CN105047198A - Voice error correction processing method and apparatus - Google Patents
Voice error correction processing method and apparatus Download PDFInfo
- Publication number
- CN105047198A CN105047198A CN201510524094.7A CN201510524094A CN105047198A CN 105047198 A CN105047198 A CN 105047198A CN 201510524094 A CN201510524094 A CN 201510524094A CN 105047198 A CN105047198 A CN 105047198A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- retrieval
- voice messaging
- result
- 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
Abstract
The invention provides a voice error correction processing method and an apparatus. The method comprises the following steps of detecting an identification result of voice information input by a user; if the detection is wrong, according to the voice information, acquiring a behavior intention of the user; according to the behavior intention, outputting an inquiry message used for correcting wrong voice to the user voice. By using the voice error correction processing method and the apparatus provided in the invention, an automatic error correction function of voice searching is realized; processing resources are saved; user searching time is reduced, and processing efficiency and a user experience degree are increased.
Description
Technical field
The application relates to communication technical field, particularly relates to a kind of voice correction processing method and device.
Background technology
Along with the development of speech recognition technology, the application of speech recognition technology is more and more wider, and the user using voice to initiate search also gets more and more.Due to various external environmental factor, speech recognition there will be the situation of partial words None-identified in some scenarios.
In prior art, speech recognition is had to the situation of partial error, Voice search engine can attempt correcting text, successfully will replace original text or the correct text of prompting user if corrected.
But if mistake appears in speech recognition, and search engine cannot be corrected the text of mistake, and search engine just may return complete incoherent result, causes without efficient search, wastes process resource, reduces treatment effeciency.
Summary of the invention
The application is intended to solve one of technical matters in correlation technique at least to a certain extent.
For this reason, first object of the application is to propose a kind of voice correction processing method, the method achieves the automatic error correction function of phonetic search, has saved process resource, decrease the search time of user, improve treatment effeciency and user experience.
Second object of the application is to propose a kind of voice error correcting handling arrangement.
For reaching above-mentioned purpose, the application's first aspect embodiment proposes a kind of voice correction processing method, comprising: the recognition result detecting the voice messaging of user's input; If detect wrong, then obtain the behavior intention of described user according to described voice messaging; Be intended to according to described behavior, export the apply for information for voice of correcting a mistake to described user speech.
The voice correction processing method of the embodiment of the present application, first the recognition result of the voice messaging of user's input is detected, if detect wrong, the behavior intention of described user is then obtained according to described voice messaging, then be intended to according to described behavior, export the apply for information for voice of correcting a mistake to described user speech.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
For reaching above-mentioned purpose, the application's second aspect embodiment proposes a kind of voice error correcting handling arrangement, comprising: detection module, for detecting the recognition result of the voice messaging of user's input; Intention analysis module, if wrong for detecting, then obtains the behavior intention of described user according to described voice messaging; Correction module, for being intended to according to described behavior, exports the apply for information for voice of correcting a mistake to described user speech.
The voice error correcting handling arrangement of the embodiment of the present application, detects the recognition result of the voice messaging of user's input by detection module; If detect wrong, obtained the behavior intention of described user according to described voice messaging by intention analysis module; Be intended to according to described behavior by correction module, export the apply for information for voice of correcting a mistake to described user speech.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the process flow diagram of the voice correction processing method of the application's embodiment;
Fig. 2 is the process flow diagram of the voice correction processing method of another embodiment of the application;
Fig. 3 is the structural representation of the voice error correcting handling arrangement of the application's embodiment;
Fig. 4 is the structural representation of the voice error correcting handling arrangement of another embodiment of the application;
Fig. 5 is the structural representation of the voice error correcting handling arrangement of another embodiment of the application.
Embodiment
Be described below in detail the embodiment of the application, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Be exemplary below by the embodiment be described with reference to the drawings, be intended to for explaining the application, and the restriction to the application can not be interpreted as.
Below with reference to the accompanying drawings voice correction processing method and the device of the embodiment of the present application are described.
Fig. 1 is the process flow diagram of the voice correction processing method of the application's embodiment.
As shown in Figure 1, this voice correction processing method comprises:
Step 101, detects the recognition result of the voice messaging of user's input.
