CN107293299A - It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency - Google Patents
It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency Download PDFInfo
- Publication number
- CN107293299A CN107293299A CN201710466569.0A CN201710466569A CN107293299A CN 107293299 A CN107293299 A CN 107293299A CN 201710466569 A CN201710466569 A CN 201710466569A CN 107293299 A CN107293299 A CN 107293299A
- Authority
- CN
- China
- Prior art keywords
- module
- unit
- speech recognition
- keyword
- word
- 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
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Machine Translation (AREA)
Abstract
The present invention relates to identification field of locating technology, more particularly to a kind of speech recognition alignment system for improving dispatcher's lookup drawing efficiency, including the speech recognition system, extraction system and search system being sequentially connected, the speech recognition system is used to voice messaging identification being converted into word and exported, the Word Input that the extraction system is identified according to goes out keyword, the search system transfers the keyword of extraction system extraction, scans for seeing according to keyword and finds out required Distributing Network GIS drawing;The extraction system includes keyword database and extracts keyword algorithm unit, the keyword database is used to store keyword and key characteristics, and the Word Input that the keyword algorithm unit is recognized according to keyword database and speech recognition system goes out keyword.
Description
【Technical field】
Know the present invention relates to identification field of locating technology, more particularly to a kind of voice for improving dispatcher's lookup drawing efficiency
Other alignment system.
【Background technology】
With the increasingly raising of modern industry, the fast development of modern agriculture and living standards of the people, entire society is to electricity
The demand of power is increasing, and the structure of power distribution network becomes increasingly complex.In electric power system field, when line fault occurs for distribution,
Field Force reports accident conditions, during dispatcher's business processing, need to be while receiving calls, while opening CAD diagram paper is looked into step by step
Look for specific faulty line position, inefficiency.How breakdown switch is quickly navigated to, for isolated fault between the first ground and adopted
The measure fast recovery of power supply of taking will play a key effect, in vertical wrong complicated distribution line, go to search branch line event by memory
Barrier switch, wastes time and energy.It is necessary to provide a kind of speech recognition alignment system for improving dispatcher's lookup drawing efficiency, can
So that when dispatcher answers Field Force and reported the developments, its voice to be identified, to solve dispatcher in incident processing procedure
Middle search opens that circuit drawing is cumbersome and the problem of business record frequent inefficiency, improves operating efficiency, mitigates dispatcher and bear
Load.
【The content of the invention】
In view of the foregoing, it is necessary to which a kind of speech recognition alignment system for improving dispatcher's lookup drawing efficiency is provided,
When being easy to the electric power system field dispatcher to answer Field Force and report the developments, its voice is identified, found beneficial to quick production
Faulty line position and business record.
To achieve the above object, the technical solution adopted by the present invention is:
It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency, including the speech recognition system being sequentially connected
System, extraction system and search system, the speech recognition system are used to voice messaging identification being converted into word and exported, described
The Word Input that extraction system is identified according to goes out keyword, and the search system transfers the key of extraction system extraction
Word, scans for seeing and finds out required Distributing Network GIS drawing according to keyword;The extraction system include keyword database and
Keyword algorithm unit is extracted, the keyword database is used to store keyword and key characteristics, the keyword algorithm
The Word Input that unit is recognized according to keyword database and speech recognition system goes out keyword;The speech recognition system includes
Orientation identification hoisting module, the orientation identification hoisting module is used to lift special sound recognition accuracy.
Further, the speech recognition system includes starting module, voice acquisition module, speech processing module, voice
Identification module, output module and display module;The starting module is connected with the voice acquisition module, the voice collecting mould
Block is connected with speech processing module, and the speech processing module is connected with the sound identification module, the sound identification module
It is connected with the output module, the output module is connected with the display module;
The starting module includes detection unit and wakeup unit, and the detection unit and wakeup unit are connected with each other, institute
Detection unit is stated for detecting whether there is the signal for starting the voice acquisition module, wakeup unit is used to wake up voice collecting mould
Block;
The voice acquisition module is used to gather voice signal;
The speech processing module includes converting unit and noise reduction unit, and the converting unit is adopted for receiving the voice
The voice signal that collection module is collected, and analog-to-digital conversion is carried out to the voice signal, the noise reduction unit is used to reduce described
The noise of voice signal;
The sound identification module include memory cell, replace word cell, hot word unit, orientation identification hoisting module and
Speech recognition algorithm unit, the memory cell, replacement word cell, hot word unit are connected with speech recognition algorithm unit, institute
Stating replacement word cell is used to set common word tone to replace word, and the hot word unit is used to store identification frequency high word and word, institute
Stating orientation identification hoisting module includes matching unit and correction unit;The matching unit is used for according to the prefabricated information of user, right
Candidate's words in the set of paths obtained by tone decoding is matched, and obtains new set of paths;The correction unit
For the class language model by being built using user's preset information as element to candidate word in the new set of paths
The probabilistic language model of word is corrected;The speech recognition algorithm unit is used to recognize the language after analog-to-digital conversion and noise reduction
Message number, the memory cell is used for set and the prefabricated information of user for storing all default voices being compared;
The output module is used to export the word that the sound identification module is identified;
The display module is used for the content for showing the output module output.
Further, the search system includes the second memory cell and search unit, and second memory cell is used for
Store Distributing Network GIS drawing, the search unit is used for according to the keyword that extracts and searched out pair in the second memory cell
The Distributing Network GIS drawing answered.
Further, the voice acquisition module converts voice signals into electric signal using microphone.
Further, the signal for starting the voice acquisition module is closing of the circuit signal.
Further, display module is electronic display.
Further, the special sound includes place name and field of power distribution major terms.
Further, the prefabricated information of the user includes what place name, field of power distribution major terms and Distributing Network GIS drawing occurred
Word, word.
A kind of speech recognition alignment system for improving dispatcher's lookup drawing efficiency is due to using above-mentioned technical proposal, this hair
It is bright to have the advantages that:
This is used for when electric power system field dispatcher telephone receiving Field Force reports the developments using invention, starting module
Closing of the circuit is detected, voice acquisition module is acquired to call voice, speech processing module processing is transferred to after collection,
Recognize, given finally by output module output identification to display module, dispatcher is according to display mould by sound identification module
The recognition result that block is shown quickly finds faulty line position.The present invention detects call scenarios at any time by starting module, can
To wake up system work in time, system standby can be saved at the energy, speech processing module when need not carry out speech recognition
Reason carries out noise reduction process to voice and causes resolution higher, replaces word cell, hot word unit and provides a weights to lift voice
Identification module is to precision of identifying speech and accuracy rate, and orientation identification hoisting module can lift recognition accuracy, output module with
Display module shows speech recognition content, and keyword extraction system can extract keyword, and such as place name breaker key message enters
And search system searches out specific faulty line drawing according to the key message of extraction, the position of the switch is quick and precisely found, significantly
Improve dispatcher's operating efficiency and mitigate its burden.
【Brief description of the drawings】
Fig. 1 is the speech recognition alignment system knot of raising dispatcher's lookup drawing efficiency in a better embodiment of the invention
Structure block diagram.
Fig. 2 is the speech recognition alignment system language of raising dispatcher's lookup drawing efficiency in a better embodiment of the invention
Sound identifying system structured flowchart.
Fig. 3 is the speech recognition alignment system language of raising dispatcher's lookup drawing efficiency in a better embodiment of the invention
Sound identification module structured flowchart.
【Embodiment】
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Refer to accompanying drawing,
It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency, including the speech recognition system being sequentially connected
System 100, extraction system 200 and search system 300, speech recognition system 100 are used to voice messaging identification being converted into word simultaneously
Output, extraction system 200 goes out keyword according to the Word Input identified, and search system 300 is transferred extraction system and carried
The keyword taken, scans for seeing and finds out required Distributing Network GIS drawing according to keyword.Extraction system 200 includes keyword
Database 201 and extraction keyword algorithm unit 202, keyword database 201 are used to store keyword and key characteristics, one
As commonly use the keyword needed for " * switches ", " * switching stations ", " * fuses ", " 10KV* lines ", " * lines ", " * cranes " etc., its
In " * " represent specific name or place name, keyword algorithm unit 202 is recognized according to keyword database and speech recognition system
Word Input goes out keyword, and the keyword now extracted is the specific name of circuit drawing, specific such as " south of the River station ",
The keywords such as " 10KV Nanhua line ", " pool lines of south of the River station 10KV eight ".As scene make a phone call report 10KV farms line farm 02 switch
Failure, system, which is transferred, is opened to 10KV farms line chart paper, and navigates to the switch interface of farm 02.
Further, speech recognition system 100 includes starting module 1, voice acquisition module 2, speech processing module 3, language
Sound identification module 4, output module 5 and display module 6.Starting module 1 is connected with voice acquisition module 2, voice acquisition module 2 with
Speech processing module 3 is connected, and speech processing module 3 is connected with sound identification module 4, and sound identification module 4 connects with output module 5
Connect, output module 5 is connected with display module 6.Starting module 1 include detection unit 11 and wakeup unit 12, detection unit 11 and
Wakeup unit 12 is connected with each other, and detection unit 11 is for detecting whether there is the signal for starting the voice acquisition module 2, and wake-up is single
Member 12 is used to wake up voice acquisition module 2.Voice acquisition module 2 is used to gather voice signal;Speech processing module 3 includes conversion
Unit 31 and noise reduction unit 32, converting unit 31 are used to receive the voice signal that voice acquisition module 2 is collected, and voice is believed
Number carry out analog-to-digital conversion, noise reduction unit 32 be used for reduce the noise of voice signal.
Sound identification module 4 includes memory cell 41, replaces word cell 43, hot word unit 44, orientation identification hoisting module
45 and speech recognition algorithm unit 42, memory cell 41, replace word cell 43, hot word unit 44 with speech recognition algorithm unit
42 are connected, and replacing word cell 43 is used to set common word tone to replace word, such as replaces " half field line ", " expecting field line ", " touching field line "
For actual correct " Pan fields line ", fixed resolution is improved, hot word unit 44 is used to store the high word of identification frequency and word is carried
Recognition accuracy is risen, speech recognition algorithm unit 42 is used to recognize the voice signal after analog-to-digital conversion and noise reduction, and storage is single
Member 41 is used to storing the set of all default voices being compared and the prefabricated information of user, the prefabricated information of user include place name,
Word, word that field of power distribution major terms and Distributing Network GIS drawing occur.The orientation identification hoisting module includes matching unit and school
Positive unit;The matching unit is used for according to the prefabricated information of user, to the candidate in the set of paths that is obtained by tone decoding
Words is matched, and obtains new set of paths and the prefabricated information of user;Orientation identification hoisting module 45 includes matching unit 451
With correction unit 452;Matching unit 451 is used for according to the prefabricated information of user, in the set of paths that is obtained by tone decoding
Candidate's words matched, obtain new set of paths;Correcting unit 452 is used for by using user's preset information as member
The class language model that element is built is corrected to the probabilistic language model of candidate's words in the new set of paths.
Output module 5 is used to export the word that sound identification module 4 is identified;Display module 6 is used for display output mould
The content that block 5 is exported.
Further, voice acquisition module 2 converts voice signals into electric signal using microphone.Start the voice to adopt
Integrate the signal of module as closing of the circuit signal.Display module 6 is electronic display.
Further, search system 300 includes the second memory cell 301 and search unit 302, the second memory cell 301
With in storage Distributing Network GIS drawing, the keyword that search unit 302 is used to extract according to is searched in the second memory cell
Go out corresponding Distributing Network GIS drawing.
Brief description present invention invention improves the application method that dispatcher searches the speech recognition alignment system of drawing efficiency,
Every distribution line can all have a CAD diagram paper file, and each file is carried out according to plant stand, region under normal circumstances
Classification And Nomenclature is stored, and such as " south of the River station ", " five inner stations ", mode name file, " 10KV Nanhua line ", " south of the River station 10KV eight
The modes such as pool line " name specific circuit.
The detection unit 11 of starting module 1 is connected with Telephone set, when Field Force's phone gives dispatcher's report accident feelings
Condition, closing of the circuit when detection unit 11 detects closing of the circuit, sends a signal to wakeup unit 12, wakeup unit 12 is sent
Wake-up signal is acquired to voice collecting unit 12, voice collecting unit 12 to the voice of telephone relation.By the language collected
Message breath passes to converting unit 31 and carries out analog-to-digital conversion, converts analog signals into data signal, then by noise reduction unit 32
The noise of voice messaging is reduced, noise can be suppressed and listener's echo is eliminated, the resolution of voice signal is improved, and by after processing
Recognizable voice signal pass to sound identification module 4 and carry out speech recognition, result after identification by output module 5 with
Written form is exported to display module 6 and shown.Extraction system 200 goes out keyword therein according to the Word Input of display,
Search system 300 opens circuit drawing according to the keyword of extraction and navigates to specific trouble point.
Claims (8)
1. a kind of improve the speech recognition alignment system that dispatcher searches drawing efficiency, it is characterised in that including what is be sequentially connected
Speech recognition system, extraction system and search system, the speech recognition system are used to voice messaging identification being converted into word
And export, the Word Input that the extraction system is identified according to goes out keyword, and the search system transfers extraction system
The keyword that system is extracted, scans for seeing according to keyword and finds out required Distributing Network GIS drawing;The extraction system includes closing
Key numerical data base and extraction keyword algorithm unit, the keyword database are used to store keyword and key characteristics, institute
State keyword algorithm unit and keyword is gone out according to the Word Input of keyword database and speech recognition system identification;The voice
Identifying system includes orientation identification hoisting module, and the orientation identification hoisting module is used to lift special sound recognition accuracy.
2. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 1, it is characterised in that institute
State speech recognition system including starting module, voice acquisition module, speech processing module, sound identification module, output module and
Display module;The starting module is connected with the voice acquisition module, the voice acquisition module and speech processing module phase
Even, the speech processing module is connected with the sound identification module, and the sound identification module is connected with the output module,
The output module is connected with the display module;
The starting module includes detection unit and wakeup unit, and the detection unit and wakeup unit are connected with each other, the inspection
Unit is surveyed for detecting whether there is the signal for starting the voice acquisition module, wakeup unit is used to wake up voice acquisition module;
The voice acquisition module is used to gather voice signal;
The speech processing module includes converting unit and noise reduction unit, and the converting unit is used to receive the voice collecting mould
The voice signal that block is collected, and analog-to-digital conversion is carried out to the voice signal, the noise reduction unit is used to reduce the voice
The noise of signal;
The sound identification module includes memory cell, replaces word cell, hot word unit, orientation identification hoisting module and voice
Recognizer unit, the memory cell, replacement word cell, hot word unit are connected with speech recognition algorithm unit, described to replace
Changing word cell is used to set common word tone to replace word, and the hot word unit is used to store identification frequency high word and word, described fixed
Include matching unit and correction unit to identification hoisting module;The matching unit is used for according to the prefabricated information of user, to passing through
Candidate's words in the set of paths that tone decoding is obtained is matched, and obtains new set of paths;The correction unit is used for
By the class language model that is built using user's preset information as element to candidate's words in the new set of paths
Probabilistic language model is corrected;The speech recognition algorithm unit is used to recognize the letter of the voice after analog-to-digital conversion and noise reduction
Number, the memory cell is used for set and the prefabricated information of user for storing all default voices being compared;
The output module is used to export the word that the sound identification module is identified;
The display module is used for the content for showing the output module output.
3. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 1, it is characterised in that:Institute
Stating search system includes the second memory cell and search unit, and second memory cell is used to store Distributing Network GIS drawing, described
The keyword that search unit is used to extract according to searches out corresponding Distributing Network GIS drawing in the second memory cell.
4. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 2, it is characterised in that:Institute
State voice acquisition module and electric signal is converted voice signals into using microphone.
5. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 2, it is characterised in that:Institute
State and start the signal of the voice acquisition module for closing of the circuit signal.
6. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 2, it is characterised in that:It is aobvious
It is electronic display to show module.
7. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 1, it is characterised in that:Institute
Stating special sound includes place name and field of power distribution major terms.
8. the speech recognition alignment system that dispatcher searches drawing efficiency is improved according to claim 2, it is characterised in that:Institute
State word, word that the prefabricated information of user occurs including place name, field of power distribution major terms and Distributing Network GIS drawing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710466569.0A CN107293299A (en) | 2017-06-16 | 2017-06-16 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710466569.0A CN107293299A (en) | 2017-06-16 | 2017-06-16 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107293299A true CN107293299A (en) | 2017-10-24 |
Family
ID=60097380
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710466569.0A Pending CN107293299A (en) | 2017-06-16 | 2017-06-16 | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107293299A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109474455A (en) * | 2018-01-30 | 2019-03-15 | 东阳市光明电力建设有限公司 | A kind of 10kV Distribution Network Failure regulation reporting system and method |
CN109949008A (en) * | 2019-03-20 | 2019-06-28 | 钱露露 | A kind of Study of intelligent discussion brainstorming conference office system |
CN110689328A (en) * | 2019-10-10 | 2020-01-14 | 国网山东省电力公司泰安供电公司 | Novel dispatching office system based on voice input |
CN111128144A (en) * | 2019-10-16 | 2020-05-08 | 国网浙江省电力有限公司金华供电公司 | Voice power grid dispatching system and method |
CN113436614A (en) * | 2021-07-02 | 2021-09-24 | 科大讯飞股份有限公司 | Speech recognition method, apparatus, device, system and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1282072A (en) * | 1999-07-27 | 2001-01-31 | 国际商业机器公司 | Error correcting method for voice identification result and voice identification system |
EP1231595A1 (en) * | 2001-02-13 | 2002-08-14 | Philips Corporate Intellectual Property GmbH | Training methode of the free parameters in a maximum entropy language model |
CN1764944A (en) * | 2003-03-26 | 2006-04-26 | 皇家飞利浦电子股份有限公司 | Speech recognition system |
TW201009298A (en) * | 2008-08-29 | 2010-03-01 | Mediatek Heifei Inc | Navigation device capable of playing voice guidance and method for playing voice guidance for a navigation device |
CN101923697A (en) * | 2010-09-09 | 2010-12-22 | 大道计算机技术(上海)有限公司 | Geographic information accessory system applicable to large screen and implementation method thereof |
CN102033953A (en) * | 2010-12-25 | 2011-04-27 | 江西九江供电公司 | Equipment accounting management method for electric distribution network |
CN102831307A (en) * | 2012-05-31 | 2012-12-19 | 山东电力集团公司青岛供电公司 | Three-dimensional GIS (Geographic Information System) technology based power grid visualization system and method |
CN103207769A (en) * | 2012-01-16 | 2013-07-17 | 联想(北京)有限公司 | Method and user equipment for voice amending |
CN103246747A (en) * | 2013-05-23 | 2013-08-14 | 国家电网公司 | Power distribution work area line query system |
CN103903619A (en) * | 2012-12-28 | 2014-07-02 | 安徽科大讯飞信息科技股份有限公司 | Method and system for improving accuracy of speech recognition |
CN105632499A (en) * | 2014-10-31 | 2016-06-01 | 株式会社东芝 | Method and device for optimizing voice recognition result |
-
2017
- 2017-06-16 CN CN201710466569.0A patent/CN107293299A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1282072A (en) * | 1999-07-27 | 2001-01-31 | 国际商业机器公司 | Error correcting method for voice identification result and voice identification system |
CN1207664C (en) * | 1999-07-27 | 2005-06-22 | 国际商业机器公司 | Error correcting method for voice identification result and voice identification system |
EP1231595A1 (en) * | 2001-02-13 | 2002-08-14 | Philips Corporate Intellectual Property GmbH | Training methode of the free parameters in a maximum entropy language model |
CN1764944A (en) * | 2003-03-26 | 2006-04-26 | 皇家飞利浦电子股份有限公司 | Speech recognition system |
TW201009298A (en) * | 2008-08-29 | 2010-03-01 | Mediatek Heifei Inc | Navigation device capable of playing voice guidance and method for playing voice guidance for a navigation device |
CN101923697A (en) * | 2010-09-09 | 2010-12-22 | 大道计算机技术(上海)有限公司 | Geographic information accessory system applicable to large screen and implementation method thereof |
CN102033953A (en) * | 2010-12-25 | 2011-04-27 | 江西九江供电公司 | Equipment accounting management method for electric distribution network |
CN103207769A (en) * | 2012-01-16 | 2013-07-17 | 联想(北京)有限公司 | Method and user equipment for voice amending |
CN102831307A (en) * | 2012-05-31 | 2012-12-19 | 山东电力集团公司青岛供电公司 | Three-dimensional GIS (Geographic Information System) technology based power grid visualization system and method |
CN103903619A (en) * | 2012-12-28 | 2014-07-02 | 安徽科大讯飞信息科技股份有限公司 | Method and system for improving accuracy of speech recognition |
CN103903619B (en) * | 2012-12-28 | 2016-12-28 | 科大讯飞股份有限公司 | A kind of method and system improving speech recognition accuracy |
CN103246747A (en) * | 2013-05-23 | 2013-08-14 | 国家电网公司 | Power distribution work area line query system |
CN105632499A (en) * | 2014-10-31 | 2016-06-01 | 株式会社东芝 | Method and device for optimizing voice recognition result |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109474455A (en) * | 2018-01-30 | 2019-03-15 | 东阳市光明电力建设有限公司 | A kind of 10kV Distribution Network Failure regulation reporting system and method |
CN109949008A (en) * | 2019-03-20 | 2019-06-28 | 钱露露 | A kind of Study of intelligent discussion brainstorming conference office system |
CN110689328A (en) * | 2019-10-10 | 2020-01-14 | 国网山东省电力公司泰安供电公司 | Novel dispatching office system based on voice input |
CN111128144A (en) * | 2019-10-16 | 2020-05-08 | 国网浙江省电力有限公司金华供电公司 | Voice power grid dispatching system and method |
CN113436614A (en) * | 2021-07-02 | 2021-09-24 | 科大讯飞股份有限公司 | Speech recognition method, apparatus, device, system and storage medium |
CN113436614B (en) * | 2021-07-02 | 2024-02-13 | 中国科学技术大学 | Speech recognition method, device, equipment, system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107293299A (en) | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency | |
CN111755001A (en) | Artificial intelligence-based power grid rapid dispatching and commanding system and method | |
CN109559754B (en) | Voice rescue method and system for tumble identification | |
CN100349206C (en) | Text-to-speech interchanging device | |
CN105608649A (en) | Face identification-based hotel check-in management system | |
CN111159387B (en) | Recommendation method based on multi-dimensional alarm information text similarity analysis | |
CN109459663B (en) | Intelligent power distribution network fault section positioning method based on multiple time scales | |
CN109119084A (en) | A kind of dispatch call method and system based on speech recognition | |
CN105472178A (en) | Method for controlling voice communication by brain wave and system thereof | |
CN112529056B (en) | Research and judgment method for large-area power failure of power distribution network | |
CN113051384B (en) | User portrait extraction method based on dialogue and related device | |
CN103217597A (en) | Construction method of general test template of digital relay protective device | |
CN107357859A (en) | A kind of intelligent terminal for realizing that knowledge base shows automatically by voice collecting | |
CN110299140A (en) | A kind of key content extraction algorithm based on Intelligent dialogue | |
CN106709018A (en) | Method and device for hitting preset problems | |
CN206758123U (en) | A kind of Distributing Network GIS speech recognition automatic positioning equipment | |
Zhang et al. | Research on spectrum sensing system based on composite neural network | |
CN208337677U (en) | A kind of dispatcher telephone device based on speech recognition | |
CN207337914U (en) | A kind of speech recognition system | |
CN106849077A (en) | Island detection method based on electric power wireless private network | |
CN202309838U (en) | Telephone user interface module | |
CN108629097B (en) | A kind of substation secondary device topology analyzing method | |
CN110969021A (en) | Named entity recognition method, device, equipment and medium in single-round conversation | |
CN110245617A (en) | Artificial intelligence analysis's method based on transient state recording waveform | |
CN109240104A (en) | A kind of speech recognition controlled smart home system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |