CN103207769A - Method and user equipment for voice amending - Google Patents
Method and user equipment for voice amending Download PDFInfo
- Publication number
- CN103207769A CN103207769A CN2012100130133A CN201210013013A CN103207769A CN 103207769 A CN103207769 A CN 103207769A CN 2012100130133 A CN2012100130133 A CN 2012100130133A CN 201210013013 A CN201210013013 A CN 201210013013A CN 103207769 A CN103207769 A CN 103207769A
- Authority
- CN
- China
- Prior art keywords
- vocabulary
- data
- typing
- user
- speech data
- 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
Landscapes
- Machine Translation (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a method for voice amending and user equipment, relates to the technical field of communication and aims at reducing the operation steps of voice amending and improving the operation experience of a user. The method comprises the steps that the user equipment receives voice data recorded by the user and used for amending wrong words in recorded data, the recorded data comprises data recorded through a keyboard or voice by the user, the user equipment searches for the wrong words in the recorded data according to the voice data, displays correct words according to the voice data and replaces the wrong words with the correct words. The method and user equipment for voice amending are mainly used for the field of data recording.
Description
Technical field
The present invention relates to communication technical field, relate in particular to a kind of method and subscriber equipment of voice correction.
Background technology
In the modern communications life, (User Equipment, UE) terminal device as communication process generally has been deep into huge numbers of families to subscriber equipment, by people are known and use.UE mainly gathers the data content of user's input by keyboard (comprising soft keyboard) when carrying out NOT-circuit territory business, for example the user is by keyboard typing short message content, record p.m.entry content etc.
For improving the intelligent degree of UE and enriching the user's data input and experience, prior art has adopted the technology of voice logging datas, collect the user's voice data content by microphone, identify the lexical data of user's needs typing according to speech recognition technology, then this lexical data is converted into text data and uses for the user.The voice input technology has been saved the time of user's logging data when having enriched data-entry-form, be subjected to numerous UE user's support and like.
In realization in the process of predicate sound logging data, the inventor finds the existing voice input technology, and there are the following problems at least: when certain vocabulary typing mistake, need the user that voice typing pattern is switched to keyboard typing pattern, pass through the vocabulary of keyboard manual correction typing mistake then, increase operation steps of user, reduced user's operating experience.
Summary of the invention
Embodiments of the invention provide a kind of method and subscriber equipment of voice correction, can revise the vocabulary of typing mistake by voice, have saved the operation steps of revising, and have improved user's operating experience.
For achieving the above object, embodiments of the invention adopt following technical scheme:
A kind of method of voice correction comprises:
Receive the speech data of user's typing, described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that described user is by the data of keyboard typing or the data by the voice typing;
In the data of typing, search described wrong vocabulary according to described speech data;
Show correct vocabulary according to described speech data;
Described wrong vocabulary is replaced with described correct vocabulary.
A kind of subscriber equipment comprises:
Adopt the sound device, be used for to receive the speech data of user's typing, described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that described user is by the data of keyboard typing or the data by the voice typing;
Searcher is used for searching described wrong vocabulary according to described speech data in the data of typing;
Processor is used for showing correct vocabulary according to described speech data;
Described processor also is used for described wrong vocabulary is replaced with described correct vocabulary.
Method and the subscriber equipment of the voice correction that the embodiment of the invention provides, can identify the vocabulary of input error according to the speech data of user's input, speech data according to user's input provides interchangeable vocabulary for the user then, and wrong vocabulary is replaced with correct vocabulary.With need the user that voice typing pattern is switched to keyboard typing pattern in the prior art to compare by keyboard manual correction mistake vocabulary then, reduced the operation steps of voice corrections, improved user's operating experience.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the method flow diagram of voice correction in the embodiment of the invention;
Fig. 2 is the method flow diagram of voice correction in the another embodiment of the present invention;
Fig. 3 is the lexical set that subscriber equipment shows in the embodiment of the invention;
Fig. 4 is the another kind of lexical set that subscriber equipment shows in the embodiment of the invention;
Fig. 5 is the another kind of lexical set that subscriber equipment shows in the embodiment of the invention;
Fig. 6 is the another kind of lexical set that subscriber equipment shows in the embodiment of the invention;
Fig. 7 is the structural representation of subscriber equipment in the embodiment of the invention;
Fig. 8 is the another kind of structural representation of subscriber equipment in the embodiment of the invention;
Fig. 9 is the another kind of structural representation of subscriber equipment in the embodiment of the invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
The embodiment of the invention provides a kind of method of voice correction, and as shown in Figure 1, described method comprises the steps:
101, UE receives the speech data of user's typing.
Described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that the user passes through the data of keyboard typing or the data by the voice typing.The data layout of the data of typing is text formatting, comprises that the user passes through the Document type data of keyboard (comprising physical keyboard and soft keyboard) typing and user by the voice typing and is converted to the data of text formatting.
102, UE searches wrong vocabulary according to speech data in the data of typing.
Described speech data is the right pronunciation of wrong vocabulary, after UE receives the speech data that the user sends, searches the wrong vocabulary of needs correction according to this speech data in the Document type data of typing.From user's angle, the user only needs the right pronunciation of the vocabulary of needs correction read and get final product, from the angle of UE, searches the vocabulary of user's needs correction according to speech data, will not search for other wrong vocabulary that exist in the text for UE.
The described wrong vocabulary that UE searches is consistent with speech data phonetic in the text data, but with the inconsistent vocabulary of speech data tone.Described tone comprises, two, three and the four tones of standard Chinese pronunciation.For the vocabulary of being made up of at least two words, to tone that should word not simultaneously, this vocabulary is wrong vocabulary in having at least one word and speech data in this vocabulary.When repeatedly occurring same wrong vocabulary in the text data, UE finds out this all in text mistake vocabulary.
103, UE shows correct vocabulary according to speech data.
The correct vocabulary that UE shows is vocabulary consistent with speech data phonetic and the tone unanimity, for the vocabulary of being formed by two words at least, when each word in this vocabulary when all and tone consistent with the phonetic of corresponding word in the speech data is consistent, this vocabulary just is correct vocabulary.
104, UE replaces with correct vocabulary with wrong vocabulary.
The method of the voice correction that the embodiment of the invention provides can identify wrong vocabulary according to the speech data of user's input, and the speech data according to user's input shows the correct vocabulary of replacing this mistake vocabulary then.With need the user that voice typing pattern is switched to keyboard typing pattern in the prior art to key in correct vocabulary again by keyboard deletion error vocabulary then and compare, particularly when repeatedly occurring same wrong vocabulary in the logging data, reduce the operation steps of voice corrections, improved user's operating experience.
Further, the embodiment of the invention provides the method for another kind of voice correction, and as shown in Figure 2, described method is the expansion to method embodiment shown in Figure 1.Described method comprises the steps:
201, UE receives the correction trigger message of user's input.
UE can receive the correction trigger message by pressing the last default correction button of keyboard (comprising physical keyboard and soft keyboard) by receiving the user, also can receive the correction trigger message by the preset trigger keyword that the reception user reads.Wherein, when the preset trigger keyword of reading by the reception user received the correction trigger message, it was " error correction ", " inspection ", " correction ", " corrigendum " that described preset trigger keyword can not limit.Described preset trigger keyword can be arranged by UE manufacturer, also can be by the user according to arranging with people's custom.
In an application scenarios of the embodiment of the invention, the user can trigger the voice update information in the process of voice typing.If trigger the voice correction by reading the mode that triggers keyword, receive the speech data of user's typing after then UE need wait for according to the default time interval again after receiving this triggering keyword, execution in step 202 again after namely waiting for according to the default time interval.Be example with " error correction " as triggering keyword: because " error correction " this word itself also may be the data that need typing in voice typing process, and " error correction " is comprised in a whole word the inside as the data that need typing the time, and this vocabulary back can connect other vocabulary.So UE is for distinguishing the data of voice update information and normal typing, can separate by the data field that the time interval of presetting will be controlled signaling and input, when " error correction " during as the voice update information, the user can read the speech data of reading correction after waited for according to the default time interval " error correction " back again, UE this moment execution in step 202 again.When " error correction " during as the data of typing, the user can continue to read follow-up vocabulary after reading " error correction ", UE knows that the user does not wait for according to the default time interval, just carries out typing with " error correction " as the data of typing after reading " error correction ".
The duration in the described time interval is arranged by UE manufacturer, also can be arranged according to the time length of oneself being accustomed to by the user, and the embodiment of the invention does not limit this.
202, UE receives the speech data of user's typing.
Described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that the user passes through the data of keyboard typing or the data by the voice typing.The data layout of the data of typing is text formatting, comprises that the user passes through the Document type data of keyboard (comprising physical keyboard and soft keyboard) typing and user by the voice typing and is converted to the data of text formatting.For example: the correct input of " beautiful seal " should be " voice " in " fast in the idiographic flow of beautiful seal ... " the words, then the speech data of user's input is " YuYin ", its tone is consistent with the tone of " voice ", and namely " Yu " is that three " Yin " are.
203, UE searches wrong vocabulary according to speech data in the data of typing.
Described speech data is the right pronunciation of wrong vocabulary, after UE receives the speech data that the user sends, searches the wrong vocabulary of needs correction according to this speech data in the Document type data of typing.From user's angle, the user only needs the right pronunciation of the vocabulary of needs correction read and get final product, from the angle of UE, searches the vocabulary of user's needs correction according to speech data, will not search for other wrong vocabulary that exist in the text for UE.
The described wrong vocabulary that UE searches is consistent with speech data phonetic in the text data, but with the inconsistent vocabulary of speech data tone.Described tone comprises, two, three and the four tones of standard Chinese pronunciation.In embodiments of the present invention, mistake vocabulary is " beautiful seal ", and " Yu " is that the four tones of standard Chinese pronunciation " Yin " are the four tones of standard Chinese pronunciation, and be inconsistent with the tone in the speech data.When also having other but tone inconsistent vocabulary consistent with speech data phonetic in the text data of typing, UE searches this vocabulary equally.For example when also having " fish seal " in the text data except " beautiful seal ", UE finds out " fish seal " equally.
In addition, for the vocabulary of being made up of at least two words, to tone that should word not simultaneously, this vocabulary is wrong vocabulary in having at least one word and speech data in this vocabulary.For example, there is " language seal " word in the text data, because the tone of " seal " word is the four tones of standard Chinese pronunciation, transfer different with a sound of " sound " word in the speech data, so " language " word is consistent with " language " word tone in the speech data in " even language seal ", UE also will " speak and print " word as wrong vocabulary.
When repeatedly occurring same wrong vocabulary in the text data, UE finds out this all in text mistake vocabulary.For example, occurred " beautiful seal " word three times in the text data of typing, then UE all finds out " the beautiful seal " of these three times appearance.In addition, when occurring the inconsistent different wrong vocabulary of the consistent tone of phonetic and speech data and speech data in the text data of typing simultaneously, UE regards phonetic as same wrong vocabulary with speech data unanimity tone and the inconsistent different wrong vocabulary of speech data and finds out.For example, when occurring " beautiful seal " and " language seal " two words in the text data of typing simultaneously, though " beautiful seal " is all consistent with the phonetic of speech data with " language seal ", but the tone between " voice " three in " beautiful seal ", " language seal " and the speech data is different in twos, and UE searches " beautiful seal " and " language seal " as same wrong vocabulary in such cases.
UE only searches wrong vocabulary according to the speech data that the user provides, and will not search for other wrong vocabulary that exist in the text data.Described other wrong vocabulary are for having the inconsistent vocabulary of corresponding word phonetic in a word and the speech data that the user provides at least.Described other wrong vocabulary can be searched in user's speech data typing next time according to user's needs.
204, UE shows the lexical set that the vocabulary consistent with speech data phonetic is formed, so that the user selects correct vocabulary in lexical set.
When phonetic and tone all with the corresponding consistent situation of speech data under interchangeable correct vocabulary during more than one, UE shows all phonetics with the form of the tone vocabulary that all correspondence is consistent with speech data with set, select correct vocabulary for the user in this set.For example, in text data " automobile and train can the student be identified in the teacher angle ... ", the user need be modified to " church " with " angle meeting " wherein, because the vocabulary of and tone unanimity consistent with " church " word phonetic also has " crossing ", so as shown in Figure 3, UE comprises " church " and " crossing " two vocabulary for the set that the user provides, and selects a vocabulary as correct vocabulary as required by the user.Perhaps have again, " meaning " is all corresponding identical with tone with " peculiar smell " phonetic, and UE needs to show " meaning " and " peculiar smell " two vocabulary equally.
Further, because the revised correct vocabulary of user might not be habitual vocabulary, so can also be selected by the user only with phonetic and the corresponding consistent vocabulary composition set of speech data.As shown in Figure 4, because the tone of vocabulary is not limited, so this set is more with respect to the optional vocabulary of the described set of Fig. 3, but extent of amendment is bigger.For example the 3rd vocabulary " friendship brightness " though be not habitual vocabulary, is not got rid of the possibility that the user needs " angle meeting " is modified to " friendship brightness ", so this vocabulary is included in the set, guarantees the extent of amendment maximum of voice correction.
Further, when the situation of the corresponding different implications of the different tones of certain vocabulary occurring, in set shown in Figure 4, only show once this vocabulary, to avoid the demonstration that repeats of identical vocabulary.For example, when the tone of " church " two words is and during the four tones of standard Chinese pronunciation, this word means " making ... association " as verb in proper order, when the tone of " church " two words all was the four tones of standard Chinese pronunciation, this word meant " religious group " as noun.UE only shows once " church " word in lexical set in such cases, and the multiple tone according to this vocabulary does not repeatedly show this vocabulary.
Preferably, when showing the set of the only vocabulary composition that phonetic and speech data is corresponding consistent shown in Figure 4, the subclass that can show each word in the vocabulary respectively, by the user each word is selected, thereby avoided showing the problem that too tediously long, the inconvenient user of set that vocabulary that all permutation and combination form causes selects.Concrete, as shown in Figure 5, when the speech data of user's input was " JiaoHui ", UE showed the optional subclass of " Jiao " word and the optional subclass of " Hui " word respectively.The user can select progressively " Jiao " word and the correct word of " Hui " word, selects correct vocabulary thus.If UE shows in mode shown in Figure 4, then each have the situation of 4 options for " Jiao " word and " Hui " word, as shown in Figure 6, UE need demonstrate 16 optional vocabulary according to the permutation and combination of 4*4, the problem that can cause the too tediously long inconvenient user of lexical set to select.
205, UE replaces with correct vocabulary with wrong vocabulary.
UE replaces with correct vocabulary in the step 204 with the wrong vocabulary of searching in the step 203.If same wrong vocabulary repeatedly occurs in the text data of typing, UE can not limit and adopt one of following two kinds of substitute modes that wrong vocabulary is replaced:
1) UE can replace with correct vocabulary in the lump with the wrong vocabulary that repeatedly occurs.For example: " beautiful seal " word occurred 5 times in the text data of typing, and then UE replaces with " voice " simultaneously with 5 " beautiful seals ".
Further, when also occurring 3 " language seal " words in the text data of typing, UE replaces " seal of speaking " and " beautiful seal " in the lump as same wrong vocabulary, and soon 5 " beautiful seal " and 3 " language seals " replaces with " voice " simultaneously.
2) UE can replace with correct vocabulary with the wrong vocabulary that repeatedly occurs one by one, and every replacement finish one should mistake vocabulary after, whether the prompting user needs the next one should be replaced by mistake vocabulary, carries out the replacement of next wrong vocabulary after the affirmation that obtains the user.For example: " beautiful seal " word occurred 5 times in the text data of typing, and UE replaces with " voice " simultaneously with 5 " beautiful seals " after carrying out pointing out the affirmation that also obtains the user for 5 times 5 times.If once pointing out, certain during the user points out 5 times does not confirm that then UE does not replace this time prompting corresponding " beautiful seal ".For the situation that also occurs 3 " language seal " words in the text data of typing, UE replaces " language seal " and " beautiful seal " in the lump one by one as same wrong vocabulary.
Further, when occurring a plurality of phonetic unanimities in the text data of typing but during the inconsistent wrong vocabulary of tone, in above-mentioned substitute mode, UE can also be successively with a plurality of phonetic unanimities but the inconsistent wrong vocabulary of tone replace.For example, " beautiful seal " word occurred 5 times in the text data of typing, and " language seal " word occurred 3 times.UE can replace with " voice " word with 5 " beautiful seals " earlier, and then 3 " language seals " are replaced with " voice " word.
The method of the voice correction that the embodiment of the invention provides can identify wrong vocabulary according to the speech data of user's input, and the speech data according to user's input shows the correct vocabulary of replacing this mistake vocabulary then.With need the user that voice typing pattern is switched to keyboard typing pattern in the prior art to key in correct vocabulary again by keyboard deletion error vocabulary then and compare, reduced the operation steps of voice corrections, improved user's operating experience.
In addition, the method for the voice correction that the embodiment of the invention provides can also the content to the typing mistake be carried out the voice correction in the process of voice typing, distinguishes the data content of voiced keyword and typing by the default time interval.Further improved user's operating experience.
Further, the method of the voice correction that the embodiment of the invention provides, can also look into all but tone inconsistent wrong vocabulary consistent with speech data phonetic and look for and replace, reduce the number of times of user's typing speech data, further reduce the step of voice corrections.
With reference to the realization of method embodiment shown in Figure 2, the embodiment of the invention provides a kind of subscriber equipment of voice correction, as shown in Figure 7, and in order to realize method embodiment shown in Figure 2.Described subscriber equipment comprises: adopt sound device 71, searcher 72 and processor 73, wherein,
The described sound device 71 of adopting be used for to receive the speech data of user's typing, and described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that the user passes through the data of keyboard typing or the data by the voice typing.The data layout of the data of typing is text formatting, comprises that the user passes through the Document type data of keyboard (comprising physical keyboard and soft keyboard) typing and user by the voice typing and is converted to the data of text formatting.
Described searcher 72 is used for searching wrong vocabulary according to speech data in the data of typing.
Described speech data is the right pronunciation of wrong vocabulary, when described adopt sound device 71 and receive the speech data that the user sends after, described searcher 72 is searched the wrong vocabulary of needs correction in the Document type data of typing according to this speech data.Angle from the user, the user only needs the right pronunciation of the vocabulary of needs correction read and gets final product, from the angle of subscriber equipment, 72 of described searchers are searched the vocabulary of user's needs correction according to speech data, will not search for other wrong vocabulary that exist in the text.
Described processor 73 is used for showing correct vocabulary according to speech data.
The correct vocabulary that described processor 73 shows is vocabulary consistent with speech data phonetic and the tone unanimity, for the vocabulary of being formed by two words at least, when each word in this vocabulary when all and tone consistent with the phonetic of corresponding word in the speech data is consistent, this vocabulary just is correct vocabulary.
Described processor 73 also is used for wrong vocabulary is replaced with correct vocabulary.
Further, as shown in Figure 8, described subscriber equipment also comprises:
The described sound device 71 of adopting also is used for receiving the preset trigger keyword that the user reads.
When the described sound device 71 of adopting receives when revising trigger message by the preset trigger keyword that receives the user and read, it is " error correction ", " inspection ", " correction ", " corrigendum " that described preset trigger keyword can not limit.Described preset trigger keyword can be arranged by UE manufacturer, also can be by the user according to arranging with people's custom.
Further, the described sound device 71 of adopting receives the speech data of user's typing also for after waiting for according to the default time interval.
In an application scenarios of the embodiment of the invention, the user can trigger the voice update information in the process of voice typing.If trigger the voice correction by reading the mode that triggers keyword, then described adopting receives the speech data of user's typing after sound device 71 need be waited for according to the default time interval again after receiving this triggering keyword, still is the data of typing in order to distinguish the speech data of user's typing for triggering keyword.
The duration in the described time interval is arranged by UE manufacturer, also can be arranged according to the time length of oneself being accustomed to by the user, and the embodiment of the invention does not limit this.
Further, described searcher 72 specifically is used for searching consistent with speech data phonetic but the inconsistent vocabulary of tone according to speech data in the data of typing.
The wrong vocabulary that described searcher 72 is searched is consistent with speech data phonetic in the text data, but with the inconsistent vocabulary of speech data tone.Described tone comprises, two, three and the four tones of standard Chinese pronunciation.In addition, for the vocabulary of being made up of at least two words, to tone that should word not simultaneously, this vocabulary is wrong vocabulary in having at least one word and speech data in this vocabulary.
When repeatedly occurring same wrong vocabulary in the text data, described searcher 72 finds out this all in text mistake vocabulary.
72 speech datas that provide according to the user of described searcher are searched wrong vocabulary, will not search for other wrong vocabulary that exist in the text.Described other wrong vocabulary are for having the inconsistent vocabulary of corresponding word phonetic in a word and the speech data that the user provides at least.Described other wrong vocabulary can be searched in user's speech data typing next time according to user's needs.
Further, the described processor 73 concrete lexical sets that are used for showing the vocabulary composition consistent with speech data phonetic are so that the user selects correct vocabulary in lexical set.
When phonetic and tone all with the corresponding consistent situation of speech data under interchangeable correct vocabulary during more than one, described processor 73 shows all phonetics with the form of the tone vocabulary that all correspondence is consistent with speech data with set, select correct vocabulary for the user in this set.Perhaps, because the revised correct vocabulary of user might not be habitual vocabulary, so described processor 73 is shown to the user only with phonetic and the corresponding consistent vocabulary composition set of speech data.
Further, when wrong vocabulary occurred at least twice in the data of typing, described processor 73 also was used for this mistake vocabulary that was occurred is replaced with correct vocabulary in batches.
Described processor 73 also is used for this mistake vocabulary that was occurred is replaced with correct vocabulary one by one.
Further, as shown in Figure 9, described subscriber equipment also comprises:
Prompting device 91 is used for after a wrong vocabulary is finished in described processor 73 every replacements, and whether the prompting user needs the next one should be replaced by mistake vocabulary, and described processor 73 carries out the replacement that the next one should mistake vocabulary after the affirmation that obtains the user.
The subscriber equipment of the voice correction that the embodiment of the invention provides can identify wrong vocabulary according to the speech data of user's input, and the speech data according to user's input shows the correct vocabulary of replacing this mistake vocabulary then.With need the user that voice typing pattern is switched to keyboard typing pattern in the prior art to key in correct vocabulary again by keyboard deletion error vocabulary then and compare, reduced the operation steps of voice corrections, improved user's operating experience.
In addition, the subscriber equipment of the voice correction that the embodiment of the invention provides can also the content to the typing mistake carry out the voice correction in the process of voice typing, distinguishes the data content of voiced keyword and typing by the default time interval.Further improved user's operating experience.
Further, the subscriber equipment of the voice correction that the embodiment of the invention provides, can also look into all but tone inconsistent wrong vocabulary consistent with speech data phonetic and look for and replace, reduce the number of times of user's typing speech data, further reduce the step of voice corrections.
UE described in the embodiment of the invention is subscriber equipment, other subscriber equipmenies that comprise mobile phone, panel computer and have the information input function, and the embodiment of the invention is not restricted this.
Through the above description of the embodiments, the those skilled in the art can be well understood to the present invention and can realize by the mode that software adds essential common hardware, can certainly pass through hardware, but the former is better embodiment under a lot of situation.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product is stored in the storage medium that can read, floppy disk as computing machine, hard disk or CD etc., comprise some instructions with so that computer equipment (can be personal computer, server, the perhaps network equipment etc.) carry out the described method of each embodiment of the present invention.
The above; only be the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; can expect easily changing or replacing, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion by described protection domain with claim.
Claims (13)
1. the method for a voice correction is characterized in that, comprising:
Receive the speech data of user's typing, described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that described user is by the data of keyboard typing or the data by the voice typing;
In the data of typing, search described wrong vocabulary according to described speech data;
Show correct vocabulary according to described speech data;
Described wrong vocabulary is replaced with described correct vocabulary.
2. the method for voice correction according to claim 1 is characterized in that, before the speech data of described reception user typing, also comprises:
Receive the correction trigger message of described user's input, described correction trigger message is used to indicate and begins to carry out the voice correction.
3. the method for voice correction according to claim 2 is characterized in that, the correction trigger message of the described user's input of described reception comprises:
Receive the described correction trigger message that described user sends by preset trigger button on the touch control keyboard; Perhaps,
Receive the preset trigger keyword that described user reads.
4. the method for voice correction according to claim 3 is characterized in that, after the preset trigger keyword that the described user of described reception reads, also comprises:
After waiting for according to the default time interval, receive the speech data of described user's typing.
5. the method for voice correction according to claim 1 is characterized in that, describedly searches described wrong vocabulary according to described speech data in the data of typing, comprising:
In the data of typing, search consistent with described speech data phonetic but the inconsistent vocabulary of tone according to described speech data.
6. the method for voice correction according to claim 1 is characterized in that, shows correct vocabulary according to described speech data, comprising:
Show the lexical set that the vocabulary consistent with described speech data phonetic is formed, so that described user selects correct vocabulary in described lexical set.
7. the method for voice correction according to claim 1 is characterized in that, when described wrong vocabulary occurs at least twice in the data of described typing, described described wrong vocabulary is replaced with described correct vocabulary, comprising:
The described wrong vocabulary that was occurred is replaced with described correct vocabulary in batches; Perhaps,
The described wrong vocabulary that was occurred is replaced with described correct vocabulary one by one, and after a described wrong vocabulary is finished in every replacement, point out described user whether to need the described wrong vocabulary of the next one is replaced, after the affirmation that obtains described user, carry out the replacement of next described wrong vocabulary.
8. a subscriber equipment is characterized in that, comprising:
Adopt the sound device, be used for to receive the speech data of user's typing, described speech data is used for revising the wrong vocabulary of the data of typing, and the data of described typing comprise that described user is by the data of keyboard typing or the data by the voice typing;
Searcher is used for searching described wrong vocabulary according to described speech data in the data of typing;
Processor is used for showing correct vocabulary according to described speech data;
Described processor also is used for described wrong vocabulary is replaced with described correct vocabulary.
9. subscriber equipment according to claim 8 is characterized in that, also comprises:
Receiver is used for receiving the described correction trigger message that described user sends by preset trigger button on the touch control keyboard;
The described sound device of adopting also is used for receiving the preset trigger keyword that described user reads.
10. subscriber equipment according to claim 9 is characterized in that, comprising:
The described sound device of adopting receives the speech data of described user's typing also for after waiting for according to the default time interval.
11. subscriber equipment according to claim 8 is characterized in that, comprising:
Described searcher specifically is used for searching consistent with described speech data phonetic but the inconsistent vocabulary of tone according to described speech data in the data of typing.
12. subscriber equipment according to claim 8 is characterized in that, comprising:
Described preparation implement body is used for showing the lexical set of the vocabulary composition consistent with described speech data phonetic, so that described user selects correct vocabulary in described lexical set.
13. subscriber equipment according to claim 8 is characterized in that, when described wrong vocabulary occurs at least twice in the data of described typing, comprising:
Described processor also is used for the described wrong vocabulary that was occurred is replaced with described correct vocabulary in batches;
Described processor also is used for the described wrong vocabulary that was occurred is replaced with described correct vocabulary one by one;
Described subscriber equipment also comprises: prompting device, be used for after a described wrong vocabulary is finished in every replacement, whether point out described user to need the described wrong vocabulary of the next one is replaced, described processor carries out the replacement of next described wrong vocabulary after the affirmation that obtains described user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210013013.3A CN103207769B (en) | 2012-01-16 | 2012-01-16 | The method of voice correction and user equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210013013.3A CN103207769B (en) | 2012-01-16 | 2012-01-16 | The method of voice correction and user equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103207769A true CN103207769A (en) | 2013-07-17 |
| CN103207769B CN103207769B (en) | 2016-10-05 |
Family
ID=48755004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210013013.3A Active CN103207769B (en) | 2012-01-16 | 2012-01-16 | The method of voice correction and user equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103207769B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699359A (en) * | 2013-12-23 | 2014-04-02 | 华为技术有限公司 | Correction method, correction system for voice command and electronic device |
| CN104331265A (en) * | 2014-09-30 | 2015-02-04 | 北京金山安全软件有限公司 | Voice input method, device and terminal |
| CN105091208A (en) * | 2014-05-23 | 2015-11-25 | 美的集团股份有限公司 | Method and system for controlling air speed of air conditioner |
| CN105185377A (en) * | 2015-09-24 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Voice-based file generation method and device |
| CN105469801A (en) * | 2014-09-11 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Input speech restoring method and device |
| CN106095766A (en) * | 2015-04-28 | 2016-11-09 | 谷歌公司 | Use selectivity again to talk and correct speech recognition |
| 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 |
| CN106406807A (en) * | 2016-09-19 | 2017-02-15 | 北京云知声信息技术有限公司 | A method and a device for voice correction of characters |
| CN106775349A (en) * | 2016-11-29 | 2017-05-31 | 珠海市魅族科技有限公司 | A kind of speech modification method and device of word content |
| CN107071553A (en) * | 2017-06-05 | 2017-08-18 | 广东小天才科技有限公司 | Method, device and computer readable storage medium for modifying video and voice |
| CN107220228A (en) * | 2017-06-13 | 2017-09-29 | 深圳市鹰硕技术有限公司 | One kind teaching recorded broadcast data correction device |
| CN107293299A (en) * | 2017-06-16 | 2017-10-24 | 朱明增 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
| CN108664984A (en) * | 2017-03-28 | 2018-10-16 | 深圳市凯立德科技股份有限公司 | A kind of method and device of data inspection |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108021554A (en) * | 2017-11-14 | 2018-05-11 | 无锡小天鹅股份有限公司 | Audio recognition method, device and washing machine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5909667A (en) * | 1997-03-05 | 1999-06-01 | International Business Machines Corporation | Method and apparatus for fast voice selection of error words in dictated text |
| CN1293427A (en) * | 1999-10-19 | 2001-05-02 | 微软公司 | Speech recognition pattern error correction system and method |
| JP2006277519A (en) * | 2005-03-30 | 2006-10-12 | Toshiba Corp | Interaction device, interaction scenario editing device, interaction method and program |
| CN101593076A (en) * | 2008-05-28 | 2009-12-02 | Lg电子株式会社 | Portable terminal and the method that is used to revise its text |
-
2012
- 2012-01-16 CN CN201210013013.3A patent/CN103207769B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5909667A (en) * | 1997-03-05 | 1999-06-01 | International Business Machines Corporation | Method and apparatus for fast voice selection of error words in dictated text |
| CN1293427A (en) * | 1999-10-19 | 2001-05-02 | 微软公司 | Speech recognition pattern error correction system and method |
| JP2006277519A (en) * | 2005-03-30 | 2006-10-12 | Toshiba Corp | Interaction device, interaction scenario editing device, interaction method and program |
| CN101593076A (en) * | 2008-05-28 | 2009-12-02 | Lg电子株式会社 | Portable terminal and the method that is used to revise its text |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015096504A1 (en) * | 2013-12-23 | 2015-07-02 | 华为技术有限公司 | Voice command correcting method, correcting system and electronic device |
| CN103699359B (en) * | 2013-12-23 | 2017-12-29 | 华为技术有限公司 | A kind of bearing calibration of voice command, correction system and electronic equipment |
| CN103699359A (en) * | 2013-12-23 | 2014-04-02 | 华为技术有限公司 | Correction method, correction system for voice command and electronic device |
| CN105091208A (en) * | 2014-05-23 | 2015-11-25 | 美的集团股份有限公司 | Method and system for controlling air speed of air conditioner |
| CN105091208B (en) * | 2014-05-23 | 2017-11-14 | 美的集团股份有限公司 | Air conditioner wind speed control method and system |
| CN105469801B (en) * | 2014-09-11 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of method and device thereof for repairing input voice |
| CN105469801A (en) * | 2014-09-11 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Input speech restoring method and device |
| CN104331265A (en) * | 2014-09-30 | 2015-02-04 | 北京金山安全软件有限公司 | Voice input method, device and terminal |
| CN106095766A (en) * | 2015-04-28 | 2016-11-09 | 谷歌公司 | Use selectivity again to talk and correct speech recognition |
| CN106095766B (en) * | 2015-04-28 | 2021-12-21 | 谷歌有限责任公司 | Correcting speech recognition using selective re-speaking |
| CN105185377B (en) * | 2015-09-24 | 2019-07-09 | 百度在线网络技术（北京）有限公司 | A kind of voice-based document generating method and device |
| CN105185377A (en) * | 2015-09-24 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Voice-based file generation method and device |
| 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 |
| CN106406807A (en) * | 2016-09-19 | 2017-02-15 | 北京云知声信息技术有限公司 | A method and a device for voice correction of characters |
| CN106775349A (en) * | 2016-11-29 | 2017-05-31 | 珠海市魅族科技有限公司 | A kind of speech modification method and device of word content |
| CN108664984A (en) * | 2017-03-28 | 2018-10-16 | 深圳市凯立德科技股份有限公司 | A kind of method and device of data inspection |
| CN108664984B (en) * | 2017-03-28 | 2024-04-09 | 深圳市凯立德科技股份有限公司 | Data checking method and device |
| CN107071553B (en) * | 2017-06-05 | 2020-02-07 | 广东小天才科技有限公司 | Method, device and computer readable storage medium for modifying video and voice |
| CN107071553A (en) * | 2017-06-05 | 2017-08-18 | 广东小天才科技有限公司 | Method, device and computer readable storage medium for modifying video and voice |
| CN107220228A (en) * | 2017-06-13 | 2017-09-29 | 深圳市鹰硕技术有限公司 | One kind teaching recorded broadcast data correction device |
| CN107220228B (en) * | 2017-06-13 | 2019-08-16 | 深圳市鹰硕技术有限公司 | A kind of teaching recorded broadcast data correction device |
| CN107293299A (en) * | 2017-06-16 | 2017-10-24 | 朱明增 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103207769B (en) | 2016-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103207769A (en) | Method and user equipment for voice amending | |
| US20200293715A1 (en) | Text editing | |
| CN105573503B (en) | For receiving the method and system of the text input on touch-sensitive display device | |
| RU2379767C2 (en) | Error correction for speech recognition systems | |
| CN105869446A (en) | Electronic reading apparatus and voice reading loading method | |
| US20060293890A1 (en) | Speech recognition assisted autocompletion of composite characters | |
| US8612879B2 (en) | Displaying and inputting symbols | |
| JP2009098490A (en) | Device for editing speech recognition result, speech recognition device and computer program | |
| CN103955454B (en) | A kind of method and apparatus that style conversion is carried out between writings in the vernacular and the writing in classical Chinese | |
| KR20090099069A (en) | Method, apparatus and computer program product for providing flexible text based language identification | |
| JP2013068952A (en) | Consolidating speech recognition results | |
| CN1229316A (en) | Method and apparatus for inputting information | |
| JP2003015803A (en) | Japanese input mechanism for small keypad | |
| CN103369122A (en) | Voice input method and system | |
| CN101916158A (en) | Method and device for configuring input mode according to input box of user device | |
| US8996995B2 (en) | Method and apparatus for phrase replacement | |
| JP2016061855A (en) | Audio learning device and control program | |
| CN108806688A (en) | Sound control method, smart television, system and the storage medium of smart television | |
| KR101137567B1 (en) | Wireless portable terminal for enabling automatic completion of character strings and method thereof | |
| CN101175272B (en) | Method for reading text short message | |
| CN102135812A (en) | method and device for inputting polyphonic Chinese characters | |
| CN104702758B (en) | A kind of terminal and its method for managing multimedia notepad | |
| Cheng | A contrastive analysis of word formation of English and Chinese neologisms | |
| Goodman | Contending the popular: Party-state and culture | |
| CN110244859A (en) | A kind of method and device of customized candidates of input method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |