CN110528913A - A kind of Novel bus platform - Google Patents
A kind of Novel bus platform Download PDFInfo
- Publication number
- CN110528913A CN110528913A CN201910798792.4A CN201910798792A CN110528913A CN 110528913 A CN110528913 A CN 110528913A CN 201910798792 A CN201910798792 A CN 201910798792A CN 110528913 A CN110528913 A CN 110528913A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- frame
- spectrum
- bus platform
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001228 spectrum Methods 0.000 claims description 67
- 238000012545 processing Methods 0.000 claims description 46
- 230000006870 function Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 238000013459 approach Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 230000005236 sound signal Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003014 reinforcing effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- ODKSFYDXXFIFQN-UHFFFAOYSA-M argininate Chemical compound [O-]C(=O)C(N)CCCNC(N)=N ODKSFYDXXFIFQN-UHFFFAOYSA-M 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000000039 congener Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E04—BUILDING
- E04H—BUILDINGS OR LIKE STRUCTURES FOR PARTICULAR PURPOSES; SWIMMING OR SPLASH BATHS OR POOLS; MASTS; FENCING; TENTS OR CANOPIES, IN GENERAL
- E04H1/00—Buildings or groups of buildings for dwelling or office purposes; General layout, e.g. modular co-ordination or staggered storeys
- E04H1/12—Small buildings or other erections for limited occupation, erected in the open air or arranged in buildings, e.g. kiosks, waiting shelters for bus stops or for filling stations, roofs for railway platforms, watchmen's huts or dressing cubicles
- E04H1/1205—Small buildings erected in the open air
- E04H1/1211—Waiting shelters for bus stops
-
- 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
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- G10L15/04—Segmentation; Word boundary detection
- G10L15/05—Word boundary detection
-
- 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
- G10L15/28—Constructional details of speech recognition 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
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- 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
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L21/0232—Processing in the frequency domain
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
-
- 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)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Architecture (AREA)
- Quality & Reliability (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Lock And Its Accessories (AREA)
Abstract
The present invention provides a kind of Novel bus platform, comprising: platform frame, platform frame include column, and column is transversely distributed on bus platform, are provided with fixed frame at the top of column, rain cover baffle is equipped on fixed frame；Self-service borrowing and returning device is provided between column, self-service borrowing and returning device includes cabinet body, and cabinet body is equipped with control panel and multiple matter storage lattices with smart lock；Seat is provided in front of self-service borrowing and returning device；The side of bus platform is provided with dustbin, and the other side is provided with smart terminal, and smart terminal is inquired for bus platform information.The present invention can satisfy various needs of the passenger when bus platform waits vehicles, improves the convenience-for-people degree of hommization of bus platform, improves passenger and wait the user experience during vehicles.
Description
Technical field
The present invention relates to city common equipment technical field, especially a kind of Novel bus platform.
Background technique
Bus-stop is the communal facility of building of the citizens of waiting exclusively for city, it provides people and waits place, is
Citizen, which wait, to be provided convenience, and as the key traffic route in city, is distributed in the streets and lanes in city, is carry city master
The traffic wanted has passenger high concentration, mobility big, the feature of residence time length.
In the prior art, the function of bus platform is more single, bus platform be only used for instruction effect, wait passenger with
The interaction of equipment is less in bus platform, and user experience is low.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of Novel bus platform.
The purpose of the present invention is realized using following technical scheme:
It is proposed a kind of Novel bus platform, comprising: platform frame, platform frame include column, and column is transversely distributed in public transport
On platform, it is provided with fixed frame at the top of column, rain cover baffle is installed on fixed frame；Self-service borrow is provided between column also to fill
It sets, self-service borrowing and returning device includes cabinet body, and cabinet body is equipped with control panel and multiple matter storage lattices with smart lock；It is self-service to borrow also
Seat is provided in front of device；The side of bus platform is provided with dustbin, and the other side is provided with smart terminal, intelligent terminal
Machine is inquired for bus platform information.
In one embodiment, rain cover baffle tilts backwards setting.
In one embodiment, the matter storage lattice of self-service borrowing and returning device is provided with cabinet door, and smart lock is arranged in cabinet door；Control
Panel processed is connect with smart lock, is used to open the smart lock of specified matter storage lattice cabinet door.
In one embodiment, barcode scanning device is additionally provided on control panel, for after scanning recognition bar code/two dimensional code
Open the smart lock of specified matter storage lattice cabinet door.
In one embodiment, smart terminal includes that the display screen being arranged on smart terminal body and voice are adopted
Collect equipment, and the central processing unit and communication module that are arranged in smart terminal；
Voice capture device sends central processing unit for user voice signal for acquiring user voice signal；
Central processing unit carries out identifying processing to user voice signal, obtains corresponding inquiry instruction；
Communication module is connect with cloud server, for sending Cloud Server for inquiry instruction, and is received by cloud service
The query result that device returns；
Display screen is for showing query result.
In one embodiment, smart terminal includes: for the bus platform information of user query
The peripheral information of bus platform is inquired, including Bus information, catering information, shopping information, sight spot information, government's machine
Close information；
Road congestion information in the route information of bus platform approach bus, the route, bus arrival crowding
Predictive information, bus arrival used time predictive information.
In one embodiment, central processing unit includes speech processing module, and speech processing module is to received user
Voice signal carries out identifying processing, obtains corresponding inquiry instruction, further comprises:
Pretreatment unit: enhancing processing is carried out to the user voice signal of acquisition, exports enhanced user voice signal；
End-point detection unit: endpoint detection processing is carried out to enhanced user voice signal, is detected in voice signal
Voiced portions；
Feature extraction unit: feature extraction processing is carried out to voiced portions, obtains the characteristic parameter of the voiced portions；
Recognition unit: the characteristic parameter that will acquire and the characteristic parameter prestored in inquiry instruction database are compared, and know
Not corresponding inquiry instruction；
Inquiry instruction database: storage inquiry instruction and its corresponding characteristic parameter.
The invention has the benefit that by the way that self-service borrowing and returning device, seat, dustbin, intelligence are arranged on bus platform
The convenience-for-people facility such as terminating machine can satisfy various needs of the passenger when bus platform waits vehicles, improve the human nature of bus platform
Change convenience-for-people degree, improves passenger and wait the user experience during vehicles.
Be provided with self-service borrowing and returning device, feature that can be widely distributed according to bus platform, realize bus platform it
Between resource it is shared, help to further increase passenger and waiting the user experience of vehicles or public transport during the journey.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structural diagram of the present invention；
Fig. 2 is the frame construction drawing of smart terminal of the present invention.
Appended drawing reference:
1- platform frame, 2- column, 3- fixed frame, 4- rain cover baffle, the self-service borrowing and returning device of 5-, 6- seat, 7- dustbin, 8-
Smart terminal, 51- cabinet body, 52- control panel, 53- matter storage lattice, 81- voice capture device, 82- central processing unit, 83- are logical
Letter module, 84- display screen, 820- speech processing module, 821- pretreatment unit, 822- end-point detection unit, 823- feature mention
Take unit, 824- recognition unit, 825- inquiry instruction database.
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of Novel bus platform is shown, comprising: platform frame 1, platform frame 1 include column 2,2 edge of column
Cross direction profiles are equipped with rain cover baffle 4 on bus platform, being provided with fixed frame 3 at the top of column 2 on fixed frame 3；Column 2 it
Between be provided with self-service borrowing and returning device 5, self-service borrowing and returning device 5 includes cabinet body 51, and cabinet body 51 is equipped with control panel 52 and multiple
Matter storage lattice 53 with smart lock；Seat 6 is provided in front of self-service borrowing and returning device 5；The side of bus platform is provided with dustbin
7, the other side is provided with smart terminal 8, and smart terminal 8 is inquired for bus platform information.
Above embodiment of the present invention, by the way that self-service borrowing and returning device, seat, dustbin, intelligence are arranged on bus platform
The convenience-for-people facility such as terminating machine can satisfy various needs of the passenger when bus platform waits vehicles, improve the human nature of bus platform
Change convenience-for-people degree, improves passenger and wait the user experience during vehicles.
Be provided with self-service borrowing and returning device, feature that can be widely distributed according to bus platform, realize bus platform it
Between resource it is shared, help to further increase passenger and waiting the user experience of vehicles or public transport during the journey.
In one embodiment, rain cover baffle 4 tilts backwards setting.
As a preferred embodiment, the sweptback angle of rain cover baffle be 15-20 degree, i.e., with the folder of horizontal plane
Angle is 15-20 degree.
In one embodiment, the matter storage lattice 53 of self-service borrowing and returning device 5 is provided with cabinet door, and smart lock is arranged in cabinet door
On；Control panel 52 is connect with smart lock, is used to open the smart lock of specified 53 cabinet door of matter storage lattice.
As a preferred embodiment, the smart lock in matter storage lattice cabinet door uses electric control lock, can further adopt
Use electromagnetic lock.After electric control lock is received from the unlocking instruction that control panel issues, which unlocks, so that passenger can
To open matter storage lattice cabinet door；After matter storage lattice cabinet door is closed, electric control lock locks automatically.
As a preferred embodiment, self-service borrowing and returning device 5 is greater than the width of cabinet door at a distance from seat 6, so that
The normal opening of self-service borrowing and returning device matter storage lattice cabinet door will not be stopped by obtaining seat.
In one embodiment, it is additionally provided with barcode scanning device on control panel 52, is used for scanning recognition bar code/two dimensional code
The smart lock of specified 53 cabinet door of matter storage lattice is opened afterwards.
In a kind of scene, passenger establishes connection by the control panel of dedicated application program and self-service borrowing and returning device,
Control panel obtains user information.
Self-service borrowing and returning device of the invention is equipped with multiple matter storage lattices, and wherein matter storage lattice is according to the article for presetting storage
Type (such as charger baby, books, newspapers and periodicals, insulated bag, portable electric fan) can be divided into different types of matter storage lattice, wherein not
Congener matter storage lattice posts the mark for classifying to article for storing different types of article on the article of storage
Label；Passenger chooses required type of goods by control panel, and control panel controls corresponding matter storage lattice and opens cabinet door, Cheng Kequ
Walk the article that need to be borrowed.
When passenger needs to return in the self-service borrowing and returning device of same bus platform or the self-service borrowing and returning device of different bus platforms
When the article also borrowed, scanned using the scanning means on control panel wait give back the label on article, control panel is known automatically
The not type of the article, one of them the idle matter storage lattice for controlling the type of goods opens cabinet door, so that passenger can be by article
It is returned in matter storage lattice.
For electrical equipments such as charger baby, portable electric fans, corresponding charging is additionally provided in the matter storage lattice of the type article
Device can charge when being placed in matter storage lattice for article.
Above embodiment of the present invention is provided to passenger and is being waited by the way that self-service borrowing and returning device is arranged in bus platform
Or required article when by bus, while different bus platform linkages, passenger can lend article in bus platform by bus,
And the bus platform in destination gives back article, realizes that passenger borrows the strange land of object to give back, and achievees the effect that article is shared, improves
Passenger is waiting or user experience on the way by bus.
In one embodiment, referring to fig. 2, smart terminal 8 includes the display being arranged on 8 body of smart terminal
Screen 84 and voice capture device 81, and the central processing unit 82 and communication module 83 that are arranged in smart terminal 8；
Voice capture device 81 sends central processing unit 82 for user voice signal for acquiring user voice signal；
Central processing unit 82 carries out identifying processing to user voice signal, obtains corresponding inquiry instruction；
Communication module 83 is connect with cloud server, for sending Cloud Server for inquiry instruction, and is received and is taken by cloud
The query result that business device returns；
Display screen 84 is for showing query result.
Big for flow of the people in bus platform, the utilization rate of smart terminal is high, and uses the extensive situation of crowd, tradition
The mode of operation of touch screen that uses of smart terminal, be easy to exist that 1) screen utilization rate is high, and operation is lack of standardization to lead to touch screen mould
Situations such as paste, poor contact；2) operation difficulty is not easy to greatly situations such as child's old man operation.In view of the above-mentioned problems, above-mentioned implementation
In mode, smart terminal obtains user voice signal by voice capture device, and obtains corresponding inquiry instruction to intelligence
The problems such as terminating machine is controled and operated, and can be avoided because conventional terminal uses touch plate consumption fast, easy to damage.
Meanwhile smart terminal can carry out information exchange with Cloud Server, it is real from Cloud Server according to inquiry instruction
When obtain needed for information, can guarantee the real-time of query result, provide effective Informational support for passenger, raising user's body
It tests.
In one embodiment, smart terminal 8 includes: for the bus platform information of user query
The peripheral information of bus platform is inquired, including Bus information, catering information, shopping information, sight spot information, government's machine
Close information；
Road congestion information in the route information of bus platform approach bus, the route, bus arrival crowding
Predictive information, bus arrival used time predictive information.
Above embodiment of the present invention, wait passenger can by smart terminal inquire bus platform periphery information,
Bus information to be stopped and corresponding line information can understand in advance required information for the passenger that waits, and plan in advance
Plan of travel further increases user experience.
In one embodiment, central processing unit 82 includes speech processing module 820, and speech processing module 820 is docked
The user voice signal of receipts carries out identifying processing, obtains corresponding inquiry instruction, further comprises:
Pretreatment unit 821: carrying out enhancing processing to the user voice signal of acquisition, exports enhanced user speech letter
Number；
End-point detection unit 822: endpoint detection processing is carried out to enhanced user voice signal, is detected in voice signal
Voiced portions；
Feature extraction unit 823: feature extraction processing is carried out to voiced portions, obtains the characteristic parameter of the voiced portions；
Recognition unit 824: the characteristic parameter that will acquire and the characteristic parameter prestored in inquiry instruction database 825 are compared
It is right, identify corresponding inquiry instruction；
Inquiry instruction database 825: storage inquiry instruction and its corresponding characteristic parameter.
Above embodiment of the present invention is arranged in central processing unit and specially handles the user voice signal of receiving
Speech processing module, enhancing processing carried out to the user voice signal of acquisition first, user voice signal is eliminated and was obtaining
Then the noise jamming being subject in journey carries out end-point detection to user voice signal, obtains the phonological component of user voice signal,
And feature extraction processing is carried out to phonological component, corresponding characteristic parameter is obtained, the characteristic parameter that will acquire and the feature prestored
Parameter is compared, and the corresponding inquiry instruction of identification this feature parameter simultaneously exports, and realizes and converts inquiry/operation for user speech
The process of instruction, accuracy are high.
In one embodiment, pretreatment unit 821 carry out enhancing processing to the user voice signal of acquisition, output
Enhanced user voice signal further comprises:
1) framing windowing process is carried out to the user voice signal of acquisition, wherein adjacent speech frame has lap；
2) Short Time Fourier Transform is carried out to each framed user's voice signal, obtains the amplitude spectrum of framed user's voice signal
And phase spectrum, wherein the user voice signal frequency spectrum Polar Coordinate Model used are as follows:
Z (i, v)=| Z (i, v) | exp (j ∠ Z (i, v))
In formula, Z (i, v) indicates the frequency spectrum of v-th of Frequency point of the i-th frame of user voice signal, | Z (i, v) | indicate user's language
The amplitude spectrum of sound signal v-th of Frequency point of the i-th frame, ∠ Z (i, v) indicate the phase of v-th of Frequency point of the i-th frame of user voice signal
Spectrum；
3) it is composed according to the amplitude Power estimation of user voice signal noise amplitude therein, and obtains the width of clean speech signal
Degree spectrum:
31) a priori SNR estimation of voice signal is obtained
The power spectrum of preceding a framed user voice signal is taken average as initial noisc power Spectral Estimation
32) variance is composed according to the high frequency and middle low frequency power of a priori SNR estimation of acquisition and the frame voice signal,
Obtaining the frame voice signal, there are the posterior probability of voice, wherein the customized posterior probability used obtains function are as follows:
In formula, P (Y1| Z) indicate the i-th frame voice signal there are the posterior probability of voice,Indicate the priori of voice signal
Signal-to-noise ratio, | Z (i, v) |2Indicate the power spectrum of v-th of Frequency point of the i-th frame of user voice signal, | Z (i) |2Indicate user speech letter
The power spectrum of number the i-th frame,Indicate that the noise power Power estimation of the (i-1)-th frame of user voice signal, V indicate user's language
The sum of message power frequency spectrum Frequency point, E1(i) indicate i-th framed user's voice signal the 1st toThe power spectral density of a Frequency point
Mean value, E2(i) i-th framed user's voice signal the is indicatedExtremelyThe power spectral density mean value of a Frequency point, ω1Indicate setting
Posterior probability regulatory factor；
33) noise power Power estimation is updated:
In formula, μ indicates smoothing processing regulatory factor,Indicate the noise power Power estimation of the i-th frame voice signal, P
(Y1| Z) indicate the i-th frame voice signal there are the posterior probability of voice, | Z (i) |2Indicate the power of the i-th frame of user voice signal
Spectrum；
34) the noise power Power estimation based on the i-th frame voice signalObtain noise amplitude Power estimation
And the amplitude spectrum based on the i-th frame voice signal | Z (i, v) | and noise amplitude Power estimationIt carries out spectrum and subtracts operation, obtain pure
The amplitude spectrum c (i, v) of net voice signal；
4) successively according to the amplitude spectrum of each frame clean speech signal | c (i, v) | and the phase spectrum ∠ Z of user voice signal
(i, v) carries out speech reconstruction, obtains the frequency spectrum of enhanced user voice signal, and using inverse Fourier transform in short-term, obtains
Enhanced user voice signal,
Wherein, the frequency spectrum of enhanced user voice signal can be expressed as C1(i, v)=| c (i, v) | exp (j ∠ Z (i,
v))。
It is typically more noisy for the environment where bus stop, it is easy to be caused by vehicle on road surface and the passenger that waits
Noise bother, and the noise is randomly generated, ambiguity and sudden strong, therefore, increasing of the tradition to voice signal
Assume that noise is to meet certain regular processing mode to be not particularly suited in the environment of bus platform in strong mode.
Above embodiment of the present invention carries out Fourier transformation to the user voice signal of acquisition first, obtains in frequency domain
User voice signal, and user voice signal is resolved into amplitude spectrum and frequency spectrum and is handled respectively, estimated to noise
Timing, the present invention are joined using the power spectrum variance etc. based on power spectrum, noise power Power estimation, power spectrum medium-high frequency and middle low frequency
There are the posterior probability of voice in several custom function Accurate Prediction voice signals, and with acquisition there are the posteriority of voice is general
Based on rate, timely replacement is carried out to noise power Power estimation, the real-time and accuracy of noise prediction is can be improved, finally leads to
It crosses spectrum-subtraction and removes noise signal from the user speech of acquisition, improve the effect to user voice signal enhancing, be suitable for
The noisy environment of bus platform lays a good foundation to accurately identifying for user voice signal for after.
In one embodiment, in pretreatment unit 821, a priori SNR estimation of voice signal is obtainedSpecifically
Include:
The a priori SNR estimation of voice signal is obtained using following customized a priori SNR estimation function:
In formula,Indicate a priori SNR estimation of i-th framed user's voice signal, | Z (i) |2Indicate the i-th framed user
The power spectrum of voice signal,Indicate that the noise power Power estimation of (i-1)-th framed user's voice signal, G indicate gain system
Number, q indicate weight regulatory factor.
Preferably,
Change for noise in bus platform is not adapted to using fixed prior weight in the processing of above-mentioned speech enhan-cement
Uncertainty and sudden, above embodiment of the present invention, the priori noise of voice signal is obtained by the way of adaptive
Than that can update a priori SNR estimation according to the power spectrum and noise power spectrum estimation self-adaptive of voice signal, adapt to public transport
The characteristics of platform noise changes at random, while joined gain coefficient in signal-to-noise ratio (SNR) estimation function, make signal-to-noise ratio (SNR) estimation function
Voice signal is faster adapted to from unvoiced segments to sound section of transition, further increases and predicts that there are the posteriority of voice in voice signal
The accuracy of probability.
In one embodiment, in pretreatment unit 821, enhancing processing is carried out to the user voice signal of acquisition, it is defeated
Enhanced user voice signal out, may further comprise:
Processing is compensated to the phase spectrum of user voice signal:
According to the phase spectrum of user voice signal and noise power Power estimation, calculates and compensated for the phase spectrum of voice signal
The factor, wherein the customized phase spectrum compensation factor used calculates function are as follows:
In formula, Λbc(i, v) indicates the phase spectrum compensation factor of i-th v-th of Frequency point of framed user's voice signal, and λ expression is set
Fixed adjustment parameter, | Z (i, v) |2Indicate the power spectrum of i-th v-th of Frequency point of framed user's voice signal,It indicates
The noise phase Power estimation of (i-1)-th v-th of Frequency point of framed user's voice signal,Show that (i-1)-th framed user's voice is believed
The power Spectral Estimation of number v-th of Frequency point, sgn () indicate sign function；
The phase spectrum of user voice signal is compensated according to the phase spectrum compensation factor of acquisition, wherein the phase used
Compose penalty function are as follows:
∠Zbc(i, v)=arg [Z (i, v)+Λbc(i, v)]
In formula, ∠ Zbc(i, v) indicates compensated user voice signal phase spectrum, and arg [] expression takes argument of complex number,
ΛbcThe phase spectrum compensation factor of (i, v) expression user voice signal；
Then in pretreatment unit 821, step (4) further comprises:
Successively according to the amplitude spectrum of each frame clean speech signal | c (i, v) | and the phase of compensated user voice signal
Position spectrum ∠ Zbc(i, v) carries out speech reconstruction, obtains the frequency spectrum of enhanced user voice signal, and use Fourier's inversion in short-term
It changes, obtains enhanced user voice signal,
Wherein, the frequency spectrum of enhanced user voice signal can be expressed as C2(i, v)=| c (i, v) | exp (j ∠ Zbc
(i, v)).
Preferably, λ=3.6.
Above embodiment of the present invention, for the reinforcing effect for further increasing user voice signal, in addition to the above method
In user voice signal amplitude spectrum is enhanced except, processing also is compensated to the phase spectrum of user voice signal, first
Obtain compensation factor according to the phase spectrum of user voice signal and noise power Power estimation, and according to compensation factor to phase spectrum into
Row compensation, enables to the Denoising disposal synchronous with phase spectrum of the amplitude spectrum in speech signal spec-trum, further increases user
The reinforcing effect of voice signal.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as analysis, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (9)
1. a kind of Novel bus platform characterized by comprising platform frame,
The platform frame includes column, and the column is transversely distributed on bus platform, is provided with fixation at the top of the column
Frame is equipped with rain cover baffle on the fixed frame；Self-service borrowing and returning device, the self-service borrowing and returning device are provided between the column
Including cabinet body, the cabinet body is equipped with control panel and multiple matter storage lattices with smart lock；Before the self-service borrowing and returning device
Side is provided with seat；The side of bus platform is provided with dustbin, and the other side is provided with smart terminal, the smart terminal
It is inquired for bus platform information.
2. a kind of Novel bus platform according to claim 1, which is characterized in that the rain cover baffle, which tilts backwards, to be set
It sets.
3. a kind of Novel bus platform according to claim 1, which is characterized in that the matter storage lattice of the self-service borrowing and returning device
It is provided with cabinet door, the smart lock is arranged in the cabinet door；The control panel is connect with the smart lock, is used to open finger
Determine the smart lock of matter storage lattice cabinet door.
4. a kind of Novel bus platform according to claim 3, which is characterized in that the self-service borrowing and returning device and the seat
The distance of chair is greater than the width of the cabinet door.
5. a kind of Novel bus platform according to claim 3, which is characterized in that be additionally provided with barcode scanning on the control panel
Device, for opening the smart lock of specified matter storage lattice cabinet door after scanning recognition bar code/two dimensional code.
6. a kind of Novel bus platform according to claim 1, which is characterized in that the smart terminal includes that setting exists
Display screen and voice capture device on the smart terminal body, and the centre being arranged in the smart terminal
Manage device and communication module；
The voice capture device sends central processing unit for the user voice signal for acquiring user voice signal；
The central processing unit carries out identifying processing to the user voice signal, obtains corresponding inquiry instruction；
The communication module is connect with cloud server, for sending Cloud Server for the inquiry instruction, and is received by cloud
The query result that server returns；
The display screen is for showing the query result.
7. a kind of Novel bus platform according to claim 6, which is characterized in that the smart terminal is for user query
Bus platform information include:
The peripheral information of the bus platform is inquired, including Bus information, catering information, shopping information, sight spot information, government's machine
Close information；
Road congestion information in the route information of the bus platform approach bus, the route, bus arrival crowding
Predictive information, bus arrival used time predictive information.
8. a kind of Novel bus platform according to claim 6, which is characterized in that the central processing unit includes at voice
Module is managed, the speech processing module carries out identifying processing to received user voice signal, obtains corresponding inquiry instruction, into
One step includes:
Pretreatment unit: enhancing processing is carried out to the user voice signal of acquisition, exports enhanced user voice signal；
End-point detection unit: carrying out endpoint detection processing to enhanced user voice signal, detects sound in voice signal
Part；
Feature extraction unit: feature extraction processing is carried out to the voiced portions, obtains the characteristic parameter of the voiced portions；
Recognition unit: the characteristic parameter that will acquire and the characteristic parameter prestored in inquiry instruction database are compared, and know
Not corresponding inquiry instruction；
Inquiry instruction database: storage inquiry instruction and its corresponding characteristic parameter.
9. a kind of Novel bus platform according to claim 8, which is characterized in that the pretreatment unit, to acquisition
User voice signal carries out enhancing processing, exports enhanced user voice signal, further comprises:
1) framing windowing process is carried out to the user voice signal of acquisition, wherein adjacent speech frame has lap；
2) Short Time Fourier Transform is carried out to each framed user's voice signal, obtains the amplitude spectrum and phase of framed user's voice signal
Position spectrum, wherein the user voice signal frequency spectrum Polar Coordinate Model used are as follows:
Z (i, v)=| Z (i, v) | exp (j ∠ Z (i, v))
In formula, Z (i, v) indicates the frequency spectrum of v-th of Frequency point of the i-th frame of user voice signal, | Z (i, v) | indicate user speech letter
The amplitude spectrum of number v-th of Frequency point of the i-th frame, ∠ Z (i, v) indicate the phase spectrum of v-th of Frequency point of the i-th frame of user voice signal；
3) it is composed according to the amplitude Power estimation of user voice signal noise amplitude therein, and obtains the amplitude of clean speech signal
Spectrum:
31) a priori SNR estimation of voice signal is obtained
The power spectrum of preceding a framed user voice signal is taken average as initial noisc power Spectral Estimation
32) variance is composed according to the high frequency and middle low frequency power of a priori SNR estimation of acquisition and the frame voice signal, obtained
There are the posterior probability of voice for the frame voice signal, wherein the customized posterior probability used obtains function are as follows:
In formula, P (Y1| Z) indicate the i-th frame voice signal there are the posterior probability of voice,Indicate the priori noise of voice signal
Than, | Z (i, v) |2Indicate the power spectrum of v-th of Frequency point of the i-th frame of user voice signal, | Z (i) |2Indicate user voice signal the
The power spectrum of i frame,Indicate that the noise power Power estimation of the (i-1)-th frame of user voice signal, V indicate user speech letter
The sum of power frequency spectrum Frequency point, E1(i) indicate i-th framed user's voice signal the 1st toThe power spectral density of a Frequency point is equal
Value, E2(i) i-th framed user's voice signal the is indicatedExtremelyThe power spectral density mean value of a Frequency point, ω1After indicating setting
Test probability regulatory factor；
33) noise power Power estimation is updated:
In formula, μ indicates smoothing processing regulatory factor,Indicate the noise power Power estimation of the i-th frame voice signal, P (Y1|Z)
Indicate the i-th frame voice signal there are the posterior probability of voice, | Z (i) |2Indicate the power spectrum of the i-th frame of user voice signal；
34) the noise power Power estimation based on the i-th frame voice signalObtain noise amplitude Power estimationAnd base
In the amplitude spectrum of the i-th frame voice signal | Z (i, v) | and noise amplitude Power estimationIt carries out spectrum and subtracts operation, obtain pure language
The amplitude spectrum c (i, v) of sound signal；
4) successively according to the amplitude spectrum of each frame clean speech signal | c (i, v) | and user voice signal phase spectrum ∠ Z (i,
V) speech reconstruction is carried out, the frequency spectrum of enhanced user voice signal is obtained, and using inverse Fourier transform in short-term, is enhanced
User voice signal afterwards,
Wherein, the frequency spectrum of enhanced user voice signal can be expressed as C1(i, v)=| c (i, v) | exp (j ∠ Z (i, v)).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798792.4A CN110528913B (en) | 2019-08-27 | 2019-08-27 | Novel bus stop |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798792.4A CN110528913B (en) | 2019-08-27 | 2019-08-27 | Novel bus stop |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110528913A true CN110528913A (en) | 2019-12-03 |
| CN110528913B CN110528913B (en) | 2021-01-05 |
Family
ID=68664567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910798792.4A Active CN110528913B (en) | 2019-08-27 | 2019-08-27 | Novel bus stop |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110528913B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5363608A (en) * | 1993-06-28 | 1994-11-15 | Conlan Michael D | See-through bus stop shelter |
| KR101373537B1 (en) * | 2013-11-13 | 2014-03-14 | 주식회사 에이치에스파트너스 | Bus platform equipped with hot-wire folding chairs and access point |
| CN107170269A (en) * | 2017-06-28 | 2017-09-15 | 厦门互啪互动科技有限公司 | A kind of intelligent Multifunctional bus platform |
| CN107464563A (en) * | 2017-08-11 | 2017-12-12 | 潘金文 | A kind of interactive voice toy |
| WO2018083570A1 (en) * | 2016-11-02 | 2018-05-11 | Chears Technology Company Limited | Intelligent hearing aid |
| CN207489354U (en) * | 2017-10-18 | 2018-06-12 | 向欣 | A kind of media all-in-one machine based on bus platform |
| CN108735225A (en) * | 2018-04-28 | 2018-11-02 | 南京邮电大学 | It is a kind of based on human ear masking effect and Bayesian Estimation improvement spectrum subtract method |
-
2019
- 2019-08-27 CN CN201910798792.4A patent/CN110528913B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5363608A (en) * | 1993-06-28 | 1994-11-15 | Conlan Michael D | See-through bus stop shelter |
| KR101373537B1 (en) * | 2013-11-13 | 2014-03-14 | 주식회사 에이치에스파트너스 | Bus platform equipped with hot-wire folding chairs and access point |
| WO2018083570A1 (en) * | 2016-11-02 | 2018-05-11 | Chears Technology Company Limited | Intelligent hearing aid |
| CN107170269A (en) * | 2017-06-28 | 2017-09-15 | 厦门互啪互动科技有限公司 | A kind of intelligent Multifunctional bus platform |
| CN107464563A (en) * | 2017-08-11 | 2017-12-12 | 潘金文 | A kind of interactive voice toy |
| CN207489354U (en) * | 2017-10-18 | 2018-06-12 | 向欣 | A kind of media all-in-one machine based on bus platform |
| CN108735225A (en) * | 2018-04-28 | 2018-11-02 | 南京邮电大学 | It is a kind of based on human ear masking effect and Bayesian Estimation improvement spectrum subtract method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110528913B (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tyagi et al. | Vehicular traffic density state estimation based on cumulative road acoustics | |
| US9697730B2 (en) | Spatial clustering of vehicle probe data | |
| CN109389766A (en) | User's identifying system and method for autonomous vehicle | |
| CN104751321B (en) | A kind of the public transport intelligence payment system and its implementation of embedded specific crowd identification | |
| CN105640748B (en) | One kind vibration guide clothes | |
| CN107351870A (en) | A kind of passenger's bootstrap technique and system | |
| CN208360015U (en) | A kind of unmanned vehicle addressee system | |
| CN105279955A (en) | Carpooling method and device | |
| CN107016369A (en) | A kind of vehicle-mounted dynamic passenger data comparison system and method based on system of real name | |
| CN108255947A (en) | Portray method, apparatus, mobile terminal and the storage medium of personnel motion trail | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN109147390A (en) | A kind of Vehicle tracing method based on quantization adaptive Kalman filter | |
| CN109240789A (en) | Multifunctional bus system and its application method based on transportation network big data | |
| CN109255386A (en) | The road pedestrian rapid detection method merged based on millimetre-wave radar and vision | |
| CN110490103A (en) | Track traffic for passenger flow Density Detection method and device | |
| CN110021169A (en) | A kind of bus passenger get-off stop estimation method based on mobile phone signaling data and public transport data | |
| CN110219543A (en) | Intelligent vehicle and its Intelligent control method for car window | |
| BR112021014864A2 (en) | DETERMINATION DEVICE FOR BOARDING PERMIT AND DETERMINATION METHOD FOR BOARDING PERMIT | |
| CN110473428A (en) | A kind of intelligent parking method, apparatus and system | |
| CN109118786A (en) | A kind of car speed prediction technique based on quantization adaptive Kalman filter | |
| CN110528913A (en) | A kind of Novel bus platform | |
| CN108154701A (en) | A kind of intelligent parking scheduling system based on technology of Internet of things | |
| CN110189537A (en) | Parking induction method, device, equipment and storage medium based on space-time characteristic | |
| CN107985190B (en) | Vehicle-mounted self-adaptive driver alcohol detection alarm system based on multiple sensors | |
| CN106781583B (en) | The optimization method to take bus |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |