CN112331205A - STM 32-based intelligent speech recognition system and method - Google Patents
STM 32-based intelligent speech recognition system and method Download PDFInfo
- Publication number
- CN112331205A CN112331205A CN202110015896.0A CN202110015896A CN112331205A CN 112331205 A CN112331205 A CN 112331205A CN 202110015896 A CN202110015896 A CN 202110015896A CN 112331205 A CN112331205 A CN 112331205A
- Authority
- CN
- China
- Prior art keywords
- user
- voice
- unit
- voice recognition
- recognition circuit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004891 communication Methods 0.000 claims abstract description 34
- 238000006243 chemical reaction Methods 0.000 claims description 67
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- 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)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an intelligent voice recognition system and method based on STM32, belonging to the technical field of voice recognition, wherein the intelligent voice recognition system comprises a user side, a communication module, a voice recognition module and a control side; the user side utilizes and establishes remote communication between communication module and the control end, the user side inputs and changes user's speech signal and passes through communication module transmission to the control end, the speech recognition module discerns the remote speech signal that the control end received, the speech recognition module sends the long-range speech recognition result to the control end, the control end is opened or is closed according to the recognition result control relay, through long-range speech recognition function, makes when the user is not at home, can the remote control open the door for the courier can directly place the express delivery at the gate of being at after the long-range speech control of user opens the door, has practiced thrift courier's time, simultaneously, has add sound wave frequency identification for remote speech recognition's safety more.
Description
Technical Field
The invention relates to the technical field of speech recognition, in particular to an intelligent speech recognition system and method based on STM 32.
Background
The voice recognition means voice communication with a machine, the machine recognizes the content of the speaking of people and executes corresponding operation according to the content of the speaking, the voice recognition technology has made remarkable progress in the last two decades, and the development of the voice recognition technology starts to move from a laboratory to the market, so that the life style of people is changed, and the life of people is more convenient;
however, existing speech recognition technologies often only can recognize speech directly uttered by people, for example: the door is opened through voice control, however, when a user has express delivery to the door, the door cannot be opened through remote control because the user is not at home, and then a courier cannot sign for the express, and the courier needs to sign for the express again with the courier business time, so that the time of the courier is wasted, and meanwhile, the great invariance is brought to the user;
therefore, if the door can be opened through remote control, a courier can place the express at a door to sign for the express, and the express is convenient to sign, so that people urgently need an intelligent voice recognition system and method based on STM32 to solve the problems.
Disclosure of Invention
The invention aims to provide an intelligent speech recognition system and method based on STM32 to solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: an intelligent speech recognition system based on STM32 comprises a user terminal, a communication module, a speech recognition module and a control terminal;
the user side establishes remote communication with the control end by using the communication module, voice signals input and converted by the user are transmitted to the control end through the communication module, the voice recognition module recognizes the remote voice signals received by the control end, the voice recognition module sends recognition results of the remote voice to the control end, and the control end controls the relay to be opened or closed according to the recognition results;
the user side comprises a voice recording unit, a voice conversion unit, a frequency conversion unit and a position positioning unit;
the voice recording unit is used for recording voice signals of a user, the frequency conversion unit is used for converting sound wave frequency of the recorded voice signals, so that the voice signals of the user are prevented from being maliciously recorded by others to perform remote voice recognition door opening, the safety of remote voice recognition is guaranteed, the voice conversion unit is used for converting the voice signals after the sound wave frequency conversion into electric signals, the communication module is conveniently used for performing remote transmission, the position positioning unit is used for positioning the current position of the user, and whether the door opening is controlled by using the remote voice signal recognition or not is conveniently judged;
the output end of the frequency conversion unit is electrically connected with the input end of the voice recording unit, and the output end of the voice recording unit is electrically connected with the input end of the voice conversion unit;
the voice recognition module comprises a first voice recognition circuit, a second voice recognition circuit and a recognition circuit conversion unit;
the first voice recognition circuit is used for recognizing remote voice signals of a user, the second voice recognition circuit is used for recognizing close-range voice signals of the user, the recognition circuit conversion unit is used for converting the use of the first voice recognition circuit and the second voice recognition circuit, and only one voice recognition circuit can be used for recognizing the voice signals, so that different voice recognition circuits can be converted to recognize the voice signals according to different positions of the user, the voice signals of the user are prevented from being illegally recorded by other people, when the user is in a remote state, the second voice recognition circuit is used for recognizing the voice signals to open the door, and the safety of opening the door by the voice recognition of the user is guaranteed.
According to the technical scheme, the voice recognition module further comprises a user position analysis unit;
the user position analysis unit is used for analyzing the current position of the user, determining the intention of the user and judging whether the voice recognition circuit conversion is needed by the recognition circuit conversion unit;
the voice conversion unit is connected with the first voice recognition circuit through the communication module, the output end of the position positioning unit is electrically connected with the input end of the user position analysis unit, the output end of the user position analysis unit is electrically connected with the input end of the recognition circuit conversion unit, and the output end of the recognition circuit conversion unit is electrically connected with the input ends of the first voice recognition circuit and the second voice recognition circuit.
According to the technical scheme, the control end comprises an STM32 control unit, a voice playing unit, a code scanning identification unit and a monitoring recording unit;
the STM32 control unit is used for intelligently controlling the whole system, the voice playing unit is used for playing audio to remind a courier to execute corresponding operation according to audio indication, the code scanning recognition unit is used for scanning and recognizing an express delivery code sent by the courier to enter the door, thereby preventing others from pretending that the courier requests a user to remotely perform voice recognition door opening, ensuring the safety of the user in opening the door by utilizing remote voice recognition, and the monitoring and recording unit is used for monitoring and recording the operation of the courier at the door, so that the responsibility can be conveniently discussed when the express is lost;
the equal electric connection STM32 the input of output of first speech recognition circuit and second speech recognition circuit, the output electric connection voice play unit of STM32 the control unit, arrest the input that can recording element and relay, sweep the input of code recognition unit's output electric connection STM32 the control unit.
According to the technical scheme, the system also comprises a logistics information base and a data calling module;
the system comprises a logistics information base, an STM32 control unit, a code scanning identification unit, a data calling module and a remote voice recognition door opening module, wherein the logistics information base is used for storing logistics information of commodities purchased by a user on line, the data calling module is used for calling logistics information data in the logistics information base, the STM32 control unit compares the logistics information called by the data calling module with express codes identified by the code scanning identification unit and judges whether the commodities are purchased on line by the user, so that a person requesting the user to remotely recognize the door opening by voice is a real courier instead of a lawbreaker, the safety performance of remote voice recognition door opening is ensured, and the privacy and property safety of the user are;
the input of the output electric connection data of STM32 the control unit, the input of the output electric connection logistics information storehouse of data retrieval module, the input of the output electric connection STM32 the control unit of logistics information storehouse.
An intelligent speech recognition method based on STM32, comprising the following steps:
s1, analyzing the user position and converting the voice recognition circuit;
s2, communication is established between the user side and the control side, and the system is awakened;
s3, the user side sends voice data to the control side, and the voice recognition module recognizes the voice data;
s4, the control end calls logistics information from the logistics information base;
s5, the control end reminds the courier of scanning express delivery bar codes through voice;
s6, the control end matches the bar code scanning content and selects whether to open the door;
in S1, the current location of the user is located by the location locating unit, a two-dimensional model of the area of the user is created by the user location analyzing unit, and a rectangular coordinate system is created with the address location of the user as the center of the circle, where the current location of the user is located by the location locating unit as (X)i，Yi) The distance L between the current position of the user and the address thereof is calculated according to the following formulaiAnd (3) calculating:
when L isiWhen the distance between the user and the address is larger than or equal to L, the user is far away from the address, the door opening operation can be performed only in a remote voice recognition mode, and the recognition circuit conversion unit is used for converting the first voice recognition circuit to recognize the remote voice signal of the user;
when L isiIf < L, the user is close to the address, but not necessarily returns to home, so the destination of the user needs to be analyzed;
where L represents a set distance threshold.
The distance calculation between the current position of the user and the address is realized through the formula, and whether the voice recognition circuit which can be used by the user is the first voice recognition circuit or the second voice recognition circuit is preliminarily judged, so that the system can preliminarily judge whether the voice recognition circuit needs to be converted.
According to the technical scheme, in S1, the position of the user is continuously refreshed by using the position locating unit, and a set Q = { (X) of the position coordinates of the user is formed1，Y1），（X2，Y2），（X3，Y3），…，（Xn，Yn）}；
Vector formed by two adjacent refreshing positions according to the following formula
And (3) calculating:
a vector formed by the current position and the position of the user address according to the following formula
And (3) calculating:
vector pair according to the following formula
And vector
Cosine value of (1)
And (3) calculating:
set P = tone constituting cosine value
}；
When there is in the set P
Cosine value of
If so, indicating that the destination of the user is an address, the identification circuit conversion unit converts the second voice identification circuit into a voice identification circuit;
when there are less than
Cosine value of
And a recognition circuit converting unit converting the first voice recognition circuit into a voice recognition circuit, wherein z represents a set duty threshold value and g represents a set angle threshold value.
Through the formula, the prediction of the walking target point of the user can be realized, so that whether the first voice recognition circuit needs to be converted into the second voice recognition circuit in time or not is determined, and the user can use the intelligent voice recognition system more conveniently.
According to the technical scheme, in S2-S3, the user side establishes communication with the control end through the communication module and wakes up the system, the user side records the remote voice signals of the user through the voice recording unit, and the user side converts the frequency of the recorded remote voice signals according to the following formula by using the frequency conversion unit;
wherein, W represents the frequency value after the frequency conversion of the remote voice signal of the user, k represents the coefficient of the conversion, and S represents the original frequency of the remote voice signal of the user;
the frequency conversion unit sends the coefficient k of the frequency conversion to a first voice recognition circuit through a communication module;
the frequency of the user remote voice signal is uniformly changed, so that the safety of voice recognition is improved, and the condition that other people illegally record the user voice to request for remote voice recognition to open a door is avoided;
after the user carries out long-range speech recognition request through a speech recognition circuit and opens the door, utilize the control recording unit to carry out real time monitoring and record, the later stage of being convenient for chases after when the express delivery is lost.
According to the technical scheme, in S4-S5, after a user utilizes a first circuit identification circuit of remote voice identification to identify a door opening voice signal, the control end utilizes a voice playing unit to remind a courier of aligning a courier code of courier to a code scanning identification unit to scan the courier code, and the code scanning identification unit identifies the content of the courier code;
and the control terminal calls the logistics information of the user from the logistics information base by using the data calling unit.
According to the technical scheme, in S6, the STM32 control unit is used for matching the content of the express delivery code with the logistics information of the user called from the logistics information base by the data calling unit;
when the matched logistics information contents are completely consistent, the STM32 control unit controls the relay to be opened, so that the door opening is realized;
when the matched logistics information contents are inconsistent, the fact that the person requesting the user to remotely open the door is not a courier is indicated, the STM32 control unit controls the voice playing unit to play an alarm sound to scare away illegal persons requesting the user to remotely recognize the door by voice.
Through the retrieval and comparison of the data, the authenticity of the identity of the courier is determined, so that the situation that a lawbreaker pretends to be an express delivery person requesting a user to open a door for theft through remote voice recognition can be effectively avoided, and the use safety of the voice recognition system is further ensured.
Compared with the prior art, the invention has the beneficial effects that:
1. through long-range speech recognition function, make when the user is not at, can the remote control open the door, make the courier can directly place the express delivery at the gate of being at after the long-range speech control of user opens the door, courier's time has been practiced thrift, and simultaneously, sound wave frequency identification has been add to long-range speech recognition function, on the one hand, it compares to open the door with long-range remote control, factor of safety is higher, the phenomenon of stealing because the remote control loses the phenomenon that leads to, on the other hand, through the in-process at long-range speech recognition conversion user's sound wave frequency, make long-range speech recognition safer, it records user's speech information and opens the door to have avoided other people to steal, great improvement long-range speech.
2. Through the code scanning identification and matching of the express delivery of the user, the authenticity of the door opening request of the courier can be further judged, malicious camouflage of lawbreakers is avoided, and the phenomenon of property loss caused by the remote voice identification of the user is requested to open the door.
3. Set up first speech recognition circuit and second speech recognition circuit, through analysis user's position, carry out identification circuit's conversion, further avoided lawless persons maliciously to record user's speech information and carry out direct speech recognition rather than long-range speech recognition request and open the door, make when the user is far away from the address, will unable use second speech recognition circuit to carry out speech recognition, simultaneously, make user self more convenient to intelligent speech recognition system's use.
Drawings
FIG. 1 is a schematic diagram of a module connection structure of an intelligent speech recognition system based on STM 32;
FIG. 2 is a schematic diagram of a module composition structure of an intelligent speech recognition system based on STM 32;
FIG. 3 is a schematic diagram of a unit connection structure of an intelligent speech recognition system based on STM 32;
fig. 4 is a schematic flow chart of steps of an intelligent speech recognition method based on STM32 according to the present invention.
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.
As shown in fig. 1 to 4, an intelligent speech recognition system based on STM32 includes a user terminal, a communication module, a speech recognition module, and a control terminal;
the user side establishes remote communication with the control end by using the communication module, voice signals input and converted by the user are transmitted to the control end through the communication module, the voice recognition module recognizes the remote voice signals received by the control end, the voice recognition module sends recognition results of the remote voice to the control end, and the control end controls the relay to be opened or closed according to the recognition results;
the user side comprises a voice recording unit, a voice conversion unit, a frequency conversion unit and a position positioning unit;
the voice recording unit is used for recording voice signals of a user, the frequency conversion unit is used for converting sound wave frequency of the recorded voice signals, so that the voice signals of the user are prevented from being maliciously recorded by others to perform remote voice recognition door opening, the safety of remote voice recognition is guaranteed, the voice conversion unit is used for converting the voice signals after the sound wave frequency conversion into electric signals, the communication module is conveniently used for performing remote transmission, the position positioning unit is used for positioning the current position of the user, and whether the door opening is controlled by using the remote voice signal recognition or not is conveniently judged;
the output end of the frequency conversion unit is electrically connected with the input end of the voice recording unit, and the output end of the voice recording unit is electrically connected with the input end of the voice conversion unit;
the voice recognition module comprises a first voice recognition circuit, a second voice recognition circuit and a recognition circuit conversion unit;
the first voice recognition circuit is used for recognizing remote voice signals of a user, the second voice recognition circuit is used for recognizing close-range voice signals of the user, the recognition circuit conversion unit is used for converting the use of the first voice recognition circuit and the second voice recognition circuit, and only one voice recognition circuit can be used for recognizing the voice signals, so that different voice recognition circuits can be converted to recognize the voice signals according to different positions of the user, the voice signals of the user are prevented from being illegally recorded by other people, when the user is in a remote state, the second voice recognition circuit is used for recognizing the voice signals to open the door, and the safety of opening the door by the voice recognition of the user is guaranteed.
The voice recognition module further comprises a user position analysis unit;
the user position analysis unit is used for analyzing the current position of the user, determining the intention of the user and judging whether the voice recognition circuit conversion is needed by the recognition circuit conversion unit;
the voice conversion unit is connected with the first voice recognition circuit through the communication module, the output end of the position positioning unit is electrically connected with the input end of the user position analysis unit, the output end of the user position analysis unit is electrically connected with the input end of the recognition circuit conversion unit, and the output end of the recognition circuit conversion unit is electrically connected with the input ends of the first voice recognition circuit and the second voice recognition circuit.
The control end comprises an STM32 control unit, a voice playing unit, a code scanning identification unit and a monitoring recording unit;
the STM32 control unit is used for intelligently controlling the whole system, the voice playing unit is used for playing audio to remind a courier to execute corresponding operation according to audio indication, the code scanning recognition unit is used for scanning and recognizing an express delivery code sent by the courier to enter the door, thereby preventing others from pretending that the courier requests a user to remotely perform voice recognition door opening, ensuring the safety of the user in opening the door by utilizing remote voice recognition, and the monitoring and recording unit is used for monitoring and recording the operation of the courier at the door, so that the responsibility can be conveniently discussed when the express is lost;
the equal electric connection STM32 the input of output of first speech recognition circuit and second speech recognition circuit, the output electric connection voice play unit of STM32 the control unit, arrest the input that can recording element and relay, sweep the input of code recognition unit's output electric connection STM32 the control unit.
The system also comprises a logistics information base and a data calling module;
the system comprises a logistics information base, an STM32 control unit, a code scanning identification unit, a data calling module and a remote voice recognition door opening module, wherein the logistics information base is used for storing logistics information of commodities purchased by a user on line, the data calling module is used for calling logistics information data in the logistics information base, the STM32 control unit compares the logistics information called by the data calling module with express codes identified by the code scanning identification unit and judges whether the commodities are purchased on line by the user, so that a person requesting the user to remotely recognize the door opening by voice is a real courier instead of a lawbreaker, the safety performance of remote voice recognition door opening is ensured, and the privacy and property safety of the user are;
the input of the output electric connection data of STM32 the control unit, the input of the output electric connection logistics information storehouse of data retrieval module, the input of the output electric connection STM32 the control unit of logistics information storehouse.
An intelligent speech recognition method based on STM32, comprising the following steps:
s1, analyzing the user position and converting the voice recognition circuit;
s2, communication is established between the user side and the control side, and the system is awakened;
s3, the user side sends voice data to the control side, and the voice recognition module recognizes the voice data;
s4, the control end calls logistics information from the logistics information base;
s5, the control end reminds the courier of scanning express delivery bar codes through voice;
s6, the control end matches the bar code scanning content and selects whether to open the door;
in S1, the current location of the user is located by the location locating unit, a two-dimensional model of the area of the user is created by the user location analyzing unit, and a rectangular coordinate system is created with the address location of the user as the center of the circle, where the current location of the user is located by the location locating unit as (X)i，Yi) The distance L between the current position of the user and the address thereof is calculated according to the following formulaiAnd (3) calculating:
when L isiWhen the distance between the user and the address is larger than or equal to L, the user is far away from the address, the door opening operation can be performed only in a remote voice recognition mode, and the recognition circuit conversion unit is used for converting the first voice recognition circuit to recognize the remote voice signal of the user;
when L isiIf < L, the user is close to the address, but not necessarily returns to home, so the destination of the user needs to be analyzed;
where L represents a set distance threshold.
The distance calculation between the current position of the user and the address is realized through the formula, and whether the voice recognition circuit which can be used by the user is the first voice recognition circuit or the second voice recognition circuit is preliminarily judged, so that the system can preliminarily judge whether the voice recognition circuit needs to be converted.
In S1, the location of the user is continuously refreshed by the location positioning unit, forming a set of user location coordinates Q = { (X)1，Y1），（X2，Y2），（X3，Y3），…，（Xn，Yn）}；
According to the following formulaVector formed by two adjacent refresh positions
And (3) calculating:
a vector formed by the current position and the position of the user address according to the following formula
And (3) calculating:
vector pair according to the following formula
And vector
Cosine value of (1)
And (3) calculating:
set P = tone constituting cosine value
}；
When there is in the set P
Cosine value of
When it is indicated that the destination of the user is an addressThe recognition circuit conversion unit converts the second voice recognition circuit into a voice recognition circuit;
when there are less than
Cosine value of
And a recognition circuit converting unit converting the first voice recognition circuit into a voice recognition circuit, wherein z represents a set duty threshold value and g represents a set angle threshold value.
Through the formula, the prediction of the walking target point of the user can be realized, so that whether the first voice recognition circuit needs to be converted into the second voice recognition circuit in time or not is determined, and the user can use the intelligent voice recognition system more conveniently.
In S2-S3, the user side establishes communication with the control side through the communication module and wakes up the system, the user side records a remote voice signal of the user through the voice recording unit, and the user side converts the frequency of the recorded remote voice signal according to the following formula by using the frequency conversion unit;
wherein, W represents the frequency value after the frequency conversion of the remote voice signal of the user, k represents the coefficient of the conversion, and S represents the original frequency of the remote voice signal of the user;
the frequency conversion unit sends the coefficient k of the frequency conversion to a first voice recognition circuit through a communication module;
the frequency of the user remote voice signal is uniformly changed, so that the safety of voice recognition is improved, and the condition that other people illegally record the user voice to request for remote voice recognition to open a door is avoided;
after the user carries out long-range speech recognition request through a speech recognition circuit and opens the door, utilize the control recording unit to carry out real time monitoring and record, the later stage of being convenient for chases after when the express delivery is lost.
In S4-S5, after the user identifies the voice signal of the side-by-side door by using the first circuit identification circuit of remote voice identification, the control end uses the voice playing unit to remind the courier to align the express code of the express to the code scanning identification unit for scanning the express code, and the code scanning identification unit identifies the content of the express code;
and the control terminal calls the logistics information of the user from the logistics information base by using the data calling unit.
In S6, matching the content of the express delivery code with logistics information of a user called from a logistics information base by the data calling unit through the STM32 control unit to the code scanning identification unit;
when the matched logistics information contents are completely consistent, the STM32 control unit controls the relay to be opened, so that the door opening is realized;
when the matched logistics information contents are inconsistent, the fact that the person requesting the user to remotely open the door is not a courier is indicated, the STM32 control unit controls the voice playing unit to play an alarm sound to scare away illegal persons requesting the user to remotely recognize the door by voice.
Through the retrieval and comparison of the data, the authenticity of the identity of the courier is determined, so that the situation that a lawbreaker pretends to be an express delivery person requesting a user to open a door for theft through remote voice recognition can be effectively avoided, and the use safety of the voice recognition system is further ensured.
The first embodiment is as follows:
the method comprises the steps of utilizing a position positioning unit to position the current position of a user, utilizing a user position analysis unit to establish a planar two-dimensional model of the area where the user is located, utilizing the address position of the user as the center of a circle to establish a planar rectangular coordinate system, wherein the current position of the user located by the position positioning unit is (12, 6), and carrying out positioning on the distance L between the current position of the user and the address according to the following formulaiAnd (3) calculating:
Lil =13.416 ≧ L =1, which indicates that the user is far from the address, the door opening operation can be performed only by remote speech recognition, and the recognition circuit conversion unit is used to convert the first speech recognition circuit to recognize the remote speech signal of the user;
where L =1km indicates a set distance threshold.
Example two:
the method comprises the steps of utilizing a position positioning unit to position the current position of a user, utilizing a user position analysis unit to establish a planar two-dimensional model of the area where the user is located, utilizing the user address position as the center of a circle to establish a planar rectangular coordinate system, wherein the coordinates of the current position of the user, positioned by the position positioning unit, are (0.5, 0.25), and carrying out positioning on the distance L between the current position of the user and the address of the user according to the following formulaiAnd (3) calculating:
Liwhen =0.559 < L =1, it indicates that the user is close to the address, but does not necessarily return to home, and therefore, the destination of the user needs to be analyzed;
where L =1km indicates a set distance threshold.
Continuously refreshing the position of the user by using the position positioning unit to form a set Q = { (0.45, 0.22), (0.41, 0.2), (0.35, 0.15), (0.32, 0.13), (0.3, 0.12) } of user position coordinates;
vector formed by two adjacent refreshing positions according to the following formula
And (3) calculating:
a vector formed by the current position and the position of the user address according to the following formula
And (3) calculating:
vector pair according to the following formula
And vector
Cosine value of (1)
And (3) calculating:
set P = tone constituting cosine value
}；
All cosine values in set P
And the identification circuit conversion unit converts the second voice identification circuit into a voice identification circuit, indicating that the destination of the user is an address.
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.
Claims (9)
1. An intelligent speech recognition system based on STM32, its characterized in that: the intelligent voice recognition system comprises a user side, a communication module, a voice recognition module and a control side;
the user side establishes remote communication with the control end by using the communication module, voice signals input and converted by the user are transmitted to the control end through the communication module, the voice recognition module recognizes the remote voice signals received by the control end, the voice recognition module sends recognition results of the remote voice to the control end, and the control end controls the relay to be opened or closed according to the recognition results;
the user side comprises a voice recording unit, a voice conversion unit, a frequency conversion unit and a position positioning unit;
the voice recording unit is used for recording voice signals of a user, the frequency conversion unit is used for converting sound wave frequency of the recorded voice signals, the voice conversion unit is used for converting the voice signals after the sound wave frequency is converted into electric signals, and the position positioning unit is used for positioning the current position of the user;
the output end of the frequency conversion unit is electrically connected with the input end of the voice recording unit, and the output end of the voice recording unit is electrically connected with the input end of the voice conversion unit;
the voice recognition module comprises a first voice recognition circuit, a second voice recognition circuit and a recognition circuit conversion unit;
the voice recognition device comprises a first voice recognition circuit, a second voice recognition circuit, a recognition circuit conversion unit and a voice recognition circuit, wherein the first voice recognition circuit is used for recognizing a remote voice signal of a user, the second voice recognition circuit is used for recognizing a close-range voice signal of the user, the recognition circuit conversion unit is used for converting the use of the first voice recognition circuit and the second voice recognition circuit, and only one voice recognition circuit can be used for recognizing the voice signal.
2. An intelligent STM 32-based speech recognition system according to claim 1, wherein: the voice recognition module further comprises a user position analysis unit;
the user position analysis unit is used for analyzing the current position of the user, determining the intention of the user and judging whether the voice recognition circuit conversion is needed by the recognition circuit conversion unit;
the voice conversion unit is connected with the first voice recognition circuit through the communication module, the output end of the position positioning unit is electrically connected with the input end of the user position analysis unit, the output end of the user position analysis unit is electrically connected with the input end of the recognition circuit conversion unit, and the output end of the recognition circuit conversion unit is electrically connected with the input ends of the first voice recognition circuit and the second voice recognition circuit.
3. An intelligent STM 32-based speech recognition system according to claim 2, wherein: the control end comprises an STM32 control unit, a voice playing unit, a code scanning identification unit and a monitoring recording unit;
the STM32 control unit is used for intelligently controlling the whole system, the voice playing unit is used for playing audio to remind a courier to execute corresponding operation according to audio indication, the code scanning identification unit is used for scanning and identifying express codes delivered to a door by the courier, and the monitoring recording unit is used for monitoring and recording the operation of the courier at the door, so that responsibility can be conveniently discussed when the express is lost;
the equal electric connection STM32 the input of output of first speech recognition circuit and second speech recognition circuit, the output electric connection voice play unit of STM32 the control unit, arrest the input that can recording element and relay, sweep the input of code recognition unit's output electric connection STM32 the control unit.
4. An intelligent STM 32-based speech recognition system according to claim 3, wherein: the system also comprises a logistics information base and a data calling module;
the system comprises a logistics information base, a data calling module, an STM32 control unit and a code scanning identification unit, wherein the logistics information base is used for storing logistics information of commodities purchased on line by a user, the data calling module is used for calling logistics information data in the logistics information base, the STM32 control unit compares the logistics information called by the data calling module with express codes identified by the code scanning identification unit and judges whether the commodities are purchased on line by the user;
the input of the output electric connection data of STM32 the control unit, the input of the output electric connection logistics information storehouse of data retrieval module, the input of the output electric connection STM32 the control unit of logistics information storehouse.
5. An intelligent speech recognition method based on STM32 is characterized in that: the intelligent voice recognition method comprises the following steps:
s1, analyzing the user position and converting the voice recognition circuit;
s2, communication is established between the user side and the control side, and the system is awakened;
s3, the user side sends voice data to the control side, and the voice recognition module recognizes the voice data;
s4, the control end calls logistics information from the logistics information base;
s5, the control end reminds the courier of scanning express delivery bar codes through voice;
s6, the control end matches the bar code scanning content and selects whether to open the door;
in S1, the current location of the user is located by the location locating unit, a two-dimensional model of the area of the user is created by the user location analyzing unit, and a rectangular coordinate system is created with the address location of the user as the center of the circle, where the current location of the user is located by the location locating unit as (X)i，Yi) The distance L between the current position of the user and the address thereof is calculated according to the following formulaiAnd (3) calculating:
when L isiWhen the distance between the user and the address is larger than or equal to L, the user is far away from the address, the door opening operation can be performed only in a remote voice recognition mode, and the recognition circuit conversion unit is used for converting the first voice recognition circuit to recognize the remote voice signal of the user;
when L isiIf < L, the user is close to the address, but not necessarily returns to home, so the destination of the user needs to be analyzed;
where L represents a set distance threshold.
6. An intelligent speech recognition method based on STM32 according to claim 5, wherein: in S1, the location of the user is continuously refreshed by the location positioning unit, forming a set of user location coordinates Q = { (X)1，Y1），（X2，Y2），（X3，Y3），…，（Xn，Yn）}；
Vector formed by two adjacent refreshing positions according to the following formula
And (3) calculating:
a vector formed by the current position and the position of the user address according to the following formula
And (3) calculating:
vector pair according to the following formula
And vector
Cosine value of (1)
And (3) calculating:
set P = tone constituting cosine value
}；
When there is in the set P
Cosine value of
If so, indicating that the destination of the user is an address, the identification circuit conversion unit converts the second voice identification circuit into a voice identification circuit;
when there are less than
Cosine value of
And a recognition circuit converting unit converting the first voice recognition circuit into a voice recognition circuit, wherein z represents a set duty threshold value and g represents a set angle threshold value.
7. An intelligent speech recognition method based on STM32 according to claim 6, wherein: in S2-S3, the user side establishes communication with the control side through the communication module and wakes up the system, the user side records a remote voice signal of the user through the voice recording unit, and the user side converts the frequency of the recorded remote voice signal according to the following formula by using the frequency conversion unit;
wherein, W represents the frequency value after the frequency conversion of the remote voice signal of the user, k represents the coefficient of the conversion, and S represents the original frequency of the remote voice signal of the user;
the frequency conversion unit sends the coefficient k of the frequency conversion to a first voice recognition circuit through a communication module;
and after the user performs remote voice recognition request to open the door through the first voice recognition circuit, real-time monitoring and recording are performed by using the monitoring recording unit.
8. An intelligent speech recognition method based on STM32 according to claim 7, wherein: in S4-S5, after the user identifies the voice signal of the side-by-side door by using the first circuit identification circuit of remote voice identification, the control end uses the voice playing unit to remind the courier to align the express code of the express to the code scanning identification unit for scanning the express code, and the code scanning identification unit identifies the content of the express code;
and the control terminal calls the logistics information of the user from the logistics information base by using the data calling unit.
9. An intelligent speech recognition method based on STM32 according to claim 8, wherein: in S6, matching the content of the express delivery code with logistics information of a user called from a logistics information base by the data calling unit through the STM32 control unit to the code scanning identification unit;
when the matched logistics information contents are completely consistent, the STM32 control unit controls the relay to be opened, so that the door opening is realized;
when the matched logistics information contents are inconsistent, the fact that the person requesting the user to remotely open the door is not a courier is indicated, the STM32 control unit controls the voice playing unit to play an alarm sound to scare away illegal persons requesting the user to remotely recognize the door by voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110015896.0A CN112331205B (en) | 2021-01-07 | 2021-01-07 | STM 32-based intelligent speech recognition system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110015896.0A CN112331205B (en) | 2021-01-07 | 2021-01-07 | STM 32-based intelligent speech recognition system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112331205A true CN112331205A (en) | 2021-02-05 |
| CN112331205B CN112331205B (en) | 2021-04-16 |
Family
ID=74301952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110015896.0A Active CN112331205B (en) | 2021-01-07 | 2021-01-07 | STM 32-based intelligent speech recognition system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112331205B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1296366A (en) * | 1999-11-15 | 2001-05-23 | 朗迅科技公司 | Method and equipment of radio telecommunication system for providing location base activity service |
| CN102427418A (en) * | 2011-12-09 | 2012-04-25 | 福州海景科技开发有限公司 | Intelligent household system based on speech recognition |
| CN107644307A (en) * | 2016-07-21 | 2018-01-30 | 深圳市丰巢科技有限公司 | Intelligence sends part method |
| CN110459019A (en) * | 2019-08-14 | 2019-11-15 | 厦门享取网络科技有限公司 | A kind of take-away rapid access method and its system |
| US10565813B2 (en) * | 2017-07-25 | 2020-02-18 | Amazon Technologies, Inc. | Remote access authentication and authorization |
| CN211900333U (en) * | 2018-08-30 | 2020-11-10 | 钟永林 | Internet monitoring anti-theft door capable of being locked in remote control mode |
| US10862313B2 (en) * | 2011-11-07 | 2020-12-08 | Kortek Industries Pty Ltd | Adaptable wireless power, light and automation system |
-
2021
- 2021-01-07 CN CN202110015896.0A patent/CN112331205B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1296366A (en) * | 1999-11-15 | 2001-05-23 | 朗迅科技公司 | Method and equipment of radio telecommunication system for providing location base activity service |
| US10862313B2 (en) * | 2011-11-07 | 2020-12-08 | Kortek Industries Pty Ltd | Adaptable wireless power, light and automation system |
| CN102427418A (en) * | 2011-12-09 | 2012-04-25 | 福州海景科技开发有限公司 | Intelligent household system based on speech recognition |
| CN107644307A (en) * | 2016-07-21 | 2018-01-30 | 深圳市丰巢科技有限公司 | Intelligence sends part method |
| US10565813B2 (en) * | 2017-07-25 | 2020-02-18 | Amazon Technologies, Inc. | Remote access authentication and authorization |
| CN211900333U (en) * | 2018-08-30 | 2020-11-10 | 钟永林 | Internet monitoring anti-theft door capable of being locked in remote control mode |
| CN110459019A (en) * | 2019-08-14 | 2019-11-15 | 厦门享取网络科技有限公司 | A kind of take-away rapid access method and its system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112331205B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1972186B (en) | A mobile identity authentication system and its authentication method | |
| US20180047226A1 (en) | Method and system for access control monitoring | |
| JP2003317100A (en) | Information terminal device, authentication system, and registering and authenticating method | |
| CN104952138A (en) | Voice interactive access control system and achievement method thereof | |
| CN104835229B (en) | A kind of method of gesture control lockset | |
| WO2021174991A1 (en) | 5g technology-based facial recognition smart lock control system | |
| CN106600762A (en) | Method and system for controlling vehicle door | |
| CN108052022A (en) | A kind of intelligent door opening method, electronic equipment, storage medium and system based on double mode | |
| CN104835230B (en) | A kind of method of face control lockset | |
| CN104835232A (en) | Voice-control lock | |
| CN109727342A (en) | Recognition methods, device, access control system and the storage medium of access control system | |
| CN109345186A (en) | Business handling method and terminal device based on Internet of Things | |
| CN112331205B (en) | STM 32-based intelligent speech recognition system and method | |
| WO2002095547A3 (en) | Method and system for providing gated access for a third party to a secure entity or service | |
| CN110390758A (en) | A kind of RFID boot cabinet and RFID detection method | |
| CN113436633A (en) | Speaker recognition method, speaker recognition device, computer equipment and storage medium | |
| CN106355684A (en) | Control method, device and system of controlled equipment | |
| CN107701064A (en) | The based reminding method and intelligent door of intelligent door | |
| CN110288492A (en) | A kind of hotel occupancy method, computer equipment and readable storage medium storing program for executing | |
| CN105469468A (en) | Novel automobile data recorder | |
| CN211906454U (en) | Household face recognition anti-theft system | |
| CN208654865U (en) | A kind of attendance checking system based on head part's gesture recognition | |
| CN112349005A (en) | Intelligent access control system capable of achieving door opening through voice recognition | |
| CN112233291A (en) | Entrance guard using method and entrance guard device based on intelligent device track | |
| CN113963467A (en) | Intelligent door lock control method, control device, intelligent equipment and storage medium |
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 |