CN104038630A - Speech processing method and device - Google Patents
Speech processing method and device Download PDFInfo
- Publication number
- CN104038630A CN104038630A CN201410230695.2A CN201410230695A CN104038630A CN 104038630 A CN104038630 A CN 104038630A CN 201410230695 A CN201410230695 A CN 201410230695A CN 104038630 A CN104038630 A CN 104038630A
- Authority
- CN
- China
- Prior art keywords
- event
- information
- module
- call
- memorandum
- 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
Abstract
The invention provides a speech processing method and a speech processing device. The speech processing method comprises the steps of: detecting whether a call or recording state of a terminal device is opened in real time; when detecting that the call or recording state of the terminal device is opened, obtaining speech information in a call or a record; performing semantic analysis to the speech information, and extracting event information included in the speech information; creating a memo event according to the event information. According to the speech processing method and device, the memo event can be automatically created for a user in a call or recording process, the user is avoided loss caused by forgetting important memo event, and thereby usage experience of the user is promoted.
Description
Technical field
The disclosure relates to communication field, in particular to method of speech processing and device.
Background technology
At present, user can come initiatively to create schedule, meeting schedule and calendar prompting etc. by electronic calendar.Applying electronic calendar, whether user only need to need to remind according to the main contents time point of event, just can generate event.Event can check in electronic calendar, also reminding user at the appointed time.
Although, use electronic calendar easily to schedule, to manage arrangement,, electronic calendar needs user initiatively to go to create generation.User needs the newly-built schedule of active, records content and alerting pattern is optionally set.For some special circumstances, for example, if relating in communication process, user needs the invitation of memorandum content, and user just need to initiatively create a memorandum in communication process or after call again, so also inconvenient.If can automatically create memorandum event in communication process or in Recording Process, will greatly promote user's experience.
Summary of the invention
Object of the present disclosure is to provide method of speech processing and device, to solve the above problems.
According to the first aspect of disclosure embodiment, the disclosure provides a kind of method of speech processing, comprising:
Whether call or the recording state of sense terminals equipment are opened in real time;
When call or recording state unlatching being detected, obtain the voice messaging in call or recording;
By described voice messaging is carried out to semantic analysis, extract the event information comprising in described voice messaging;
According to described event information, create memorandum event.
The technical scheme that embodiment of the present disclosure provides, can avoid causing damage because user forgets important memorandum event automatically for user creates memorandum event in communication process or in Recording Process, thereby promote user's experience.
Above-mentioned method of speech processing can also comprise following features, and whether the call of described real-time sense terminals equipment or recording state comprise before opening:
Whether whether prompting user need the call of real-time sense terminals equipment or recording state to open, and the selection result of returning according to user arranges the real-time detection of call or recording state.
The technical scheme that embodiment of the present disclosure provides, can arrange according to user's wish the real-time detection of call or recording state, contributes to promote user's satisfaction.
Above-mentioned method of speech processing can also comprise following features, described by described voice messaging is carried out to semantic analysis, extracts the event information comprising in described voice messaging and comprises:
Based on continuous speech recognition, from described voice messaging, extract paragraph or the statement relevant to event;
Based on keyword identification, from the described paragraph relevant to event or statement, extract the keyword of event;
Based on isolated word recognition, according to voice context, extract the related people information of event, and/or, according to telephone directory, extract the related people information of event.
The technical scheme that embodiment of the present disclosure provides, can improve memorandum event, improves the accuracy of the memorandum event creating, and promotes user's satisfaction.
Above-mentioned method of speech processing can also comprise following features, also comprises:
The people information extracting during more than the required people information of described memorandum event, sends all people informations from extracting and selects the notice that memorandum event relates to personage;
Reception relates to personage's selection result to memorandum event;
According to described selection result, determine the people information of memorandum event.
The technical scheme that embodiment of the present disclosure provides, can improve the accuracy of created memorandum event, makes its expectation that meets user, thereby promotes user's satisfaction.
Above-mentioned method of speech processing can also comprise following features, also comprises:
Reception is to creating the modification information of memorandum event;
Described in revising according to described modification information, created memorandum event.
The technical scheme that embodiment of the present disclosure provides, can modify to creating memorandum event user, further promotes user's experience.
Above-mentioned method of speech processing can also comprise following features, described according to described event information, create memorandum event after, also comprise:
According to the time of described event information, be that described memorandum event arranges prompting.
The technical scheme that embodiment of the present disclosure provides, can remind memorandum event to user in time, promotes user's experience.
According to the second aspect of disclosure embodiment, the disclosure provides a kind of voice processing apparatus, comprising:
Detection module, for whether call or the recording state of sense terminals equipment are opened in real time;
Acquisition module, while opening for call or recording state detected when described detection module, obtains the voice messaging in call or recording;
Analyze extraction module, for the voice messaging by described acquisition module is obtained, carry out semantic analysis, extract the event information comprising in described voice messaging;
Creation module, creates memorandum event for the event information extracting according to described analysis extraction module.
The technical scheme that embodiment of the present disclosure provides, can avoid causing damage because user forgets important memorandum event automatically for user creates memorandum event in communication process or in Recording Process, thereby promote user's experience.
Above-mentioned voice processing apparatus can also comprise following features, also comprises:
Reminding module, is connected with described detection module, and whether for pointing out call or the recording state whether user needs real-time sense terminals equipment to open, the selection result of returning according to user arranges the real-time detection of call or recording state.
The technical scheme that embodiment of the present disclosure provides, can arrange according to user's wish the real-time detection of call or recording state, contributes to promote user's satisfaction.
Above-mentioned voice processing apparatus can also comprise following features, and described analysis extraction module comprises:
The first extraction unit for based on continuous speech recognition, extracts paragraph or the statement relevant to event from described voice messaging;
The second extraction unit for based on keyword identification, extracts the keyword of event from the described paragraph relevant to event or statement;
The 3rd extraction unit, for based on isolated word recognition, extracts the related people information of event according to voice context, and/or, according to telephone directory, extract the related people information of event.
The technical scheme that embodiment of the present disclosure provides, can improve memorandum event, improves the accuracy of the memorandum event creating, and promotes user's satisfaction.
Above-mentioned voice processing apparatus can also comprise following features, also comprises:
Select notification module, for the people information extracting, during more than the required people information of described memorandum event, send all people informations from extracting and select the notice that memorandum event relates to personage;
Selective reception module, for receiving the selection result that memorandum event is related to personage;
Determination module, for determining the people information of memorandum event according to the selection result of described selective reception module reception.
The technical scheme that embodiment of the present disclosure provides, can improve the accuracy of created memorandum event, makes its expectation that meets user, thereby promotes user's satisfaction.
Above-mentioned voice processing apparatus can also comprise following features, also comprises:
Revise receiver module, for receiving creating the modification information of memorandum event;
Modified module, has created memorandum event described in revising for the modification information receiving according to described modification receiver module.
The technical scheme that embodiment of the present disclosure provides, can modify to creating memorandum event user, further promotes user's experience.
Above-mentioned voice processing apparatus can also comprise following features, after described creation module, also comprises:
Prompting arranges module, for being that the memorandum event that described creation module creates arranges prompting according to the time of described event information.
The technical scheme that embodiment of the present disclosure provides, can remind memorandum event to user in time, promotes user's experience.
Should be understood that, it is only exemplary that above general description and details are hereinafter described, and can not limit the disclosure.
Accompanying drawing explanation
Fig. 1 is according to one of flow chart of a kind of method of speech processing shown in an exemplary embodiment.
Fig. 2 is according to two of the flow chart of a kind of method of speech processing shown in an exemplary embodiment.
Fig. 3 is according to three of the flow chart of a kind of method of speech processing shown in an exemplary embodiment.
Fig. 4 is according to four of the flow chart of a kind of method of speech processing shown in an exemplary embodiment.
Fig. 5 is according to one of structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.
Fig. 6 is according to two of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.
Fig. 7 is according to analyzing the structured flowchart of extraction module 30 in a kind of voice processing apparatus shown in an exemplary embodiment.
Fig. 8 is according to three of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.
Fig. 9 is according to four of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.
Figure 10 is according to five of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.
Accompanying drawing is herein merged in specification and forms the part of this specification, shows and meets embodiment of the present disclosure, and be used from and explain principle of the present disclosure with specification one.
Embodiment
Below by specific embodiment, also by reference to the accompanying drawings the disclosure is described in further detail.
Fig. 1 is according to one of flow chart of a kind of method of speech processing shown in an exemplary embodiment.As shown in Figure 1, in the present embodiment, method of speech processing can comprise the steps:
In step S101, whether call or the recording state of sense terminals equipment are opened in real time, if call or recording state unlatching detected, perform step S102;
In step S102, obtain the voice messaging in call or recording;
Such as user makes a phone call, or record, the voice messaging in these processes is the object that step S102 obtains.
In step S103, the voice messaging by obtaining in step S102 is carried out to semantic analysis, extract the event information comprising in this voice messaging;
Wherein, event information can comprise event content information, time point information, location information, people information etc.For example, in " we go international trade to have a meal Friday ", " we ", " Friday ", " international trade ", " having a meal " all belong to event information, wherein, " having a meal " is event content information.
Semantic analysis is converted into structurized index by speech recognition by voice messaging exactly, for example, interrogate rumours sound, and user language is carried out to automated analysis classification, for other application provide support.Speech recognition is converted into corresponding text or other information by voice signal after allowing exactly equipment identify by understanding.Speech recognition mainly contains three classes: the one, and isolated word recognition, i.e. prior some known isolated vocabulary, as " shutdown " etc.; The 2nd, keyword identification,, according to one section of voice or a word, does not analyze whole sentence, but extracts key vocabularies; The 3rd, continuous speech recognition, identifies one section of voice, and continuous speech recognition is the main target of speech recognition.
Event information mainly comprises event content information, time point information, location information, people information.For example making a phone call in process with mother, when mentioning " we go international trade to have a meal Friday ", just can extract relevant keyword " we ", " Friday ", " international trade ", " having a meal ".Wherein, " having a meal " is event content information, and " Friday " is time point information, " international trade " be location information, " we " are people information.
Wherein, the voice messaging obtaining is carried out to semantic analysis, extracting the event information comprising in this voice messaging can comprise: based on continuous speech recognition, extract paragraph or the statement relevant to event from voice messaging; Based on keyword identification, from the paragraph relevant to event or statement, extract the keyword of event; Based on isolated word recognition, one of the employing two kinds of modes below related people information of extraction event: a kind of mode is, according to voice context, extract the related people information of event, another kind of mode is to extract the related people information of event according to telephone directory.
For example, if speech or memory are recorded, in Recording Process can according to voice context extract speechmaker's identity and on the theme of once giving a lecture, then " we " of event can be matched to relevant speechmaker's identity, generate and aly take " certain professor's XX lecture " is the event of content.
For another example, if in communication process, can be according to telephone directory, extract characters name, or extract name in the self-introduction of call, if the people information that different extracting modes extracts clashes, can after memorandum event creates, eject prompting and allow user select which contact person.
In step S104, according to the event information extracting, create memorandum event in step S103.
If the event information extracting in step S103 comprises event content information, time point information, location information, people information, the content of the memorandum event of this establishment composition can be so: personage+time point+place+event content.
Suppose to extract in Recording Process as keywords such as " this Saturday ", " international trade ", " meeting ", these keywords have just formed event information, can automatically create the memorandum event of " meet Saturday at international trade and who " according to these keywords.
In other embodiment of the disclosure, after step S104, can also be that the memorandum event creating in step S104 arranges prompting according to the time of event information.
Arrange after prompting, the memorandum event that just at the appointed time call user's attention creates, makes the user can be because not forgeing the important event of missing.Alerting pattern can adopt any mode that can cause that user notes.
Method of speech processing shown in the present embodiment, can avoid because user forgets the loss that important memorandum event causes automatically for user creates memorandum event in communication process or in Recording Process, thereby promotes user's experience.
Fig. 2 is according to two of the flow chart of a kind of method of speech processing shown in an exemplary embodiment.As shown in Figure 2, in the present embodiment, method of speech processing can comprise the steps:
In step S201, whether whether prompting user need the call of real-time sense terminals equipment or recording state to open, and the selection result of returning according to user arranges the real-time detection of call or recording state;
In step S202, whether call or the recording state of sense terminals equipment are opened in real time, if call or recording state unlatching detected, perform step S203;
In step S203, obtain the voice messaging in call or recording;
In step S204, by the voice messaging obtaining is carried out to semantic analysis, extract the event information comprising in this voice messaging in step S203;
Wherein, event information can comprise event content information, time point information, location information, people information etc.
In step S205, according to the event information extracting, create memorandum event in step S204.
Method of speech processing shown in the present embodiment, can arrange according to user's wish the real-time detection of call or recording state, contributes to promote user's satisfaction.
In other embodiment of the disclosure, after step S205, can also comprise the steps: to send the notice that memorandum event has created.Like this, can notify in time user by the memorandum event of establishment, further promote user's experience.
Fig. 3 is according to three of the flow chart of a kind of method of speech processing shown in an exemplary embodiment.As shown in Figure 3, in the present embodiment, method of speech processing can comprise the steps:
In step S301, whether call or the recording state of sense terminals equipment are opened in real time, if call or recording state unlatching detected, perform step S302;
In step S302, obtain the voice messaging in call or recording;
In step S303, by the voice messaging obtaining is carried out to semantic analysis, extract the event information comprising in this voice messaging in step S302;
Wherein, event information can comprise event content information, time point information, location information, people information etc.
In step S304, at the people information extracting, during more than the required people information of memorandum event to be created, send all people informations from extracting and select the notice that memorandum event relates to personage;
In step S305, receive the selection result of sending out public notice in step S304;
In step S306, according to the selection result in step S305, determine the people information of memorandum event to be created;
In step S307, according to the event information obtaining, create memorandum event;
For example, the content of the memorandum event of this establishment composition can be: personage+time point+place+event content.
In this step, create in the event information of memorandum event institute foundation, the information such as time point, place, event content are carried out the event information extracting in comfortable step S303, and people information carrys out definite people information in comfortable step S306.
In other embodiment of the disclosure, also can after create the complete part of forgetting things, send again and select the notice that memorandum event relates to personage, and according to the selection result receiving, revise this and created the people information in memorandum event.
Method of speech processing shown in the present embodiment, can improve the accuracy of created memorandum event, makes its expectation that meets user, thereby promotes user's satisfaction.
Fig. 4 is according to four of the flow chart of a kind of method of speech processing shown in an exemplary embodiment.As shown in Figure 4, in the present embodiment, method of speech processing can comprise the steps:
In step S401, whether call or the recording state of sense terminals equipment are opened in real time, if call or recording state unlatching detected, perform step S402;
In step S402, obtain the voice messaging in call or recording;
In step S403, by the voice messaging obtaining is carried out to semantic analysis, extract the event information comprising in this voice messaging in step S402;
In step S404, according to the event information extracting, create memorandum event in step S403;
In step S405, receive creating the modification information of memorandum event;
In step S406, according to the modification information receiving, revise the memorandum event that created in step S405.
Method of speech processing shown in the present embodiment, can modify to creating memorandum event user, further promotes user's experience.
One of ordinary skill in the art will appreciate that, all or part of processing in said method embodiment can complete by the relevant hardware of program command, aforesaid program can be stored in a kind of computer read/write memory medium, this program is when carrying out, execution comprises the step of preceding method embodiment, and aforesaid storage medium comprises: the various media that can be program code stored such as ROM, RAM, magnetic disc or CD.
Fig. 5 is according to one of structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.As shown in Figure 5, in the present embodiment, voice processing apparatus can comprise detection module 10, acquisition module 20, analyze extraction module 30 and creation module 40.Wherein, detection module 10 is for whether call or the recording state of sense terminals equipment are opened in real time.When acquisition module 20 is opened for call or recording state detected when detection module 10, obtain the voice messaging in call or recording.Analyze extraction module 30 and carry out semantic analysis for the voice messaging by acquisition module 20 is obtained, extract the event information comprising in this voice messaging.Wherein, event information can comprise event content information, time point information, location information, people information etc.Creation module 40 is for creating memorandum event according to the event information of analyzing extraction module 30 extractions.Wherein, the content of memorandum event composition can be: personage+time point+place+event content.
Voice processing apparatus shown in the present embodiment, can, automatically for user creates memorandum event in communication process or in Recording Process, avoid because user forgets the loss that important memorandum event causes, thereby promote user's experience.
Fig. 6 is according to two of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.As shown in Figure 6, in the present embodiment, voice processing apparatus can comprise reminding module 00, detection module 10, acquisition module 20, analyze extraction module 30 and creation module 40.Wherein, detection module 10, acquisition module 20, analyze existing explanation before the function of extraction module 30 and creation module 40, repeat no more herein.Reminding module 00 is connected with detection module 10, and whether reminding module 00 is opened for call or the recording state of pointing out user and whether needing real-time sense terminals equipment, and the selection result of returning according to user arranges the real-time detection of call or recording state.
Voice processing apparatus shown in the present embodiment, can arrange according to user's wish the real-time detection of call or recording state, contributes to promote user's satisfaction.
In other embodiment of the disclosure, after creation module 40, can also comprise establishment notification module.Create notification module for sending the notice that memorandum event has created.Like this, can notify in time user by the memorandum event of establishment, further promote user's experience.
Fig. 7 is according to analyzing the structured flowchart of extraction module 30 in a kind of voice processing apparatus shown in an exemplary embodiment.As shown in Figure 7, in the present embodiment, analyze in extraction module 30 and can comprise the first extraction unit 310, the second extraction unit 320 and the 3rd extraction unit 330.Wherein, the first extraction unit 310, for based on continuous speech recognition, extracts paragraph or the statement relevant to event from voice messaging.The second extraction unit 320, for based on keyword identification, extracts the keyword of event from the paragraph relevant to event or statement.The 3rd extraction unit 330, for based on isolated word recognition, extracts the related people information of event according to voice context, and/or, according to telephone directory, extract the related people information of event.
Fig. 8 is according to three of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.As shown in Figure 8, in the present embodiment, voice processing apparatus can comprise detection module 10, acquisition module 20, analysis extraction module 30, creation module 40, select notification module 50, selective reception module 60 and determination module 70.Wherein, detection module 10, acquisition module 20, analyze existing explanation before the function of extraction module 30 and creation module 40, repeat no more herein.Select notification module 50, to send all people informations from extracting and select the notice that memorandum event relates to personage during more than the required people information of memorandum event for the people information extracting.Selective reception module 60 is for receiving the selection result that memorandum event is related to personage.Determination module 70 is determined the people information of memorandum event for the selection result receiving according to selective reception module 60.
Voice processing apparatus shown in the present embodiment, can improve the accuracy of created memorandum event, makes its expectation that meets user, thereby promotes user's satisfaction.
Fig. 9 is according to four of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.As shown in Figure 9, in the present embodiment, voice processing apparatus can comprise that detection module 10, acquisition module 20, analysis extraction module 30, creation module 40 and prompting arrange module 80.Wherein, detection module 10, acquisition module 20, analyze existing explanation before the function of extraction module 30 and creation module 40, repeat no more herein.Prompting arranges module 80 for being that the memorandum event that creation module 40 creates arranges prompting according to the time of event information.
Method of speech processing shown in the present embodiment, the memorandum event that at the appointed time call user's attention creates, makes the user can be because not forgeing the important event of missing.
Figure 10 is according to five of the structured flowchart of a kind of voice processing apparatus shown in an exemplary embodiment.As shown in figure 10, in the present embodiment, voice processing apparatus can comprise detection module 10, acquisition module 20, analysis extraction module 30, creation module 40, revise receiver module 90 and modified module 100.Wherein, detection module 10, acquisition module 20, analyze existing explanation before the function of extraction module 30 and creation module 40, repeat no more herein.Revise receiver module 90 for receiving creating the modification information of memorandum event.Modified module 100 is for revising according to the modification information of revising receiver module 90 receptions the memorandum event that created.
Voice processing apparatus shown in the present embodiment, can modify to creating memorandum event user, further promotes user's experience.
It will be understood by those skilled in the art that the module in the device in embodiment can be distributed in the device of embodiment according to embodiment description, also can carry out respective change and be arranged in the one or more devices that are different from the present embodiment.The module of above-described embodiment can be merged into a module, also can further split into a plurality of submodules.
The foregoing is only preferred embodiment of the present disclosure, be not limited to the disclosure, for a person skilled in the art, the disclosure can have various modifications and variations.All within spirit of the present disclosure and principle, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection range of the present disclosure.
Claims (12)
1. a method of speech processing, is characterized in that, comprising:
Whether call or the recording state of sense terminals equipment are opened in real time;
When call or recording state unlatching being detected, obtain the voice messaging in call or recording;
By described voice messaging is carried out to semantic analysis, extract the event information comprising in described voice messaging;
According to described event information, create memorandum event.
2. method according to claim 1, is characterized in that, whether the call of described real-time sense terminals equipment or recording state comprise before opening:
Whether whether prompting user need the call of real-time sense terminals equipment or recording state to open, and the selection result of returning according to user arranges the real-time detection of call or recording state.
3. method according to claim 1, is characterized in that, describedly by described voice messaging is carried out to semantic analysis, extracts the event information comprising in described voice messaging, comprising:
Based on continuous speech recognition, from described voice messaging, extract paragraph or the statement relevant to event;
Based on keyword identification, from the described paragraph relevant to event or statement, extract the keyword of event;
Based on isolated word recognition, according to voice context, extract the related people information of memorandum event, and/or, according to telephone directory, extract the related people information of memorandum event.
4. method according to claim 1, is characterized in that, also comprises:
The people information extracting during more than the required people information of described memorandum event, sends all people informations from extracting and selects the notice that memorandum event relates to personage;
Reception relates to personage's selection result to memorandum event;
According to described selection result, determine the people information of memorandum event.
5. method according to claim 1, is characterized in that, also comprises:
Reception is to creating the modification information of memorandum event;
Described in revising according to described modification information, created memorandum event.
6. method according to claim 1, is characterized in that, described according to described event information, create memorandum event after, also comprise:
According to the time of described event information, be that described memorandum event arranges prompting.
7. a voice processing apparatus, is characterized in that, comprising:
Detection module, for whether call or the recording state of sense terminals equipment are opened in real time;
Acquisition module, while opening for call or recording state detected when described detection module, obtains the voice messaging in call or recording;
Analyze extraction module, for the voice messaging by described acquisition module is obtained, carry out semantic analysis, extract the event information comprising in described voice messaging;
Creation module, creates memorandum event for the event information extracting according to described analysis extraction module.
8. device according to claim 7, is characterized in that, also comprises:
Reminding module, is connected with described detection module, and whether for pointing out call or the recording state whether user needs real-time sense terminals equipment to open, the selection result of returning according to user arranges the real-time detection of call or recording state.
9. device according to claim 7, is characterized in that, described analysis extraction module comprises:
The first extraction unit for based on continuous speech recognition, extracts paragraph or the statement relevant to event from described voice messaging;
The second extraction unit for based on keyword identification, extracts the keyword of event from the described paragraph relevant to event or statement;
The 3rd extraction unit, for based on isolated word recognition, extracts the related people information of event according to voice context, and/or, according to telephone directory, extract the related people information of event.
10. device according to claim 7, is characterized in that, also comprises:
Select notification module, for the people information extracting, during more than the required people information of described memorandum event, send all people informations from extracting and select the notice that memorandum event relates to personage;
Selective reception module, for receiving memorandum event being related to personage's selection result;
Determination module, for determining the people information of memorandum event according to the selection result of described selective reception module reception.
11. devices according to claim 7, is characterized in that, also comprise:
Revise receiver module, for receiving creating the modification information of memorandum event;
Modified module, has created memorandum event described in revising for the modification information receiving according to described modification receiver module.
12. devices according to claim 7, is characterized in that, after described creation module, also comprise:
Prompting arranges module, for being that the memorandum event that described creation module creates arranges prompting according to the time of described event information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410230695.2A CN104038630A (en) | 2014-05-28 | 2014-05-28 | Speech processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410230695.2A CN104038630A (en) | 2014-05-28 | 2014-05-28 | Speech processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104038630A true CN104038630A (en) | 2014-09-10 |
Family
ID=51469213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410230695.2A Pending CN104038630A (en) | 2014-05-28 | 2014-05-28 | Speech processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104038630A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104980549A (en) * | 2015-06-12 | 2015-10-14 | 努比亚技术有限公司 | Information processing method and mobile terminal |
| CN104994229A (en) * | 2015-06-23 | 2015-10-21 | 上海卓易科技股份有限公司 | Memorandum processing method and device based on call content |
| CN105847520A (en) * | 2016-05-19 | 2016-08-10 | 北京小米移动软件有限公司 | Recording realization method and device in conversation process |
| CN106327151A (en) * | 2016-08-15 | 2017-01-11 | 捷开通讯(深圳)有限公司 | Note recording method and system based on voice recognition |
| CN106528059A (en) * | 2015-09-10 | 2017-03-22 | 百度在线网络技术（北京）有限公司 | Method and device used for generating calendar prompt information |
| CN106557913A (en) * | 2016-12-01 | 2017-04-05 | 合肥永君数码科技有限公司 | Innovation undertaking based on voice technology promotes service system |
| CN106961510A (en) * | 2016-01-12 | 2017-07-18 | 北京搜狗科技发展有限公司 | A kind of voice communication processing method and processing device |
| CN108512984A (en) * | 2018-03-01 | 2018-09-07 | 珠海市魅族科技有限公司 | Information displaying method and device, information-pushing method, terminal and storage medium |
| CN108702411A (en) * | 2017-03-21 | 2018-10-23 | 华为技术有限公司 | A kind of method and device of control call |
| CN108958846A (en) * | 2018-09-27 | 2018-12-07 | 出门问问信息科技有限公司 | A kind of creation method and device of notepad item |
| CN109243435A (en) * | 2018-08-07 | 2019-01-18 | 北京云迹科技有限公司 | Phonetic order executes method and system |
| CN109286728A (en) * | 2018-11-29 | 2019-01-29 | 维沃移动通信有限公司 | A kind of dialog context processing method and terminal device |
| CN110111816A (en) * | 2019-02-27 | 2019-08-09 | 咪咕数字传媒有限公司 | Method, the method for audio processing, electronic equipment and the server-side of recording audio |
| CN110245922A (en) * | 2019-06-21 | 2019-09-17 | Oppo广东移动通信有限公司 | A kind of agenda managing method, device and computer readable storage medium |
| CN110415703A (en) * | 2019-07-17 | 2019-11-05 | 北京小米移动软件有限公司 | Voice memos information processing method and device |
| CN110797023A (en) * | 2019-11-05 | 2020-02-14 | 出门问问信息科技有限公司 | Voice shorthand method and device |
| CN111222848A (en) * | 2019-12-30 | 2020-06-02 | 北京明略软件系统有限公司 | Memorandum management method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299851A (en) * | 2008-06-16 | 2008-11-05 | 中兴通讯股份有限公司 | Method for booking prompting in call as well as mobile terminal |
| JP2010092258A (en) * | 2008-10-08 | 2010-04-22 | Casio Computer Co Ltd | Schedule retrieval device and schedule retrieval program |
| CN102256012A (en) * | 2011-06-28 | 2011-11-23 | 中兴通讯股份有限公司 | Device and method for setting event reminder |
| CN103167119A (en) * | 2012-07-05 | 2013-06-19 | 深圳市金立通信设备有限公司 | System and method for quickly setting reminder or schedule in mobile phone calling process |
-
2014
- 2014-05-28 CN CN201410230695.2A patent/CN104038630A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101299851A (en) * | 2008-06-16 | 2008-11-05 | 中兴通讯股份有限公司 | Method for booking prompting in call as well as mobile terminal |
| JP2010092258A (en) * | 2008-10-08 | 2010-04-22 | Casio Computer Co Ltd | Schedule retrieval device and schedule retrieval program |
| CN102256012A (en) * | 2011-06-28 | 2011-11-23 | 中兴通讯股份有限公司 | Device and method for setting event reminder |
| CN103167119A (en) * | 2012-07-05 | 2013-06-19 | 深圳市金立通信设备有限公司 | System and method for quickly setting reminder or schedule in mobile phone calling process |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104980549A (en) * | 2015-06-12 | 2015-10-14 | 努比亚技术有限公司 | Information processing method and mobile terminal |
| CN104994229A (en) * | 2015-06-23 | 2015-10-21 | 上海卓易科技股份有限公司 | Memorandum processing method and device based on call content |
| CN106528059A (en) * | 2015-09-10 | 2017-03-22 | 百度在线网络技术（北京）有限公司 | Method and device used for generating calendar prompt information |
| CN106961510A (en) * | 2016-01-12 | 2017-07-18 | 北京搜狗科技发展有限公司 | A kind of voice communication processing method and processing device |
| CN105847520A (en) * | 2016-05-19 | 2016-08-10 | 北京小米移动软件有限公司 | Recording realization method and device in conversation process |
| CN106327151A (en) * | 2016-08-15 | 2017-01-11 | 捷开通讯(深圳)有限公司 | Note recording method and system based on voice recognition |
| CN106557913A (en) * | 2016-12-01 | 2017-04-05 | 合肥永君数码科技有限公司 | Innovation undertaking based on voice technology promotes service system |
| CN108702411A (en) * | 2017-03-21 | 2018-10-23 | 华为技术有限公司 | A kind of method and device of control call |
| US10938978B2 (en) | 2017-03-21 | 2021-03-02 | Huawei Technologies Co., Ltd. | Call control method and apparatus |
| CN108512984A (en) * | 2018-03-01 | 2018-09-07 | 珠海市魅族科技有限公司 | Information displaying method and device, information-pushing method, terminal and storage medium |
| CN109243435A (en) * | 2018-08-07 | 2019-01-18 | 北京云迹科技有限公司 | Phonetic order executes method and system |
| CN109243435B (en) * | 2018-08-07 | 2022-01-11 | 北京云迹科技有限公司 | Voice instruction execution method and system |
| CN108958846A (en) * | 2018-09-27 | 2018-12-07 | 出门问问信息科技有限公司 | A kind of creation method and device of notepad item |
| CN109286728A (en) * | 2018-11-29 | 2019-01-29 | 维沃移动通信有限公司 | A kind of dialog context processing method and terminal device |
| CN109286728B (en) * | 2018-11-29 | 2021-01-08 | 维沃移动通信有限公司 | Call content processing method and terminal equipment |
| CN110111816A (en) * | 2019-02-27 | 2019-08-09 | 咪咕数字传媒有限公司 | Method, the method for audio processing, electronic equipment and the server-side of recording audio |
| CN110245922A (en) * | 2019-06-21 | 2019-09-17 | Oppo广东移动通信有限公司 | A kind of agenda managing method, device and computer readable storage medium |
| CN110415703A (en) * | 2019-07-17 | 2019-11-05 | 北京小米移动软件有限公司 | Voice memos information processing method and device |
| CN110797023A (en) * | 2019-11-05 | 2020-02-14 | 出门问问信息科技有限公司 | Voice shorthand method and device |
| CN111222848A (en) * | 2019-12-30 | 2020-06-02 | 北京明略软件系统有限公司 | Memorandum management method and device, storage medium and electronic equipment |
| CN111222848B (en) * | 2019-12-30 | 2023-05-30 | 北京明略软件系统有限公司 | Memorandum management method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104038630A (en) | Speech processing method and device | |
| CN106201424B (en) | A kind of information interacting method, device and electronic equipment | |
| CN107038220B (en) | Method, intelligent robot and system for generating memorandum | |
| US9230356B2 (en) | Document collaboration effects | |
| CN103247290A (en) | Communication device and control method thereof | |
| CN103035240A (en) | Speech recognition repair using contextual information | |
| US9542366B2 (en) | Smart text in document chat | |
| US20130160142A1 (en) | Track Changes Permissions | |
| CN110020010A (en) | Data processing method, device and electronic equipment | |
| US10936641B2 (en) | Call summary | |
| US20130159849A1 (en) | Jump to Collaborator Cursor | |
| CN105592343A (en) | Display Apparatus And Method For Question And Answer | |
| WO2018214895A1 (en) | Data processing method, data processing apparatus, storage device and network device | |
| CN101931701A (en) | Method, system and mobile terminal for prompting contact information in communication process | |
| CN103916513A (en) | Method and device for recording communication message at communication terminal | |
| CN105469789A (en) | Voice information processing method and voice information processing terminal | |
| KR102144868B1 (en) | Apparatus and method for providing call record | |
| US20180122369A1 (en) | Information processing system, information processing apparatus, and information processing method | |
| CN104484116A (en) | Information input method and information input device | |
| US11527251B1 (en) | Voice message capturing system | |
| US20130253932A1 (en) | Conversation supporting device, conversation supporting method and conversation supporting program | |
| CN102915493A (en) | Information processing apparatus and method | |
| CN114092060A (en) | Automatic capture of information from audio data and computer operational context | |
| KR102548365B1 (en) | Method for generating conference record automatically and apparatus thereof | |
| KR102312993B1 (en) | Method and apparatus for implementing interactive message using artificial neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140910 |
|
| RJ01 | Rejection of invention patent application after publication |