CN109600424B - A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal - Google Patents
A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal Download PDFInfo
- Publication number
- CN109600424B CN109600424B CN201811393665.8A CN201811393665A CN109600424B CN 109600424 B CN109600424 B CN 109600424B CN 201811393665 A CN201811393665 A CN 201811393665A CN 109600424 B CN109600424 B CN 109600424B
- Authority
- CN
- China
- Prior art keywords
- voice signal
- mainframe micro
- classroom
- audio
- micro
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/04—Segmentation; Word boundary detection
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal 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
Abstract
The present invention provides the classroom wisdom terminal of a kind of integrated mainframe micro, network insertion and audio collection, mainframe micro is integrated in the classroom wisdom terminal, audio collection module and network access module, wherein the mainframe micro is connect with the audio collection module and network access module respectively;The audio collection module teaches indoor audio signal for acquiring, and sends mainframe micro for the audio signal of acquisition;The mainframe micro is for being handled and being saved to the audio signal;And data interaction is carried out by the network access module and device end;The network access module realizes the data interaction of the classroom wisdom terminal and the electronic equipment for establishing connection by cable network and/or wireless network with device end.Integrated level of the present invention is high, and structure is simple, and scalability is strong, can accurately obtain the audio-frequency information on classroom.
Description
Technical field
The present invention relates to teaching equipment field, especially a kind of integrated mainframe micro, network insertion and audio collection classroom
Wisdom terminal.
Background technique
As the epoch are progressive and the development of science and technology, in entity scene classroom, more and more electronic equipments are answered
For wherein, but electronic equipment type and quantity is various, and the installation of the stabilization of multimedia host and various softwares becomes pipe
Reason is difficult, so that the operation that operation maintenance personnel needs to carry out is sufficiently complex;Currently, classroom is all respectively arranged with PC terminal and middle control eventually
End controls religion indoor equipment, and middle control terminal is only the integrated control to extraneous facility switching state, and scalability is not
By force;When classroom needs on-premise network, special NAF network access facility is needed, it is complicated in cable management, power management and access
Property management on there are serious dispersibilities, it is difficult to effectively it is carried out safety and specification access;When needing the sound to classroom
When frequency information is acquired, need to be acquired audio-frequency information using special audio-frequency information acquisition equipment, and need
The collected audio-frequency information of equipment will be acquired after acquisition imported into special storage facilities do further working process, a side
Face exacerbates the dispersion and management complexity of classroom furniture, be on the other hand also unfavorable for audio using upper and AI speech engine etc. its
A kind of integrated mainframe micro, network insertion and audio collection are invented in the docking of his system, therefore to meet the development of wisdom classroom
Classroom wisdom terminal urgently has needs.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of classroom intelligence of integrated mainframe micro, network insertion and audio collection
Intelligent terminal.
The purpose of the present invention is realized using following technical scheme:
A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal, which is characterized in that
Mainframe micro, audio collection module and network access module are integrated in the classroom wisdom terminal, wherein
The mainframe micro is connect with the audio collection module and network access module respectively;
The audio collection module teaches indoor audio signal for acquiring, and sends micro- master for the audio signal of acquisition
Machine;
The mainframe micro is for being handled and being saved to the audio signal;And by the network access module with
Device end carries out data interaction;
The network access module is realized for establishing connection by cable network and/or wireless network with device end
The data interaction of the classroom wisdom terminal and the electronic equipment.
In one embodiment, the audio collection module includes AUX interface, and the AUX interface is for connecting user
Equipment acquires the audio output signal of the user equipment;And/or
The audio collection module includes microphone, for acquiring user voice signal.
In one embodiment, on the network access module include HDMI interface, the HDMI interface with it is described micro-
Host connection, for exporting the operation interface of the mainframe micro to display equipment or projection device.
In one embodiment, the network access module includes wireless aps antenna, so as to the classroom wisdom terminal
As classroom AP access point, connection and data interaction with access device are realized;And/or
The network access module includes routing function submodule, and the routing function submodule supports IPv4/IPv6 bis-
Stack access, the conversion of IPv4 to IPv6, pure IPv6 access, IPv6 conversion function.
In one embodiment, the mainframe micro is also connect by the network access module with management equipment, described
Management equipment is for remotely being managed and/or being controlled to the mainframe micro;And/or
The mainframe micro also passes through the network access module and connect with user equipment, and user is by the mainframe micro to institute
It states user equipment and carries out long-range management and/control.
In one embodiment, the mainframe micro is also used to carry out coded treatment to received audio signal, generates phase
The audio file answered and preservation, wherein after mainframe micro generates audio file, audio file is transferred to by network access module
Storage facilities realizes that digital display data save, wherein the storage facilities includes mobile hard disk, USB flash disk, network cloud disk, cloud service
Device.
The invention has the benefit that being integrated with mainframe micro, audio collection module and net in wisdom terminal in classroom of the present invention
Network AM access module, integrated level is high, and structure is simple, can replace using PC terminal and middle control terminal in modern classroom, effectively save
Save space and the complexity for reducing device layout, wiring in classroom;Indoor audio letter letter is taught by audio collection module acquisition
Number, and be transferred to mainframe micro and audio signal is further processed or is saved, it can accurately obtain the audio letter on classroom
Breath lays a good foundation for further processing to the audio-frequency information to be subsequent;Mainframe micro passes through network access module and other simultaneously
Device end realizes data interaction, can integrate the indoor all devices terminal of religion, and scalability is strong.
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 frame construction drawing of one embodiment of the present invention;
Fig. 2 is the frame construction drawing of another embodiment of the present invention;
Fig. 3 is the frame construction drawing of speech control module of the present invention.
Appended drawing reference:
Classroom wisdom terminal 0, audio collection module 1, mainframe micro 2, network access module 3, AUX interface 11, voice control
Module 20, speech enhancement unit 21, end-point detection unit 22, feature extraction unit 23, instruction identification unit 24, instruction database 25,
HDMI interface 31, USB interface 32, routing function submodule 33, wireless aps antenna 34, wired network interface 35
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, the classroom wisdom terminal of a kind of integrated mainframe micro 2, network insertion and audio collection, the religion are shown
Audio collection module 1, mainframe micro 2 and network access module 3 are integrated in room wisdom terminal 0;
The mainframe micro 2 is connect with the audio collection module 1 and network access module 3 respectively;
The audio collection module 1 teaches indoor audio signal for acquiring, and sends the audio signal of acquisition to micro-
Host 2;
The mainframe micro 2 is for being handled and being saved to the audio signal;And pass through the network access module 3
Data interaction is carried out with device end.
The network access module 3, it is real for establishing connection by cable network and/or wireless network with device end
The data interaction of existing the classroom wisdom terminal and the electronic equipment.
Above embodiment of the present invention is integrated with mainframe micro 2, audio collection module 1 and network in the wisdom terminal of classroom and connects
Enter module 3, integrated level is high, and structure is simple, can replace using PC terminal and middle control terminal in modern classroom, be effectively saved sky
Between and reduce classroom in device layout, wiring complexity;Indoor audio is taught to believe signal by the acquisition of audio collection module 1,
And be transferred to mainframe micro 2 and audio signal is further processed or is saved, the audio-frequency information on classroom can be accurately obtained,
It lays a good foundation for further processing to be subsequent to the audio-frequency information;Mainframe micro 2 is set by network access module 3 with other simultaneously
Standby terminal realizes data interaction, can integrate the indoor all devices terminal of religion, and scalability is strong.
It in one embodiment, include HDMI interface 31, the HDMI interface 31 and institute on the network access module 3
The connection of mainframe micro 2 is stated, for exporting the operation interface of the mainframe micro 2 to display equipment or projection device.
In a kind of scene, mainframe micro 2 is connect by network access module 3 with projector, and operation interface thereon is passed
It is defeated that screen projection function is realized into projector.
In one embodiment, on the network access module 3 include USB interface 32, the USB interface 32 with it is outer
Operation equipment connection is set, the mainframe micro 2 is operated by the external operation equipment for user, wherein the external behaviour
It include keyboard, mouse, control pen etc. as equipment.
In one embodiment, the network access module 3 includes routing function submodule 33, routing function
Module 33 supports the functions such as IPv4/IPv6 dual stack access, the conversion of IPv4 to IPv6, pure IPv6 access, IPv6 conversion.
In a kind of scene, user terminal accesses classroom wisdom terminal by WIFI interface, by the road of classroom wisdom terminal
Internet, which is accessed, by function sub-modules 33 realizes online.
In a kind of scene, user terminal accesses classroom wisdom terminal by WIFI interface thereon, realizes user terminal
With the data interaction of classroom wisdom terminal.
In a kind of scene, network access module is linked into first line of a couplet network by IPv6.
In one embodiment, the network access module 3 includes wired network interface 35, specifically includes RJ-45 and connects
Mouthful.
In a kind of scene, student terminal is (laptop computer that student carries, flat if indoor desktop computer is being taught in setting
Plate computer, mobile phone etc.) classroom wisdom terminal is connected to by WIFI interface, mainframe micro 2 passes through network access module 3 and the student
Terminal realizes data interaction, including the operation interface of mainframe micro 2 or audio signal transmission is whole to student terminal, or to student
End transmission file etc..
In one embodiment, the network access module 3 includes wireless aps antenna 34, so that the classroom wisdom is whole
End is used as classroom AP access point, realizes connection and data interaction with access device.
In a kind of scene, the AP simultaneously as the wireless access point for throwing screen, realize and the connection of access device and screen,
The interaction of audio.
In a kind of scene, AP access point is equipped in the wisdom terminal of classroom, the AP access point is connect with wireless controller,
Internet is accessed by wireless controller;Indoor user terminal is taught just by wireless network connection to classroom wisdom terminal
Internet is connected to by the AP access point of classroom wisdom terminal;Meanwhile administrator can also pass through 2 pairs of mainframe micro accesses of operation
User terminal carry out the control such as " a key suspension ".
In a kind of scene, user terminal can also access the AP access point of classroom wisdom terminal by wireless network, realize
The data interaction of user terminal and mainframe micro 2, wherein user terminal includes projector, laptop computer, mobile phone, tablet computer etc..
In a kind of scene, the classroom wisdom terminal in each classroom is designed with wireless aps antenna 34, can pass through multiple antennas
It realizes the AP network coverage of teaching building, improves network performance.
Above embodiment of the present invention, classroom wisdom terminal can support wireless routing simultaneously, wireless aps network and wired
Access function, improves the suitability of wisdom terminal applies scene, while improving wisdom terminal and realizing classroom networking and function
Extended capability.
In one embodiment, the audio collection module 1 includes AUX interface 11, and the AUX interface 11 is for connecting
User equipment acquires the audio output signal of the user equipment.
In a kind of scene, the audio collection module 1 is connect by AUX interface 11 with user equipment, by user equipment
Audio output signal be directly inputted in the classroom wisdom terminal, by 2 pairs of the mainframe micro input audio signal carry out
Enhancing processing, and by the network access module 3 by the audio signal transmission into public address equipment, realize external equipment
Sound amplification function.
In one embodiment, the audio collection module 1 includes microphone, for acquiring user voice signal;
In a kind of scene, user enhances the voice signal by microphone input voice signal, mainframe micro 2
Processing, and pass through network access module 3 by the transmitting voice signal into public address equipment, the function that amplifies of realization user speech input
Energy.
Above embodiment of the present invention, audio collection module 1 support user voice signal input and other equipment to export sound
Frequency is capable of the needs of flexible adaptation various teaching scene as modes such as inputs.
In one embodiment, the classroom wisdom terminal further includes power module, the power module with it is described micro-
Host 2, audio collection module 1 and network access module 3 connect, for above-mentioned module for power supply.
In one embodiment, the mainframe micro 2 includes display screen, and the display screen is for showing the mainframe micro 2
Operation interface and operation content.
In one embodiment, the display screen is touch display screen, by the touch display screen to micro- master
Machine 2 is operated.
In one embodiment, the mainframe micro 2 includes using arm processor, and use (SuSE) Linux OS, branch
It holds user and installs and run according to actual needs the softwares such as OFFICE, browser, cloud client in the mainframe micro 2.
In a kind of scene, user runs PPT by mainframe micro 2, and PPT displaying picture is passed through network access module
3 HDMI interface 31 is transferred on projector, realizes the throwing screen of the content of courses.
Above embodiment of the present invention is installed with (SuSE) Linux OS on mainframe micro 2, supports the fortune of various application programs
Row, and pass through the input of touch screen or external operating device progress operational order.
In one embodiment, the mainframe micro 2 is also established with Cloud Server by the network access module 3 and is connected
It connects, realizes the data interaction of mainframe micro 2 and Cloud Server;
In a kind of scene, the mainframe micro 2 is equipped with cloud desktop client, and for accessing cloud desktop, user passes through institute
It states cloud desktop to operate virtual application and virtual system, further the ability for running various software on mainframe micro is mended
Foot.
Above embodiment of the present invention, mainframe micro 2 is connect by network access module 3 with cloud server, and micro- master
It is installed with cloud desktop client on machine 2, virtual system or program are operated by cloud desktop client for user, pass through cloud
The application of desktop, can efficiently reduce the pressure in locally-stored space, while improve the diversity of application program.
In one embodiment, agent module built in the mainframe micro 2 passes through the network access module 3 and management
Equipment connection, the management equipment is for remotely being managed and/or being controlled to the mainframe micro 2.
In a kind of scene, the mainframe micro 2 can also be connect by network access module 3 with management equipment, pass through IP electricity
Words realize the calling to administrative center.
In one embodiment, the mainframe micro 2 is also connect by the network access module 3 with user equipment, is used
Family carries out long-range management and/control to the user equipment by the mainframe micro 2.
In one embodiment, the mainframe micro 2 can also obtain the shapes such as its access device presence, operation load
State information.
Above embodiment of the present invention, classroom wisdom terminal can be set by remote control or remote control other accesses
It is standby, strong flexibility.
In one embodiment, the mainframe micro 2 is also used to carry out coded treatment to received audio signal, generates phase
The audio file answered and preservation.
In one embodiment, after mainframe micro 2 generates audio file, audio file is passed by network access module 3
It is defeated to arrive storage facilities, realize that digital display data save, wherein the storage facilities includes mobile hard disk, USB flash disk, network cloud disk, cloud
Server etc..
In a kind of scene, network access module 3 supports iSCSI, cifs, nfs various protocols, will be micro- by network interface
Audio signal in host 2 is saved into Cloud Server.
In a kind of scene, audio collection module acquires the audio signal on classroom, and is sent to mainframe micro and is handled,
Classroom audio file is generated, and is uploaded to classroom audio file in management server by network access module by mainframe micro,
So that management server carries out classification preservation to the audio file, for subsequent calls;And it is further analyzed, including
Identify audio content, semantic analysis and the analysis of public opinion etc..
In a kind of scene, the classroom audio file of generation is also transferred to AI voice by network access module by mainframe micro
In engine, it is for further processing by AI speech engine.
In one embodiment, mainframe micro 2 is connect by network access module 3 with external camera, and mainframe micro 2 passes through
The camera obtains the video pictures in teacher and is stored into designated position.
In a kind of scene, mainframe micro 2 is connected with camera by the USB interface 32 on network access module 3, by this
Camera obtains the video image in teacher, and the video image is uploaded to cloud service by cloud interface by mainframe micro 2
The video image is further processed in device, analyzes the face information in the video image, realizes that the wisdom in classroom is called the roll
Function.
In a kind of scene, the camera is integrated with the classroom wisdom terminal, connect with mainframe micro 2.
Above embodiment of the present invention, classroom wisdom terminal is also integrated or is externally connected to camera, and functions expanding is strong.
In one embodiment, referring to fig. 2, the classroom wisdom terminal also has the function of voice control;Audio is adopted
Collection module 1 is also used to acquire user voice signal, and the user voice signal of acquisition is transferred to the mainframe micro 2;
The mainframe micro 2 further includes speech control module 20, and the speech control module 20 is used for audio collection module 1
The user voice signal of middle acquisition carries out identifying processing, and output is instructed with the user voice signal corresponding operation, for mainframe micro 2
Execute the operational order.
In one embodiment, referring to Fig. 3, the speech control module 20 includes speech enhancement unit 21, endpoint inspection
Survey unit 22, feature extraction unit 23 and instruction identification unit 24;
The speech enhancement unit 21 exports enhanced language for carrying out enhancing processing to received user voice signal
Sound signal;
The end-point detection unit 22 is used to carry out the enhanced voice signal endpoint detection processing, described in mark
Sound end and voice segments in enhanced voice signal;
The feature extraction unit 23, for being carried out at feature extraction to the voice segments in the enhanced voice signal
Reason exports speech characteristic parameter;
Described instruction recognition unit 24, the operational order for being prestored in instruction database 25 according to the speech characteristic parameter
Corresponding characteristic parameter is matched, when the speech characteristic parameter and the characteristic parameter similarity prestored are greater than the threshold value set
When, export the corresponding operational order of the characteristic parameter prestored;When the speech characteristic parameter is respectively less than with the characteristic parameter prestored
When the threshold value of setting, recognition failures message is exported, which is shown by mainframe micro 2.
Above embodiment of the present invention, mainframe micro 2 are handled received user voice signal by blocking design,
Enhancing processing is carried out to user voice signal first, exports enhanced voice signal, is facilitated enhanced voice signal
It further uploads Cloud Server, teller machines or identifying processing further is carried out to voice signal;Then to enhanced language
Sound signal carries out endpoint detection processing, identifies the sound end and voice segments of the signal, establishes base for subsequent voice instruction identification
Plinth;Then feature extraction processing is carried out to voice signal terminal volume voice segments, obtains substantial voice segments in voice signal
Characteristic parameter, the characteristic parameter then obtained in the speech characteristic parameter that will acquire and the instruction database 25 that prestores are compared, and match
The operational order of response and output.It is designed by blocking, can be improved the efficiency of user voice signal identifying processing, meet reality
The needs of when property.
In a kind of scene, user wakes up the voice control function of classroom wisdom terminal by specific phonetic order, when
After user issues the phonetic order of " opening voice control ", the phonetic order of user is acquired by audio collection module 1, and by micro- master
Machine 2 identifies the phonetic order, and after identifying successfully, mainframe micro 2 opens voice command control function, and acquisition user connects down
It come the phonetic order issued and is identified, corresponding operation is executed, the case where the maloperation avoided.
Above embodiment of the present invention, user can execute corresponding behaviour by voice command control classroom wisdom terminal
Make, realizes that, to external equipment such as projector instrument brightness, the control such as loudspeaker volume, strong flexibility meets modern intelligent tutoring
It needs.
In one embodiment, the speech enhancement unit 21 is for carrying out at enhancing received user voice signal
Reason, exports enhanced voice signal, specifically includes:
(1) framing windowing process is carried out to received user voice signal;
(2) Fast Fourier Transform (FFT) is carried out to the voice signal of each frame, obtains the amplitude spectrum of voice signal;
(3) noise estimation processing is carried out to each frame voice signal respectively, obtains the noise amplitude Power estimation of voice signal;
(4) to each frame voice signal, noise amplitude Power estimation will be subtracted in the amplitude spectrum of voice signal, obtain pure language
Sound signal amplitude spectrum;
(5) by carrying out inverse fast fourier transform to clean speech signal amplitude spectrum, the frame voice signals enhancement is obtained
Voice signal afterwards, and the enhanced voice signal combination of each frame is exported into enhanced voice signal.
In one embodiment, noise estimation is carried out to each frame voice signal respectively in the speech enhancement unit 21
Processing, obtains the noise amplitude Power estimation of voice signal, specifically includes:
Wherein, the noise amplitude Power estimation function of use are as follows:
In formula,Indicate the noise amplitude Power estimation in the i-th frame voice signal at the n-th frequency point, | R (i, n) | it indicates
Amplitude spectrum in i-th framed user's voice signal at the n-th frequency point, T expression judge the factor,BGc(i-1,
N) the fluctuation estimation of noise spectrum is indicated,U table
The dynamic estimation adjustment parameter of oscillography, v indicate smoothing fluctuations parameter, and α, β and γ respectively indicate the smooth adjustment factor.
Above embodiment of the present invention composes noise amplitude under unstable noise circumstance due to traditional vad algorithm
Estimation effect is poor, thus the present invention adopt in manner just described voice signal carry out noise amplitude Power estimation, joined it is smooth because
Son, can adaptively to voice signal noise amplitude spectrum estimate, improve the effect and text-to-speech of speech enhan-cement
Information intelligibility is laid a good foundation for the instruction identification of subsequent voice signal.
In one embodiment, to each frame voice signal in the speech enhancement unit 21, by the width of voice signal
Noise amplitude Power estimation is subtracted in degree spectrum, clean speech signal amplitude spectrum is obtained, specifically includes:
For each frame voice signal, its clean speech signal amplitude spectrum is obtained using following spectrum subtraction function:
Wherein,
In formula,Indicate that the clean speech signal amplitude spectrum of m frequency point in the frame voice signal, R (m) indicate the frame
The amplitude spectrum at kth frequency point in user voice signal,Indicate the noise amplitude in the frame voice signal at m frequency point
Power estimation,Indicate the prior weight of m frequency point in the frame voice signal,Indicate that the signal-to-noise ratio of setting is minimum
Value, sN (m) indicate that the posteriori SNR of m frequency point in the frame voice signal, ω indicate impact factor,Indicate the frame language
The clean speech signal amplitude spectrum that sound signal former frame obtains.
Above embodiment of the present invention obtains the amplitude spectrum of clean speech signal, energy using above-mentioned customized spectrum subtraction function
The noise jamming being enough effectively removed in user voice signal, hence it is evident that the voice matter of the clean speech signal obtained after raising processing
Amount improves the subsequent accuracy that instruction identification is carried out to voice signal indirectly.
In one embodiment, the end-point detection unit 22 is used to carry out endpoint to the enhanced voice signal
Detection processing identifies sound end and voice segments in the enhanced voice signal, specifically includes:
Framing, windowing process are carried out to enhanced voice signal;
Fourier transformation is carried out to each frame voice signal, obtains the power spectrum of each frame voice signal;
The end-point detection factor of voice signal described in each frame is obtained respectively, wherein the end-point detection saturation used
Are as follows:
Wherein,
In formula, Sc(i) the end-point detection factor of the i-th frame of expression voice signal, Gc(i indicates that the i-th frame voice signal is set
Fixed sub-band sum,Expression judges the factor,W indicates the sum of speech frame, X (f, i
Indicate that f-th of power spectral amplitude of the i-th frame voice signal, U indicate that the sample number in the frame voice signal, H indicate setting
The sub-band division factor, Yc(d, i) indicates d-th of subband spectrum energy of the i-th frame voice signal,
Successively the threshold value of the end-point detection factor of each frame voice signal and setting is compared, if opened from X frame
Begin the threshold value for having the end-point detection factor of continuous 5 frame voice signal to be greater than setting, is just believed using the frame number of the X frame as the voice
Number voice starting endpoint;And be compared the threshold value of the end-point detection factor of subsequent each frame voice signal and setting,
If the end-point detection factor for beginning with continuous 5 frame voice signal from y frame is less than the threshold value of setting, just with the frame number of the y frame
Voice end caps as the voice signal;And by the voice signal between the voice starting endpoint and voice end caps
Labeled as voice segments.
Above embodiment of the present invention is adopted and is handled in manner just described enhanced voice signal, and the letter is obtained
Number voice segments, sub-frame processing is carried out to enhanced voice signal first, Fu then is carried out to the voice signal of each frame
In leaf transformation obtain the power spectrum of the voice signal, the endpoint of each frame voice signal is then calculated using above-mentioned custom function
Detecting factor, and whether be that voice segments are identified according to end-point detection factor pair voice signal, can be adaptive according to language
Sound signal speciality carries out sub-band division to power spectrum, to reduce the susceptibility of the end-point detection factor pair noise of calculating, improves
The accuracy of speech terminals detection is laid a good foundation for the subsequent accurate characteristic parameter for obtaining user 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 (6)
1. the classroom wisdom terminal of a kind of integrated mainframe micro, network insertion and audio collection, which is characterized in that
Mainframe micro, audio collection module and network access module are integrated in the classroom wisdom terminal, wherein
The mainframe micro is connect with the audio collection module and network access module respectively;
The audio collection module teaches indoor audio signal for acquiring, and sends mainframe micro for the audio signal of acquisition;
The mainframe micro is for being handled and being saved to the audio signal;And pass through the network access module and equipment
Terminal carries out data interaction;
The network access module, for establishing connection by cable network and/or wireless network with device end, described in realization
The data interaction of classroom wisdom terminal and electronic equipment;
Wherein, the audio collection module is also used to acquire user voice signal, and the user voice signal of acquisition is transferred to institute
State mainframe micro;
The mainframe micro further includes speech control module, and the speech control module is used for the use acquired in audio collection module
Family voice signal carries out identifying processing, and output is instructed with the user voice signal corresponding operation, executes the operation for mainframe micro
Instruction;
Wherein, the speech control module includes speech enhancement unit, end-point detection unit, feature extraction unit and instruction identification
Unit;
The speech enhancement unit exports enhanced voice letter for carrying out enhancing processing to received user voice signal
Number;
The end-point detection unit is used to carry out endpoint detection processing to the enhanced voice signal, after identifying the enhancing
Voice signal in sound end and voice segments;
The feature extraction unit, it is defeated for carrying out feature extraction processing to the voice segments in the enhanced voice signal
Speech characteristic parameter out;
Described instruction recognition unit, the corresponding spy of operational order for being prestored in instruction database according to the speech characteristic parameter
Sign parameter is matched, when the speech characteristic parameter is greater than the threshold value of setting with the characteristic parameter similarity prestored, output
The corresponding operational order of the characteristic parameter prestored;When the speech characteristic parameter is respectively less than the threshold set with the characteristic parameter prestored
When value, recognition failures message is exported, which is shown by mainframe micro;
Wherein, the speech enhancement unit exports enhanced language for carrying out enhancing processing to received user voice signal
Sound signal specifically includes:
(1) framing windowing process is carried out to received user voice signal;
(2) Fast Fourier Transform (FFT) is carried out to the voice signal of each frame, obtains the amplitude spectrum of voice signal;
(3) noise estimation processing is carried out to each frame voice signal respectively, obtains the noise amplitude Power estimation of voice signal;
(4) to each frame voice signal, noise amplitude Power estimation will be subtracted in the amplitude spectrum of voice signal, obtains clean speech letter
Number amplitude spectrum;
(5) by carrying out inverse fast fourier transform to clean speech signal amplitude spectrum, after obtaining the frame voice signals enhancement
Voice signal, and the enhanced voice signal combination of each frame is exported into enhanced voice signal;
Noise estimation processing is carried out to each frame voice signal respectively in the speech enhancement unit, obtains the noise of voice signal
Amplitude Power estimation, specifically includes:
Wherein, the noise amplitude Power estimation function of use are as follows:
In formula,Indicate the noise amplitude Power estimation in the i-th frame voice signal at the n-th frequency point, | R (i, n) | indicate the i-th frame
Amplitude spectrum in user voice signal at the n-th frequency point, T expression judge the factor,BGc(i-1, n) table
Show the fluctuation estimation of noise spectrum,U indicates wave
Dynamic estimation adjustment parameter, v indicate smoothing fluctuations parameter, and α, β and γ respectively indicate the smooth adjustment factor.
2. the classroom wisdom terminal of a kind of integrated mainframe micro according to claim 1, network insertion and audio collection, special
Sign is that the audio collection module includes AUX interface, and the AUX interface acquires the user and set for connecting user equipment
Standby audio output;And/or
The audio collection module includes microphone, for acquiring user voice signal.
3. the classroom wisdom terminal of a kind of integrated mainframe micro according to claim 1, network insertion and audio collection, special
Sign is, includes HDMI interface on the network access module, and the HDMI interface is connect with the mainframe micro, and being used for will be described
The operation interface of mainframe micro is exported to display equipment or projection device.
4. the classroom wisdom terminal of a kind of integrated mainframe micro according to claim 1, network insertion and audio collection, special
Sign is that the network access module includes wireless aps antenna, real so that the classroom wisdom terminal is as classroom AP access point
Now with the connection of access device and data interaction;And/or
The network access module includes routing function submodule, and the routing function submodule supports IPv4/IPv6 dual stack to connect
Enter, the conversion of IPv4 to IPv6, pure IPv6 access, IPv6 conversion function.
5. the classroom wisdom terminal of a kind of integrated mainframe micro according to claim 1, network insertion and audio collection, special
Sign is that the mainframe micro is also connect by the network access module with management equipment, and the management equipment is used for described
Mainframe micro is remotely managed and/or is controlled;And/or
The mainframe micro also passes through the network access module and connect with user equipment, and user is by the mainframe micro to the use
Family equipment carries out long-range management and/control.
6. the classroom wisdom terminal of a kind of integrated mainframe micro according to claim 1, network insertion and audio collection, special
Sign is that the mainframe micro is also used to carry out coded treatment to received audio signal, generates corresponding audio file and saves,
Wherein, after mainframe micro generates audio file, audio file is transferred to storage facilities by network access module, realizes digital display number
According to preservation, wherein the storage facilities includes mobile hard disk, USB flash disk, network cloud disk, cloud server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811393665.8A CN109600424B (en) | 2018-11-21 | 2018-11-21 | A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811393665.8A CN109600424B (en) | 2018-11-21 | 2018-11-21 | A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109600424A CN109600424A (en) | 2019-04-09 |
CN109600424B true CN109600424B (en) | 2019-08-20 |
Family
ID=65959156
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811393665.8A Expired - Fee Related CN109600424B (en) | 2018-11-21 | 2018-11-21 | A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109600424B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111208725B (en) * | 2020-02-26 | 2021-12-28 | 无锡职业技术学院 | Multifunctional alarm clock system for classroom |
CN111294681B (en) * | 2020-02-28 | 2021-10-22 | 联想(北京)有限公司 | Classroom terminal system and control method, controller and master control equipment thereof |
CN112863544A (en) * | 2021-01-11 | 2021-05-28 | 新疆品宣生物科技有限责任公司 | Early warning equipment and early warning method based on sound wave analysis |
CN116567483B (en) * | 2023-04-18 | 2024-02-09 | 北京万讯博通科技发展有限公司 | Intelligent management method and system for infrared wireless teaching sound expansion |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103428441A (en) * | 2013-05-27 | 2013-12-04 | 王�锋 | Course recording method and course recording device used for on-line teaching |
CN103440790B (en) * | 2013-09-14 | 2015-07-22 | 大连联达科技有限公司 | Teaching interactive learning system and method |
CN205230416U (en) * | 2015-09-23 | 2016-05-11 | 成都往来教育科技有限公司 | Smart classroom system |
JP6638435B2 (en) * | 2016-02-04 | 2020-01-29 | カシオ計算機株式会社 | Personal adaptation method of emotion estimator, emotion estimation device and program |
CN105931510A (en) * | 2016-06-16 | 2016-09-07 | 北京数智源科技股份有限公司 | Synchronous comment recording classroom platform and method thereof |
CN108230795A (en) * | 2018-01-25 | 2018-06-29 | 黄淮学院 | A kind of university's applied mathematics Teaching System |
CN108389441A (en) * | 2018-03-06 | 2018-08-10 | 东莞职业技术学院 | A kind of wisdom classroom system |
-
2018
- 2018-11-21 CN CN201811393665.8A patent/CN109600424B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN109600424A (en) | 2019-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109600424B (en) | A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal | |
WO2018036149A1 (en) | Multimedia interactive teaching system and method | |
US10930281B2 (en) | Method, apparatus and system for testing intelligent voice device | |
CN105578115B (en) | A kind of Network teaching method with Speech Assessment function and system | |
CN105681920B (en) | A kind of Network teaching method and system with speech identifying function | |
CN112863547B (en) | Virtual resource transfer processing method, device, storage medium and computer equipment | |
CN109903773B (en) | Audio processing method, device and storage medium | |
JP2016524724A (en) | Method and system for controlling a home electrical appliance by identifying a position associated with a voice command in a home environment | |
JP2009518662A (en) | Determining audio device quality | |
CN101141610A (en) | Apparatus and method for video mixing and computer readable medium | |
KR20220027187A (en) | Scene interaction method and apparatus, electronic device and computer storage medium | |
CN111179962A (en) | Training method of voice separation model, voice separation method and device | |
CN111405301B (en) | Screen recording interaction method and device for terminal, computer equipment and storage medium | |
JP2018195276A (en) | Simultaneous translation device with double-sided display, method, device, and electronic device | |
CN108874283A (en) | Image identification method, mobile terminal and computer readable storage medium | |
CN105430494A (en) | Method and device for identifying audio from video in video playback equipment | |
WO2021147157A1 (en) | Game special effect generation method and apparatus, and storage medium and electronic device | |
CN111986691B (en) | Audio processing method, device, computer equipment and storage medium | |
US20210319802A1 (en) | Method for processing speech signal, electronic device and storage medium | |
CN111405416A (en) | Stereo recording method, electronic device and storage medium | |
CN112860572A (en) | Cloud testing method, device, system, medium and electronic equipment of mobile terminal | |
CN109616119A (en) | A kind of Multifunctional gateway equipment based on IPv6 agreement | |
WO2012174711A1 (en) | User terminal device, server device, system and method for assessing quality of media data | |
US20170206898A1 (en) | Systems and methods for assisting automatic speech recognition | |
TWM574267U (en) | Live broadcast system of synchronous and automatic translation of real-time voice and subtitle |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190820 Termination date: 20211121 |