CN206595039U - A kind of interactive system for vehicle-mounted voice - Google Patents
A kind of interactive system for vehicle-mounted voice Download PDFInfo
- Publication number
- CN206595039U CN206595039U CN201720101617.1U CN201720101617U CN206595039U CN 206595039 U CN206595039 U CN 206595039U CN 201720101617 U CN201720101617 U CN 201720101617U CN 206595039 U CN206595039 U CN 206595039U
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- vehicle
- phonetic order
- vocal print
- 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.)
- Expired - Fee Related
Links
Landscapes
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
Abstract
The utility model belongs to safe driving technical field there is provided a kind of interactive system for vehicle-mounted voice, including：Sound pick up equipment, speech processing module, voice characteristics information module, fuzzy voice module, on-vehicle host module, suggestion device；Sound pick up equipment is connected with speech processing module, and voice characteristics information module is connected with speech processing module, on-vehicle host module and fuzzy voice module respectively, and on-vehicle host module is also connected with executive agent.When determining that the phonetic order received includes predetermined keyword due to speech processing module, corresponding executive agent is not controlled directly to perform corresponding actions, but the vocal print feature of phonetic order is extracted by voice characteristics information module, judge whether it is consistent with pre-stored vocal print feature, the e.g. vocal print feature of driver, if, then perform the phonetic order, if not performing the phonetic order then, irrelevant people's acoustic jamming can not be removed by thus efficiently solving prior art, cause the problem of speech recognition malfunctions.
Description
Technical field
The utility model is related to safe driving technical field, more particularly to a kind of interactive system for vehicle-mounted voice.
Background technology
As automobile steps into intellectuality, vehicle-mounted voice interaction technique is also promoted, it not only simply save by
The operation of key, and by voice, you can be interactive with car, show the intellectuality of car, hommization, current intelligent sound interaction
Technology is used widely in each large-scale vechicle.
Current speech recognition technology is the basic theories based on statistical-simulation spectrometry, and a complete speech recognition system can
It is roughly divided into three parts：(1) speech feature extraction：Purpose is that the phonetic feature sequence changed over time is extracted from speech waveform；
(2) acoustic model and pattern match：Identifying system underlying model, is that voice module is set up in each pronunciation；(3) semantic understanding：Calculate
Machine carries out grammer, semantic analysis to recognition result.
But influenceed by ambient noise, it is frequently encountered when being spoken to on-vehicle host, it can remind you " not hear
Chu, pardon ", when especially two or more people speak together, on-vehicle host can not remove irrelevant people's acoustic jamming,
The probability of error in judgement is bigger, has a strong impact on customer experience effect.
Utility model content
The purpose of this utility model is to provide a kind of interactive system for vehicle-mounted voice, and not phase can not be removed to solve prior art
Dry people's acoustic jamming, causes the problem of speech recognition malfunctions.
To achieve these goals, the utility model provides following technical scheme：
A kind of interactive system for vehicle-mounted voice, including：
Sound pick up equipment, speech processing module, voice characteristics information module, fuzzy voice module, on-vehicle host module, prompting
Device；
Sound pick up equipment is connected with speech processing module, voice characteristics information module respectively with speech processing module, vehicle-mounted master
Machine module is connected with fuzzy voice module, and on-vehicle host module is also connected with executive agent；
Sound pick up equipment is used to pick up phonetic order, and sends speech processing module to；
Whether speech processing module is used to judge the phonetic order received comprising predetermined keyword, if it is, by voice
Instruction is sent to voice characteristics information module；
Voice characteristics information module is used for the vocal print feature for extracting phonetic order；
Fuzzy voice module is not used for the vocal print feature of the vocal print feature and storage extracted when voice characteristics information module not
Timing, sends to suggestion device and retells hint instructions；
The vocal print feature that on-vehicle host module is used to extract when voice characteristics information module is matched with the vocal print feature stored
When, control voice instructs corresponding executive agent to perform corresponding actions.
Preferably, the interactive system for vehicle-mounted voice also includes：
Memory module, is connected with voice characteristics information module, refers to for storing first voice comprising predetermined keyword
The vocal print feature of order.
Preferably, the memory module is specifically for the voice that includes predetermined keyword in setting time memory storage first
The vocal print feature of instruction.
Preferably, during the setting time is electricity on this vehicle；Or
The setting time is before receiving closing voice interactive function instruction；Or
The setting time be this vehicle on electricity when from, until receive closing voice interactive function instruction when stop or
Stop when electric under vehicle.
Preferably, the speech processing module includes：
Memory cell, for storing predetermined keyword, the predetermined keyword includes conventional phonetic, word and sentence；
Whether comparing unit, the phonetic order for comparing reception includes predetermined keyword, if it is, by phonetic order
It is sent to voice characteristics information module.
Preferably, the vocal print feature includes：Tonality feature, audio frequency characteristics and tamber characteristic；The voice characteristics information
Module includes：
Tonality feature extraction unit, the tonality feature for extracting phonetic order；
Audio feature extraction unit, the audio frequency characteristics for extracting phonetic order；
Tamber characteristic extraction unit, the tamber characteristic for extracting phonetic order.
Preferably, the on-vehicle host module includes：
Standard instruction database memory cell, for storing standard instruction database；
Processor, for when the vocal print feature that voice characteristics information module is extracted with store vocal print feature match when, from
Stereotyped command corresponding with phonetic order is chosen in standard instruction database, stereotyped command then is sent into corresponding executive agent performs
Corresponding actions.
Preferably, the sound pick up equipment include it is following any one or more：
Microphone, microphone array.
Preferably, the suggestion device include it is following any one or more：
Voice announcer, display.
The interactive system for vehicle-mounted voice that the utility model is provided, including：Sound pick up equipment, speech processing module, phonetic feature
Information module, fuzzy voice module, on-vehicle host module, suggestion device.Because speech processing module determines that the voice received refers to
It is not directly to control corresponding executive agent to perform corresponding actions, but further pass through voice when order includes predetermined keyword
Characteristic information module extracts the vocal print feature of phonetic order, judges whether the sound instruction is consistent with pre-stored vocal print feature,
The e.g. vocal print feature of driver, if it is, perform the phonetic order, if not performing the phonetic order then, this
Sample just effectively prevent causes the situation of maloperation to occur using the voice of copilot or other passengers as phonetic order by mistake, effectively
Irrelevant people's acoustic jamming can not be removed by solving prior art, cause the problem of speech recognition malfunctions.
Further, the interactive system for vehicle-mounted voice that the utility model is provided, the interactive system for vehicle-mounted voice also includes：
Memory module, is connected with voice characteristics information module, the vocal print for storing first phonetic order comprising predetermined keyword
Feature.So it is easy to systematic collection and stores vocal print feature, realization is automatically controlled.
Further, the interactive system for vehicle-mounted voice that the utility model is provided, the memory module is specifically in setting
Time memory stores up the vocal print feature of first phonetic order comprising predetermined keyword.So it is easy to upgrade in time the sound of driver
Line feature, the convenient degree of interactive voice when occurring situations such as in order to change driver.Preferably, the setting time is this
On vehicle during electricity；Or the setting time is before receiving closing voice interactive function instruction；Or during the setting
Between on this vehicle during electricity from, until stop when receiving closing voice interactive function instruction or vehicle under electricity when stop.This week
Phase setting can optimize using effect.
Further, the interactive system for vehicle-mounted voice that the utility model is provided, the speech processing module includes：Storage is single
Member, for storing predetermined keyword, the predetermined keyword includes conventional phonetic, word and sentence；Comparing unit, for than
Whether the phonetic order relatively received includes predetermined keyword, if it is, phonetic order is sent into voice characteristics information module.
Predetermined keyword, which includes conventional phonetic, word and sentence, can be easy to implement more rich man-machine interaction content.
Further, the interactive system for vehicle-mounted voice that the utility model is provided, the on-vehicle host module includes：Standard refers to
Stock's storage unit is made, for storing standard instruction database；Processor, for the vocal print feature extracted when voice characteristics information module with
During the vocal print feature matching of storage, stereotyped command corresponding with phonetic order is chosen from standard instruction database, then refers to standard
Order is sent to corresponding executive agent and performs corresponding actions.The degree of accuracy of phonetic order execution can be so provided.
Brief description of the drawings
Fig. 1 is the first structural representation according to interactive system for vehicle-mounted voice provided by the utility model；
Fig. 2 is second of structural representation according to interactive system for vehicle-mounted voice provided by the utility model；
Fig. 3 is the third structural representation according to interactive system for vehicle-mounted voice provided by the utility model.
Embodiment
In order that the purpose of this utility model, technical scheme and advantage are more clearly understood, below in conjunction with accompanying drawing and implementation
Example, the utility model is further elaborated.It should be appreciated that specific embodiment described herein is only to explain this
Utility model, is not used to limit the utility model.
As shown in figure 1, being the first structural representation according to interactive system for vehicle-mounted voice provided by the utility model.
In the present embodiment, the system can include：Sound pick up equipment, speech processing module, voice characteristics information module, mould
Paste voice module, on-vehicle host module, suggestion device.Sound pick up equipment is connected with speech processing module, voice characteristics information module
Be connected respectively with speech processing module, on-vehicle host module and fuzzy voice module, on-vehicle host module also with executive agent phase
Even.
Wherein, sound pick up equipment is used to pick up phonetic order, and sends speech processing module to；Speech processing module is used to sentence
Whether the phonetic order that disconnecting is received includes predetermined keyword, if it is, phonetic order is sent into voice characteristics information module；
Voice characteristics information module is used for the vocal print feature for extracting phonetic order；Fuzzy voice module is used to work as voice characteristics information module
When the vocal print feature of extraction and the vocal print feature of storage are mismatched, sent to suggestion device and retell hint instructions；On-vehicle host mould
Block is used for when the vocal print feature of voice characteristics information module extraction is matched with the vocal print feature stored, and control voice instruction is corresponding
Executive agent performs corresponding actions.
In a specific embodiment, the sound pick up equipment include it is following any one or more：Microphone, microphone array
Row；The suggestion device include it is following any one or more：Voice announcer, display.Vocal print feature can include following
Any one or more：Tonality feature, audio frequency characteristics and tamber characteristic.For example, when microphone receives signal language, " hello, language
Sound assistant ", speech processing module is sent to by voice signal, and the keyword of voice signal and storage is done ratio by speech processing module
It is right, judge whether include keyword in voice signal, if so, voice signal is sent in voice characteristics information module, extraction
State the tone of voice signal, audio, tone color, and by tone, one threshold value of audio settings；It is again that pitch value, audio value, tone color is special
Reference number memory a period of time carries out voiceprint in order to follow-up；If it is not, above-mentioned voice signal is sent into fuzzy voice mould
Block, above-mentioned fuzzy voice module sends " not hearing, pardon " voice signal to loudspeaker.
The interactive system for vehicle-mounted voice that the utility model is provided, because speech processing module determines the phonetic order bag of reception
When containing predetermined keyword, be not that the related executive agent of direct control performs corresponding actions, but further pass through phonetic feature
Information module extracts the vocal print feature of phonetic order, judges whether the sound instruction is consistent with pre-stored vocal print feature, for example
It is the vocal print feature of driver, if it is, performing the phonetic order, if not the phonetic order is not performed then, thus
Effectively prevent causes the situation of maloperation to occur using the voice of copilot or other passengers as phonetic order by mistake, effectively solves
Prior art is influenceed to cause the problem of speech recognition malfunctions by ambient noise.
As shown in Fig. 2 being second of structural representation according to interactive system for vehicle-mounted voice provided by the utility model.
In the present embodiment, the interactive system for vehicle-mounted voice also includes：Memory module, with voice characteristics information module phase
Even, the vocal print feature for first phonetic order comprising predetermined keyword of storage.
Preferably, the memory module is specifically for the voice that includes predetermined keyword in setting time memory storage first
The vocal print feature of instruction.Wherein, setting time can rule of thumb set or meet a period of time of particular decision condition,
This is not limited.
In a specific embodiment, during the setting time is electricity on this vehicle；Or the setting time is
Receive before closing voice interactive function instruction；Or from the setting time is when being electricity on this vehicle, until receive
Close voice interactive function instruction when stop or vehicle under electricity when stop.
As shown in figure 3, being the third structural representation according to interactive system for vehicle-mounted voice provided by the utility model.
In the present embodiment, the speech processing module includes：Memory cell, it is described pre- for storing predetermined keyword
If keyword includes conventional phonetic, word and sentence；Comparing unit, for whether comparing the phonetic order of reception comprising default
Keyword, if it is, phonetic order is sent into voice characteristics information module.
The vocal print feature can include：Tonality feature, audio frequency characteristics and tamber characteristic.Correspondingly, the phonetic feature
Information module can include：Tonality feature extraction unit, the tonality feature for extracting phonetic order；Audio feature extraction list
Member, the audio frequency characteristics for extracting phonetic order；Tamber characteristic extraction unit, the tamber characteristic for extracting phonetic order.
The on-vehicle host module includes：Standard instruction database memory cell, for storing standard instruction database；Processor, is used
In the vocal print feature extracted when voice characteristics information module with store vocal print feature match when, from standard instruction database choose and
The corresponding stereotyped command of phonetic order, is then sent to corresponding executive agent by stereotyped command and performs corresponding actions.
In a specific embodiment, voice signal is sent language by microphone in the sentence after receiving signal language
Sound processing module, speech processing module compares voice signal and received pronunciation, judges the main words and phrases of voice signal and standard
Whether voice words and phrases are consistent, if unanimously, voice signal is sent into comparison module, the pitch value of relatively more above-mentioned voice signal, sound
Whether frequency value is in above-mentioned memory module voice signal threshold range, and whether tone color is identical, if all meeting, on-vehicle host mould
Block chooses instruction from standard instruction database, is then sent to corresponding executive agent, performs corresponding actions, Vague language is sent to if not
Sound module, then sent " not hearing, pardon " by loudspeaker.
Although the utility model combination above example is described, the utility model is not limited to above-mentioned reality
Example is applied, and is only limited by claim, those of ordinary skill in the art easily can modify and change to it, but simultaneously
Without departing from essential idea of the present utility model and scope.
Claims (9)
1. a kind of interactive system for vehicle-mounted voice, it is characterised in that including：
Sound pick up equipment, speech processing module, voice characteristics information module, fuzzy voice module, on-vehicle host module, prompting dress
Put；
Sound pick up equipment is connected with speech processing module, voice characteristics information module respectively with speech processing module, on-vehicle host mould
Block is connected with fuzzy voice module, and on-vehicle host module is also connected with executive agent；
Sound pick up equipment is used to pick up phonetic order, and sends speech processing module to；
Whether speech processing module is used to judge the phonetic order received comprising predetermined keyword, if it is, by phonetic order
It is sent to voice characteristics information module；
Voice characteristics information module is used for the vocal print feature for extracting phonetic order；
When the vocal print feature that fuzzy voice module is used for the vocal print feature and storage extracted when voice characteristics information module is mismatched,
Sent to suggestion device and retell hint instructions；
On-vehicle host module is used for when the vocal print feature of voice characteristics information module extraction is matched with the vocal print feature stored, control
The corresponding executive agent of phonetic order processed performs corresponding actions.
2. interactive system for vehicle-mounted voice according to claim 1, it is characterised in that the interactive system for vehicle-mounted voice is also wrapped
Include：
Memory module, is connected with voice characteristics information module, for first phonetic order comprising predetermined keyword of storage
Vocal print feature.
3. interactive system for vehicle-mounted voice according to claim 2, it is characterised in that the memory module is specifically for setting
The vocal print feature of first phonetic order comprising predetermined keyword of memory storage of fixing time.
4. interactive system for vehicle-mounted voice according to claim 3, it is characterised in that
During the setting time is electricity on this vehicle；Or
The setting time is before receiving closing voice interactive function instruction；Or
From when the setting time is electricity on this vehicle, until stopping or vehicle when receiving closing voice interactive function instruction
Stop when lower electric.
5. interactive system for vehicle-mounted voice according to claim 1, it is characterised in that the speech processing module includes：
Memory cell, for storing predetermined keyword, the predetermined keyword includes conventional phonetic, word and sentence；
Whether comparing unit, the phonetic order for comparing reception includes predetermined keyword, if it is, phonetic order is sent
Give voice characteristics information module.
6. interactive system for vehicle-mounted voice according to claim 1, it is characterised in that the vocal print feature includes：Tone is special
Levy, audio frequency characteristics and tamber characteristic；The voice characteristics information module includes：
Tonality feature extraction unit, the tonality feature for extracting phonetic order；
Audio feature extraction unit, the audio frequency characteristics for extracting phonetic order；
Tamber characteristic extraction unit, the tamber characteristic for extracting phonetic order.
7. interactive system for vehicle-mounted voice according to claim 1, it is characterised in that the on-vehicle host module includes：
Standard instruction database memory cell, for storing standard instruction database；
Processor, for when the vocal print feature that voice characteristics information module is extracted is matched with the vocal print feature stored, from standard
Stereotyped command corresponding with phonetic order is chosen in instruction database, stereotyped command then is sent into corresponding executive agent performs accordingly
Action.
8. interactive system for vehicle-mounted voice according to claim 1, it is characterised in that the sound pick up equipment includes following any
It is one or more：
Microphone, microphone array.
9. interactive system for vehicle-mounted voice according to claim 1, it is characterised in that the suggestion device includes following any
It is one or more：
Voice announcer, display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201720101617.1U CN206595039U (en) | 2017-01-25 | 2017-01-25 | A kind of interactive system for vehicle-mounted voice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201720101617.1U CN206595039U (en) | 2017-01-25 | 2017-01-25 | A kind of interactive system for vehicle-mounted voice |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206595039U true CN206595039U (en) | 2017-10-27 |
Family
ID=60127792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201720101617.1U Expired - Fee Related CN206595039U (en) | 2017-01-25 | 2017-01-25 | A kind of interactive system for vehicle-mounted voice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206595039U (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107682786A (en) * | 2017-10-31 | 2018-02-09 | 广东小天才科技有限公司 | A kind of microphone apparatus anti-interference method and microphone apparatus |
| CN108520747A (en) * | 2018-03-29 | 2018-09-11 | 浙江吉利汽车研究院有限公司 | A kind of on-vehicle control apparatus with speech identifying function |
| CN108962248A (en) * | 2018-08-14 | 2018-12-07 | 福建龙马环卫装备股份有限公司 | A kind of intelligence environmental sanitation equipment speech recognition control system and method |
| CN109035896A (en) * | 2018-08-13 | 2018-12-18 | 广东小天才科技有限公司 | A kind of Oral Training method and facility for study |
| CN109246473A (en) * | 2018-09-13 | 2019-01-18 | 苏州思必驰信息科技有限公司 | The voice interactive method and terminal system of individualized video barrage based on Application on Voiceprint Recognition |
| CN110103989A (en) * | 2019-05-17 | 2019-08-09 | 爱驰汽车有限公司 | Automatic Pilot active interactive onboard system, method, equipment and storage medium |
| CN111145743A (en) * | 2019-12-18 | 2020-05-12 | 北京海兰信数据科技股份有限公司 | Ship autopilot control device and method based on voice interaction |
| CN111923924A (en) * | 2020-07-09 | 2020-11-13 | 奇瑞新能源汽车股份有限公司 | Automobile oil filler cap voice opening control system and control method thereof |
| CN114290986A (en) * | 2021-11-25 | 2022-04-08 | 合众新能源汽车有限公司 | Night driving assisting method and device |
-
2017
- 2017-01-25 CN CN201720101617.1U patent/CN206595039U/en not_active Expired - Fee Related
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107682786A (en) * | 2017-10-31 | 2018-02-09 | 广东小天才科技有限公司 | A kind of microphone apparatus anti-interference method and microphone apparatus |
| CN108520747A (en) * | 2018-03-29 | 2018-09-11 | 浙江吉利汽车研究院有限公司 | A kind of on-vehicle control apparatus with speech identifying function |
| CN109035896A (en) * | 2018-08-13 | 2018-12-18 | 广东小天才科技有限公司 | A kind of Oral Training method and facility for study |
| CN108962248A (en) * | 2018-08-14 | 2018-12-07 | 福建龙马环卫装备股份有限公司 | A kind of intelligence environmental sanitation equipment speech recognition control system and method |
| CN109246473A (en) * | 2018-09-13 | 2019-01-18 | 苏州思必驰信息科技有限公司 | The voice interactive method and terminal system of individualized video barrage based on Application on Voiceprint Recognition |
| CN110103989A (en) * | 2019-05-17 | 2019-08-09 | 爱驰汽车有限公司 | Automatic Pilot active interactive onboard system, method, equipment and storage medium |
| CN111145743A (en) * | 2019-12-18 | 2020-05-12 | 北京海兰信数据科技股份有限公司 | Ship autopilot control device and method based on voice interaction |
| CN111923924A (en) * | 2020-07-09 | 2020-11-13 | 奇瑞新能源汽车股份有限公司 | Automobile oil filler cap voice opening control system and control method thereof |
| CN114290986A (en) * | 2021-11-25 | 2022-04-08 | 合众新能源汽车有限公司 | Night driving assisting method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN206595039U (en) | A kind of interactive system for vehicle-mounted voice | |
| US10380992B2 (en) | Natural language generation based on user speech style | |
| US8423362B2 (en) | In-vehicle circumstantial speech recognition | |
| US8639508B2 (en) | User-specific confidence thresholds for speech recognition | |
| US6839670B1 (en) | Process for automatic control of one or more devices by voice commands or by real-time voice dialog and apparatus for carrying out this process | |
| CN102999161B (en) | A kind of implementation method of voice wake-up module and application | |
| US8296145B2 (en) | Voice dialing using a rejection reference | |
| US7974843B2 (en) | Operating method for an automated language recognizer intended for the speaker-independent language recognition of words in different languages and automated language recognizer | |
| US9881609B2 (en) | Gesture-based cues for an automatic speech recognition system | |
| US8756062B2 (en) | Male acoustic model adaptation based on language-independent female speech data | |
| US8762151B2 (en) | Speech recognition for premature enunciation | |
| US9484027B2 (en) | Using pitch during speech recognition post-processing to improve recognition accuracy | |
| US20070265849A1 (en) | Distinguishing out-of-vocabulary speech from in-vocabulary speech | |
| US9911408B2 (en) | Dynamic speech system tuning | |
| CN102693725A (en) | Speech recognition dependent on text message content | |
| US9997155B2 (en) | Adapting a speech system to user pronunciation | |
| US9473094B2 (en) | Automatically controlling the loudness of voice prompts | |
| US20130211832A1 (en) | Speech signal processing responsive to low noise levels | |
| CN105047196B (en) | Speech artefacts compensation system and method in speech recognition system | |
| KR20130063091A (en) | Speech recognition apparatus for vehicle | |
| CN111833870A (en) | Awakening method and device of vehicle-mounted voice system, vehicle and medium | |
| US20120197643A1 (en) | Mapping obstruent speech energy to lower frequencies | |
| CN113223527A (en) | Voice control method for intelligent instrument of electric vehicle and electric vehicle | |
| US20090138264A1 (en) | Speech to dtmf generation | |
| CN102542705A (en) | Voice reminding method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171027 Termination date: 20200125 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |