CN109284505A - It is a kind of for vehicle-mounted natural language semantic analysis - Google Patents
It is a kind of for vehicle-mounted natural language semantic analysis Download PDFInfo
- Publication number
- CN109284505A CN109284505A CN201811318257.6A CN201811318257A CN109284505A CN 109284505 A CN109284505 A CN 109284505A CN 201811318257 A CN201811318257 A CN 201811318257A CN 109284505 A CN109284505 A CN 109284505A
- Authority
- CN
- China
- Prior art keywords
- sound
- acquisition
- text
- information
- natural language
- 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
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003825 pressing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000001914 filtration Methods 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G10L15/08—Speech classification or search
- G10L15/083—Recognition networks
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The present invention relates to vehicle-mounted natural language semantic analysis technology fields, it is especially a kind of for vehicle-mounted natural language semantic analysis, present invention improves over traditional sound collection modes, carry out noise reduction processing and sound wave filtration treatment, can quality to the sound collection of driver it is high, effectively prevent the interference of noise, for driving the complicated natural language of input, system realizes automatic network savvy, web search can be passed through and obtain complicated acoustic information, and it downloads and is saved in system sounds library, when being conducive to next driver's input same sound, quickly it can identify and execute instruction.Of the invention is practical, is worthy to be popularized.
Description
Technical field
The present invention relates to vehicle-mounted natural language semantic analysis technology fields more particularly to a kind of for vehicle-mounted natural language
Semantic analysis.
Background technique
Natural language typically refers to a kind of language to develop naturally with culture, Chinese, and English, Chinese, Japanese are nature
The example of language, and Esperanto is then fabricated language, is a kind of language created for certain specific purposes, but, sometimes
The language (including the above-mentioned language to develop naturally with culture and fabricated language) that all mankind use can all be considered as " certainly
So " language sets " artificial " language to be computer relative to such as programming language etc., a kind of this usage is found in natural language
It handles in a word, natural language is the main tool of Human communication and thinking, and natural language is the crystallization of the wisdom of humanity, natural language
Speech processing is one of problem the most difficult in artificial intelligence, and is also filled with glamour and challenge to the research of natural language processing
And each compatriots expression one of method, with the enhancing that people realize driving safety, Human-machine Control side in driving
Formula requirement is more simple and efficient, does not disperse the attention in driver drives vehicle, current each common control unit of system controller
There are the modes such as touch screen, knob, switch, the entity on other interior controllers such as instrument mostly exclusive use or multiplexing steering wheel is pressed
Key, and it is complex when multiplex mode switching and operation, then pillow screen uses included touch screen, higher cost.Interior each control
Reusability is low between the control unit of device processed, realizes that multiplexing switching mode is complicated, the control list that driver needs to pay close attention in the car
Member is more, is easy to take sb's mind off sth when there is the operational requirements of multiple controllers, is unfavorable for safe driving, currently, automobile is all real
Vehicle-mounted voice function is showed, still, some vehicle-mounted voices can not often identify the complicated natural language that driver inputs, all
The meaning of a word of some natural languages cannot understand that this just causes certain puzzlement to driver.
Summary of the invention
The purpose of the present invention is to solve the unrecognized disadvantages of natural language that complexity exists in the prior art, and mention
Out a kind of for vehicle-mounted natural language semantic analysis.
To achieve the goals above, present invention employs following technical solutions:
It designs a kind of for vehicle-mounted natural language semantic analysis, comprising the following steps:
Step 1: pressing vice activation key, start vehicle-mounted speech pattern;
Step 2: driver carries out natural-sounding input by speech ciphering equipment, and onboard system adopts driver's sound
Collection, while carrying out noise reduction process, so that the sound of acquisition is more clear, and is conducive to identify;
Step 3: system identifies the sound of acquisition, in fact includes a speech recognition program, the program is for examining
Whether the sound for surveying acquisition is the common sound of driver, if detect be driver common sound, system is by acquisition
Sound is converted into text, and if not common sound, system then enters voice bank and scans for extracting;
Step 4: system is when voice bank scans for, and including a sound extraction procedure, the program is for detecting
The information of acquisition sound can be extracted in voice bank, if it is possible to extract the information of acquisition sound, then system will acquire sound
Information be converted into text, if the information of acquisition sound can not be extracted, system if, carries out web search acquisition sound letter
Breath;
Step 5: system acquires sound source by web search, obtains program including a sound, which is used for
Can detection obtain the information of acquisition sound by web search, if it is possible to obtain the letter that acquisition sound arrives by web search
Acquisition acoustic information can be downloaded and be saved in voice bank, text is then converted into, if can not search by network by breath, system
Rope obtains the information that arrives of acquisition sound, system will active termination order, and driver is reminded to re-enter;
Step 6: after the sound of acquisition is converted into text by system, it will the dictionary search for carrying out system, including one
The program of a uncommon word of detection, whether the text which is used to detect conversion is uncommon word, if the text of conversion is not raw
Out-of-the-way word, then system can obtain the meaning of a word of text, then generate order, if the text of fruit conversion is uncommon word, system can pass through
Network lexicon scans for, and text information is then downloaded to dictionary, then extracts the meaning of a word of text, and generates instruction;
Step 7: system will execute instruction, and complete the instruction of driver's input.
Preferably, it is equipped with reservoir in the voice bank and dictionary, is used for stored voice source and word information, while right
New sound source and word is saved by downloading.
Preferably, sound enhanced processing has been carried out during the sound collection, has been conducive to system identification.
Preferably, the system comprises having to connect network program automatically, this can help system can obtain more information.
Preferably, during the system carries out noise reduction process, including acoustic wave filter program, the program being capable of automatic fitrations
Fall the sound wave of some interference sounds.
Proposed by the present invention a kind of for vehicle-mounted natural language semantic analysis, beneficial effect is: of the invention
Benefit be can quality to the sound collection of driver it is high, the interference of noise is effectively prevented, for driving the complexity of input
Natural language, web search can be carried out by system and obtain acoustic information, and downloads and is saved in system sounds library, is had
When inputting same sound conducive to next driver, quickly it can identify and execute instruction.
Detailed description of the invention
Fig. 1 is a kind of flow chart for vehicle-mounted natural language semantic analysis proposed by the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
It is referring to Fig.1, a kind of for vehicle-mounted natural language semantic analysis, comprising the following steps:
Step 1: pressing vice activation key, start vehicle-mounted speech pattern;
Step 2: driver carries out natural-sounding input by speech ciphering equipment, and onboard system adopts driver's sound
Collection, while carrying out noise reduction process, so that the sound of acquisition is more clear, and is conducive to identify;
Step 3: system identifies the sound of acquisition, in fact includes a speech recognition program, the program is for examining
Whether the sound for surveying acquisition is the common sound of driver, if detect be driver common sound, system is by acquisition
Sound is converted into text, and if not common sound, system then enters voice bank and scans for extracting;
Step 4: system is when voice bank scans for, and including a sound extraction procedure, the program is for detecting
The information of acquisition sound can be extracted in voice bank, if it is possible to extract the information of acquisition sound, then system will acquire sound
Information be converted into text, if the information of acquisition sound can not be extracted, system if, carries out web search acquisition sound letter
Breath;
Step 5: system acquires sound source by web search, obtains program including a sound, which is used for
Can detection obtain the information of acquisition sound by web search, if it is possible to obtain the letter that acquisition sound arrives by web search
Acquisition acoustic information can be downloaded and be saved in voice bank, text is then converted into, if can not search by network by breath, system
Rope obtains the information that arrives of acquisition sound, system will active termination order, and driver is reminded to re-enter;
Step 6: after the sound of acquisition is converted into text by system, it will the dictionary search for carrying out system, including one
The program of a uncommon word of detection, whether the text which is used to detect conversion is uncommon word, if the text of conversion is not raw
Out-of-the-way word, then system can obtain the meaning of a word of text, then generate order, if the text of fruit conversion is uncommon word, system can pass through
Network lexicon scans for, and text information is then downloaded to dictionary, then extracts the meaning of a word of text, and generates instruction;
Step 7: system will execute instruction, and complete the instruction of driver's input.
Wherein, it is equipped with reservoir in voice bank and dictionary, is used for stored voice source and word information, while to new sound
Source of sound and word are saved by downloading;Sound enhanced processing has been carried out during sound collection, has been conducive to system identification;System packet
Included and connected network program automatically, this can help system can obtain more information;During system carries out noise reduction process, packet
Include acoustic wave filter program, the program can automatic fitration fall the sound waves of some interference sounds.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (5)
1. a kind of for vehicle-mounted natural language semantic analysis, which comprises the following steps:
Step 1: pressing vice activation key, start vehicle-mounted speech pattern;
Step 2: driver carries out natural-sounding input by speech ciphering equipment, and onboard system is acquired driver's sound, together
Shi Jinhang noise reduction process, so that the sound of acquisition is more clear, and is conducive to identify;
Step 3: system identifies the sound of acquisition, in fact includes a speech recognition program, which adopts for detecting
Whether the sound of collection is the common sound of driver, if detect be driver common sound, system is by the sound of acquisition
It is converted into text, if not common sound, system then enters voice bank and scans for extracting;
Step 4: system is when voice bank scans for, and including a sound extraction procedure, the program is for detecting sound
The information of acquisition sound can be extracted in library, if it is possible to extract the information of acquisition sound, then system will acquire the letter of sound
Breath is converted into text, if the information of acquisition sound can not be extracted, system if carries out web search acquisition acoustic information;
Step 5: system acquires sound source by web search, obtains program including a sound, the program is for detecting
The information of acquisition sound can be obtained by web search, if it is possible to the information that acquisition sound arrives is obtained by web search,
Voice bank can be downloaded and be saved in acquisition acoustic information by system, text is then converted into, if can not pass through web search
Obtain the information that arrives of acquisition sound, system will active termination order, and driver is reminded to re-enter;
Step 6: after the sound of acquisition is converted into text by system, it will the dictionary search for carrying out system is examined including one
The program of uncommon word is surveyed, whether the text which is used to detect conversion is uncommon word, if the text of conversion is not uncommon word,
Then system can obtain the meaning of a word of text, then generate order, if the text of fruit conversion is uncommon word, system can pass through network word
Library scans for, and text information is then downloaded to dictionary, then extracts the meaning of a word of text, and generates instruction;
Step 7: system will execute instruction, and complete the instruction of driver's input.
2. according to claim 1 a kind of for vehicle-mounted natural language semantic analysis, which is characterized in that the sound
It is equipped with reservoir in sound library and dictionary, is used for stored voice source and word information, while passing through to new sound source and word
Downloading saves.
3. according to claim 1 a kind of for vehicle-mounted natural language semantic analysis, which is characterized in that the sound
Sound enhanced processing has been carried out in sound collection process, is conducive to system identification.
4. according to claim 1 a kind of for vehicle-mounted natural language semantic analysis, which is characterized in that the system
System includes to connect network program automatically, this can help system can obtain more information.
5. according to claim 1 a kind of for vehicle-mounted natural language semantic analysis, which is characterized in that the system
During system carries out noise reduction process, including acoustic wave filter program, the program can automatic fitration fall the sound waves of some interference sounds.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811318257.6A CN109284505A (en) | 2018-11-07 | 2018-11-07 | It is a kind of for vehicle-mounted natural language semantic analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811318257.6A CN109284505A (en) | 2018-11-07 | 2018-11-07 | It is a kind of for vehicle-mounted natural language semantic analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109284505A true CN109284505A (en) | 2019-01-29 |
Family
ID=65174622
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811318257.6A Pending CN109284505A (en) | 2018-11-07 | 2018-11-07 | It is a kind of for vehicle-mounted natural language semantic analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109284505A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120265527A1 (en) * | 2011-04-15 | 2012-10-18 | Hon Hai Precision Industry Co., Ltd. | Interactive voice recognition electronic device and method |
CN103428355A (en) * | 2012-05-24 | 2013-12-04 | 上海博泰悦臻电子设备制造有限公司 | Mobile terminal-based voice control apparatus and mobile terminal-based voice control method |
CN103745722A (en) * | 2014-02-10 | 2014-04-23 | 上海金牌软件开发有限公司 | Voice interaction smart home system and voice interaction method |
CN104240700A (en) * | 2014-08-26 | 2014-12-24 | 智歌科技(北京)有限公司 | Global voice interaction method and system for vehicle-mounted terminal device |
CN105931645A (en) * | 2016-04-12 | 2016-09-07 | 深圳市京华信息技术有限公司 | Control method of virtual reality device, apparatus, virtual reality device and system |
CN107454508A (en) * | 2017-08-23 | 2017-12-08 | 深圳创维-Rgb电子有限公司 | The television set and television system of microphone array |
CN107845381A (en) * | 2017-10-27 | 2018-03-27 | 安徽硕威智能科技有限公司 | A kind of method and system of robot semantic processes |
-
2018
- 2018-11-07 CN CN201811318257.6A patent/CN109284505A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120265527A1 (en) * | 2011-04-15 | 2012-10-18 | Hon Hai Precision Industry Co., Ltd. | Interactive voice recognition electronic device and method |
CN103428355A (en) * | 2012-05-24 | 2013-12-04 | 上海博泰悦臻电子设备制造有限公司 | Mobile terminal-based voice control apparatus and mobile terminal-based voice control method |
CN103745722A (en) * | 2014-02-10 | 2014-04-23 | 上海金牌软件开发有限公司 | Voice interaction smart home system and voice interaction method |
CN104240700A (en) * | 2014-08-26 | 2014-12-24 | 智歌科技(北京)有限公司 | Global voice interaction method and system for vehicle-mounted terminal device |
CN105931645A (en) * | 2016-04-12 | 2016-09-07 | 深圳市京华信息技术有限公司 | Control method of virtual reality device, apparatus, virtual reality device and system |
CN107454508A (en) * | 2017-08-23 | 2017-12-08 | 深圳创维-Rgb电子有限公司 | The television set and television system of microphone array |
CN107845381A (en) * | 2017-10-27 | 2018-03-27 | 安徽硕威智能科技有限公司 | A kind of method and system of robot semantic processes |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106985137B (en) | Multi-modal exchange method and system for intelligent robot | |
CN108227903B (en) | Virtual reality language interaction system and method | |
CN107657950B (en) | Automobile voice control method, system and device based on cloud and multi-command words | |
Avci et al. | Speech recognition using a wavelet packet adaptive network based fuzzy inference system | |
CN105654943A (en) | Voice wakeup method, apparatus and system thereof | |
CN206595039U (en) | A kind of interactive system for vehicle-mounted voice | |
CN106502649A (en) | A kind of robot service awakening method and device | |
EP1349145A3 (en) | System and method for providing information using spoken dialogue interface | |
MY126144A (en) | Character recognizing and translating system and voice recognizing and translating system | |
CN109243462A (en) | Voice awakening method and device | |
CN109545207A (en) | Voice awakening method and device | |
CN103198829A (en) | Method, device and equipment of reducing interior noise and improving voice recognition rate | |
CN110428805A (en) | Non-generic words and mandarin inter-translation method, device and equipment | |
CN112542156A (en) | Civil aviation maintenance worker card system based on voiceprint recognition and voice instruction control | |
CN111179903A (en) | Voice recognition method and device, storage medium and electric appliance | |
Ying et al. | Characteristics of human auditory model based on compensation of glottal features in speech emotion recognition | |
CN109284505A (en) | It is a kind of for vehicle-mounted natural language semantic analysis | |
CN109544745A (en) | A kind of intelligent door lock control method, apparatus and system | |
CN110232918B (en) | Unmanned aerial vehicle ground control station voice control system and control method | |
CN116612754A (en) | Voice instruction recognition method and device applied to vehicle | |
CN111098709B (en) | Unlocking and starting method and system for safe driving system | |
CN115482583A (en) | Vehicle-mounted sign language translation method | |
CN113160821A (en) | Control method and device based on voice recognition | |
CN113593556A (en) | Human-computer interaction method and device for vehicle-mounted voice operating system | |
CN206441536U (en) | A kind of active voice assistant based on recognition of face |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190129 |