CN110675877A

CN110675877A - Speech recognition sensor and speech control system in intelligent toy system

Info

Publication number: CN110675877A
Application number: CN201911073272.3A
Authority: CN
Inventors: 王玉成; 王泓瑞
Original assignee: Individual
Current assignee: Individual
Priority date: 2019-11-05
Filing date: 2019-11-05
Publication date: 2020-01-10

Abstract

The invention relates to the technical field of intelligent recognition, in particular to a voice recognition sensor and a voice control system in an intelligent toy system, which comprise: the audio sampling and distinguishing module is used for collecting voice data; the memory is connected with the audio sampling and distinguishing module and is used for storing the voice data transmitted by the audio sampling and distinguishing module and storing the voice data; the reading module is used for calling the voice data stored in the memory and integrating the voice data; and the judging module is used for receiving the voice data integrated by the reading module and performing executive judgment on the received voice data so as to realize different mode switching. The invention has novel design, the arranged judging module can carry out executive judgment aiming at different voice commands so as to realize different mode switching, and a user can creatively design three modes of a high-precision competition mode, an entertainment mode and a standard mode according to the noise and the interference of the site environment.

Description

Speech recognition sensor and speech control system in intelligent toy system

Technical Field

The invention relates to the technical field of intelligent recognition, in particular to a voice recognition sensor and a voice control system in an intelligent toy system. A typical application is as a component in a toy robot suit.

Background

The sensor (english name: transducer/sensor) is a detection device, which can sense the measured information and convert the sensed information into electric signals or other information in required form according to a certain rule to output, so as to meet the requirements of information transmission, processing, storage, display, recording, control and the like.

The sensor features include: miniaturization, digitalization, intellectualization, multifunction, systematization and networking. The method is the first link for realizing automatic detection and automatic control. The existence and development of the sensor enable the object to have the senses of touch, taste, smell and the like, and the object slowly becomes alive. Generally, the sensor is classified into ten categories, i.e., a thermosensitive element, a photosensitive element, a gas-sensitive element, a force-sensitive element, a magnetic-sensitive element, a humidity-sensitive element, a sound-sensitive element, a radiation-sensitive element, a color-sensitive element, and a taste-sensitive element, according to their basic sensing functions.

Disclosure of Invention

The present invention is directed to a voice recognition sensor and a voice control system in an intelligent toy system, so as to solve the problems in the background art.

In order to achieve the purpose, the invention provides the following technical scheme:

a speech recognition sensor in an intelligent toy system, comprising:

the audio sampling and distinguishing module is used for collecting voice data;

the memory is connected with the audio sampling and distinguishing module and is used for storing the voice data transmitted by the audio sampling and distinguishing module and storing the voice data;

the reading module is used for calling the voice data stored in the memory and integrating the voice data;

and the judging module is used for receiving, comparing and reading the voice data integrated by the module and automatically dividing the recognition result into three types, wherein one type is a command for controlling the action of the toy robot, the other type is a command for controlling the voice conversation of the toy robot, and the other type is a register for changing the sensor to realize the switching of three modes. After the judgment and identification are finished, the identification result is converted into a digital signal and is sent to the communication module.

As a further scheme of the invention: the audio sampling identification module comprises an acquisition submodule and an identification submodule, wherein the acquisition submodule is used for acquiring voice data, and the identification submodule is used for directionally identifying audio.

As a further scheme of the invention: and the memory is connected with an external socket for connecting the data line to reload the entries in the audio identification process.

A voice control system comprises the voice recognition sensor in the intelligent toy system.

As a further scheme of the invention: the voice control system further includes:

the sending module is connected with the voice recognition sensor in the intelligent toy system and used for sending the voice instruction collected in the voice recognition sensor in the intelligent toy system;

the detection module is used for detecting the voice command sent by the sending module, detecting the communication completion condition, then switching the baud rate and sending the voice command in a format approved by the execution module;

and the execution module is used for executing the voice instruction sent by the detection module.

Compared with the prior art, the invention has the beneficial effects that: the invention has novel design, the arranged judging module can carry out executive judgment aiming at different voice commands so as to realize different mode switching, and a user can creatively design three modes of a high-precision competition mode, an entertainment mode and a standard mode according to the noise and the interference of the site environment. In order to improve the reliability and the long-time connection stability of the sensor, the invention is additionally provided with an identification self-check restart module and a communication self-check restart module.

Drawings

Fig. 1 is a block diagram of a voice recognition sensor in an intelligent toy system.

Fig. 2 is a block diagram of a voice control system.

In the figure: 100-audio sampling identification module, 101-memory, 102-reading module, 103-judging module, 200-voice recognition sensor in intelligent toy system, 201-executing module, 202-detecting module, 203-sending 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.

Referring to fig. 1, in an embodiment of the present invention, a speech recognition sensor in an intelligent toy system includes:

an audio sampling discrimination module 100 for collecting voice data;

the memory 101 is connected with the audio sampling identification module 100 and is used for storing the voice data transmitted by the audio sampling identification module 100 and storing the voice data;

the reading module 102 is configured to call the voice data stored in the memory 101 and integrate the voice data;

and the judging module 103 is used for receiving, comparing and reading the voice data integrated by the module, automatically dividing the recognition result into three types, namely a command for controlling the action of the toy robot, a command for controlling the voice conversation of the toy robot, a register for changing the sensor to realize the switching of the three modes, and converting the recognition result into a digital signal and sending the digital signal to the communication module after the judgment and the recognition are finished.

In the embodiment of the invention, the communication module is a bridge for the sensor to communicate with the toy robot host. The invention supports the UART protocol, IIC protocol, SPI protocol, classic Bluetooth (spp protocol) and BLE Bluetooth five protocols, the section is explained by typical UART protocol, the IIC and SPI protocols, classic Bluetooth and BLE Bluetooth principles are the same and are not repeated. The UART protocol and the program communication process in the sensor are described as follows, firstly, the connection is established with the toy robot system by adopting the baud rate of 2400bit/s, and then a data channel is established with the toy robot system by adopting the baud rate of 57600bit/s to carry out the data transmission of the voice recognition result. Two baud rates are supported to transfer information, one is the aforementioned 57600bit/s, and the other is 460800 bit/s. That is, the highest data transmission rate when the UART protocol is adopted in the invention is 460800 bit/s. The communication head code sending content comprises the following items, namely the type ID of the sensor, the data communication rate, the English name of the sensor communication mode, and the data format of the communication packet comprises the number of data sets, the communication data type, the communication data digit and the decimal point digit. After the communication head code is recognized by the toy robot set, the host computer sends a confirmation command. And after the sensor receives the confirmation command, switching the baud rate. And transmitting the communication data packet according to the fourth format in the head code. The communication packet has 4 bytes, the first byte is a head code, the second and third bytes are data bits for sending digital commands (the identification result in the judgment module is converted into 16-system numbers), and the fourth byte is a check bit (for checking whether the data transmission process is correct and complete, so as to prevent sending error communication codes). All communication data, whether the communication data is a command or the communication data, are checked, and the method is that all the communication data and 0xFF are subjected to XOR check to generate check bits. Thereby ensuring the integrity and accuracy of data transfer.

In the embodiment of the invention, the voice recognition sensor in the intelligent toy system further comprises a self-checking restarting module, the sensor can check the state of the internal register before voice recognition every time, and if the self-checking finds that the abnormal state cannot be correctly recognized, the self-checking restarting module can be automatically restarted. Recalibrating the various states ensures that the sensor can be normally identified.

The toy robot suit host machine is characterized by further comprising a communication self-checking module, wherein the communication self-checking module is set optimally and is used for preventing the sensor from being disconnected from the toy robot suit host machine in communication, which is a very special accidental state, and the abnormal situation occurs with a certain probability when the sensor is continuously connected with the host machine for more than 1 hour and the electric quantity of the host machine is lower than 30 percent through detection. While this problem can be eliminated by unplugging the sensor and reconnecting it, the experience presented to the user is not user friendly. Although the voice recognition function is normal in this state, the communication with the host computer is abnormally interrupted, so that the voice recognition function can be recognized and normally transmitted, but the voice recognition function cannot be correctly received and sensed by the host computer. And the communication self-checking module enables the sensor to check the communication state with the host computer every 1000 milliseconds. If the host watchdog command is not received, the host cannot correctly receive the identification result sent by the sensor. Then the sensor will automatically restart the communication module, adjust the communication rate to the initial 2400bit/s, and send the communication header code. After receiving the host confirmation signal, switching to 57600bit/s and sending a communication data packet. The packet format is the same as described above and will not be repeated. This module ensures that the system can quickly return to normal even if occasional exceptions occur.

As an embodiment of the present invention, the audio sampling identification module 100 includes an acquisition sub-module and an identification sub-module, where the acquisition sub-module is configured to acquire voice data, and the identification sub-module is configured to perform directional identification on audio, and it is simply understood that the identification sub-module may perform comparison between the recorded audio and the newly acquired audio, and eliminate interfering audio to perform directional control.

In the embodiment of the invention, the acquisition submodule is mainly used for acquiring the terms in the audio, the acquisition of the terms depends on the recognition of pinyin, for example, if the 'late' pronunciation of the Shanghai is 'ya', the 'late newspaper' is marked as 'wanbao' by the mandarin, and if the 'ya bao' is marked as the pronunciation of the Shanghai, the 'ya bao' is recognized, so that the 'ya bao' late newspaper of the Shanghai can be recognized by setting the 'ya bao' in the terms. Similarly, the English version is also marked by the Pinyin, the upper part of Chinese in English is up-a pu Chinese, and the lower part of Chinese in English is down- "Pinyin dang.

As an embodiment of the present invention, an external socket is connected to the memory 101 for reloading the entry in the audio recognition process.

In the embodiment of the invention, the memory 101 adopts a patch FT245BL single FIFO memory, and the FIFO is the abbreviation of First in/First-Out and means First-in First-Out. The FIFO memory is divided into a write-only area and a read-only area. The read operation and the write operation can be performed asynchronously, and the data written on the write area is read from the area at the read end in the order of writing, similar to a buffer that absorbs the speed difference between the write end and the read end.

Referring to fig. 2, a voice control system according to an embodiment of the present invention includes a voice recognition sensor 200 in the intelligent toy system according to the above embodiment.

As an embodiment of the present invention, the voice control system further includes:

the sending module 203 is connected with the voice recognition sensor 200 in the intelligent toy system and is used for sending the voice instruction collected in the voice recognition sensor 200 in the intelligent toy system;

the detection module 202 is used for detecting the voice command sent by the sending module 203, detecting the communication completion condition, then switching the baud rate, and sending the voice command in a format approved by the execution module;

and the execution module 201 is configured to execute the voice instruction sent by the detection module 202.

In the embodiment of the invention, the device is specially used for receiving the 16-system character string sent by the sensor through the serial port protocol, and outputting the complex 16-system character string in a simple digital mode, so that students can conveniently use numbers to program.

It should be noted that the set judgment module can perform executive judgment for different voice commands, so as to realize different mode switching, and all parameters of a general voice recognition product are completely solidified before leaving a factory, including the recognition accuracy and the optimal recognition distance of the microphone. The invention takes the three modes as voice commands to the sensor, and new codes can be written into the internal register for the second time after the sensor is identified, thereby realizing the free switching of three modes of 'high-precision competition mode', 'entertainment mode' and 'standard mode' creatively designed by users according to the noise and the interference of the site environment.

The intelligent robot suit toy system does not have a voice recognition sensor in the intelligent toy system at present, and a matched sensor in the existing toy robot suit has a touch sensor, a color sensor, a gyroscope sensor, an ultrasonic sensor, an infrared sensor and an image recognition sensor, so that the sensor belongs to the initiative in the subdivision field of the toy robot suit. The robot suit of a crowd of followers such as domestic ability storm, middle singing and the like also does not have a voice recognition sensor in the intelligent toy system.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.

Claims

1. A voice recognition sensor in an intelligent toy system, comprising:

the audio sampling and distinguishing module is used for collecting voice data;

and the judging module is used for receiving the voice data integrated by the reading module and performing executive judgment on the received voice data so as to realize different mode switching.

2. The voice recognition sensor of claim 1, wherein the audio sampling identification module comprises an acquisition sub-module and an identification sub-module, wherein the acquisition sub-module is used for acquiring voice data, and the identification sub-module is used for performing directional identification on audio.

3. The speech recognition sensor of claim 1, wherein the memory is connected to an external jack for connecting a data line to reload entries during audio recognition.

4. A speech control system comprising a speech recognition sensor in an intelligent toy system as claimed in any one of claims 1-3.

5. The voice control system of claim 4, further comprising: