CN108564950A - Method, intelligent terminal and the computer storage media of speech-to-text - Google Patents
Method, intelligent terminal and the computer storage media of speech-to-text Download PDFInfo
- Publication number
- CN108564950A CN108564950A CN201810167024.4A CN201810167024A CN108564950A CN 108564950 A CN108564950 A CN 108564950A CN 201810167024 A CN201810167024 A CN 201810167024A CN 108564950 A CN108564950 A CN 108564950A
- Authority
- CN
- China
- Prior art keywords
- sensitive word
- feature words
- word
- voice messaging
- conversion
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
Abstract
The present embodiments relate to conversion technology of information field, a kind of method of speech-to-text, intelligent terminal and computer storage media are disclosed.The correspondence of Feature Words and sensitive word is pre-set in the present invention；Identify voice messaging input by user；If recognizing Feature Words, according to pre-set correspondence, sensitive word corresponding with Feature Words is found；According to voice messaging input by user and the sensitive word found, the conversion text information of voice messaging is generated；By conversion word-information display on the display interface of intelligent terminal.When so that voice conversion word being used to send information in public, it is not necessary to say sensitive word, sensitive word can also be sent, avoid and say sensitive word in public and cause user awkward.
Description
Technical field
The present embodiments relate to conversion technology of information field, more particularly to the method for speech-to-text, intelligent terminal and
Computer storage media.
Background technology
For mobile phone as essential smart machine in people's daily life, intelligentized degree is higher and higher, man-machine
Interactive demand is also just increasingly stronger.Voice has irreplaceable role as a kind of medium of human-computer interaction.Existing hand
The function of voice dialogue, voice and video even voice control etc. has may be implemented in machine.With the raising of mobile phone recording quality with
And the development of speech-to-text engine, many mobile phones can realize speech-to-text function.
Inventor has found that at least there are the following problems in the prior art：It needs to use speech-to-text function in public place
When, it is sometimes desirable to some sensitive words are sent to other side, but say sensitive word in public, often cause the embarrassment of user.
Invention content
Embodiment of the present invention is designed to provide a kind of method of speech-to-text, intelligent terminal and computer storage
Medium so that when voice conversion word being used to send information in public, it is not necessary to say sensitive word, sensitive text can also be sent
Word avoids and says sensitive word in public and cause user awkward.
In order to solve the above technical problems, embodiments of the present invention provide a kind of method of speech-to-text, it is applied to
Intelligent terminal, including：Pre-set the correspondence of Feature Words and sensitive word；Identify voice messaging input by user；If identification
To Feature Words, then according to pre-set correspondence, sensitive word corresponding with Feature Words is found；According to language input by user
The sensitive word that message is ceased and found, generates the conversion text information of voice messaging；Word-information display will be converted at intelligent end
On the display interface at end.
Embodiments of the present invention additionally provide a kind of intelligent terminal, including：At least one processor；And at least
The memory of one processor communication connection；Wherein, memory is stored with the instruction that can be executed by least one processor, instruction
It is executed by least one processor, so that the method that at least one processor is able to carry out above-mentioned speech-to-text.
Embodiments of the present invention additionally provide a kind of computer readable storage medium, are stored with computer program, calculate
Machine program realizes above-mentioned speech-to-text method when being executed by processor.
Embodiment of the present invention in terms of existing technologies, pre-sets the correspondence of Feature Words and sensitive word；Know
Voice messaging not input by user；If recognizing Feature Words, according to pre-set correspondence, find and Feature Words pair
The sensitive word answered；According to voice messaging input by user and the sensitive word found, the conversion text information of voice messaging is generated；
By conversion word-information display on the display interface of intelligent terminal.So that needing to send the language for including sensitive word in public
When message ceases, user can directly say the voice messaging comprising Feature Words, and according to the correspondence of Feature Words and sensitive word,
Corresponding sensitive word is found, conversion text information is generated according to voice messaging input by user and sensitive word, and be shown in intelligence
On the display interface of energy terminal so that quick needing to send when user uses voice conversion word to send information in public
When feeling word, it is not necessary to say sensitive word, sensitive word can also be sent, avoid saying sensitive word in public and awkward.
In addition, according to voice messaging input by user and the sensitive word found, the conversion word letter of voice messaging is generated
Breath, specifically includes：Voice messaging is converted into initial text information；Increase before Feature Words in initial text information and finds
Sensitive word, obtain conversion text information；Alternatively, increase the sensitive word found after Feature Words in initial text information,
Obtain conversion text information.It provides a kind of generated according to voice messaging input by user and the sensitive word found and converts word
The realization method of information.
In addition, according to voice messaging input by user and the sensitive word found, the conversion word letter of voice messaging is generated
Breath, specifically includes：Voice messaging is converted into initial text information；Feature Words in initial text information are substituted for and are found
Sensitive word, obtain conversion text information.Another is provided according to voice messaging input by user and the sensitivity found
Word generates the realization method of conversion text information, and makes the conversion text information generated more clear and coherent.
In addition, pre-setting the correspondence of Feature Words and sensitive word, specially：Pre-set Feature Words and at least two
Contact person, wherein each contact person is correspondingly arranged a sensitive word；According to pre-set correspondence, find with
The corresponding sensitive word of Feature Words, specifically includes：Obtain the sending object of voice messaging；If sending object belongs to contact person, root
Sensitive word corresponding with Feature Words is found according to the correspondence of sending object and contact person and sensitive word.Provide one to the user
The set-up mode of the correspondence of kind Feature Words and sensitive word.
In addition, pre-setting the correspondence of Feature Words and sensitive word, specially：Pre-set Feature Words and at least two
Contact person, wherein each contact person corresponds at least two sensitive words；According to pre-set correspondence, find and feature
The corresponding sensitive word of word, specifically includes：Obtain the sending object of voice messaging；If sending object belongs to contact person, according to hair
It send the correspondence of object and contact person and sensitive word to find at least two sensitive words corresponding with Feature Words, and selects wherein
One sensitive word corresponding with Feature Words.The setting side of the correspondence of another Feature Words and sensitive word is provided to the user
Formula.
In addition, after it will convert word-information display on the display interface of intelligent terminal, further include：When detecting use
When family confirms transmission conversion text information, conversion text information is sent to sending object.It waits for that user confirms and sends conversion word
The case where retransmiting the conversion text information after information, provide the chance of revision to the user, and avoiding the occurrence of hair mistake sending object.
Description of the drawings
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element with same reference numbers label is expressed as similar element in attached drawing, removes
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is the idiographic flow schematic diagram according to the method for the speech-to-text of first embodiment of the invention；
Fig. 2 is the idiographic flow schematic diagram according to the method for the speech-to-text of second embodiment of the invention；
Fig. 3 is the structural schematic diagram according to the intelligent terminal of third embodiment of the invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order to make the reader understand this application better, many technical details are proposed.But even if without these technical details
And various changes and modifications based on the following respective embodiments, it can also realize the application technical solution claimed.
The first embodiment of the present invention is related to a kind of methods of speech-to-text.The core of present embodiment is in advance
The correspondence of Feature Words and sensitive word is set；Identify voice messaging input by user；If recognizing Feature Words, according in advance
The correspondence of setting finds sensitive word corresponding with Feature Words；According to voice messaging input by user and find quick
Feel word, generates the conversion text information of voice messaging；By conversion word-information display on the display interface of intelligent terminal.So that
When needing to send the voice messaging comprising sensitive word in public, user can directly say the letter of the voice comprising Feature Words
Breath, and according to the correspondence of Feature Words and sensitive word, finds corresponding sensitive word, according to voice messaging input by user and
Sensitive word generates conversion text information, and is shown on the display interface of intelligent terminal so that user uses language in public
When sound converts word transmission information, when needing to send sensitive word, it is not necessary to say sensitive word, sensitive word can also be sent, kept away
Exempt to say sensitive word in public and awkward.
The realization details of the method for the speech-to-text of present embodiment is specifically described below, the following contents is only
For convenience of the realization details provided is understood, not implement the necessary of this programme.
Particular flow sheet in present embodiment is as shown in Figure 1, specifically include；
Step 101：Pre-set the correspondence of Feature Words and sensitive word.
Specifically, illustrated by taking a Feature Words as an example in present embodiment, but in practical applications, Feature Words can
Think multiple, the number of Feature Words is not defined in present embodiment.User can pre-set Feature Words and at least
Two contact persons, wherein each contact person is correspondingly arranged a sensitive word.I.e. a Feature Words correspond at least two contact persons,
Each contact person then corresponds to a sensitive word.As shown in table 1, Feature Words one correspond to the first contact person, the second contact person and
Three contact persons, the first contact person correspond to sensitive word one, and the second contact person corresponds to sensitive word two, and third contact person corresponds to sensitive word
Three.In this way, different contact persons can be arranged different sensitive words in user, to realize personalized distinguish.Such as：It can be arranged
Feature Words one are " you ", and the first contact is artificial " wife ", and the second contact is artificial " mother ", sensitive word corresponding with the first contact person
One can be " Honey ", and sensitive word corresponding with the second contact person two can be " mommy ", herein by way of example only.
Table 1
Alternatively, pre-setting Feature Words and at least two contact persons, wherein it is quick that each contact person is correspondingly arranged at least two
Feel word.I.e. a Feature Words correspond at least two contact persons, and each contact person then corresponds at least two sensitive words.Such as table 2
Shown, Feature Words one correspond to the first contact person, the second contact person and third contact person, and the first contact person corresponds to sensitive word one, quick
Feel word two, sensitive word three；Second contact person corresponds to sensitive word four, sensitive word five；Third contact person corresponds to sensitive word six, sensitive word
Seven, sensitive word eight.It is noted that the number of the corresponding sensitive word of each contact person can be different, user can basis
The demand of oneself is configured.In this way, different contact persons can be arranged multiple and different sensitive words in user, to realize individual character
Change and distinguishes.
Table 2
Step 102：Identify voice messaging input by user.
Step 103：Judge whether to recognize Feature Words.If it is not, then entering step 104, directly voice messaging is converted to
Convert text information；If so, entering step 105, according to pre-set correspondence, find corresponding with Feature Words quick
Feel word.
Specifically, the voice messaging of the microphone acquisition user of intelligent terminal, intelligent terminal identify the voice letter of user
Whether user pre-set Feature Words are had in breath.If unidentified arrive Feature Words, voice messaging is directly converted into conversion text
The voice messaging of the user of acquisition is directly converted to text information by word information, intelligent terminal using speech-to-text engine.If
Recognize the pre-set Feature Words of user, then according to the correspondence of pre-set Feature Words and sensitive word in step 101,
Find sensitive word corresponding with Feature Words.
When pre-set correspondence is in step 101：Pre-set Feature Words and at least two contact persons, wherein
When each contact person is correspondingly arranged a sensitive word, step 105 is first to obtain the sending object of voice messaging；If sending object
Belong to contact person, then sensitivity corresponding with Feature Words is found according to the correspondence of sending object and contact person and sensitive word
Word.Since in the correspondence of such a feature word and sensitive word, contact person corresponds with sensitive word, therefore, if sending object
Belong to contact person, then can directly find corresponding sensitive word.
When pre-set correspondence is in step 101：Pre-set Feature Words and at least two contact persons, wherein
When each contact person is correspondingly arranged at least two sensitive words, step 105 is first to obtain the sending object of voice messaging；If sending
Object belongs to contact person, then according to the correspondence of sending object and contact person and sensitive word find it is corresponding with Feature Words extremely
Few two sensitive words, and select one of them sensitive word corresponding with Feature Words.Since such a feature word is corresponding with sensitive word
In relationship, contact person belongs to one-to-many relationship with sensitive word, therefore, if sending object belongs to contact person, can only directly look into
Corresponding multiple sensitive words are found, one of sensitive word can be randomly choosed at this time, or pass through counting user and the transmission
The frequency of interaction of object, to select sensitive word.User can be that intimate grade, user and the sending object is arranged in multiple sensitive words
Frequency of interaction it is more high, the sensitive word for selecting intimate higher grade.Specifically how intimate grade is set and how to be selected quick
Feel word, user can be configured according to the hobby of oneself, no longer be repeated herein.
Step 106：Voice messaging is converted into initial text information.Step 107：Feature Words in initial text information
It is preceding to increase the sensitive word found, obtain conversion text information；It is searched alternatively, increasing after Feature Words in initial text information
The sensitive word arrived obtains conversion text information.
Specifically, after step 105, i.e., it is defeated according to user after finding sensitive word corresponding with Feature Words
The voice messaging entered and the sensitive word found, intelligent terminal are turned voice messaging input by user using speech-to-text engine
It is changed to text information, and according to the correspondence of Feature Words and sensitive word, generates conversion text information.Present embodiments provide for
A kind of realization method generating conversion text information according to voice messaging input by user and the sensitive word found.Intelligent terminal
Speech-to-text engine voice messaging input by user is converted into initial text information, then in the spy of initial text information
Word is levied before or after Feature Words, increases the corresponding sensitive word found according to Feature Words, obtains transformed word letter
Breath.Accordingly even when user does not send sensitive word in input voice information, but voice messaging is being switched to convert text information
Later, sensitive word still can be carried, user is avoided and sends sensitive word in public and cause embarrassment.
Step 108：By conversion word-information display on the display interface of intelligent terminal.
Specifically, after voice messaging is directly converted to conversion text information by step 104, or in step 107
Increase the sensitive word found before Feature Words in initial text information, obtains conversion text information；Alternatively, in initial word
Increase the sensitive word found after Feature Words in information, after obtaining conversion text information, conversion word-information display is existed
On the display interface of intelligent terminal, so that user checks whether the conversion text information generated is correct.
It is noted that after it will convert word-information display on the display interface of intelligent terminal, further include：When
When detecting that user confirms transmission conversion text information, conversion text information is sent to sending object.Word letter will converted
Breath is sent to before sending object, and user can confirm, checks whether correct and sending object is conversion text information
It is no be it is correct, avoid directly transmitting the case where mistaking caused by conversion text information or accidentally sending out.
Compared with prior art, present embodiments provide for a kind of methods of speech-to-text, are applied to intelligent terminal, in advance
The correspondence of Feature Words and sensitive word is first set；Identify voice messaging input by user；If recognizing Feature Words, according to pre-
The correspondence being first arranged finds sensitive word corresponding with Feature Words；According to voice messaging input by user and find
Sensitive word generates the conversion text information of voice messaging；By conversion word-information display on the display interface of intelligent terminal.Make
When obtaining the voice messaging for needing transmission to include sensitive word in public, user can directly say the letter of the voice comprising Feature Words
Breath, and according to the correspondence of Feature Words and sensitive word, finds corresponding sensitive word, according to voice messaging input by user and
Sensitive word generates conversion text information, and is shown on the display interface of intelligent terminal so that user uses language in public
When sound converts word transmission information, when needing to send sensitive word, it is not necessary to say sensitive word, sensitive word can also be sent, kept away
Exempt to say sensitive word in public and awkward.
Second embodiment of the present invention is related to a kind of method of speech-to-text.Second embodiment and the first embodiment party
Formula is roughly the same, is in place of the main distinction：The mode of generation conversion text information is in the first embodiment：In initial text
Increase the sensitive word found before Feature Words in word information, obtains conversion text information；Alternatively, in initial text information
Increase the sensitive word found after Feature Words, obtains conversion text information.And conversion text information is generated in the present embodiment
Mode be：Feature Words in initial text information are substituted for the sensitive word found, obtain conversion text information.It provides
Another generates the realization method of conversion text information according to voice messaging input by user and the sensitive word found so that
The conversion text information of generation is more clear and coherent.
The particular flow sheet of present embodiment is as shown in Figure 2：
Step 201：Pre-set the correspondence of Feature Words and sensitive word.
Step 202：Identify voice messaging input by user.
Step 203：Judge whether to recognize Feature Words.If it is not, then entering step 204, directly voice messaging is converted to
Text information；If so, entering step 205, according to pre-set correspondence, sensitivity corresponding with Feature Words is found
Word.
Above-mentioned steps 201 are roughly the same to step 105 with the step 101 in first embodiment to step 205, herein not
It is repeated again.
After step 205,206 are entered step：Voice messaging is converted into initial text information.Step 207：It will be initial
Feature Words in text information are substituted for the sensitive word found, obtain conversion text information.
Specifically, step 206 and step 207 provide another according to voice messaging input by user and find
Sensitive word generate conversion text information realization method.Directly the Feature Words in initial text information are substituted for and to be found
Sensitive word, in this way, even if user does not send sensitive word in input voice information, but voice messaging is being switched to convert word
After information, sensitive word still can be carried, user is avoided and sends sensitive word in public and cause embarrassment, and to generate
Conversion text information read it is more clear and coherent.
Step 208：By conversion word-information display on the display interface of intelligent terminal.
Above-mentioned steps 208 are roughly the same with the step 107 in first embodiment, no longer repeated herein.
Compared with prior art, raw according to voice messaging input by user and the sensitive word found in present embodiment
At the conversion text information of voice messaging, specifically include：Voice messaging is converted into initial text information；By initial text information
Interior Feature Words are substituted for the sensitive word found, obtain conversion text information.Another is provided according to input by user
Voice messaging and the sensitive word found generate the realization method of conversion text information, even if user does not have in input voice information
There is transmission sensitive word, but after switching to voice messaging to convert text information, still can carry sensitive word, avoid user and exist
Public situation sends sensitive word and causes embarrassment, and makes the conversion text information generated more clear and coherent.
The step of various methods divide above, be intended merely to describe it is clear, when realization can be merged into a step or
Certain steps are split, multiple steps are decomposed into, as long as including identical logical relation, all in the protection domain of this patent
It is interior；To either adding inessential modification in algorithm in flow or introducing inessential design, but its algorithm is not changed
Core design with flow is all in the protection domain of the patent.
Third embodiment of the invention is related to a kind of intelligent terminal, as shown in figure 3, including at least one processor 302；With
And the memory 301 communicated to connect at least one processor 302；Wherein, be stored with can be by least one place for memory 301
The instruction that device 302 executes is managed, instruction is executed by least one processor 302, so that at least one processor 302 is able to carry out
The method for stating any speech-to-text.
Wherein, memory 301 is connected with processor 302 using bus mode, and bus may include any number of interconnection
Bus and bridge, bus one or more processors 302 and the various of memory 301 are electrically connected to together.Bus may be used also
To be electrically connected to the various other of such as peripheral equipment, voltage-stablizer and management circuit or the like together, these are all
It is known in the art, therefore, it will not be further described herein.Bus interface provides between bus and transceiver
Interface.Transceiver can be an element, can also be multiple element, such as multiple receivers and transmitter, provide for
The unit communicated with various other devices on transmission medium.Through processor 302 handle data by antenna on the radio medium
It is transmitted, further, antenna also receives data and transfers data to processor 302.
Processor 302 is responsible for bus and common processing, can also provide various functions, including timing, periphery connects
Mouthful, voltage adjusting, power management and other control functions.And memory 301 can be used to store processor and execute behaviour
Used data when making.
Four embodiment of the invention is related to a kind of computer readable storage medium, is stored with computer program.Computer
Any of the above-described embodiment of the method is realized when program is executed by processor.
That is, it will be understood by those skilled in the art that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, which is stored in a storage medium, including some instructions are making
It obtains an equipment (can be microcontroller, chip etc.) or processor (processor) executes side described in each embodiment of the application
The all or part of step of method.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize specific embodiments of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (9)
1. a kind of method of speech-to-text is applied to intelligent terminal, which is characterized in that including：
Pre-set the correspondence of Feature Words and sensitive word；
Identify voice messaging input by user；
If recognizing the Feature Words, according to the pre-set correspondence, find corresponding with the Feature Words
Sensitive word；
According to the voice messaging input by user and the sensitive word found, the conversion word of the voice messaging is generated
Information；
By the conversion word-information display on the display interface of the intelligent terminal.
2. the method for speech-to-text according to claim 1, which is characterized in that described according to the language input by user
The sensitive word that message is ceased and found, generates the conversion text information of the voice messaging, specifically includes：
The voice messaging is converted into initial text information；
Increase the sensitive word found before the Feature Words in the initial text information, obtains the conversion word
Information；Alternatively, increasing the sensitive word found after Feature Words in the initial text information, described turn is obtained
Change text information.
3. the method for speech-to-text according to claim 1, which is characterized in that described according to the language input by user
The sensitive word that message is ceased and found, generates the conversion text information of the voice messaging, specifically includes：
The voice messaging is converted into initial text information；
The Feature Words in the initial text information are substituted for the sensitive word found, obtain the conversion word
Information.
4. the method for speech-to-text according to claim 1, which is characterized in that described to pre-set Feature Words and sensitivity
The correspondence of word, specially：
Pre-set Feature Words and at least two contact persons, wherein each contact person is correspondingly arranged a sensitive word；
It is described according to the pre-set correspondence, find sensitive word corresponding with the Feature Words, specifically include：
Obtain the sending object of the voice messaging；
If the sending object belongs to the contact person, according to the sending object and the contact person and the sensitive word
Correspondence finds sensitive word corresponding with the Feature Words.
5. the method for speech-to-text according to claim 1, which is characterized in that described to pre-set Feature Words and sensitivity
The correspondence of word, specially：
Pre-set Feature Words and at least two contact persons, wherein each contact person corresponds at least two sensitive words；
It is described according to the pre-set correspondence, find sensitive word corresponding with the Feature Words, specifically include：
Obtain the sending object of the voice messaging；
If the sending object belongs to the contact person, according to the sending object and the contact person and the sensitive word
Correspondence finds at least two sensitive words corresponding with the Feature Words, and selects one of them corresponding with the Feature Words
Sensitive word.
6. the method for speech-to-text according to claim 4 or 5, which is characterized in that described by the conversion word
After presentation of information is on the display interface of the intelligent terminal, further include：
When detecting that user confirms the transmission conversion text information, the conversion text information is sent to the transmission pair
As.
7. the method for speech-to-text according to claim 1, which is characterized in that in the identification voice input by user
After information, further include：
If unidentified arrive the Feature Words, the voice messaging is directly converted into conversion text information.
8. a kind of intelligent terminal, which is characterized in that including：
At least one processor；And
The memory being connect at least one processor communication；Wherein,
The memory is stored with the instruction that can be executed by least one processor, and described instruction is by least one place
It manages device to execute, so that at least one processor is able to carry out such as the speech-to-text as described in any in claim 1 to 7
Method.
9. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the computer program is handled
The method that the speech-to-text described in any one of claim 1 to 7 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810167024.4A CN108564950A (en) | 2018-02-28 | 2018-02-28 | Method, intelligent terminal and the computer storage media of speech-to-text |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810167024.4A CN108564950A (en) | 2018-02-28 | 2018-02-28 | Method, intelligent terminal and the computer storage media of speech-to-text |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108564950A true CN108564950A (en) | 2018-09-21 |
Family
ID=63531426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810167024.4A Pending CN108564950A (en) | 2018-02-28 | 2018-02-28 | Method, intelligent terminal and the computer storage media of speech-to-text |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564950A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798854A (en) * | 2020-06-16 | 2020-10-20 | 普强信息技术（北京）有限公司 | Voice-to-text method based on video communication |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140156796A1 (en) * | 2011-07-19 | 2014-06-05 | Sk Planet Co, Ltd | Intelligent information providing system and method |
| CN104464735A (en) * | 2014-12-12 | 2015-03-25 | 宇龙计算机通信科技(深圳)有限公司 | Voice information recognition method and device, and terminal |
| CN105183761A (en) * | 2015-07-27 | 2015-12-23 | 网易传媒科技（北京）有限公司 | Sensitive word replacement method and apparatus |
| CN106203170A (en) * | 2016-07-19 | 2016-12-07 | 北京同余科技有限公司 | The Database Dynamic desensitization method of servicing of based role and system |
| CN106203145A (en) * | 2016-08-04 | 2016-12-07 | 北京网智天元科技股份有限公司 | Data desensitization method and relevant device |
| CN106920303A (en) * | 2017-01-21 | 2017-07-04 | 云丁网络技术(北京)有限公司 | A kind of method for unlocking and its intelligent door lock system based on speech recognition |
| CN107135452A (en) * | 2017-05-31 | 2017-09-05 | 北京小米移动软件有限公司 | Audiphone adaptation method and device |
-
2018
- 2018-02-28 CN CN201810167024.4A patent/CN108564950A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140156796A1 (en) * | 2011-07-19 | 2014-06-05 | Sk Planet Co, Ltd | Intelligent information providing system and method |
| CN104464735A (en) * | 2014-12-12 | 2015-03-25 | 宇龙计算机通信科技(深圳)有限公司 | Voice information recognition method and device, and terminal |
| CN105183761A (en) * | 2015-07-27 | 2015-12-23 | 网易传媒科技（北京）有限公司 | Sensitive word replacement method and apparatus |
| CN106203170A (en) * | 2016-07-19 | 2016-12-07 | 北京同余科技有限公司 | The Database Dynamic desensitization method of servicing of based role and system |
| CN106203145A (en) * | 2016-08-04 | 2016-12-07 | 北京网智天元科技股份有限公司 | Data desensitization method and relevant device |
| CN106920303A (en) * | 2017-01-21 | 2017-07-04 | 云丁网络技术(北京)有限公司 | A kind of method for unlocking and its intelligent door lock system based on speech recognition |
| CN107135452A (en) * | 2017-05-31 | 2017-09-05 | 北京小米移动软件有限公司 | Audiphone adaptation method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798854A (en) * | 2020-06-16 | 2020-10-20 | 普强信息技术（北京）有限公司 | Voice-to-text method based on video communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109514586B (en) | Method and system for realizing intelligent customer service robot | |
| CN107256707B (en) | Voice recognition method, system and terminal equipment | |
| CN107393534B (en) | Voice interaction method and device, computer device and computer readable storage medium | |
| CN104102409A (en) | Scenario adaptation device and method for user interface | |
| CN104205161A (en) | System, method, and computer program product for decompression of block compressed images | |
| CN110489440A (en) | Data query method and apparatus | |
| CN108564950A (en) | Method, intelligent terminal and the computer storage media of speech-to-text | |
| EP3059731B1 (en) | Method and apparatus for automatically sending multimedia file, mobile terminal, and storage medium | |
| CN115116458B (en) | Voice data conversion method, device, computer equipment and storage medium | |
| CN106598391A (en) | Blind operation realization method and device of mobile terminal | |
| CN110752973B (en) | Terminal equipment control method and device and terminal equipment | |
| CN108427671B (en) | Information conversion method and apparatus, storage medium, and electronic apparatus | |
| CN107562733A (en) | A kind of instant message interpretation method and system and a kind of electronic equipment | |
| CN109299948A (en) | A kind of red packet sending method, device, wearable device and storage medium | |
| CN109547329A (en) | The display methods and Related product of group information | |
| CN104536570A (en) | Information processing method and device of intelligent watch | |
| CN111625636B (en) | Method, device, equipment and medium for rejecting man-machine conversation | |
| CN209514900U (en) | A kind of point reading verifying device | |
| CN115019788A (en) | Voice interaction method, system, terminal equipment and storage medium | |
| CN109873893B (en) | Information pushing method and related device | |
| CN103209241A (en) | Information sending method and electronic device | |
| CN110580902A (en) | voice interaction system capable of being rapidly recognized | |
| CN110347438A (en) | Function selection method, function selection device and mobile terminal | |
| CN108924326A (en) | The calibration method and mobile terminal of earphone | |
| CN111414760A (en) | Natural language processing method and related device, system and storage device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180921 |