CN103903618A - Voice input method and electronic device - Google Patents
Voice input method and electronic device Download PDFInfo
- Publication number
- CN103903618A CN103903618A CN201210584246.9A CN201210584246A CN103903618A CN 103903618 A CN103903618 A CN 103903618A CN 201210584246 A CN201210584246 A CN 201210584246A CN 103903618 A CN103903618 A CN 103903618A
- Authority
- CN
- China
- Prior art keywords
- statement
- adjusted
- content
- clause
- input object
- 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
Images
Abstract
The invention provides a voice input method and an electronic device. The method is applied to the electronic device. The method comprises the steps that a first statement is input in a voice input manner; the first statement is analyzed to acquire a correct input object; and based on the correct input object, a content to be adjusted is adjusted.
Description
Technical field
The present invention relates to electronic technology field, relate in particular to a kind of pronunciation inputting method and electronic equipment.
Background technology
Along with the development of electronic device technology, various electronic equipments have entered user's life, along with the development of speech recognition technology, to carry out the scene of interactive voice more and more by voice control electronic equipment or with electronic equipment for user, bring great convenience to people's life.
Under the situation of voice control or interactive voice, can exist some input errors, for example user with phonetic entry " Wang Lan ", but electronic equipment and do not know user really want input what is, so may just be entered as " Wang Lan ", need user to proofread and correct; Again for example, the input of voice command is " making a phone call to Wang Lan ", just in time has " Wang Lan " and " Wang Lan " in the phone directory of electronic equipment, so the possibility of result of coupling is wrong execution, " Wang Lan " made in order, or cannot fill order; Again for example, carry out the input of punctuation mark by voice, if each punctuation mark carries out phonetic entry, will cause man-machine interaction complexity to improve, and mistake easily appears in the mode of automatically adding, so also need to modify.Even, in some cases, even if be not the content of text by phonetic entry, also can there is mistake, for example, utilize the word of input method input by keyboard, because some close word together, so easily choosing is wrong, so also need to modify.
In the prior art, the mode that the mode of amendment adopts keyboard, mouse conventionally chooses the place of needs amendment, and then re-enters by fight sound or five-stroke input method of keyboard, or utilizes phonetic entry to input one time again.
But, the inventor finds in the process that realizes the technical scheme in the embodiment of the present invention, the alter mode of available technology adopting keyboard, mouse will first be selected wrong place, and then input one time, efficiency is lower, and input may also can be selected because of close words mistake again, so accuracy rate is low; And for voice command, just more difficult amendment of mode of the prior art, because electronic equipment may have been carried out wrong order; Even or use again phonetic entry one time, and may be still the same with original mistake, again input by mistake, so efficiency and accuracy rate are all very low.Therefore there is efficiency and the low technical matters of accuracy rate in alter mode of the prior art.
Summary of the invention
The invention provides a kind of pronunciation inputting method and electronic equipment, in order to solve the low and low technical matters of accuracy rate of efficiency that alter mode of the prior art exists.
One aspect of the present invention provides a kind of pronunciation inputting method, is applied in an electronic equipment, and described method comprises: input the first statement by the mode of phonetic entry; Analyze described the first statement, obtain a correct input object; Based on described correct input object, one content to be adjusted is adjusted.
Optionally, before the described mode by phonetic entry is inputted the first statement, described method also comprises by the mode of phonetic entry inputs the second statement; Based on described the second statement, determine described content to be adjusted.
Optionally, the described mode by phonetic entry is inputted the second statement and is specially: the first clause that input comprises voice command and the second clause who comprises described content to be adjusted.
Optionally, described the first statement of described analysis, obtains a correct input object, specifically comprises: judge whether described the first statement comprises punctuation mark; In the time that described the first statement comprises described punctuation mark, obtain described punctuation mark.
Optionally, describedly based on described correct input object, one content to be adjusted is adjusted, be specially: the punctuation mark of replacing least significant end in described content to be adjusted with described punctuation mark.
Optionally, described the first statement of described analysis, obtains a correct input object and specifically comprises: described the first statement is carried out to word segmentation processing, obtain at least three clauses; In described at least three clauses, determine the first identical clause, described the first clause is described correct input object.
Optionally, describedly based on described correct input object, described content to be adjusted is adjusted, be specially: replace content relevant to described the first clause in described content to be adjusted with described the first clause.
Optionally, described the first statement of described analysis, obtains a correct input object, specifically comprises: described the first statement is carried out to participle taking word as unit, obtain at least three independent words; Described last independent word determined in all the other independent words based on except last independent word; Described last independent word is defined as to correct input object.
Optionally, describedly based on described correct input object, described content to be adjusted is adjusted, is specially: with described in last independent word of determining replace in described content to be adjusted to described in the relevant content of last independent word of determining.
One embodiment of the invention also provides a kind of electronic equipment, comprising: sound collection unit, for gathering the first statement; The first processing unit, for analyzing described the first statement, obtains a correct input object; The second processing unit, for adjusting a content to be adjusted based on described correct input object.
Optionally, described sound collection unit specifically, also for before gathering described the first statement, gathers the second statement; Described the second processing unit specifically, also for based on described the second statement, is determined described content to be adjusted.
Optionally, described the second statement is specially the first clause who comprises voice command and the second clause who comprises described content to be adjusted.
Optionally, described the first processing unit is specifically for judging whether described the first statement comprises punctuation mark; In the time that described the first statement comprises described punctuation mark, obtain described punctuation mark.
Optionally, described the second processing unit is specifically for replacing the punctuation mark of least significant end in described content to be adjusted with described punctuation mark.
Optionally, described the first processing unit, specifically for described the first statement is carried out to word segmentation processing, obtains at least three clauses; In described at least three clauses, determine the first identical clause, described the first clause is described correct input object.
Optionally, described the second processing unit is specifically for replacing content relevant to described the first clause in described content to be adjusted with described the first clause.
Optionally, described the first processing unit, specifically for described the first statement is carried out to participle taking word as unit, obtains at least three independent words; Described last independent word determined in all the other independent words based on except last independent word; Described last independent word is defined as to correct input object.
Optionally, described the second processing unit specifically for last independent word of determining described in use replace in described content to be adjusted to described in the relevant content of last independent word of determining.
The one or more technical schemes that provide in the embodiment of the present invention, at least have following technique effect or advantage:
One embodiment of the invention is inputted the first statement by the mode of phonetic entry, then analyzes the first statement, obtains a correct input object, then based on this correct input object, one content to be adjusted is adjusted.Method in the present embodiment is because be the mode by phonetic entry, input a correct content, then just can adjust a content to be adjusted based on this correct content, so such alter mode accuracy rate is high, and method in the present embodiment does not need first to go to select especially wrong place, as long as the correct content of input can complete automatic amendment, so efficiency is also high.
Further, in one embodiment of the invention, also the mode by phonetic entry is inputted the second statement, then based on the second statement, determines content to be adjusted.Therefore, in the present embodiment, first can navigate to accurately fast needed position by phonetic entry, can solve in prior art because viewing area is less, cause the problem that positioning precision is low; Secondly first content to be adjusted is determined, can be reduced the calculated amount of coupling, so saved time and calculated amount, reduced power consumption.
Brief description of the drawings
Fig. 1 is the process flow diagram of the pronunciation inputting method in one embodiment of the invention;
Fig. 2 a-Fig. 2 c is the schematic diagram of the pronunciation inputting method in first embodiment of the invention;
Fig. 3 is the functional block diagram of the electronic equipment in one embodiment of the invention.
Embodiment
The invention provides a kind of pronunciation inputting method and electronic equipment, in order to solve the low and low technical matters of accuracy rate of efficiency that the alter mode that exists in prior art exists.
Technical scheme in the embodiment of the present invention is to solve above-mentioned technical matters, and general thought is as follows:
Input the first statement by the mode of phonetic entry, then analyze the first statement, obtain a correct input object, then based on this correct input object, one content to be adjusted is adjusted.Method in the present embodiment is because be the mode by phonetic entry, input a correct content, then just can adjust a content to be adjusted based on this correct content, so such alter mode accuracy rate is high, and method in the present embodiment does not need first to go to select especially wrong place, as long as the correct content of input can complete automatic amendment, so efficiency is also high.
In order better to understand technique scheme, below in conjunction with Figure of description and concrete embodiment, technique scheme is described in detail.
One embodiment of the invention provides a kind of pronunciation inputting method, be applied on the electronic equipment of a support voice identification, this electronic equipment is for example the electronic equipments such as mobile phone, panel computer, notebook computer, on this electronic equipment, receive a content to be adjusted, this content to be adjusted can be by phonetic entry, also can input by keyboard, can be also that other electronic equipment sends.
Please refer to Fig. 1, the method comprises:
Step 101: input the first statement by the mode of phonetic entry;
Step 102: analyze the first statement, obtain a correct input object;
Step 103: one content to be adjusted is adjusted based on correct input object.
Wherein, in step 101, input the first statement by the mode of phonetic entry, concrete example collects the first statement of user's input in this way by the sound collection unit on electronic equipment, the first statement is for example the statement that comprises punctuation mark, adjusts for the punctuation mark to content to be adjusted; The first statement is for example also the descriptive statement of the content to adjusting; Certainly, in other embodiments, the first statement can also be other statement, as long as comprise correct input object.
In step 102, analyze the first statement, concrete example is in this way first by the extraction of acoustic feature, for example calculating of linear predictor coefficient LPC, cepstrum coefficient CEP, Mel cepstrum coefficient MFCC and perception linear prediction PLP and MFCC; Mate by acoustic model again, for example, utilize hidden Markov model; Mate by language model, the content that this part is well known to those skilled in the art, so be not described in detail in this again.
In step 102, by analyzing the first statement, obtain a correct input object, i.e. the correct input object for content to be adjusted is adjusted, for example, be punctuation mark or a word or a word.
Next perform step 103, the correct input object based on obtaining in step 102, adjusts content to be adjusted, for example, by wrong part in correct punctuation mark or word or the alternative content to be adjusted of word.
In a further embodiment, before step 101, the method also comprises: input the second statement by the mode of phonetic entry; Based on the second statement, determine content to be adjusted.
In specific implementation process, inputting the second statement is for example input the first clause who comprises voice command and the second clause who comprises content to be adjusted, for example the second statement is " choosing ' you have had a meal today ' ", " choose " so and be the first clause, represent the instruction that needs electronic equipment to carry out, " you have had a meal today " is the second clause, is content to be adjusted; Wherein, the mode of choosing, for example, be by the outstanding selected content of highlighted demonstration, or by changing the mode of font, to give prominence to different in the display effect of selected content and not selected content; For example the second clause of user's input is " after navigating to ' you have had a meal today ' fullstop " again, " location " is the first clause so, represent that the instruction that electronic equipment need to be carried out positions cursor exactly, and determine being included in the second clause of bit position, " ' you have had a meal today ' fullstop " afterwards, and the second clause also represents that content to be adjusted is " ' you have had a meal today ' fullstop ".
Therefore, in the present embodiment, can navigate to accurately fast the position needing by phonetic entry, so it is less to solve in prior art because viewing area, cause the problem that positioning precision is low, secondly first content to be adjusted is determined, can reduce the calculated amount of coupling, so saved time and calculated amount, reduced power consumption.
In order more to clearly demonstrate the implementation process of the pronunciation inputting method in the present embodiment, below will describe for example respectively.
The first embodiment:
In the present embodiment, for example user is by text of phonetic entry, for example note, and select automatic configuration punctuation mark, but because configuration punctuation mark is not entirely true automatically, for example user is by phonetic entry " you have had a meal today ", then by speech recognition, user's phonetic entry is presented on display unit by identification, and return to punctuation mark according to automatic configuration punctuation mark: fullstop, please refer to shown in Fig. 2 a, on display unit 20, show a content 201 to be adjusted.But what in fact go up that user more wishes to return here is question mark, so at this moment user can input the first statement by the mode of phonetic entry, for example " question mark ", carried out step 101, so at this moment continue execution step 102, analyze the first statement, whether interpretation the first statement comprises punctuation mark, by analyzing, find that the first statement comprises punctuation mark in the present embodiment, so just further analyze, get this punctuation mark, i.e. question mark.Then perform step 103, replace the punctuation mark of least significant end in content to be adjusted with the punctuation mark getting, in the present embodiment, replaced that last fullstop of text with question mark, the schematic diagram after having replaced please refer to shown in Fig. 2 b.
In another embodiment, step 103 can be also to replace all punctuation marks, for example, all punctuates that need to revise are met with voice and chosen, and for example user inputs " choosing comma ", so all commas all can be selected, then in step 103, is replaced.
Certainly, in practice, even if user finds that punctuation mark is wrong herein, but do not want to modify, just can continue the input of next, for example recycle phonetic entry " I also do not eat ", electronic equipment detects in this statement and does not comprise punctuation mark so, so be not the statement for adjusting punctuation mark, just identifies according to the process of normal voice identification, and by this statement output display for example, on display unit 20, as shown in Figure 2 c.
Then can repeat said process, until text has been inputted.
The second embodiment:
In the present embodiment, if user has sent a phonetic order, " phone Wang Lan ", electronic equipment is after collecting this phonetic entry, just it is carried out to speech recognition, identify be " phoning Wang Lan " afterwards, but do not know " Wang Lan " or " Wang Lan ", so will remove to go in phone directory " Wang Lan " or " Wang Lan " corresponding telephone number, if but the phone directory of now storing in the phone directory of electronic equipment not only comprises " Wang Lan ", also comprise " Wang Lan ", so electronic equipment is in the process of coupling, likely match " Wang Lan ", instead of " Wang Lan ", being exactly two has all matched, which is because cannot determine the end, so just do not carry out the instruction of " making a phone call ", be exactly to dial at random one, so likely just dial wrong.
Therefore, at this moment, user just can be in input " phoning Wang Lan " afterwards, just and then input the first statement, for example " orchid of orchid ", performs step 101, and first electronic equipment identifies " phoning Wang Lan " so, after identifying and being a phonetic order of making a phone call to Wang Lan, just then identify next sentence, i.e. the first statement, performs step 102, specifically comprise: the first statement is carried out to word segmentation processing, obtain at least three clauses; In at least three clauses, determine the first identical clause, the first clause is correct input object.
For example, the first statement of the input to user carries out semantic analysis, extract " " syllable, carry out word segmentation processing, can be broken down into as " orchid of orchid " " ", " orchid ", " orchid " three parts, and determine last " " after word " orchid " be target text; Then identification " " front modification vocabulary " orchid ", extract the word repeating with target text, i.e. " orchid ", and determine that this word is correct input object.
Then perform step 103, replace content relevant to the first clause in content to be adjusted with the first clause.In the present embodiment, for example use " orchid " to replace " haze " in electronic equipment " phoning Wang Lan " of identifying, so after electronic equipment execution of step 103, the voice command obtaining is " phoning Wang Lan ", next remove again to mate phone directory, will be correct find " Wang Lan ", and call.
Therefore, by the method in the present embodiment can be accurately, high efficiency modifying need the content of amendment.
In another embodiment, if in the Preset Time of electronic equipment after identifying voice command, also do not receive the first statement, so just continue to carry out voice command, or abandon this voice command, certainly, other coping style also can be set, for example, point out user to input the first statement.
In the present embodiment, describe as example to adjust a voice command, but the method in the present embodiment can be applicable to the amendment to text equally, for example user has utilized keyboard or phonetic entry one section of content of text, wherein there is " phoning Wang Lan ", but what really want because of user is " phoning Wang Lan ", so at this moment can trigger by a trigger action flow process of amendment, for example use phonetic entry " amendment ", or trigger by a graphical interfaces, as long as allow electronic equipment know that the statement of next input is the statement of adjusting.
User can input the first statement so, for example " orchid of orchid ", then can determine correct input object for " orchid " by mode similar to the above, then performs step 103, find with the word of " orchid " unisonance, partials and change, change to " orchid ".
The 3rd embodiment:
In the present embodiment, no matter user is in input voice command or the process at input text, can carry out bug patch by another kind of mode, for example user has utilized phonetic entry word, " Mr. Zhang ", but because phonetic entry is inaccurate, be identified as " Mr. Zhang ", so at this moment user just can input the first statement by the mode of phonetic entry, " Mr. Zhang " is corrected, for example the first statement of user's input is " length of bow opens ", and now, step 101 is complete.
Specifically, for example the first statement is " length of bow opens ", so just the first statement is divided into " bow ", " length " and " opening " three parts, certainly, in the time that reality is identified, because the first statement is also by phonetic entry, so " bow " also may be identified as other, for example " be total to ", " length " and " opening " also may be identified as other equally, so at this moment will determine which zhang last independent word is according to " bow " and " length ", specifically can identify and determine which the word that simultaneously comprises the shape of gong and chang in all zhang of identifying is by font, this word is exactly correct input object so, in the present embodiment, the word of finally determining is " opening ".
In addition, neutralizing analysis rules different in the 3rd embodiment how rationally use for the second embodiment, can be first to judge in the first statement, whether there be " ", if having " ", just adopt the mode in the second embodiment to analyze; If do not have " ", so just can adopt the analysis mode in the 3rd embodiment to analyze.
Certainly, in other embodiments, also can adopt other analysis mode, specifically can be according to the different analysis mode of the different employings of the object of amendment.
A kind of electronic equipment is also provided in one embodiment of the invention, and this electronic equipment is for example the electronic equipments such as mobile phone, panel computer, notebook computer, this electronic equipment support voice identification.
As shown in Figure 3, this electronic equipment comprises: sound collection unit 301, for gathering the first statement; The first processing unit 302, for analyzing the first statement, obtains a correct input object; The second processing unit 303, for adjusting a content to be adjusted based on correct input object.
In one embodiment, sound collection unit 301 specifically, also for before gathering the first statement, gathers the second statement; The second processing unit 303 specifically, also for based on the second statement, is determined this content to be adjusted.
Further, the second statement is specially the first clause who comprises voice command and the second clause who comprises this content to be adjusted.
In another embodiment, the first processing unit 302 is specifically for judging whether the first statement comprises punctuation mark; In the time that the first statement comprises this punctuation mark, obtain this punctuation mark.
Further, the second processing unit 303 is specifically for replacing the punctuation mark of least significant end in content to be adjusted with punctuation mark.
In another embodiment, the first processing unit 302, specifically for the first statement is carried out to word segmentation processing, obtains at least three clauses; In at least three clauses, determine the first identical clause, the first clause is correct input object.
Further, the second processing unit 303 is specifically for replacing content relevant to the first clause in content to be adjusted with the first clause.
In another embodiment, the first processing unit 302, specifically for the first statement is carried out to participle taking word as unit, obtains at least three independent words; Last independent word determined in all the other independent words based on except last independent word; Last independent word is defined as to correct input object.
Further, the second processing unit 303 is specifically for replacing content relevant to last independent word of determining in content to be adjusted with last independent word of determining.
In one embodiment, the first processing unit 302 concrete examples pronounciation processing chip in this way, is arranged on the circuit board of electronic equipment.
Further, the second processing unit 303 can be integrated in the central processing unit of electronic equipment, can be also independent process chip, is arranged on the circuit board of electronic equipment.
Further, the first processing unit 302 can be identical chips with the second processing unit 303, can be also different chips.
Further, sound collection unit, for example, be microphone, microphone array.
Each embodiment can implement separately above, also can be in conjunction with enforcement, and technician can select according to actual needs.
Various variation patterns in pronunciation inputting method in earlier figures 1 embodiment and instantiation are equally applicable to the electronic equipment of the present embodiment, by the aforementioned detailed description to pronunciation inputting method, those skilled in the art can clearly know the implementation method of electronic equipment in the present embodiment, so succinct for instructions, is not described in detail in this.
The one or more technical schemes that provide in the embodiment of the present invention, at least have following technique effect or advantage:
One embodiment of the invention is inputted the first statement by the mode of phonetic entry, then analyzes the first statement, obtains a correct input object, then based on this correct input object, one content to be adjusted is adjusted.Method in the present embodiment is because be the mode by phonetic entry, input a correct content, then just can adjust a content to be adjusted based on this correct content, so such alter mode accuracy rate is high, and method in the present embodiment does not need first to go to select especially wrong place, as long as the correct content of input can complete automatic amendment, so efficiency is also high.
Further, in one embodiment of the invention, also the mode by phonetic entry is inputted the second statement, then based on the second statement, determines content to be adjusted.Therefore, in the present embodiment, first can navigate to accurately fast needed position by phonetic entry, can solve in prior art because viewing area is less, cause the problem that positioning precision is low; Secondly first content to be adjusted is determined, can be reduced the calculated amount of coupling, so saved time and calculated amount, reduced power consumption.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt complete hardware implementation example, completely implement software example or the form in conjunction with the embodiment of software and hardware aspect.And the present invention can adopt the form at one or more upper computer programs of implementing of computer-usable storage medium (including but not limited to magnetic disk memory and optical memory etc.) that wherein include computer usable program code.
The present invention is with reference to describing according to process flow diagram and/or the block scheme of the method for the embodiment of the present invention, equipment (system) and computer program.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or the combination of square frame.Can provide these computer program instructions to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, the instruction that makes to carry out by the processor of computing machine or other programmable data processing device produces the device for realizing the function of specifying at flow process of process flow diagram or multiple flow process and/or square frame of block scheme or multiple square frame.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, the instruction that makes to be stored in this computer-readable memory produces the manufacture that comprises command device, and this command device is realized the function of specifying in flow process of process flow diagram or multiple flow process and/or square frame of block scheme or multiple square frame.
These computer program instructions also can be loaded in computing machine or other programmable data processing device, make to carry out sequence of operations step to produce computer implemented processing on computing machine or other programmable devices, thereby the instruction of carrying out is provided for realizing the step of the function of specifying in flow process of process flow diagram or multiple flow process and/or square frame of block scheme or multiple square frame on computing machine or other programmable devices.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if these amendments of the present invention and within modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.
Claims (18)
1. a pronunciation inputting method, is applied in an electronic equipment, it is characterized in that, described method comprises:
Input the first statement by the mode of phonetic entry;
Analyze described the first statement, obtain a correct input object;
Based on described correct input object, one content to be adjusted is adjusted.
2. the method for claim 1, is characterized in that, before the described mode by phonetic entry is inputted the first statement, described method also comprises:
Input the second statement by the mode of phonetic entry;
Based on described the second statement, determine described content to be adjusted.
3. method as claimed in claim 2, is characterized in that, the described mode by phonetic entry is inputted the second statement, is specially:
The first clause that input comprises voice command and the second clause who comprises described content to be adjusted.
4. the method for claim 1, is characterized in that, described the first statement of described analysis obtains a correct input object, specifically comprises:
Judge whether described the first statement comprises punctuation mark;
In the time that described the first statement comprises described punctuation mark, obtain described punctuation mark.
5. method as claimed in claim 4, is characterized in that, describedly based on described correct input object, one content to be adjusted is adjusted, and is specially:
Replace the punctuation mark of least significant end in described content to be adjusted with described punctuation mark.
6. the method for claim 1, is characterized in that, described the first statement of described analysis obtains a correct input object, specifically comprises:
Described the first statement is carried out to word segmentation processing, obtain at least three clauses;
In described at least three clauses, determine the first identical clause, described the first clause is described correct input object.
7. method as claimed in claim 6, is characterized in that, describedly based on described correct input object, described content to be adjusted is adjusted, and is specially:
Replace content relevant to described the first clause in described content to be adjusted with described the first clause.
8. the method for claim 1, is characterized in that, described the first statement of described analysis obtains a correct input object, specifically comprises:
Described the first statement is carried out to participle taking word as unit, obtain at least three independent words;
Described last independent word determined in all the other independent words based on except last independent word;
Described last independent word is defined as to correct input object.
9. method as claimed in claim 8, is characterized in that, describedly based on described correct input object, described content to be adjusted is adjusted, and is specially:
With the independent word of described last that determine replace in described content to be adjusted to described in the relevant content of last independent word of determining.
10. an electronic equipment, is characterized in that, comprising:
Sound collection unit, for gathering the first statement;
The first processing unit, for analyzing described the first statement, obtains a correct input object;
The second processing unit, for adjusting a content to be adjusted based on described correct input object.
11. electronic equipments as claimed in claim 10, is characterized in that, described sound collection unit specifically, also for before gathering described the first statement, gathers the second statement;
Described the second processing unit specifically, also for based on described the second statement, is determined described content to be adjusted.
12. electronic equipments as claimed in claim 11, is characterized in that, described the second statement is specially the first clause who comprises voice command and the second clause who comprises described content to be adjusted.
13. electronic equipments as claimed in claim 10, is characterized in that, described the first processing unit is specifically for judging whether described the first statement comprises punctuation mark; In the time that described the first statement comprises described punctuation mark, obtain described punctuation mark.
14. electronic equipments as claimed in claim 13, is characterized in that, described the second processing unit is specifically for replacing the punctuation mark of least significant end in described content to be adjusted with described punctuation mark.
15. electronic equipments as claimed in claim 10, is characterized in that, described the first processing unit, specifically for described the first statement is carried out to word segmentation processing, obtains at least three clauses; In described at least three clauses, determine the first identical clause, described the first clause is described correct input object.
16. electronic equipments as claimed in claim 15, is characterized in that, described the second processing unit is specifically for replacing content relevant to described the first clause in described content to be adjusted with described the first clause.
17. electronic equipments as claimed in claim 10, is characterized in that, described the first processing unit, specifically for described the first statement is carried out to participle taking word as unit, obtains at least three independent words; Described last independent word determined in all the other independent words based on except last independent word; Described last independent word is defined as to correct input object.
18. electronic equipments as claimed in claim 17, is characterized in that, described the second processing unit specifically for last independent word of determining described in use replace in described content to be adjusted to described in the relevant content of last independent word of determining.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210584246.9A CN103903618B (en) | 2012-12-28 | 2012-12-28 | A kind of pronunciation inputting method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210584246.9A CN103903618B (en) | 2012-12-28 | 2012-12-28 | A kind of pronunciation inputting method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103903618A true CN103903618A (en) | 2014-07-02 |
| CN103903618B CN103903618B (en) | 2017-08-29 |
Family
ID=50994900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210584246.9A Active CN103903618B (en) | 2012-12-28 | 2012-12-28 | A kind of pronunciation inputting method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103903618B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869632A (en) * | 2015-01-22 | 2016-08-17 | 北京三星通信技术研究有限公司 | Speech recognition-based text revision method and device |
| CN105893345A (en) * | 2016-03-28 | 2016-08-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN106250364A (en) * | 2016-07-20 | 2016-12-21 | 科大讯飞股份有限公司 | A kind of text modification method and device |
| CN106293368A (en) * | 2015-05-26 | 2017-01-04 | 联想(北京)有限公司 | A kind of data processing method and electronic equipment |
| CN106484134A (en) * | 2016-09-20 | 2017-03-08 | 深圳Tcl数字技术有限公司 | The method and device of the phonetic entry punctuation mark based on Android system |
| CN106782543A (en) * | 2017-03-24 | 2017-05-31 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN107221328A (en) * | 2017-05-25 | 2017-09-29 | 百度在线网络技术（北京）有限公司 | The localization method and device in modification source, computer equipment and computer-readable recording medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1482469A2 (en) * | 2003-05-29 | 2004-12-01 | Robert Bosch Gmbh | System, method and device for language education through a voice portal server |
| CN1645477A (en) * | 2004-01-20 | 2005-07-27 | 微软公司 | Automatic speech recognition learning using user corrections |
| CN1703923A (en) * | 2002-10-18 | 2005-11-30 | 中国科学院声学研究所 | Portable digital mobile communication apparatus and voice control method and system thereof |
| CN1892817A (en) * | 2005-06-28 | 2007-01-10 | 阿瓦雅技术公司 | Speech recognition assisted autocompletion of composite characters |
| CN1941077A (en) * | 2005-09-27 | 2007-04-04 | 株式会社东芝 | Apparatus and method speech recognition of character string in speech input |
| JP4064413B2 (en) * | 2005-06-27 | 2008-03-19 | 株式会社東芝 | Communication support device, communication support method, and communication support program |
| CN102792320A (en) * | 2010-01-18 | 2012-11-21 | 苹果公司 | Intelligent automated assistant |
| WO2012167168A2 (en) * | 2011-06-03 | 2012-12-06 | Apple Inc. | Generating and processing task items that represent tasks to perform |
-
2012
- 2012-12-28 CN CN201210584246.9A patent/CN103903618B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1703923A (en) * | 2002-10-18 | 2005-11-30 | 中国科学院声学研究所 | Portable digital mobile communication apparatus and voice control method and system thereof |
| EP1482469A2 (en) * | 2003-05-29 | 2004-12-01 | Robert Bosch Gmbh | System, method and device for language education through a voice portal server |
| CN1645477A (en) * | 2004-01-20 | 2005-07-27 | 微软公司 | Automatic speech recognition learning using user corrections |
| JP4064413B2 (en) * | 2005-06-27 | 2008-03-19 | 株式会社東芝 | Communication support device, communication support method, and communication support program |
| CN1892817A (en) * | 2005-06-28 | 2007-01-10 | 阿瓦雅技术公司 | Speech recognition assisted autocompletion of composite characters |
| CN1941077A (en) * | 2005-09-27 | 2007-04-04 | 株式会社东芝 | Apparatus and method speech recognition of character string in speech input |
| CN102792320A (en) * | 2010-01-18 | 2012-11-21 | 苹果公司 | Intelligent automated assistant |
| WO2012167168A2 (en) * | 2011-06-03 | 2012-12-06 | Apple Inc. | Generating and processing task items that represent tasks to perform |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869632A (en) * | 2015-01-22 | 2016-08-17 | 北京三星通信技术研究有限公司 | Speech recognition-based text revision method and device |
| CN106293368A (en) * | 2015-05-26 | 2017-01-04 | 联想(北京)有限公司 | A kind of data processing method and electronic equipment |
| CN106293368B (en) * | 2015-05-26 | 2020-05-26 | 联想(北京)有限公司 | Data processing method and electronic equipment |
| CN105893345A (en) * | 2016-03-28 | 2016-08-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN106250364A (en) * | 2016-07-20 | 2016-12-21 | 科大讯飞股份有限公司 | A kind of text modification method and device |
| CN106484134A (en) * | 2016-09-20 | 2017-03-08 | 深圳Tcl数字技术有限公司 | The method and device of the phonetic entry punctuation mark based on Android system |
| WO2018053964A1 (en) * | 2016-09-20 | 2018-03-29 | 深圳Tcl数字技术有限公司 | Android-based method and apparatus for voice input of punctuation mark |
| CN106782543A (en) * | 2017-03-24 | 2017-05-31 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN107221328A (en) * | 2017-05-25 | 2017-09-29 | 百度在线网络技术（北京）有限公司 | The localization method and device in modification source, computer equipment and computer-readable recording medium |
| US10528670B2 (en) | 2017-05-25 | 2020-01-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | Amendment source-positioning method and apparatus, computer device and readable medium |
| CN107221328B (en) * | 2017-05-25 | 2021-02-19 | 百度在线网络技术（北京）有限公司 | Method and device for positioning modification source, computer equipment and readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103903618B (en) | 2017-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103903618A (en) | Voice input method and electronic device | |
| CN106598939B (en) | A kind of text error correction method and device, server, storage medium | |
| CN102682763B (en) | Method, device and terminal for correcting named entity vocabularies in voice input text | |
| CN1918578B (en) | Handwriting and voice input with automatic correction | |
| KR102191425B1 (en) | Apparatus and method for learning foreign language based on interactive character | |
| KR101590724B1 (en) | Method for modifying error of speech recognition and apparatus for performing the method | |
| CN103000176B (en) | Speech recognition method and system | |
| CN103578471B (en) | Speech identifying method and its electronic installation | |
| US20140108004A1 (en) | Text/character input system, such as for use with touch screens on mobile phones | |
| KR20120011010A (en) | Handwriting recognition method and device | |
| CN102439540A (en) | Input method editor | |
| CN104166462A (en) | Input method and system for characters | |
| JP2005084681A (en) | Method and system for semantic language modeling and reliability measurement | |
| KR101474854B1 (en) | Apparatus and method for selecting a control object by voice recognition | |
| CN103400576B (en) | Based on speech model update method and the device of User action log | |
| CN102148031A (en) | Voice recognition and interaction system and method | |
| GB2355833A (en) | Natural language input | |
| CN103021412A (en) | Voice recognition method and system | |
| JP2002116796A (en) | Voice processor and method for voice processing and storage medium | |
| Vertanen et al. | Parakeet: A continuous speech recognition system for mobile touch-screen devices | |
| CN110738997B (en) | Information correction method and device, electronic equipment and storage medium | |
| CN103186522A (en) | Electronic device and natural language analyzing method thereof | |
| CN103631784B (en) | Page content retrieval method and system | |
| CN107424612A (en) | Processing method, device and machine readable media | |
| CN113343671A (en) | Statement error correction method, device and equipment after voice recognition and storage medium |
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 |