The voice correction processing method that the embodiment of the present invention provides is applied to be had in the terminal device of audio input and output function, generally, terminal device realizes audio input and output function by man machine language's interactive interface, concrete speech input interface can be the equipment such as microphone, and voice output interface can be the equipment such as sound equipment.It should be noted that, terminal device should be able to be used for as user provides phonetic search service by what can access man machine language's interactive interface, this application can be selected according to actual needs, such as: have the navigation application of audio input and output function, search engine etc., the present embodiment is not restricted this.
When user needs to carry out phonetic search service, to man machine language's interactive interface input voice information, then the voice messaging of user's input is identified and detected recognition result, to return corresponding Search Results based on testing result to user.
But, in actual applications sometimes to the recognition result failure of voice messaging, namely know and accurately can not identify the voice that user inputs, such as: the situations such as the noisy especially interference ratio of background sound is larger, speech recognition failure can be caused, a lot of to the concrete detection mode of voice identification result, can need to select according to practical application, the present embodiment is not restricted this, in order to explanation identification processing procedure clearly, illustrates as follows:
Mode one, detects according to result for retrieval, comprising:
Retrieval voice identification result,
Judge whether result for retrieval is less than default retrieval quality, if so, then detect wrong, otherwise, detect correct.
Specifically, adopt the retrieve data of learning model to a period of time preset to analyze, be provided with retrieval quality, wherein, retrieval quality comprises the numerical value of some parameter informations, such as: the quantity of result for retrieval, and/or, the correlativity between result for retrieval.
Carry out identification to the voice messaging of input to go forward side by side line retrieval, the retrieval quality according to presetting is analyzed result for retrieval, judges whether result for retrieval is less than default retrieval quality.
Know that result for retrieval is less than default retrieval quality if judge, such as, the quantity of result for retrieval is less than default numerical value; Then illustrate that result for retrieval does not reach default standard, therefore, think that searching object is wrong by counter the pushing away of result for retrieval, namely voice identification result is wrong, thus assert the voice messaging detection of user's input wrong.
Know that result for retrieval is more than or equal to default retrieval quality if judge, such as, the quantity of result for retrieval is more than or equal to default numerical value, then illustrate that result for retrieval reaches default standard, therefore, think that searching object is correct by counter the pushing away of result for retrieval, namely voice identification result is correct, thus assert the voice messaging detection of user's input correct.
Mode two, detects according to language model, comprising:
The language model preset is adopted to mate voice identification result;
Judge whether matching degree is less than default threshold value, if so, then recognition failures, otherwise, identify successfully.
Specifically, analyze according to the retrieve data of a period of time, be provided with language model, wherein, language model comprises multiple characteristic information, and the weighted value shared by each characteristic information, such as: person characteristic information, Site characterization information, affair character information etc., the application that characteristic information concrete in language model carries out phonetic search depending on user is selected.Such as: user is when navigation application carries out phonetic search, characteristic information in so corresponding with navigation application language model comprises Site characterization information, such as sight name, street name, road name etc., and mode of transportation characteristic information, such as subway, walking, public transport etc., wherein, the weight of Site characterization information accounts for 0.6, and the weight of mode of transportation characteristic information accounts for 0.4.
Adopt the language model preset to mate voice identification result, obtain the matching degree of characteristic information in voice identification result and language model.Then according to the threshold value preset, matching degree is analyzed, judge whether matching degree is less than default threshold value.
Know that matching degree is less than default threshold value if judge, then illustrate by counter the pushing away of matching degree, matching degree does not reach default standard, therefore, thinks that match objects is wrong, namely voice identification result is wrong, thus assert the voice messaging detection of user's input correct.
Know that matching degree is more than or equal to default threshold value if judge, then illustrate by counter the pushing away of matching degree, matching degree reaches default standard, therefore, thinks that match objects is correct, namely voice identification result is correct, thus assert the voice messaging detection of user's input wrong.
Step 102, if detect wrong, then obtains the behavior intention of described user according to described voice messaging.
If judge know to user input voice messaging detect wrong after, then by this voice messaging analysis obtain user behavior intention.It should be noted that, the behavior intention related in the embodiment of the present invention refers to the event that user will do, illustrate as follows: 1) when the voice messaging that user inputs in navigation application is: time " I will remove the Forbidden City ", the behavior of user is intended to " I will go "; 2) when the voice messaging that user inputs in Video Applications is: time " I will see a film ", the behavior of user is intended to " I will see ".
The implementation obtaining the behavior intention of user according to voice messaging has a lot, selects according to actual needs, illustrates as follows:
Mode one: directly carry out matching detection by phonetic feature value,
Specifically, the eigenwert of the voice messaging of user's input can be extracted, phonetic feature storehouse according to setting up in advance is detected extracted eigenwert, a large amount of speech sample values describing user behavior intention is stored in phonetic feature storehouse, by detecting speech sample values and the matching degree of the eigenwert extracted, from voice messaging, obtain the behavior intention of user.
Mode two, by becoming word to detect speech conversion, comprising:
By described converting voice message into text message;
Instruction semantic feature database according to presetting carries out semantic analysis to described Word message, obtains the behavior intention of described user.
Specifically, first adopt language and characters converting system by converting voice message into text message, then according to the instruction semantic feature database preset, semantic analysis is carried out to Word message, obtain the behavior intention of user.Wherein, instruction semantic feature database comprises the instruction sample value prestored according to application type, can need to carry out selection the present embodiment be not restricted this according to practical application.Such as: the instruction sample value in the instruction semantic feature database in navigation application comprises: " I will go ", " navigating to " etc. represent the instruction of behavior intention, and the instruction sample value in the instruction semantic feature database in Video Applications comprises: " I will see ", " broadcasting " etc. represent the instruction of behavior intention.By detecting in voice messaging whether comprise instruction sample value, thus obtain the behavior intention of user according to voice messaging.
Step 103, is intended to according to described behavior, exports the apply for information for voice of correcting a mistake to described user speech.
Specifically, in order to the voice messaging making user clarify recognition failures, according to the behavior intention obtained, export the apply for information for voice of correcting a mistake to user speech.Illustrate:
When the voice messaging identified is " I will deluster ", recognition failures is thought according to result for retrieval or language model, but the behavior that can obtain user according to this voice messaging is intended to " I will remove XX ", therefore, after according to the behavior, intention understands user's request, the apply for information for voice of correcting a mistake can be generated and send to user in the mode of voice, such as: by voice to user's query " where the destination that you will go is? "Again inputted voice messaging is clarified for user.As can be seen here, for the situation of speech recognition failure, as long as semanteme is substantially complete, initiatively can send apply for information according to identified user behavior intention, correct a mistake promptly voice, decreases cost for correcting error, improves error correction and recall precision.
The voice correction processing method of the embodiment of the present application, first the recognition result of the voice messaging of user's input is detected, if detect wrong, the behavior intention of described user is then obtained according to described voice messaging, then be intended to according to described behavior, export the apply for information for voice of correcting a mistake to described user speech.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
Fig. 2 is the process flow diagram of the voice correction processing method of another embodiment of the application.
As shown in Figure 2, after above-described embodiment step 103, can also comprise the following steps:
Step 201, detects the recognition result of the correction voice messaging that described user inputs according to described apply for information;
Step 202, if detect wrong, then retrieves according to described correction voice messaging and described behavior intention;
Step 203, sends result for retrieval to described user.
Particularly, when user receives apply for information, before knowing, the voice messaging of input is not detected correct, and then again inputs correction voice messaging according to apply for information.
After receiving the correction voice messaging that user re-enters, adopt embodiment illustrated in fig. 1 in the recognition result of step 101 to this correction voice messaging re-start detection, and judge whether to detect correct.If detect correct, then retrieve according to correction voice messaging and behavior intention, and send result for retrieval to user.Illustrate as follows:
User's input voice information in navigation application is " the Forbidden City is removed in navigation ", but causes being identified as " navigation is delustered " this voice messaging due to various factors, and know detect wrong.But, semantic analysis can be carried out to " navigation is delustered ", acquisition behavior is intended to " XXX is removed in navigation ", thus to understand user's request be think " destination is gone in navigation ", therefore initiatively initiate inquiry " where your destination is? " then user clarifies demand further, re-enter error correction voice messaging " the Forbidden City ", and then again identify that error correction voice messaging is known as " the Forbidden City ", the user behavior intention obtained before finally error correction voice messaging being combined, can retrieve " the Forbidden City is removed in navigation ", and return the navigation way of current location to the Forbidden City to user.
The voice correction processing method of the embodiment of the present application, by detecting the recognition result of the correction voice messaging that user inputs according to apply for information, if retrieval is correct, then retrieves according to described correction voice messaging and described behavior intention, and send result for retrieval to described user.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
In order to realize above-described embodiment, the application also proposes a kind of voice error correcting handling arrangement.
Fig. 3 is the structural representation of the voice error correcting handling arrangement of the application's embodiment.
As shown in Figure 3, this voice error correcting handling arrangement comprises:
Detection module 11, for detecting the recognition result of the voice messaging of user's input;
Intention analysis module 12, if wrong for detecting, then obtains the behavior intention of described user according to described voice messaging;
Correction module 13, for being intended to according to described behavior, exports the apply for information for voice of correcting a mistake to described user speech.
It should be noted that, the aforementioned explanation to voice correction processing method embodiment illustrates the voice error correcting handling arrangement being also applicable to this embodiment, repeats no more herein.
The voice error correcting handling arrangement of the embodiment of the present application, detects the recognition result of the voice messaging of user's input by detection module; If recognition failures, obtained the behavior intention of described user according to described voice messaging by intention analysis module; Be intended to according to described behavior by correction module, export the apply for information for voice of correcting a mistake to described user speech.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
Fig. 4 is the structural representation of the voice error correcting handling arrangement of another embodiment of the application, as shown in Figure 4, based on embodiment illustrated in fig. 3,
Described detection module 11 comprises:
Retrieval unit 111, for retrieving voice identification result,
First judging unit 112, for judging whether result for retrieval is less than default retrieval quality, if so, then detects wrong, otherwise, detect successfully.
Or continue see Fig. 4, described detection module 11 comprises:
Matching unit 113, mates voice identification result for adopting default language model;
Second judging unit 114, for judging whether matching degree is less than default threshold value, if so, then recognition failures, otherwise, identify successfully.
Further, described intention analysis module 12, comprising:
Parsing unit 121, for by described converting voice message into text message;
Semantic analysis unit 122, for carrying out semantic analysis according to the instruction semantic feature database preset to described Word message, obtains the behavior intention of described user.
It should be noted that, the aforementioned explanation to voice correction processing method embodiment illustrates the voice error correcting handling arrangement being also applicable to this embodiment, repeats no more herein.
The voice error correcting handling arrangement of the embodiment of the present application, detects the recognition result of the voice messaging of user's input by detection module; If detect wrong, obtained the behavior intention of described user according to described voice messaging by intention analysis module; Be intended to according to described behavior by correction module, export the apply for information for voice of correcting a mistake to described user speech.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
Fig. 5 is the structural representation of the voice error correcting handling arrangement of another embodiment of the application, based on Fig. 3 or embodiment illustrated in fig. 4, also comprises: retrieval module 14 and sending module 15, for Fig. 3, as shown in Figure 5, wherein,
Detection module 11, also for detecting the recognition result of the correction voice messaging that described user inputs according to described apply for information;
Retrieval module 14, if correct for detecting, then retrieves according to described correction voice messaging and described behavior intention;
Sending module 15, for sending result for retrieval to described user.
It should be noted that, the aforementioned explanation to voice correction processing method embodiment illustrates the voice error correcting handling arrangement being also applicable to this embodiment, repeats no more herein.
The voice error correcting handling arrangement of the embodiment of the present application, detects the recognition result of the correction voice messaging that user inputs according to described apply for information by detection module; If detect correct, retrieved according to described correction voice messaging and described behavior intention by retrieval module; Result for retrieval is sent to described user by sending module.Thus, achieve the automatic error correction function of phonetic search, decrease the search time of user, improve treatment effeciency and user experience.
In the description of this instructions, at least one embodiment that specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained in the application or example.In this manual, to the schematic representation of above-mentioned term not must for be identical embodiment or example.And the specific features of description, structure, material or feature can combine in one or more embodiment in office or example in an appropriate manner.In addition, when not conflicting, the feature of the different embodiment described in this instructions or example and different embodiment or example can carry out combining and combining by those skilled in the art.
In addition, term " first ", " second " only for describing object, and can not be interpreted as instruction or hint relative importance or imply the quantity indicating indicated technical characteristic.Thus, be limited with " first ", the feature of " second " can express or impliedly comprise at least one this feature.In the description of the application, the implication of " multiple " is at least two, such as two, three etc., unless otherwise expressly limited specifically.
Describe and can be understood in process flow diagram or in this any process otherwise described or method, represent and comprise one or more for realizing the module of the code of the executable instruction of the step of specific logical function or process, fragment or part, and the scope of the preferred implementation of the application comprises other realization, wherein can not according to order that is shown or that discuss, comprise according to involved function by the mode while of basic or by contrary order, carry out n-back test, this should understand by the embodiment person of ordinary skill in the field of the application.
In flow charts represent or in this logic otherwise described and/or step, such as, the sequencing list of the executable instruction for realizing logic function can be considered to, may be embodied in any computer-readable medium, for instruction execution system, device or equipment (as computer based system, comprise the system of processor or other can from instruction execution system, device or equipment instruction fetch and perform the system of instruction) use, or to use in conjunction with these instruction execution systems, device or equipment.With regard to this instructions, " computer-readable medium " can be anyly can to comprise, store, communicate, propagate or transmission procedure for instruction execution system, device or equipment or the device that uses in conjunction with these instruction execution systems, device or equipment.The example more specifically (non-exhaustive list) of computer-readable medium comprises following: the electrical connection section (electronic installation) with one or more wiring, portable computer diskette box (magnetic device), random access memory (RAM), ROM (read-only memory) (ROM), erasablely edit ROM (read-only memory) (EPROM or flash memory), fiber device, and portable optic disk ROM (read-only memory) (CDROM).In addition, computer-readable medium can be even paper or other suitable media that can print described program thereon, because can such as by carrying out optical scanning to paper or other media, then carry out editing, decipher or carry out process with other suitable methods if desired and electronically obtain described program, be then stored in computer memory.
Should be appreciated that each several part of the application can realize with hardware, software, firmware or their combination.In the above-described embodiment, multiple step or method can with to store in memory and the software performed by suitable instruction execution system or firmware realize.Such as, if realized with hardware, the same in another embodiment, can realize by any one in following technology well known in the art or their combination: the discrete logic with the logic gates for realizing logic function to data-signal, there is the special IC of suitable combinational logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) etc.
Those skilled in the art are appreciated that realizing all or part of step that above-described embodiment method carries is that the hardware that can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, this program perform time, step comprising embodiment of the method one or a combination set of.
In addition, each functional unit in each embodiment of the application can be integrated in a processing module, also can be that the independent physics of unit exists, also can be integrated in a module by two or more unit.Above-mentioned integrated module both can adopt the form of hardware to realize, and the form of software function module also can be adopted to realize.If described integrated module using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.
The above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.Although illustrate and described the embodiment of the application above, be understandable that, above-described embodiment is exemplary, can not be interpreted as the restriction to the application, and those of ordinary skill in the art can change above-described embodiment, revises, replace and modification in the scope of the application.
Claims (10)
1. a voice correction processing method, is characterized in that, comprises the following steps:
Detect the recognition result of the voice messaging of user's input;
If detect wrong, then obtain the behavior intention of described user according to described voice messaging;
Be intended to according to described behavior, export the apply for information for voice of correcting a mistake to described user speech.
2. voice correction processing method as claimed in claim 1, is characterized in that, the recognition result of the voice messaging of described detection user input, comprising:
Retrieval voice identification result,
Judge whether result for retrieval is less than default retrieval quality, if so, then detect wrong, otherwise, detect correct.
3. voice correction processing method as claimed in claim 1, is characterized in that, the recognition result of the voice messaging of described detection user input, comprising:
The language model preset is adopted to mate voice identification result;
Judge whether matching degree is less than default threshold value, if so, then detect wrong, otherwise, detect correct.
4. the voice correction processing method as described in as arbitrary in claim 1-3, is characterized in that, the described behavior intention obtaining described user according to described voice messaging, comprising:
By described converting voice message into text message;
Instruction semantic feature database according to presetting carries out semantic analysis to described Word message, obtains the behavior intention of described user.
5. the voice correction processing method as described in as arbitrary in claim 1-3, is characterized in that, described to after described user speech exports the apply for information for voice of correcting a mistake, and also comprises:
Detect the recognition result of the correction voice messaging that described user inputs according to described apply for information;
If detect correct, then retrieve according to described correction voice messaging and described behavior intention;
Result for retrieval is sent to described user.
6. a voice error correcting handling arrangement, is characterized in that, comprising:
Detection module, for detecting the recognition result of the voice messaging of user's input;
Intention analysis module, if wrong for detecting, then obtains the behavior intention of described user according to described voice messaging;
Correction module, for being intended to according to described behavior, exports the apply for information for voice of correcting a mistake to described user speech.
7. voice error correcting handling arrangement as claimed in claim 6, it is characterized in that, described detection module comprises:
Retrieval unit, for retrieving voice identification result,
First judging unit, for judging whether result for retrieval is less than default retrieval quality, if so, then detects wrong, otherwise, detect correct.
8. voice error correcting handling arrangement as claimed in claim 6, it is characterized in that, described detection module comprises:
Matching unit, mates voice identification result for adopting default language model;
Second judging unit, for judging whether matching degree is less than default threshold value, if so, then detects wrong, otherwise, detect correct.
9. the voice error correcting handling arrangement as described in as arbitrary in claim 6-8, it is characterized in that, described intention analysis module, comprising:
Parsing unit, for by described converting voice message into text message;
Semantic analysis unit, for carrying out semantic analysis according to the instruction semantic feature database preset to described Word message, obtains the behavior intention of described user.
10. the voice error correcting handling arrangement as described in as arbitrary in claim 6-8, it is characterized in that, described device also comprises:
Described detection module, also for detecting the recognition result of the correction voice messaging that described user inputs according to described apply for information;
Retrieval module, if correct for detecting, then retrieves according to described correction voice messaging and described behavior intention;
Sending module, for sending result for retrieval to described user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510524094.7A CN105047198B (en) | 2015-08-24 | 2015-08-24 | Voice error correction processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510524094.7A CN105047198B (en) | 2015-08-24 | 2015-08-24 | Voice error correction processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105047198A true CN105047198A (en) | 2015-11-11 |
| CN105047198B CN105047198B (en) | 2020-09-22 |
Family
ID=54453685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510524094.7A Active CN105047198B (en) | 2015-08-24 | 2015-08-24 | Voice error correction processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105047198B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869642A (en) * | 2016-03-25 | 2016-08-17 | 海信集团有限公司 | Voice text error correction method and device |
| CN106098060A (en) * | 2016-05-19 | 2016-11-09 | 北京搜狗科技发展有限公司 | The correction processing method of voice and device, the device of correction process for voice |
| CN106328145A (en) * | 2016-08-19 | 2017-01-11 | 北京云知声信息技术有限公司 | Voice correction method and voice correction device |
| CN107045496A (en) * | 2017-04-19 | 2017-08-15 | 畅捷通信息技术股份有限公司 | The error correction method and error correction device of text after speech recognition |
| CN107993653A (en) * | 2017-11-30 | 2018-05-04 | 南京云游智能科技有限公司 | The incorrect pronunciations of speech recognition apparatus correct update method and more new system automatically |
| CN109389983A (en) * | 2017-08-10 | 2019-02-26 | 奥迪股份公司 | For handling the method and switching equipment of the recognition result of automatic online-speech recognition device of mobile terminal device |
| CN109841216A (en) * | 2018-12-26 | 2019-06-04 | 珠海格力电器股份有限公司 | Processing method, device and the intelligent terminal of voice data |
| CN109949813A (en) * | 2017-12-20 | 2019-06-28 | 北京君林科技股份有限公司 | A kind of method, apparatus and system converting speech into text |
| CN110020244A (en) * | 2017-11-03 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of pair of website information carries out the method and device of error correction |
| CN110289000A (en) * | 2019-05-27 | 2019-09-27 | 北京蓦然认知科技有限公司 | A kind of audio recognition method, device |
| CN110415679A (en) * | 2019-07-25 | 2019-11-05 | 北京百度网讯科技有限公司 | Voice error correction method, device, equipment and storage medium |
| CN110473543A (en) * | 2019-09-25 | 2019-11-19 | 北京蓦然认知科技有限公司 | A kind of audio recognition method, device |
| CN111415656A (en) * | 2019-01-04 | 2020-07-14 | 上海擎感智能科技有限公司 | Voice semantic recognition method and device and vehicle |
| CN112328737A (en) * | 2019-07-17 | 2021-02-05 | 北方工业大学 | Spelling data generation method |
| CN112455442A (en) * | 2019-09-09 | 2021-03-09 | 通用汽车环球科技运作有限责任公司 | Method and device for assisting voice-controlled steering in a driving vehicle |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1231742A (en) * | 1996-07-19 | 1999-10-13 | 微软公司 | Intelligent user assistance facility |
| CN1959628A (en) * | 2005-10-31 | 2007-05-09 | 西门子（中国）有限公司 | Man-machine interactive navigation system |
| CN103366741A (en) * | 2012-03-31 | 2013-10-23 | 盛乐信息技术（上海）有限公司 | Voice input error correction method and system |
| CN103744836A (en) * | 2014-01-08 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device |
| CN103841268A (en) * | 2014-03-17 | 2014-06-04 | 联想(北京)有限公司 | Information processing method and information processing device |
| CN104794218A (en) * | 2015-04-28 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Voice searching method and device |
-
2015
- 2015-08-24 CN CN201510524094.7A patent/CN105047198B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1231742A (en) * | 1996-07-19 | 1999-10-13 | 微软公司 | Intelligent user assistance facility |
| CN1959628A (en) * | 2005-10-31 | 2007-05-09 | 西门子（中国）有限公司 | Man-machine interactive navigation system |
| CN103366741A (en) * | 2012-03-31 | 2013-10-23 | 盛乐信息技术（上海）有限公司 | Voice input error correction method and system |
| CN103744836A (en) * | 2014-01-08 | 2014-04-23 | 苏州思必驰信息科技有限公司 | Man-machine conversation method and device |
| CN103841268A (en) * | 2014-03-17 | 2014-06-04 | 联想(北京)有限公司 | Information processing method and information processing device |
| CN104794218A (en) * | 2015-04-28 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Voice searching method and device |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869642A (en) * | 2016-03-25 | 2016-08-17 | 海信集团有限公司 | Voice text error correction method and device |
| CN105869642B (en) * | 2016-03-25 | 2019-09-20 | 海信集团有限公司 | A kind of error correction method and device of speech text |
| CN106098060A (en) * | 2016-05-19 | 2016-11-09 | 北京搜狗科技发展有限公司 | The correction processing method of voice and device, the device of correction process for voice |
| CN106098060B (en) * | 2016-05-19 | 2020-01-31 | 北京搜狗科技发展有限公司 | Method and device for error correction processing of voice |
| CN106328145B (en) * | 2016-08-19 | 2019-10-11 | 北京云知声信息技术有限公司 | Voice modification method and device |
| CN106328145A (en) * | 2016-08-19 | 2017-01-11 | 北京云知声信息技术有限公司 | Voice correction method and voice correction device |
| CN107045496A (en) * | 2017-04-19 | 2017-08-15 | 畅捷通信息技术股份有限公司 | The error correction method and error correction device of text after speech recognition |
| CN107045496B (en) * | 2017-04-19 | 2021-01-05 | 畅捷通信息技术股份有限公司 | Error correction method and error correction device for text after voice recognition |
| CN109389983A (en) * | 2017-08-10 | 2019-02-26 | 奥迪股份公司 | For handling the method and switching equipment of the recognition result of automatic online-speech recognition device of mobile terminal device |
| CN109389983B (en) * | 2017-08-10 | 2023-07-07 | 奥迪股份公司 | Method for processing recognition results of an automatic online voice recognizer of a mobile terminal and switching device |
| CN110020244A (en) * | 2017-11-03 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of pair of website information carries out the method and device of error correction |
| CN107993653A (en) * | 2017-11-30 | 2018-05-04 | 南京云游智能科技有限公司 | The incorrect pronunciations of speech recognition apparatus correct update method and more new system automatically |
| CN109949813A (en) * | 2017-12-20 | 2019-06-28 | 北京君林科技股份有限公司 | A kind of method, apparatus and system converting speech into text |
| CN109841216A (en) * | 2018-12-26 | 2019-06-04 | 珠海格力电器股份有限公司 | Processing method, device and the intelligent terminal of voice data |
| CN109841216B (en) * | 2018-12-26 | 2020-12-15 | 珠海格力电器股份有限公司 | Voice data processing method and device and intelligent terminal |
| CN111415656A (en) * | 2019-01-04 | 2020-07-14 | 上海擎感智能科技有限公司 | Voice semantic recognition method and device and vehicle |
| CN110289000A (en) * | 2019-05-27 | 2019-09-27 | 北京蓦然认知科技有限公司 | A kind of audio recognition method, device |
| CN112328737A (en) * | 2019-07-17 | 2021-02-05 | 北方工业大学 | Spelling data generation method |
| CN112328737B (en) * | 2019-07-17 | 2023-05-05 | 北方工业大学 | Spelling data generation method |
| CN110415679B (en) * | 2019-07-25 | 2021-12-17 | 北京百度网讯科技有限公司 | Voice error correction method, device, equipment and storage medium |
| US11328708B2 (en) | 2019-07-25 | 2022-05-10 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Speech error-correction method, device and storage medium |
| CN110415679A (en) * | 2019-07-25 | 2019-11-05 | 北京百度网讯科技有限公司 | Voice error correction method, device, equipment and storage medium |
| CN112455442A (en) * | 2019-09-09 | 2021-03-09 | 通用汽车环球科技运作有限责任公司 | Method and device for assisting voice-controlled steering in a driving vehicle |
| CN110473543A (en) * | 2019-09-25 | 2019-11-19 | 北京蓦然认知科技有限公司 | A kind of audio recognition method, device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105047198B (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105047198A (en) | Voice error correction processing method and apparatus | |
| US10831345B2 (en) | Establishing user specified interaction modes in a question answering dialogue | |
| US11854570B2 (en) | Electronic device providing response to voice input, and method and computer readable medium thereof | |
| CN105183422A (en) | Voice control method and apparatus for application program | |
| CN107146612B (en) | Voice guidance method and device, intelligent equipment and server | |
| US20200193983A1 (en) | Vehicle having dialogue system and control method thereof | |
| CN104504649A (en) | Picture cutting method and device | |
| CN105575386A (en) | Method and device for voice recognition | |
| CN105095186A (en) | Semantic analysis method and device | |
| CN108039175B (en) | Voice recognition method and device and server | |
| CN104573099A (en) | Topic searching method and device | |
| US20200005782A1 (en) | Method and apparatus for pushing information | |
| CN105529030A (en) | Speech recognition processing method and device | |
| CN105491126A (en) | Service providing method and service providing device based on artificial intelligence | |
| CN105183778A (en) | Service providing method and apparatus | |
| CN113421561B (en) | Voice control method, voice control device, server, and storage medium | |
| US20170161386A1 (en) | Adaptive product questionnaire | |
| CN103995845A (en) | Information search method and device | |
| CN110992937A (en) | Language offline recognition method, terminal and readable storage medium | |
| CN109597996B (en) | Semantic analysis method, device, equipment and medium | |
| CN116932919B (en) | Information pushing method, device, electronic equipment and computer readable medium | |
| CN104468926A (en) | Method and device for controlling contact persons in mobile terminal | |
| CN110704592B (en) | Statement analysis processing method and device, computer equipment and storage medium | |
| CN113409777B (en) | Method for recording user attention point, vehicle-mounted host and vehicle | |
| US20120311417A1 (en) | Attaching Audio Generated Scripts To Graphical Representations of Applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |