KR19990058319A - Voice recognition vehicle navigation system and control method - Google Patents

Abstract

The present invention relates to a voice recognition vehicle navigation apparatus and a control method, and more particularly, to a voice recognition vehicle navigation apparatus and a control method by which a user can quickly and safely set a starting point and a destination using a voice by constructing a user database.

According to the voice recognition vehicle navigation apparatus and the control method according to the present invention, the data of the place where the user frequently goes into the database in the memory to load the data of the place to go to the user's voice from the database built in the memory to the screen The starting point and destination can be set quickly and safely.

Thus, in navigation system that requires complicated operation process such as many commands and names, the driver can set the starting point and destination by voice command, freeing the driver's eyes and hands from the machine operation, and the driver from the risk of accidents caused by system operation while driving. It can not only protect the power, but also maximize the convenience of the driver.

In addition, as the data is loaded from the memory, the access time can be shortened, so that the information desired by the user can be displayed on the screen in a shorter time.

Description

Voice recognition vehicle navigation system and control method

The present invention relates to a voice recognition vehicle navigation apparatus and a control method, and more particularly, to a voice recognition vehicle navigation apparatus and a control method by which a user can quickly and safely set a starting point and a destination using a voice by constructing a user database.

In recent years, the increasing number of vehicles on the road has caused a very large traffic congestion. In large cities, traffic congestion is more serious, but a lot of resources are required to expand the road network due to rising land prices.

Therefore, as a more practical solution, attempts have been made to use the existing road network as it is but to efficiently control traffic flow using an artificial intelligence system. Thus, as one way, a car navigation system is being developed.

The most basic function of the vehicle navigation system is to track the location of the vehicle in operation and display it on the road map accurately.The additional function is to provide useful information about traffic conditions, gas stations, and government offices on other roads. .

Such a vehicle navigation system employs a plurality of sensors and uses the information provided therefrom to track a vehicle location using a stand-alone navigation system and a navigational navigation system using location information provided by a GPS satellite. Devices and hybrid navigation systems combining these two devices, and the vehicle navigation systems described below represent all cases of the above-described navigation devices.

In general, the vehicle navigation apparatus receives the location information from the Global Positioning Satellite (GPS) satellite using the Global Positioning Satellite Antenna and maps the received location information data to the map data recorded on the compact disc. It is a device that shows the current location on the screen by performing map matching.

1 is a block diagram of a conventional vehicle navigation apparatus.

Referring to Fig. 1, a general conventional vehicle navigation apparatus includes a GPS antenna 2 for receiving a position signal from three or more GPS satellites 1, and a hardness of the point in the position signal received by the GPS antenna 2. And a receiver (3) for calculating latitude, a remote controller transmitter (4) for remotely controlling the vehicle navigation system, a remote controller receiver (5) for receiving a vehicle navigation device control signal transmitted by the remote controller transmitter (4); Controls a compact disk (CD) 6 storing road map data, a CD-ROM driver 7 for reading data from the compact disk 6, and a vehicle navigation system. And a display unit 9 for displaying information.

In the above-described configuration, the map data stored in the compact disc 6 is based on the topographical map of a predetermined scale ratio made based on aerial photographs, and the geographical information on the road running and the road management is digitized. Such map data is stored by adding attribute data based on the map data of the basic road. The attribute data includes information on intersections, and the intersections appearing during road driving are classified by the intersection name for determining the intersection and the main buildings of the intersection.

The user first inputs the control contents of the differential navigation apparatus through the remote controller transmitter 4. When the user inputs control contents, the remote controller transmitter 4 converts the contents input by the user into an infrared signal and launches them.

The remote controller receiver 5 receives an infrared signal transmitted from the remote controller transmitter 5, converts the infrared signal into a form that can be recognized by the controller 8, and inputs the same to the controller 8.

The controller 8 receives the output from the remote controller transmitter 4 as an input and determines a function desired by the user.

The control unit 8 drives the CD-ROM driver 7 to read the map data contained in the Compact Disk 6 and display it on the display unit 9. Generally, the display unit 9 uses many small liquid crystal monitors.

The user sets the destination and the starting point by sequentially searching for the place name shown on the display unit 9 using the scroll key of the remote controller transmitter 4 (or the key input unit (not shown)) to go to the desired place. .

However, in the conventional vehicle navigation apparatus, the user visually checks and has to operate by hand using the remote controller transmitter 4 or the key input unit (not shown). Therefore, the user may make a wrong operation by mistake and interfere with the safe driving while driving.

When setting the destination and starting point where the user wants to go, the information stored in the compact disc 6 is read by the CD-ROM driver 7 through the place name search and set. This method takes a long time because the user has to find and set a place name, and the access time is long because the CD-ROM driver 7 directly reads it from the compact disc 6.

SUMMARY OF THE INVENTION In order to solve the above problems, an object of the present invention is to provide a voice recognition vehicle navigation apparatus and a control method that allow a user to quickly and securely set a starting point and a destination by voice by building a user database and storing it in a memory.

1 is a block diagram of a conventional navigation apparatus.

2 is a block diagram of a voice recognition vehicle navigation apparatus according to the present invention.

3 is a block diagram of a voice processing unit of the voice recognition vehicle navigation apparatus according to the present invention.

Explanation of symbols on the main parts of the drawings

11: GPS satellite 40: Preprocessing unit 50: Voice processing unit 60: Memory

70: cdrom driver 71: compact disc 90: controller

According to an aspect of the present invention, there is provided a vehicle navigation apparatus including a compact disc having map data stored therein, a cdrom driver capable of loading map data from the compact disc, and a display unit for displaying a map. And a memory for storing information, a voice recognition unit for receiving and recognizing a voice for a user's origin / destination, and a controller for loading the result of the voice recognition unit from a memory or a compact disc and displaying the result on the display unit. .

It is a system that provides a variety of information necessary for driving by receiving a destination from a vehicle navigation device driver, and requires a complicated operation process such as many commands and names. Voice recognition technology frees the driver's eyes and hands from machine operation to protect the driver from accident risks caused by system operation while driving and maximizes the operator's convenience by operating the system using voice.

Speech recognition systems can be divided into speaker dependent speech recognition system (Speaker dependent speech recognition system) and speaker independent speech recognition system (Speaker independent speech recognition system). The speaker dependent system refers to a system that recognizes only a specific speaker's voice. Learning from one person's voice signal, the person's voice shows a high recognition rate, but the recognition rate of the other person's voice is very low. In contrast, speaker dependent system refers to speech recognition for unspecified speakers.

Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings.

2 is a block diagram of a voice recognition vehicle navigation apparatus according to the present invention.

2, the voice recognition vehicle navigation apparatus according to the present invention, the GPS antenna 12 receiving the position signals from the three or more GPS satellites 11, and the position signal received by the GPS antenna 12 A receiver 13 for calculating the longitude and latitude of the point, a remote controller transmitter 21 for remotely controlling the vehicle navigation system, and a remote controller receiver for receiving a vehicle navigation device control signal transmitted by the remote controller transmitter 21 ( 22), a microphone 30 for inputting voice, a preprocessor 40 (hereinafter analog / digital converter) for converting the voice input through the microphone 30 into digital signal processing, and an analog / digital converter. A CD-ROM driver 70 for reading data from a voice processing unit 50 for recognizing a voice by the digital output of the unit 40, a memory 60 for storing a user database, and a compact disc 71 containing map data. Wow A display unit 80 for displaying a beam and a control unit 90 for controlling the vehicle navigation system are provided.

3 is a block diagram of a voice processing unit of the voice recognition vehicle navigation apparatus according to the present invention.

4 is a control flowchart of the voice recognition vehicle navigation apparatus according to the present invention.

The user inputs a destination to which he or she wants to go through the microphone 30 together with the starting point (S10). The user inputs a voice through the microphone 30, and the input voice passes through a voice processing process (S20).

The voice input by the user through the microphone 30 is converted into a digital signal by an analog to digital converter 40.

The analog / digital converter 40 converts the input voice into digital and then inputs the voice to the voice processor 50 by performing a predetermined signal process. The detailed processing is as follows.

The user inputs voice through the microphone 30. The voice input through the microphone 30 is input to the analog / digital converter 40. The voice input to the microphone 30 is input to an analog / digital converter (A / D converter) 40 and converted to digital to undergo a pre-processing process. The preprocessing process converts an analog signal, which is a voice signal input through the microphone 30 into a digital signal, at a sampling frequency of about 10 kHz by analog / digital conversion into a digital signal, thereby converting the S / N ratio. ), The pre-emphasis process is used to improve the

The analog / digital converter 40 pre-processes the input voice and outputs it to the voice processor 50.

The voice processing unit 50 receives the output of the analog / digital converter 40 as an input and performs endpoint detection for distinguishing between the silence of the signal input through the endpoint detection unit 51 and the voice. .

If unnecessary silence is included in the voice interval, the time required for word recognition is increased, and the end point is detected to distinguish between silence and voice. In the end point detection, the end point detection 82 is performed by estimating the noise level.

The output of the endpoint detector 51 is input to the noise canceller 52, and the noise canceller 52 removes noise from the data. Noise subtraction is the removal of noise mixed with speech to make it resemble the original signal. Noise reduction uses methods to remove noise mixed with voice by knowing the shape of noise added to the voice in advance or by measuring the statistical characteristics of noise in the silent period.

The signal from which the noise is removed from the noise removing unit 52 is input to the vector extracting unit 53. The vector extractor 53 extracts a feature vector resistant to noise from the input signal after the noise is removed. As a feature vector of a speech signal, a linear predictive coding (LPC cepstrum) using a linear predictive coding (LPC) analysis method is generally used. Linear Predictive Coding (LPC) is the prediction of each input sample by a linear combination of the previous (not the actual samples) regenerated samples, subtracted from the actual input sample value, and the difference is quantized and encoded. That's how. Cepstrum is a Fourier inverse transform of the power spectrum of a signal.

After the feature vector extraction in the vector extracting unit 53, voice recognition is performed through a reference model obtained through training and a Viterbi decoding process (S30).

When the user's voice is recognized, the controller 90 determines whether the word of the recognized voice exists in the user database stored in the memory 60 (S40).

The memory 60 has a database of data about destinations and departure points that users frequently visit. The contents of the memory 60 can be arbitrarily reset, and the memory 60 does not need a backup power source and can be rewritten in a flash memory format and can be implemented in other types of memories.

If it is determined that the word of the recognized voice is in the user database stored in the memory 60, the controller 90 loads information corresponding to the word of the recognized voice from the database stored in the memory 60 (S50).

The controller 90 sets the starting point / destination point after loading data from the memory 60 (S60). After the starting / destination setting is made, the controller 90 displays the data on the display unit 80.

On the other hand, if it is determined that the word of the voice recognized in the determination (S40) is not in the user database stored in the memory 60, the control unit 90 reads data from the compact disc 71 with the CD-ROM driver 70 (S41). .

The controller 90 loads data from the compact disc 71 with the CD-ROM driver 70 and sets a starting point / destination destination (S60). After the starting / destination setting is made, the controller 90 displays the data on the display unit 80.

As described in detail above, according to the voice recognition vehicle navigation apparatus and the control method according to the present invention, data about a place where the user frequently goes is constructed as a database in the memory and data where the user wants to go with the user's voice is built in the memory. It loads from a database and displays it on the screen, allowing you to quickly and securely set your origin and destination.

Thus, in navigation system that requires complicated operation process such as many commands and names, the driver can set the starting point and destination by voice command, freeing the driver's eyes and hands from the machine operation, and the driver from the risk of accidents caused by system operation while driving. It can not only protect the power, but also maximize the convenience of the driver.

In addition, as the data is loaded from the memory, the access time can be shortened, so that the information desired by the user can be displayed on the screen in a shorter time.

Claims (4)

A vehicle navigation apparatus comprising a compact disc having map data stored therein, a cdrom driver capable of loading map data from the compact disc, and a display unit for displaying a map. Memory for storing information about origin / destination, Voice recognition unit for receiving and recognizing the voice of the user's origin / destination, And a controller which loads the result recognized by the voice recognition unit from the memory or the compact disc and displays the display unit. The method of claim 1, And the memory stores data on a place where the user has recently gone, and the user can arbitrarily store data on the origin / destination in the memory. According to claim 1, The controller determines whether the voice recognition unit recognizes the result first in the memory, and if there is a result recognized by the voice recognition unit, loads the data from the memory and if the result recognized by the voice recognition unit does not exist in the memory. Voice recognition vehicle navigation apparatus, characterized in that for loading the corresponding data from the compact disc. A first step of receiving and recognizing a user's voice; A second step of determining whether the voice recognized in the first step exists in a database stored in a memory; A third step of setting a starting point / destination destination by loading data stored in the memory when it is determined that the voice recognized in the first step exists in the database stored in the memory in the second step; And in the second step, when it is determined that the voice recognized in the first step does not exist in the database stored in the memory, a third step of loading data stored in the compact disc and setting a starting point / destination point is included. A method for controlling a voice recognition vehicle navigation apparatus.