阅读说明：本技术 一种课堂语音识别用教学机 (Classroom is teaching machine for speech recognition ) 是由 于传 唐毅 吴可汗 李俊良 黄炎 于 2021-07-20 设计创作，主要内容包括：本发明公开了一种课堂语音识别用教学机,包括外壳,显示机构的一侧设置有扬声器,外壳的顶部设置有摄像头,显示机构的另一侧设置有启动机构,外壳的内腔设置有语音教学机构,显示机构包含显示槽和显示屏,显示屏固定嵌设于显示槽的内腔,语音教学机构包含显示模块、存储模块、人脸表情识别分析模块、语音识别模块、语音分割模块和控制处理模块。本发明利用语音识别模块、语音分割模块、存储模块及人脸表情识别分析模块相配合的设置方式,使教学过程中教师上课的语音转化为文字及对语音进行分割处理,便于通过存储模块进行存储,便于视频图像和语音识别的融合保存,使学生课后的教学更加方便。(The invention discloses a teaching machine for classroom voice recognition, which comprises a shell, wherein one side of a display mechanism is provided with a loudspeaker, the top of the shell is provided with a camera, the other side of the display mechanism is provided with a starting mechanism, the inner cavity of the shell is provided with a voice teaching mechanism, the display mechanism comprises a display groove and a display screen, the display screen is fixedly embedded in the inner cavity of the display groove, and the voice teaching mechanism comprises a display module, a storage module, a facial expression recognition analysis module, a voice recognition module, a voice segmentation module and a control processing module. The invention utilizes the matched setting mode of the voice recognition module, the voice segmentation module, the storage module and the facial expression recognition analysis module to convert the voice of a teacher in class into characters and segment the voice in the teaching process, thereby being convenient for storage through the storage module, being convenient for fusion storage of video images and voice recognition and leading the teaching of students after class to be more convenient.)

1. A teaching machine for classroom voice recognition comprises a shell (1), and is characterized in that a display mechanism (2) is arranged on the front side of the shell (1), a loudspeaker (3) is arranged on one side of the display mechanism (2), a camera (4) is arranged on the top of the shell (1), a starting mechanism (5) is arranged on the other side of the display mechanism (2), and a voice teaching mechanism (8) is arranged in an inner cavity of the shell (1);

display mechanism (2) contain display slot (201) and display screen (202), the fixed inner chamber of locating display slot (201) of inlaying in display screen (202), pronunciation teaching mechanism (8) contain display module (801), storage module (802), facial expression recognition analysis module (803), speech recognition module (804), pronunciation segmentation module (805) and control processing module (806).

2. The classroom teaching machine for speech recognition according to claim 1, wherein the actuating mechanism (5) comprises a fixed slot (501), four push switches (502) and four indicator lights (503), and the push switches (502) and the indicator lights (503) are fixedly inserted into the inner wall of the fixed slot (501).

3. A teaching machine for classroom speech recognition according to claim 1, wherein the bottom of the housing (1) is fixedly connected with at least two support pads (6) at equal intervals, and the top of the housing (1) is provided with a pulling mechanism (7).

4. The teaching machine for classroom speech recognition according to claim 3, wherein the pulling mechanism (7) comprises two clamping blocks (701), two clamping grooves (702), a handle (703), four limiting grooves (704) and four limiting blocks (705), and the clamping blocks (701) are fixedly connected with the top end of the housing (1).

5. The classroom teaching machine for speech recognition according to claim 4, wherein the slot (702) is opened at one end of the fixture block (701), and two ends of the pull handle (703) are slidably connected with inner cavities of the two slots (702), respectively.

6. The teaching machine for classroom speech recognition according to claim 4, wherein two adjacent limiting grooves (704) are formed on two sides of the inner wall of the slot (702), and two adjacent limiting blocks (705) are fixedly connected with two sides of one end of the handle (703), respectively.

7. The teaching machine for classroom speech recognition according to claim 4, wherein the limiting block (705) is slidably inserted into the inner cavity of the limiting groove (704), and the outer walls of the speaker (3) and the camera (4) are fixedly inserted into the front surface of the housing (1).

Technical Field

The invention relates to the field of voice recognition, in particular to a teaching machine for classroom voice recognition.

Background

In recent years, speech recognition technology has advanced significantly and started to move from the laboratory to the market, and the fields related to speech recognition technology include: signal processing, pattern recognition, probability theory and information theory, sound production mechanism and auditory mechanism, artificial intelligence and the like, and the voice recognition technology enters various fields of industry, household appliances, communication, automobile electronics, medical treatment, family service, consumer electronics and the like.

In the existing classroom teaching process, the thought reaction capacity of some students is poor, so that the content explained by teachers in a classroom cannot be understood, and the teacher teaching content is not converted into knowledge point slices through classroom recording and voice recognition technology, so that some students with poor thought reaction capacity cannot catch up with the study, and the study effect of the students is influenced.

Disclosure of Invention

The invention aims to provide a teaching machine for classroom speech recognition, which aims to solve the problems in the background technology.

In order to achieve the purpose, the invention provides the following technical scheme: a teaching machine for classroom voice recognition comprises a shell, wherein a display mechanism is arranged on the front surface of the shell, a loudspeaker is arranged on one side of the display mechanism, a camera is arranged at the top of the shell, a starting mechanism is arranged on the other side of the display mechanism, and a voice teaching mechanism is arranged in an inner cavity of the shell;

display mechanism contains display slot and display screen, the fixed inner chamber of locating the display slot that inlays of display screen, pronunciation teaching mechanism contains display module, storage module, facial expression discernment analysis module, speech recognition module, pronunciation segmentation module and control processing module.

Preferably, the starting mechanism comprises a fixing groove, four pressing switches and four indicating lamps, and the pressing switches and the indicating lamps are fixedly inserted and connected with the inner wall of the fixing groove.

Preferably, the bottom equidistance fixedly connected with of shell supports the gasket by at least two, the top of shell is provided with pulling mechanism.

Preferably, the pulling mechanism comprises two clamping blocks, two clamping grooves, a handle, four limiting grooves and four limiting blocks, and the clamping blocks are fixedly connected with the top end of the shell.

Preferably, the clamping grooves are formed in one ends of the clamping blocks, and two ends of the handle are respectively connected with the inner cavities of the two clamping grooves in a sliding mode.

Preferably, two adjacent limiting grooves are formed in two side sides of the inner wall of the clamping groove, and the two adjacent limiting blocks are fixedly connected with two side sides of one end of the handle respectively.

Preferably, the limiting block is connected with the inner cavity of the limiting groove in a sliding and penetrating mode, and the outer walls of the loudspeaker and the camera are respectively connected with the front face of the shell in a fixed and penetrating mode.

The invention has the technical effects and advantages that:

(1) the invention utilizes the matched setting mode of the voice recognition module, the voice segmentation module, the storage module and the facial expression recognition analysis module, converts the voice of a teacher in class into characters and performs segmentation processing on the voice in the teaching process through voice recognition and voice segmentation, is convenient to store through the storage module, is convenient for fusion storage of video images and voice recognition through the combination of the facial expression recognition analysis training evaluation system and the display module, and makes teaching of students after class more convenient;

(2) the invention utilizes the setting mode of the matching of the loudspeaker, the camera and the display screen, is convenient for recording the recognition of the facial expression and inputting common words, sentences and tones, takes the characteristic vector as a template to be stored in the storage module, compares the similarity of the characteristic vector of the input voice with each template in the template library in sequence in the recognition stage, and outputs the person with the highest similarity as a recognition result to be displayed through the display and the loudspeaker;

(3) the invention utilizes the arrangement mode of matching the handle and the supporting gasket, is convenient for improving the stability of the device, ensures that the device is not influenced when being stored through the handle, is convenient for a person taking the teaching machine, and improves the convenience of the use of the device.

Drawings

Fig. 1 is a schematic view of the overall structure of the present invention.

Fig. 2 is a schematic view of the overall structure of the present invention.

FIG. 3 is a schematic cross-sectional view of a fixture block of the present invention.

Fig. 4 is a schematic sectional view of the housing of the present invention.

FIG. 5 is a block diagram of a memory module according to the present invention.

FIG. 6 is a block diagram of a control processing module according to the present invention.

In the figure: 1. a housing; 2. a display mechanism; 201. a display slot; 202. a display screen; 3. a speaker; 4. a camera; 5. a starting mechanism; 501. fixing grooves; 502. a push switch; 503. an indicator light; 6. a support pad; 7. a pulling mechanism; 701. a clamping block; 702. a card slot; 703. a handle; 704. a limiting groove; 705. a limiting block; 8. a voice teaching mechanism; 801. a display module; 802. a storage module; 803. a facial expression recognition analysis module; 804. a voice recognition module; 805. a voice segmentation module; 806. and a control processing module.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The invention provides a teaching machine for classroom voice recognition, which is shown in figures 1-6 and comprises a shell 1, wherein the shell 1 is made of PE (polyethylene), a display mechanism 2 is arranged on the front surface of the shell 1, so that pictures and texts can be conveniently displayed, a loudspeaker 3 is arranged on one side of the display mechanism 2, so that audio can be conveniently input and output, a camera 4 is arranged on the top of the shell 1, so that video can be conveniently output, a starting mechanism 5 is arranged on the other side of the display mechanism 2, and a voice teaching mechanism 8 is arranged in an inner cavity of the shell 1, so that the completeness of the mechanism is convenient;

the display mechanism 2 comprises a display groove 201 and a display screen 202, the display groove 201 is a rectangular groove, the display screen 202 is an LED display panel, the display screen 202 is fixedly embedded in an inner cavity of the display groove 201, the actuating mechanism 5 comprises a fixing groove 501, four push switches 502 and four indicator lamps 503, the fixing groove 501 is in a long rectangular groove structure, the four push switches 502 are arranged in the inner cavity of the fixing groove 501 to prevent the push switches 502 from being touched randomly, the indicator lamps 503 are electrically connected with the push switches 502, so that when the push switches 502 are actuated, by lighting the indicator lamp 503, the user can more intuitively see the on/off state of the push switch 502, the four push switches 502 are respectively a power button, an information storage button, a video identification button and a learning button, so that the teaching machine can be conveniently used with different functions;

the bottom end of the shell 1 is fixedly connected with at least two supporting gaskets 6 at equal intervals, the supporting gaskets 6 are made of rubber materials, friction force on a table top is convenient to improve, and stability of the teaching machine in use is improved, a pulling mechanism 7 is arranged at the top end of the shell 1 and is convenient to stably pull the teaching machine, the pulling mechanism 7 comprises two clamping blocks 701, two clamping grooves 702, a handle 703, four limiting grooves 704 and four limiting blocks 705, the handle 703 is made of flexible materials and is convenient to pull more comfortably, and the clamping blocks 701 are fixedly connected with the top end of the shell 1;

the clamping grooves 702 are formed in one end of the clamping block 701, two ends of the handle 703 are respectively connected with inner cavities of the two clamping grooves 702 in a sliding mode, the two ends of the handle 703 can be conveniently stored, the handle 703 is not influenced by a handle when being stored, two adjacent limiting grooves 704 are formed in two side sides of the inner wall of the clamping grooves 702, two adjacent limiting blocks 705 are respectively fixedly connected with two side sides of one end of the handle 703, the limiting blocks 705 are connected with the inner cavities of the limiting grooves 704 in a sliding and penetrating mode, stability of positions of two ends of the handle 703 can be improved, position limitation of the handle 703 can be facilitated, the teaching machine can be pulled more stably, outer walls of the loudspeaker 3 and the camera 4 are respectively connected with the front face of the shell 1 in a fixed and penetrating mode, and output and input of audio and input of video can be more conveniently achieved through the loudspeaker 3 and the camera 4;

the voice teaching mechanism 8 comprises a display module 801, a storage module 802, a facial expression recognition and analysis module 803, a voice recognition module 804, a voice segmentation module 805 and a control processing module 806, the control processing module 806 comprises a control module and a processing module, a power button is electrically connected with the control module, the control module is electrically connected with the processing module, a camera 4 is electrically connected with the facial expression recognition and analysis module 803, a speaker 3 is electrically connected with the voice recognition module 804, the voice recognition module 804 is electrically connected with the voice segmentation module 805, the voice segmentation module 805 and the facial expression recognition and analysis module 803 are both electrically connected with the storage module 802, the storage module 802 is electrically connected with the control processing module 806, the output end of the control processing module 806 is electrically connected with the receiving end of the display screen 202 through the display module 801, and the output end of the control processing module 806 is electrically connected with the receiving end of the speaker 3, the display screen 202, the speaker 3, the camera 4, the display module 801, the storage module 802, the facial expression recognition and analysis module 803, the voice recognition module 804, the voice segmentation module 805 and the control processing module 806 are all electrically connected with the storage battery inside the housing 1 through a switch of the push switch 502.

The working principle of the invention is as follows:

when in use, the teaching machine is convenient to start by turning on a power button on the teaching machine, the information storage button is turned on, the AI voice recognition algorithm on the voice recognition module 804 is convenient to convert the lesson voice of a teacher in the teaching process into characters by the voice recognition module 804, common questioning words, sentences, tones and the like are convenient to input, the common ending words, sentences and tones can be recognized by the voice segmentation module 805, finally the recognized knowledge point slices are processed and classified, the branch current detection in the control processing module 806 is convenient to be combined with the facial expression recognition analysis module 803 by the information storage and information recognition and processing of the storage module 802 and the pressing start of the video recognition button, the video image is convenient to be stored by the storage module 802 and the control processing module 806, and the voice recognition result is planted in the video for storage, the knowledge point slices are converted into three-dimensional sounds, characters and pictures from the original two-dimensional sounds and characters, so that the application scene of the voice recognition technology is continuously expanded, the cost of the technology application is reduced, and the flexibility of the technology application is ensured;

when a student needs to learn the teaching contents explained by a teacher in a classroom, the two ends of the handle 703 slide in the inner cavity of the clamping groove 702 by pulling the handle 703, the position of the handle 703 is conveniently limited by the limiting groove 704 and the limiting block 705, so that the handle 703 can stably pull the shell 1, the teaching machine can be conveniently driven to move, the support gasket 6 is convenient for the teaching machine to stably stand on a horizontal table, so that the learning is more convenient, by turning on the learning button, the control processing module 806, the display module 801, the storage module 802, the facial expression recognition and analysis module 803, the voice recognition module 804 and the voice segmentation module 805 are convenient for inputting the classroom teaching contents that the student wants to learn on the display screen 202, so that the loudspeaker 3 is matched with the display screen 202, the teaching contents explained by the corresponding classroom teacher can be displayed, and the out-of-class learning of the student is more convenient.

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.