, for putting in order according to determined, described voice messaging and described data message is contrasted successively, it is determined that matching degree；
Relatively determine module, for described matching degree and preset matching degree being compared, when determining that described matching degree is spent more than preset matching, stop subsequent contrast；
3rd determines module, for determining that described matching degree is the target data information corresponding with described voice messaging more than the data message of preset matching degree；
Described first control unit performs the action corresponding more than the target data information of preset matching degree with matching degree specifically for controlling described electronic equipment.
Preferably, the data message of described pre-stored includes the corresponding relation of first environment and data message；
Described coupling acquiring unit includes:
Identify acquisition module, be used for utilizing speech recognition algorithm that described voice messaging is identified, obtain identification information；
4th determines module, is used for utilizing described data message that described identification information is corrected, it is determined that the identification information after correction；
Described first control unit performs the action corresponding with the identification information after described correction specifically for controlling described electronic equipment.
Known via above-mentioned technical scheme, compared with prior art, the embodiment of the invention discloses a kind of method of speech processing, the first environment that electronic equipment is presently in is determined by the acquired first information, and then can determine the target data information relevant to first environment, when user input voice information, it is possible to based on this target data information, voice messaging is mated, thus controlling electronic equipment to perform the action corresponding with matching result；As can be seen here, the environment facies that the voice messaging that user inputs is presently in electronic equipment can be combined by the present invention, to determine the voice messaging being most likely to occur under the present circumstances, and then the accuracy identifying voice messaging can be improved and reduce the coupling time shared by voice messaging.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is only embodiments of the invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to the accompanying drawing provided.
Fig. 1 is the schematic flow sheet of a kind of method of speech processing disclosed in one embodiment of the invention；
Fig. 2 is the part schematic flow sheet of a kind of method of speech processing disclosed in another embodiment of the present invention；
Fig. 3 is the part schematic flow sheet of a kind of method of speech processing disclosed in further embodiment of this invention；
Fig. 4 is the part schematic flow sheet of a kind of method of speech processing disclosed in further embodiment of this invention；
Fig. 5 is the structural representation of a kind of electronic equipment disclosed in one embodiment of the invention；
Fig. 6 is the structural representation of the first acquiring unit disclosed in another embodiment of the present invention；
Fig. 7 is the structural representation of one embodiment of the invention disclosed coupling acquiring unit；
Fig. 8 is the structural representation of another embodiment of the present invention disclosed coupling acquiring unit.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
One embodiment of the invention discloses a kind of method of speech processing, it is possible to be applied to the electronic equipments such as mobile phone, panel computer, palm PC.
As it is shown in figure 1, the method may comprise steps of:
Step 101: obtain the first information relevant to electronic equipment；
Wherein, the first information is used for characterizing electronic equipment and is presently in environment.Such as, this first information specifically may be used for characterizing the geographical position that electronic equipment is presently in；Or, the first information can be also used for characterizing electronic equipment and is presently in state, and wherein, electronic equipment is presently in state generally can include resting state and kinestate；Certain first information can also can characterize electronic equipment for other and be presently in the information of environment, for instance the wireless connection conditions etc. that electronic equipment is current, the present invention does not limit.
Step 102: determining that electronic equipment is presently in environment based on the first information is first environment；
It is presently in environment owing to the first information can characterize electronic equipment, therefore, it can determine electronic equipment is presently in environment specifically which type of environment by the first information, i.e. determining that electronic equipment is presently in environment is first environment.
Step 103: obtain the voice messaging of user's input；
Concrete, electronic equipment when the first operation receiving user, can obtain the voice messaging of user's input.
As, when the time of the first button on user's trigger electronics reaches Preset Time, electronic equipment obtains the voice messaging of user's input by voice acquisition module.
Or, the voice acquisition module of electronic equipment is constantly in duty, and electronic equipment can obtain the voice messaging for inputting at any time.
Step 104: determine the target data information relevant to first environment in the data message of pre-stored；
In electronic equipment, the data message of pre-stored can include the data message corresponding with varying environment, hence, it can be determined that the target data information relevant to first environment.
It should be noted that in the present invention, step 101～step 104 does not have fixing sequencing, as long as namely on logical basis, execution sequence successively can change.As step 103 can be first carried out, perform step 101, step 102 and step 104 again；Or, it is possible to first carry out step 101, again perform step 103, then perform step 102, step 104.
Wherein, in the present invention, obtain the first information relevant to electronic equipment, determine that electronic equipment is presently in the process that environment is first environment and can be regarded as the process that electronic equipment local environment is identified based on the first information.So, in the present invention, can be specifically after the voice messaging getting user's input, then carry out the identification of electronic equipment local environment；It is of course also possible to carry out the renewal identification of electronic equipment local environment with certain time interval, namely obtain at regular intervals once with the first information of electronic equipment relation, and to determine that electronic equipment is presently in environment based on the first information be first environment.Or, the a certain parameter preset of electronic equipment can also be monitored in real time, when determining the renewal identification only carrying out electronic equipment local environment when this parameter changes, as, whether the parameter relevant to wireless network connection of detection electronic equipment changes, when determine change time, carry out the renewal identification of electronic equipment local environment.
Step 105: voice messaging is mated by based target data message, obtains matching result；
Target data information is the information relevant to first environment, then, by target data information, voice is identified, it is possible to determine the voice messaging being most likely to occur under electronic equipment is presently in environment.
Wherein, concrete recognition methods can be discussed in detail later.
Step 106: control electronic equipment and perform the action corresponding with matching result.
Wherein, the different execution action of different matching result correspondence electronic equipments.As, when matching result is for phoning Zhang San, then, electronic equipment can search the phone number corresponding with Zhang San in address list, and then pull out and phone Zhang San；When matching result is for opening camera, electronic equipment can control photographic head unlatching etc..
In the present embodiment, the first environment that electronic equipment is presently in is determined by the acquired first information, and then can determine the target data information relevant to first environment, when user input voice information, based on this target data information, voice messaging can be mated, thus controlling electronic equipment to perform the action corresponding with matching result；As can be seen here, the environment facies that the voice messaging that user inputs is presently in electronic equipment can be combined by the present invention, to determine the voice messaging being most likely to occur under the present circumstances, and then the accuracy identifying voice messaging can be improved and reduce the coupling time shared by voice messaging.
It should be noted that, method of speech processing disclosed by the invention can be applied in speech identifying function or the speech recognition software of electronic equipment, it is also possible to is applied in the process that voice wakes described speech identifying function or speech recognition software up.
In order to make it easy to understand, the processing procedure being applied in voice wakeup process for method of speech processing is described in detail；
In electronic equipment, the data message of pre-stored is voice data information；When user want the mode waken up by voice control electronic equipment open speech identifying function and perform corresponding actions time, user can directly to electronic equipment input voice information in the way of voice, and electronic equipment is when after the voice messaging receiving user's input, speech processes process can be carried out, after electronic equipment can determine the target audio data message relevant to the first environment residing for electronic equipment in the data message of pre-stored, based on this target audio information, the voice messaging obtained is mated, perform the action corresponding with matching result thus controlling electronic equipment and open speech identifying function.
And as a kind of concrete implementation mode, electronic equipment may determine that the sequencing of a plurality of target audio data message relevant to first environment, and successively acquired voice messaging is mated according to this sequencing, after determining that a certain bar target sound frequency it is believed that breath mates with this voice messaging, stop subsequent contrast, control electronic equipment and perform the action of the target audio data matched with voice messaging, and open speech identifying function.
It should be noted that electronic equipment determines that in the data message of pre-stored the first environment in the target audio information relevant to first environment is particular by obtaining the first information relevant with electronic equipment, determines based on the first information.As, getting first environment is office environment, the target audio data message corresponding with first environment and being ordered as: " making a phone call ", " sending short messages ", " projection ", " shutdown ", " music ".User directly says " making a phone call " to electronic equipment, electronic equipment mates in order with target audio data after obtaining, when the match is successful for the voice messaging obtained and target audio data message, then can control electronic equipment and open speech identifying function, and the information continued upon receipt, after " Zhang San ", address list is searched the telephone number of Zhang San, and performs dial action.
For another example, when first environment is other environment, the content of target audio data message and sequence are all it may happen that change.Such as, the first environment of acquisition is living environment (family), the target audio data message corresponding with first environment and being ordered as: " music ", " chat ", " making a phone call ", " video ", " shutdown ".User directly says " chat " to electronic equipment, electronic equipment mates in order with target audio data after obtaining this voice messaging, when the match is successful for the voice messaging got and target audio data message, then can control electronic equipment and open speech identifying function, and receiving candidate information, after " QQ ", search " QQ " and run.
In actual applications, the voice messaging that user is inputted by electronic equipment at diverse location is not quite similar.Such as, in company, user generally can control electronic equipment by the mode of voice and be in conference model, opens notepad etc., and generally will not control electronic equipment and open XX game etc.；At home, user generally can control electronic equipment by the mode of voice and open wechat, opens video etc., and generally will not control electronic equipment and be in conference model etc..
Accordingly, as a kind of concrete implementation mode, the first information can be geographical location information；
Accordingly, determining that electronic equipment is presently in environment based on the first information is first environment, is specifically as follows:
Determine the first environment for electronic equipment corresponding with geographical location information.
Wherein, different geographical location information is corresponding to different environment, and the corresponding relation of geographical location information and environment can define in advance in the electronic device.
Such as, geographical location information is C mansion, B district of A city, and in the electronic device, C mansion, B district of A city is corresponding with company, then, it may be determined that the first environment of electronic equipment is company.
Again such as, geographical location information is D community, B district of A city, and in the electronic device, D community, B district of A city is corresponding with family, then, it may be determined that the first environment of electronic equipment is family.
Wherein, target data information is corresponding with first environment.Such as, when determining that electronic equipment is in company, it is possible to based on the data message relevant to company, voice messaging is mated such that it is able to improve the accuracy rate identified and shorten recognition time.
Concrete, in the present invention, obtain the first information relevant to electronic equipment and may include that
A1: obtain the focus mark of the wireless network focus being connected with electronic equipment；
A2: determine the geographical location information that electronic equipment is presently according to focus mark.
Wherein, electronic equipment can be previously stored with the corresponding relation of focus mark and geographical location information, after determining that electronic equipment connects wireless network, the focus mark of the wireless network focus being connected with electronic equipment can be obtained, thus searching the geographical location information corresponding with focus mark in corresponding relation.
Such as, the focus of the wireless network focus being connected with electronic equipment is designated Lenovo, and C mansion, B district of Lenovo and A city is corresponding, then, it may be determined that the geographical location information corresponding with this focus mark is C mansion, B district of A city.
Or, electronic equipment can include locating module, obtains the first information relevant to electronic equipment and may include that the geographical location information utilizing locating module acquisition electronic equipment to be presently in.
Concrete, when determine need to obtain geographical location information that electronic equipment is presently in time, it is possible to open locating module, obtain the geographical location information that the electronic equipment of locating module location is presently in.Certainly, locating module can also be in real-time opening, when determine need obtain electronic equipment be presently in geographical location information time, directly obtain locating module position geographical location information.
And in another kind is applied, the voice messaging that user is inputted by electronic equipment under different conditions is also not quite similar.Such as, user controls, by voice mode most probable, the action that electronic equipment performs in rest process, and when user is in motor process, it is possible to become most unlikely controlling the action that electronic equipment performs.As, user generally can control electronic equipment by the mode of voice in rest process and open XX game, and user generally opens XX game without control electronic equipment in motor process, because it is very inconvenient to play game in motor process.
Accordingly, as another kind of implementation, electronic equipment can include sensing module, accordingly, obtains the first information relevant to electronic equipment, as in figure 2 it is shown, may comprise steps of:
Step 2011: utilize sensing module to obtain the first parameter for electronic equipment；
Step 2012: determine the first information relevant to electronic equipment based on the first parameter；
Wherein, the first information is used for characterizing electronic equipment and is presently in state, and the state of electronic equipment can include resting state and kinestate.It is considered as electronic equipment is presently in a kind of concrete manifestation form of environment it should be noted that electronic equipment is presently in state.
Can determining that electronic equipment is kept in motion or resting state by the first parameter that sensing module gathers, this sensing module is specifically as follows velocity sensor, gravity sensor etc..
After determining the first information that electronic equipment is presently in state, it is possible to determining that electronic equipment is presently in environment based on the first information is first environment；It should be noted that, the first information characterizes electronic equipment and is kept in motion the relation with first environment, and the first information characterizes electronic equipment and remains static the relation with first environment, it is possible to preset in the electronic device, limit the present invention is not concrete.
Such as, when the first information characterize electronic equipment be presently in state be kinestate time, it may be determined that the first environment of electronic equipment is public place, such as park, road etc..When the first information characterize electronic equipment be presently in state be resting state time, it may be determined that the first environment of electronics is recreating facility, such as family.And the data message of pre-stored can include the data message corresponding with public place and the data message corresponding with recreating facility in electronic equipment, and then based on the target data information relevant to first environment, voice messaging can be mated, obtain matching result, thus controlling electronic equipment to perform the action corresponding with matching result.
Certainly, more than simply a kind of concrete implementation mode, more such as, when the first information characterize electronic equipment be presently in state be kinestate time, it may be determined that the first environment of electronic equipment is movement environment；When the first information characterize electronic equipment be presently in state be resting state time, it may be determined that the first environment of electronic equipment is static situation.And the data message of pre-stored can include the data message corresponding with movement environment and the data message corresponding with static situation in electronic equipment, and then based on the target data information relevant to first environment, voice messaging can be mated, obtain matching result, thus controlling electronic equipment to perform the action corresponding with matching result.
The present invention will be discussed in detail, with different embodiments, the voice messaging corresponding action of execution how electronic equipment inputs according to user respectively below；
First, one embodiment of the invention is directed in prior art, when electronic equipment is pre-stored with a plurality of data message being able to carry out, if the random each data information with this plurality of data message of voice messaging that user inputs being mated, the technical problem of too much time can be taken；
In the present embodiment, a kind of method of speech processing may comprise steps of:
S01: obtain the first information relevant to electronic equipment；
Wherein, the first information is used for characterizing electronic equipment and is presently in environment.
S02: determining that electronic equipment is presently in environment based on the first information is first environment；
S03: obtain the voice messaging of user's input；
S04: determine the target data information relevant to first environment in the data message of pre-stored；
Wherein, the data message of pre-stored can include the corresponding relation put in order of first environment and a plurality of data message, and this plurality of data message refers at least two data information.Accordingly, the data message of pre-stored is determined the target data information relevant to first environment, is specifically as follows: in data message, determine putting in order of a plurality of data message corresponding with first environment.
Such as, electronic equipment includes 5 data information, particularly as follows: conference model, open wechat, open video, now some.
With first environment be 5 data information corresponding to company put in order for: open conference model, open notepad, now some, open wechat, open video；
With first environment be 5 data information corresponding to family put in order for: open wechat, open video, open notepad, now some, open conference model.
If first environment is company, then may determine that a plurality of data message corresponding with company put in order for: conference model, open notepad, now some, open wechat, open video.
S05: voice messaging is mated by based target data message, obtains matching result；
Concrete, as it is shown on figure 3, voice messaging is mated by based target data message, obtain matching result, it is possible to comprise the following steps:
Step 3051: put in order according to determined, contrasts voice messaging and data message, it is determined that matching degree successively；
It should be noted that, this data message is specifically as follows voice data information, and user can record in advance in the electronic device.It is possible to directly successively voice messaging and voice data information are contrasted.And this data message can also be text data information, then, it is possible to by speech recognition algorithm, voice messaging is converted to text message, then contrasts with text data.
Step 3052: matching degree and preset matching degree are compared, when determining that matching degree is spent more than preset matching, stops subsequent contrast；
Preset matching degree can be pre-defined by system, it is also possible to supports User Defined.
Such as, first environment is company, determined data message put in order for: open conference model, open notepad, now some, open wechat, open video；And the voice messaging of user's input be " now some ", then, it is possible to first " now what time " is mated with " unlatching conference model ", it is determined that its matching degree is less than preset matching degree；So, continue to mate " now some " with " opening notepad ", it is determined that its matching degree is still less than preset matching degree；So, continue to mate " now some " with " now some ", owing to determining that its matching degree is more than preset matching degree, therefore, it can stopping subsequent match.Namely need not continue to mate with " opening wechat " and " opening video " by " now some " again.
Step 3053: determine that matching degree is the target data information corresponding with voice messaging more than the data message of preset matching degree；
S06: control electronic equipment and perform the action corresponding with matching result；
Accordingly, control electronic equipment and perform the action corresponding with described matching result, be specifically as follows: control electronic equipment and perform the action corresponding more than the target data information of preset matching degree with matching degree.
Such as, when determining the matching degree target data information more than preset matching degree for " now some ", electronic equipment may determine that current time speech chronopher.
It should be noted that in the present invention, electronic equipment can support self study, so that it is determined that the putting in order of a plurality of data message optimum under each environment.Certainly, it is possible to by putting in order of a plurality of data message under the pre-defined a plurality of data message corresponding with varying environment of user and varying environment.
Secondly, another embodiment of the present invention is directed in prior art, and when the semanteme represented by user is unclear, the technical problem of mistake easily occurs in identification process in electronic equipment；
In the present embodiment, a kind of method of speech processing may comprise steps of:
S11: obtain the first information relevant to electronic equipment；
Wherein, the first information is used for characterizing electronic equipment and is presently in environment.
S12: determining that electronic equipment is presently in environment based on the first information is first environment；
S13: obtain the voice messaging of user's input；
S14: determine the target data information relevant to first environment in the data message of pre-stored；
Wherein, the data message of pre-stored includes the corresponding relation of first environment and data message；
Wherein, first environment can be corresponding with a data information, it is also possible to corresponding with a plurality of data message.
S15: voice messaging is mated by based target data message, obtains matching result；
Concrete, as shown in Figure 4, based on described target data information, voice messaging is mated, obtains matching result, it is possible to comprise the following steps:
Step 4051: utilize speech recognition algorithm that voice messaging is identified, obtains identification information；
Wherein, this identification information is specifically as follows text message, naturally it is also possible to for command information.
Step 4052: utilize data message that identification information is corrected, it is determined that the identification information after correction；
Owing to user is for expression way subjective of voice messaging, therefore, when utilizing speech recognition algorithm that voice messaging is identified, acquired identification information is likely that there are mistake, therefore, can utilize the data message corresponding with first environment that identification information is corrected, so that the identification information after correcting and first environment fit well on.
It should be noted that, the process that identification information is corrected by data message is utilized to be actually process data message and identification information compared, and owing to being not that every identification information all exists mistake, therefore, identification information after correction is likely to consistent with the identification information before correction, but, the present invention data message and identification information are compared after identification information be referred to as the identification information after correction.
S16: control electronic equipment and perform the action corresponding with matching result；
Wherein, control electronic equipment and perform the action corresponding with described matching result, be specifically as follows: control electronic equipment and perform the action corresponding with the identification information after correction.
For the ease of understanding, illustrate with an instantiation, voice messaging such as user's input is " opening wechat ", and owing to user states unclear, making the identification information that electronic equipment is determined is " opening danger ", it is clear that electronic equipment identification mistake, in the prior art, electronic equipment then needs to remind user to re-enter.
And in the present invention, the first environment determining electronic equipment is family, and storage has the corresponding relation of family and data message in electronic equipment, this data message includes " opening wechat ", so, can utilize " opening wechat " in data message that the information of identification " opening danger " is corrected, so that it is determined that identify after correcting that information is " opening wechat ", and then control electronic equipment unlatching wechat.
One embodiment of the invention discloses a kind of electronic equipment, and this electronic equipment can be mobile phone, panel computer, palm PC etc..As it is shown in figure 5, this electronic equipment may include that the first acquiring unit 501, first determines unit 502, second acquisition unit 503, second determines unit 504, coupling acquiring unit 505 and the first control unit 506；Wherein:
First acquiring unit 501, it is possible to for obtaining the first information relevant to electronic equipment；
Wherein, the first information is used for characterizing described electronic equipment and is presently in environment；
First determines unit 502, it is possible to being used for determining that electronic equipment is presently in environment based on the first information is first environment；
Second acquisition unit 5023, it is possible to for obtaining the voice messaging of user's input；
Second determines unit 504, it is possible to for determining the target data information relevant to first environment in the data message of pre-stored；
Coupling acquiring unit 505, it is possible to voice messaging is mated for based target data message, obtains matching result；
First control unit 506, it is possible to perform the action corresponding with matching result for controlling electronic equipment.
In the present embodiment, the first environment that electronic equipment is presently in is determined by the acquired first information, and then can determine the target data information relevant to first environment, when user input voice information, based on this target data information, voice messaging can be mated, thus controlling electronic equipment to perform the action corresponding with matching result；As can be seen here, the environment facies that the voice messaging that user inputs is presently in electronic equipment can be combined by the present invention, to determine the voice messaging being most likely to occur under the present circumstances, and then the accuracy identifying voice messaging can be improved and reduce the coupling time shared by voice messaging.
In the present invention, the form that implements of the first information has multiple；
As a kind of implementation, the first information is specifically as follows geographical location information；Accordingly, first determines that unit is specifically determined for the first environment for electronic equipment corresponding with geographical location information.
Accordingly, the first acquiring unit, it is possible to including: the first acquisition module and first determines module；Wherein:
First acquisition module, it is possible to for obtaining the focus mark of the wireless network focus being connected with electronic equipment；
First determines module, it is possible to for determining, according to focus mark, the geographical location information that electronic equipment is presently in.
Or, electronic equipment specifically can include locating module, and the first acquiring unit specifically may be used for utilizing locating module to obtain the geographical location information that electronic equipment is presently in.
As another kind of implementation, electronic equipment can include sensing module, and as shown in Figure 6, the first acquiring unit specifically may include that the second acquisition module 6011 and second determines module 6012；Wherein:
Second acquisition module 6011, it is possible to for utilizing sensing module to obtain the first parameter for electronic equipment；
Second determines module 6012, it is possible to for determining the first information relevant to electronic equipment based on the first parameter；
Wherein, the described first information is used for characterizing described electronic equipment and is presently in state, and the state of described electronic equipment includes resting state and kinestate.
In the present invention, the implementation of the data message of pre-stored has multiple；
As a kind of implementation, the data message of pre-stored can comprise the corresponding relation put in order of first environment and a plurality of data message；
Unlike the embodiments above, second determines that unit specifically may be used for determining putting in order of a plurality of data message corresponding with first environment in data message；
Accordingly, as it is shown in fig. 7, coupling acquiring unit specifically may include that contrast is determined module 7051, compared and determine that module the 7052, the 3rd determines module 7053；Wherein:
Module 7051 is determined in contrast, it is possible to for putting in order according to determined, voice messaging and data message is contrasted successively, it is determined that matching degree；
Relatively determine module 7052, it is possible to for matching degree and preset matching degree being compared, when determining that described matching degree is spent more than preset matching, stop subsequent contrast；
3rd determines module 7053, it is possible to for determining that matching degree is the target data information corresponding with described voice messaging more than the data message of preset matching degree.
Accordingly, the first control unit specifically may be used for controlling the action that electronic equipment execution is corresponding more than the target data information of preset matching degree with matching degree.
As another kind of implementation, the data message of pre-stored can include the corresponding relation of first environment and data message；
Unlike the embodiments above, as shown in Figure 8, coupling acquiring unit may include that identification acquisition module 8051 and the 4th determines module 8052；
Identify acquisition module 8051, it is possible to be used for utilizing speech recognition algorithm that voice messaging is identified, obtain identification information；
4th determines module 8052, it is possible to be used for utilizing data message that identification information is corrected, it is determined that the identification information after correction.
Accordingly, the first control unit specifically may be used for the action that the identification information after controlling electronic equipment execution and correcting is corresponding.
The embodiment of each device is corresponding with embodiment of the method above, specifically can referring to embodiment of the method, and in this not go into detail.
In this specification, each embodiment adopts the mode gone forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar portion mutually referring to.For device disclosed in embodiment, owing to it corresponds to the method disclosed in Example, so what describe is fairly simple, relevant part illustrates referring to method part.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses the present invention.The multiple amendment of these embodiments be will be apparent from for those skilled in the art, and generic principles defined herein can without departing from the spirit or scope of the present invention, realize in other embodiments.Therefore, the present invention is not intended to be limited to the embodiments shown herein, and is to fit to the widest scope consistent with principles disclosed herein and features of novelty.
Claims (12)
1. a method of speech processing, it is characterised in that being applied in electronic equipment, the method includes:
Obtain the first information relevant to described electronic equipment；Wherein, the described first information is used for characterizing described electronic equipment and is presently in environment；
Determining that described electronic equipment is presently in environment based on the described first information is first environment；
Obtain the voice messaging of user's input；
The data message of pre-stored is determined the target data information relevant to described first environment；
Based on described target data information, described voice messaging is mated, obtain matching result；
Control described electronic equipment and perform the action corresponding with described matching result.
2. method according to claim 1, it is characterised in that the described first information is specially geographical location information, it is described that to determine that described electronic equipment is presently in environment based on the described first information be first environment, particularly as follows:
Determine the first environment for described electronic equipment corresponding with described geographical location information.
3. method according to claim 2, it is characterised in that the first information that described acquisition is relevant to described electronic equipment, including:
Obtain the focus mark of the wireless network focus being connected with described electronic equipment；
The geographical location information that described electronic equipment is presently in is determined according to described focus mark；
Or, described electronic equipment specifically includes locating module；
The first information that described acquisition is relevant to described electronic equipment includes:
Described locating module is utilized to obtain the geographical location information that described electronic equipment is presently in.
4. method according to claim 1, it is characterised in that described electronic equipment includes sensing module, the first information that described acquisition is relevant to described electronic equipment, including:
Described sensing module is utilized to obtain the first parameter for described electronic equipment；
The first information relevant to described electronic equipment is determined based on described first parameter；
Wherein, the described first information is used for characterizing described electronic equipment and is presently in state, and the state of described electronic equipment includes resting state and kinestate.
5. the method according to any one of Claims 1 to 4, it is characterised in that the data message of described pre-stored comprises the corresponding relation put in order of first environment and a plurality of data message；
Described in the data message of pre-stored, determine the target data information relevant to described first environment, including:
Described data message is determined putting in order of a plurality of data message corresponding with described first environment；
Described based on described target data information, described voice messaging is mated, obtain matching result, including:
Put in order according to determined, successively described voice messaging and described data message are contrasted, it is determined that matching degree；
Described matching degree and preset matching degree are compared, when determining that described matching degree is spent more than preset matching, stops subsequent contrast；
Determine that described matching degree is the target data information corresponding with described voice messaging more than the data message of preset matching degree；
The described electronic equipment of described control performs the action corresponding with described matching result, particularly as follows:
Control described electronic equipment and perform the action corresponding more than the target data information of preset matching degree with matching degree.
6. the method according to any one of Claims 1 to 4, it is characterised in that the data message of described pre-stored includes the corresponding relation of first environment and data message；
Described based on described target data information, described voice messaging is mated, obtain matching result, including:
Utilize speech recognition algorithm that described voice messaging is identified, obtain identification information；
Utilize described data message that described identification information is corrected, it is determined that the identification information after correction；
The described electronic equipment of described control performs the action corresponding with described matching result, particularly as follows:
Control described electronic equipment and perform the action corresponding with the identification information after described correction.
7. an electronic equipment, it is characterised in that including:
First acquiring unit, for obtaining the first information relevant to described electronic equipment；Wherein, the described first information is used for characterizing described electronic equipment and is presently in environment；
First determines unit, is first environment for determining that described electronic equipment is presently in environment based on the described first information；
Second acquisition unit, for obtaining the voice messaging of user's input；
Second determines unit, for determining the target data information relevant to described first environment in the data message of pre-stored；
Coupling acquiring unit, for described voice messaging being mated based on described target data information, obtains matching result；
First control unit, performs the action corresponding with described matching result for controlling described electronic equipment.
8. electronic equipment according to claim 7, it is characterised in that the described first information is specially geographical location information, described first determines that unit is specifically for determining the first environment for described electronic equipment corresponding with described geographical location information.
9. electronic equipment according to claim 8, it is characterised in that described first acquiring unit, including:
First acquisition module, for obtaining the focus mark of the wireless network focus being connected with described electronic equipment；
First determines module, for determining, according to described focus mark, the geographical location information that described electronic equipment is presently in；
Or, described electronic equipment specifically includes locating module；
Described first acquiring unit obtains, specifically for utilizing described locating module, the geographical location information that described electronic equipment is presently in.
10. electronic equipment according to claim 7, it is characterised in that described electronic equipment includes sensing module, described first acquiring unit, including:
Second acquisition module, for utilizing described sensing module to obtain the first parameter for described electronic equipment；
Second determines module, for determining the first information relevant to described electronic equipment based on described first parameter；
Wherein, the described first information is used for characterizing described electronic equipment and is presently in state, and the state of described electronic equipment includes resting state and kinestate.
11. according to the electronic equipment described in any one of claim 7～10, it is characterised in that the data message of described pre-stored comprises the corresponding relation put in order of first environment and a plurality of data message；
Described second determines that unit specifically for determining putting in order of a plurality of data message corresponding with described first environment in described data message；
Accordingly, described coupling acquiring unit includes
Module is determined in contrast, for putting in order according to determined, described voice messaging and described data message is contrasted successively, it is determined that matching degree；
Relatively determine module, for described matching degree and preset matching degree being compared, when determining that described matching degree is spent more than preset matching, stop subsequent contrast；
3rd determines module, for determining that described matching degree is the target data information corresponding with described voice messaging more than the data message of preset matching degree；
Described first control unit performs the action corresponding more than the target data information of preset matching degree with matching degree specifically for controlling described electronic equipment.
12. according to the electronic equipment described in any one of claim 7～10, it is characterised in that the data message of described pre-stored includes the corresponding relation of first environment and data message；
Described coupling acquiring unit includes:
Identify acquisition module, be used for utilizing speech recognition algorithm that described voice messaging is identified, obtain identification information；
4th determines module, is used for utilizing described data message that described identification information is corrected, it is determined that the identification information after correction；
Described first control unit performs the action corresponding with the identification information after described correction specifically for controlling described electronic equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410804192.1A CN105788598B (en) | 2014-12-19 | 2014-12-19 | Voice processing method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410804192.1A CN105788598B (en) | 2014-12-19 | 2014-12-19 | Voice processing method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105788598A true CN105788598A (en) | 2016-07-20 |
| CN105788598B CN105788598B (en) | 2019-12-24 |
Family
ID=56385220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410804192.1A Active CN105788598B (en) | 2014-12-19 | 2014-12-19 | Voice processing method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105788598B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108922520A (en) * | 2018-07-12 | 2018-11-30 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
| CN109003607A (en) * | 2018-07-12 | 2018-12-14 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001034292A (en) * | 1999-07-26 | 2001-02-09 | Denso Corp | Word string recognizing device |
| JP2004219918A (en) * | 2003-01-17 | 2004-08-05 | Canon Inc | Speech recognition environment judging method |
| JP2009175630A (en) * | 2008-01-28 | 2009-08-06 | Sharp Corp | Speech recognition device, mobile terminal, speech recognition system, speech recognition device control method, mobile terminal control method, control program, and computer readable recording medium with program recorded therein |
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| CN103282957A (en) * | 2010-08-06 | 2013-09-04 | 谷歌公司 | Automatically monitoring for voice input based on context |
| CN103745722A (en) * | 2014-02-10 | 2014-04-23 | 上海金牌软件开发有限公司 | Voice interaction smart home system and voice interaction method |
| CN103903611A (en) * | 2012-12-24 | 2014-07-02 | 联想(北京)有限公司 | Speech information identifying method and equipment |
-
2014
- 2014-12-19 CN CN201410804192.1A patent/CN105788598B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001034292A (en) * | 1999-07-26 | 2001-02-09 | Denso Corp | Word string recognizing device |
| JP2004219918A (en) * | 2003-01-17 | 2004-08-05 | Canon Inc | Speech recognition environment judging method |
| JP2009175630A (en) * | 2008-01-28 | 2009-08-06 | Sharp Corp | Speech recognition device, mobile terminal, speech recognition system, speech recognition device control method, mobile terminal control method, control program, and computer readable recording medium with program recorded therein |
| CN103282957A (en) * | 2010-08-06 | 2013-09-04 | 谷歌公司 | Automatically monitoring for voice input based on context |
| CN102074231A (en) * | 2010-12-30 | 2011-05-25 | 万音达有限公司 | Voice recognition method and system |
| CN103903611A (en) * | 2012-12-24 | 2014-07-02 | 联想(北京)有限公司 | Speech information identifying method and equipment |
| CN103745722A (en) * | 2014-02-10 | 2014-04-23 | 上海金牌软件开发有限公司 | Voice interaction smart home system and voice interaction method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108922520A (en) * | 2018-07-12 | 2018-11-30 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
| CN109003607A (en) * | 2018-07-12 | 2018-12-14 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105788598B (en) | 2019-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11393472B2 (en) | Method and apparatus for executing voice command in electronic device | |
| CN106796791B (en) | Speaker identification and unsupported speaker adaptation techniques | |
| US11538328B2 (en) | Mobile device self-identification system | |
| JP6335139B2 (en) | Manual start / end point specification and reduced need for trigger phrases | |
| CN106154158B (en) | Terminal motor detecting method and device | |
| CN104703252B (en) | Terminal device accesses the method and device of wireless network | |
| JP2018525751A (en) | Interactive control method and apparatus for voice and video calls | |
| CN110674801B (en) | Method and device for identifying user motion mode based on accelerometer and electronic equipment | |
| KR20160127117A (en) | Performing actions associated with individual presence | |
| CN105491048A (en) | Account management method and apparatus | |
| CN111063354A (en) | Man-machine interaction method and device | |
| US9564037B2 (en) | Mobile device loss prevention using audio and spatial indicia | |
| US20150234633A1 (en) | Methods and Systems for Voice Management | |
| EP3247137B1 (en) | Detecting method and apparatus | |
| CN106657543B (en) | Voice information processing method and device | |
| KR101379405B1 (en) | Method of processing voice communication and mobile terminal performing the same | |
| CN108920085B (en) | Information processing method and device for wearable device | |
| CN105788598A (en) | Speech processing method and electronic device | |
| CN109274825A (en) | A kind of message prompt method and device | |
| CN105391620B (en) | Information cuing method and device | |
| CN107368278B (en) | Information processing method and device | |
| CN105094891B (en) | effect display method and device | |
| CN105959139A (en) | Information display method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |