KR20100101986A - Telematics terminal, metohd for voice recognition and computer recordable medium - Google Patents

Abstract

PURPOSE: A telematics terminal, method for voice recognition and a computer recordable medium are provided to improve voice recognition in nose conditions by using a proper acoustic model. CONSTITUTION: A microphone(132) receives the voice of a vehicle passenger. A wireless communications unit transmits the information related to the noise environment of the vehicle to server. A wireless communications unit(110) receive the information related to the acoustic models which are selected by the sever. A controller(190) recognizes a voice by using the selected acoustic model. A user input portion(140) receives an input enabling a voice recognition function from the passenger of the vehicle.

Description

Telematics terminal, voice recognition method of telematics terminal and computer readable recording medium {TELEMATICS TERMINAL, METOHD FOR VOICE RECOGNITION AND COMPUTER RECORDABLE MEDIUM}

The present invention relates to a voice recognition method for recognizing the voice of a vehicle occupant in a vehicle telematics terminal and a telematics terminal using the same.

Telematics is a compound word of Telecommunications and Informatics, also known as Information and Communications Technology (ICT), which collectively refers to a technology for transmitting, receiving, and storing information through a communication device. do.

In recent years, telematics may be implemented in a form in which a navigation system using GPS technology and a mobile communications technology are combined.

These vehicle telematics include remote diagnostics of vehicles, fault diagnosis of electrical / mechanical components mounted on a vehicle, vehicle control, between a call center and a vehicle or between vehicles equipped with a vehicle telematics terminal. It can be used in various fields such as telecommunications, intelligent transportation systems, and user-vehicle interface implementation.

In the case of a telematics terminal equipped with a microphone, voice recognition technology may provide an alternative interface in addition to the traditional human-to-device interface (including input through a keyboard, a keypad, and a touchpad). For example, a telematics terminal equipped with a microphone may make a call to another terminal using voice recognition.

In a vehicle telematics terminal performing voice recognition, the noise environment is changed by various internal / external variables. Internal / external variables include vehicle speed, wind noise, and air conditioner module operation.

In the case of a vehicle, the noise environment varies more depending on internal and external variables than the noise environment in general speech recognition. Therefore, consideration of a method for improving the speech recognition rate in a condition in which the noise environment changes is required.

The present invention relates to a speech recognition method and a telematics terminal of a telematics terminal capable of obtaining an improved speech recognition rate compared to a conventional method even in a noise environment of a vehicle which varies according to a variable.

Voice recognition method of the telematics terminal according to an embodiment of the present invention for realizing the above object, the step of transmitting information related to the noise environment of the vehicle to the server, and the information related to the driving environment of the plurality of acoustic models Receiving information related to the acoustic model selected by the server using the server; and performing voice recognition using the selected acoustic model.

In one aspect of the present invention, the information related to the noise environment of the vehicle may include at least one of a driving speed of the vehicle, whether the air conditioner module is operated and the strength of the operation, whether the window is opened or closed, and the vehicle position information.

In another aspect of the present invention, the transmitting may be a step of periodically transmitting information related to the noise environment of the vehicle to a server.

In another aspect of the present invention, the transmitting may include transmitting information related to the noise environment of the vehicle to a server when an input for activating a voice recognition function is received from a passenger of the vehicle.

In another aspect of the present invention, the transmitting may be a step of transmitting, to the server when any event occurs, information related to the noise condition of the vehicle.

In another aspect of the present invention, the random event includes at least one of an increase or decrease in vehicle interior noise, an increase or decrease in vehicle running speed, an operation of an air conditioner module, a change in operation intensity and an end of operation, and an opening or closing of a window. It may include one.

In still another aspect of the present invention, the plurality of acoustic models may be stored in whole or in part in the telematics terminal, or in whole or in part in the server.

In another aspect of the present invention, if the selected acoustic model is not stored in the telematics terminal, the method may further include downloading the selected acoustic model from the server.

In another aspect of the present invention, the selected acoustic model may be an acoustic model selected from a plurality of acoustic models using information related to the noise environment of the vehicle received from the vehicle or information collected by a server.

In another aspect of the present invention, the information collected by the server may include at least one of a road state of a road on which the vehicle is running, a noise state around the vehicle, and weather around the vehicle.

In the computer-readable recording medium related to an embodiment of the present invention for realizing the above object, a program for performing a voice recognition method of the telematics terminal is recorded.

Telematics terminal according to an embodiment of the present invention for realizing the above object, the microphone for receiving the voice of the vehicle occupant, and transmits the information related to the noise environment of the vehicle to the server, the driving environment of the plurality of acoustic models It includes a wireless communication unit for receiving information related to the acoustic model selected by the server using the information associated with the control unit for performing voice recognition using the selected acoustic model.

In one aspect of the present invention, the information related to the noise environment of the vehicle may include at least one of a driving speed of the vehicle, whether the air conditioner module is operated and the strength of the operation, whether the window is opened or closed, and the position information of the vehicle.

In another aspect of the present invention, the wireless communication unit may periodically transmit information related to the noise environment of the vehicle to the server.

In another aspect of the invention, the user input unit for receiving an input for activating the voice recognition function from the occupant of the vehicle, the wireless communication unit, when the input is received, the information related to the noise environment of the vehicle You can send it to the server.

In another aspect of the present invention, the wireless communication unit may transmit information related to the noise environment of the vehicle to the server when any event occurs.

In another aspect of the present invention, the random event includes at least one of an increase or decrease in vehicle interior noise, an increase or decrease in vehicle running speed, an operation of an air conditioner module, a change in operation intensity and an end of operation, and an opening or closing of a window. It can contain one.

In still another aspect of the present invention, the apparatus may further include a memory configured to store all or part of the plurality of acoustic models.

In another aspect of the present invention, the controller determines whether the selected acoustic model is stored in the telematics terminal, and the wireless communication unit, if the selected acoustic model is not stored in the telematics terminal, The selected acoustic model can be downloaded from.

In another aspect of the present invention, the selected acoustic model may be an acoustic model selected from a plurality of acoustic models using information related to the noise environment of the vehicle received from the vehicle or information collected by a server.

In another aspect of the present invention, the information collected by the server may include at least one of a road state of a road on which the vehicle is running, a noise state around the vehicle, and weather around the vehicle.

In the speech recognition method of the telematics terminal according to an embodiment of the present invention, by selecting an acoustic model suitable for the noise environment of the moving object and performing the speech recognition, a high speech recognition rate may be obtained even in a rapidly changing noise environment.

In addition, since the selection of the acoustic model is made at the server, it is possible to reduce the traffic of the telematics terminal for selecting the appropriate acoustic model.

Hereinafter, a telematics terminal related to the present invention will be described in more detail with reference to the accompanying drawings. The suffixes "module" and "unit" for components used in the following description are given or used in consideration of ease of specification, and do not have distinct meanings or roles from each other.

1 is a block diagram of a telematics terminal related to an embodiment of the present invention.

The telematics terminal 100 includes a wireless communication unit 110, a location information module 120, an A / V input unit 130, a user input unit 140, a sensing unit 150, and an output unit 160. , A memory 170, an interface unit 180, a controller 190, a power supply unit 200, and the like. The components shown in FIG. 1 are not essential, so a telematics terminal having more or fewer components may be implemented.

Hereinafter, the components will be described in order.

The wireless communication unit 110 may include one or more modules that enable wireless communication between the telematics terminal 100 and a wireless communication system or between a network in which the telematics terminal 100 and the telematics terminal 100 are located. For example, the wireless communication unit 110 may include a broadcast receiving module 111, a mobile communication module 112, a wireless internet module 113, a short range communication module 114, and the like.

The broadcast receiving module 111 receives a broadcast signal and / or broadcast related information from an external broadcast management server through a broadcast channel.

The broadcast channel may include a satellite channel and a terrestrial channel. The broadcast management server may mean a server that generates and transmits a broadcast signal and / or broadcast related information or a server that receives a previously generated broadcast signal and / or broadcast related information and transmits the same to a terminal. The broadcast signal may include not only a TV broadcast signal, a radio broadcast signal, and a data broadcast signal, but also a broadcast signal having a data broadcast signal combined with a TV broadcast signal or a radio broadcast signal.

The broadcast related information may mean information related to a broadcast channel, a broadcast program, or a broadcast service provider. The broadcast related information may also be provided through a mobile communication network. In this case, it may be received by the mobile communication module 112.

The broadcast related information may exist in various forms. For example, it may exist in the form of Electronic Program Guide (EPG) of Digital Multimedia Broadcasting (DMB) or Electronic Service Guide (ESG) of Digital Video Broadcast-Handheld (DVB-H).

The broadcast receiving module 111 may include, for example, Digital Multimedia Broadcasting-Terrestrial (DMB-T), Digital Multimedia Broadcasting-Satellite (DMB-S), Media Forward Link Only (MediaFLO), and Digital Video Broadcast (DVB-H). Digital broadcast signals can be received using digital broadcasting systems such as Handheld and Integrated Services Digital Broadcast-Terrestrial (ISDB-T). Of course, the broadcast reception module 111 may be configured to be suitable for not only the above-described digital broadcast system but also other broadcast systems.

The broadcast signal and / or broadcast related information received through the broadcast receiving module 111 may be stored in the memory 170.

The mobile communication module 112 transmits and receives a wireless signal with at least one of a base station, an external terminal, and a server on a mobile communication network. The wireless signal may include various types of data according to transmission and reception of a voice call signal, a video call call signal, or a text / multimedia message.

The wireless internet module 113 refers to a module for wireless internet access and may be built in or external to the telematics terminal 100. Wireless Internet technologies may include Wireless LAN (Wi-Fi), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA), and the like.

The short range communication module 114 refers to a module for short range communication. As a short range communication technology, Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and the like may be used.

The location information module 120 is a module for obtaining a location of a mobile terminal, and a representative example thereof is a GPS (Global Position System) module.

The GPS module receives a signal containing time information from at least three navigation satellites, and calculates a distance from each satellite using the GPS signal. Position information may be obtained by applying triangulation to the calculated distance. The GPS module may increase the accuracy of the calculated location information by further applying techniques such as map matching and dead reckoning to the location information obtained by applying the triangulation method.

The location information module 120 may obtain location information by using various technologies such as cell tower signals, wireless internet signals, and Bluetooth sensors in addition to the GPS module to determine the location of the mobile terminal. This technique is called Hybrid Positioning System.

Referring to FIG. 1, the A / V input unit 130 is for inputting an audio signal or a video signal, and may include a camera 131 and a microphone 132. The camera 131 processes image frames such as still images or moving images obtained by the image sensor in the photographing mode. The processed image frame may be displayed on the display unit 161.

The image frame processed by the camera 131 may be stored in the memory 170 or transmitted to the outside through the wireless communication unit 110. Two or more cameras 131 may be provided according to a usage environment.

The microphone 132 receives an external sound signal by a microphone in a call mode, a recording mode, a voice recognition mode, etc., and processes the external sound signal into electrical voice data. The microphone 132 may implement various noise removing algorithms for removing noise generated in the process of receiving an external sound signal.

The user input unit 140 generates input data for controlling a user's telematics terminal operation. The user input unit 140 may include a key pad dome switch, a touch pad (static pressure / capacitance), a jog wheel, a jog switch, and the like.

A steering wheel, an acceleration pedal, a brake pedal, a gear shift lever, and the like mounted on the vehicle may configure the user input unit 130.

Sensing unit 150, whether the user contacts the telematics terminal 100, whether the vehicle door or window opening and closing, whether the seat belt is worn, the operating state of the driver's steering wheel, accelerator pedal, brake pedal, gear shift lever, vehicle Temperature inside or outside, collision and strength of the vehicle with other objects, distance between the vehicle and other objects, status of parts mounted on the vehicle, flashing state or brightness of lamps mounted inside or outside the vehicle The sensor detects the current state of the vehicle or the telematics terminal 100 such as whether the occupant is seated and generates a sensing signal for controlling the operation of the telematics terminal 100 or the vehicle. For example, the vehicle door may be detected when it is opened, or when the vehicle occupant is seated, it may be detected by using the pressure applied to the chair. In addition, whether the power supply unit 200 is supplied with power, whether the interface unit 180 is coupled with an external device or a vehicle component may be sensed. The sensing unit 150 may include a proximity sensor 151.

The output unit 160 is used to generate an output related to sight, hearing, or tactile sense, and includes a display unit 161, a sound output module 162, an alarm unit 163, and a haptic module 164. Can be.

The display unit 161 displays (outputs) information processed by the telematics terminal 100. For example, when the telematics terminal is in a route search mode, the telematics terminal displays a user interface (UI) or a graphical user interface (GUI) related to route search. When the telematics terminal 100 is in a video call mode or a photographing mode, the telematics terminal 100 displays a photographed and / or received image, a UI, or a GUI.

The display unit 161 includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display (flexible). and at least one of a 3D display.

Some of these displays can be configured to be transparent or light transmissive so that they can be seen from the outside. This may be referred to as a transparent display. A representative example of the transparent display is TOLED (Transparant OLED).

The display unit 161 may be implemented in the form of a head up display (HUD). For example, the display unit 161 may be implemented in a window provided in the windshield or the door of the vehicle. In this case, the display unit 161 may be configured as a transparent type or a light transmissive type.

According to an embodiment of the telematics terminal 100, two or more display units 161 may exist.

When the display unit 161 and a sensor for detecting a touch operation (hereinafter, referred to as a touch sensor) form a mutual layer structure (hereinafter referred to as a touch screen), the display unit 161 may be used in addition to an output device. Can also be used as an input device. The touch sensor may have, for example, a form of a touch film, a touch sheet, a touch pad, or the like.

The touch sensor may be configured to convert a change in pressure applied to a specific portion of the display unit 161 or capacitance generated at a specific portion of the display unit 161 into an electrical input signal. The touch sensor may be configured to detect not only the position and area of the touch but also the pressure at the touch.

If there is a touch input to the touch sensor, the corresponding signal (s) is sent to the touch controller. The touch controller processes the signal (s) and then transmits the corresponding data to the controller 190. As a result, the controller 190 may determine which area of the display unit 161 is touched.

Referring to FIG. 1, a proximity sensor 151 may be disposed near an inner region of the telematics terminal wrapped by the touch screen or near the touch screen. The proximity sensor refers to a sensor that detects the presence or absence of an object approaching a predetermined detection surface or an object present in the vicinity without using a mechanical contact by using an electromagnetic force or infrared rays. Proximity sensors have a longer life and higher utilization than touch sensors.

Examples of the proximity sensor include a transmission photoelectric sensor, a direct reflection photoelectric sensor, a mirror reflection photoelectric sensor, a high frequency oscillation proximity sensor, a capacitive proximity sensor, a magnetic proximity sensor, and an infrared proximity sensor. When the touch screen is capacitive, the touch screen is configured to detect the proximity of the pointer by a change in an electric field according to the proximity of the pointer. In this case, the touch screen (touch sensor) may be classified as a proximity sensor.

Hereinafter, for convenience of explanation, the act of allowing the pointer to be recognized without being in contact with the touch screen so that the pointer is located on the touch screen is referred to as a "proximity touch", and the touch The act of actually touching the pointer on the screen is called "contact touch." The position where the proximity touch is performed by the pointer on the touch screen refers to a position where the pointer is perpendicular to the touch screen when the pointer is in proximity proximity.

The proximity sensor detects a proximity touch and a proximity touch pattern (for example, a proximity touch distance, a proximity touch direction, a proximity touch speed, a proximity touch time, a proximity touch position, and a proximity touch movement state). Information corresponding to the sensed proximity touch operation and proximity touch pattern may be output on the touch screen.

The sound output module 162 may output audio data received from the wireless communication unit 110 or stored in the memory 160 in a call signal reception, a call mode or a recording mode, a voice recognition mode, a broadcast reception mode, a path search mode, and the like. . The sound output module 152 may also output a sound signal related to a function (eg, a call signal reception sound, a message reception sound, a route guidance voice, etc.) performed by the telematics terminal 100. The sound output module 162 may include a receiver, a speaker, a buzzer, and the like.

The alarm unit 163 outputs a signal for notifying occurrence of an event of the telematics terminal 100. Examples of events occurring in the telematics terminal include call signal reception, message reception, touch input, abnormalities of components mounted on the vehicle, and abnormal opening and closing of vehicle doors and windows. The alarm unit 163 may output a signal for notifying the occurrence of an event by vibration, in addition to a video signal or an audio signal. The video signal or the audio signal may also be output through the display unit 161 or the audio output module 162, so that they 161 and 162 may be classified as part of the alarm unit 163.

The haptic module 164 generates various tactile effects that a user can feel. Vibration is a representative example of the haptic effect generated by the haptic module 164. The intensity and pattern of vibration generated by the haptic module 164 can be controlled. For example, different vibrations may be synthesized and output or may be sequentially output.

In addition to the vibration, the haptic module 164 may be configured to provide a pin array that vertically moves with respect to the contact skin surface, a jetting force or suction force of air through the jetting or suction port, grazing to the skin surface, contact of the electrode, electrostatic force, and the like. Various tactile effects can be generated, such as effects by the endothermic and the reproduction of a sense of cold using the elements capable of endotherm or heat generation.

The haptic module 164 may not only deliver the haptic effect through direct contact, but may also be implemented to allow the user to feel the haptic effect through a muscle sense such as a finger or an arm. Two or more haptic modules 164 may be provided according to a configuration aspect of the telematics terminal 100. The haptic module 164 may be provided where frequent contact with the user is in the vehicle. For example, it may be provided in a steering wheel, a shift gear lever, a seat seat, and the like.

The memory 170 may store a program for the operation of the controller 190 and may temporarily store input / output data (for example, music, still images, video, map data, and the like). The memory 170 may store data regarding vibration and sound of various patterns output when a touch input on the touch screen is performed.

The memory 170 may include a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), RAM (Random Access Memory, RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), Magnetic Memory, Magnetic It may include a storage medium of at least one type of disk, optical disk. The telematics terminal 100 may operate in association with a web storage that performs a storage function of the memory 170 on the Internet.

The interface unit 180 serves as a path with all external devices connected to the telematics terminal 100. The interface unit 180 receives data from an external device, receives power, transfers the power to each component inside the telematics terminal 100, or transmits the data inside the telematics terminal 100 to an external device. For example, wired / wireless headset ports, external charger ports, wired / wireless data ports, memory card ports, ports for connecting devices with identification modules, audio input / output (I / O) ports, The video input / output (I / O) port, the earphone port, and the like may be included in the interface unit 180.

The interface unit 180 may be implemented using a controller-area network (CAN), a local interconnect network (LIN), a FlexRay, or a media-oriented systems transport (MOST).

The identification module is a chip that stores various types of information for authenticating the usage rights of the telematics terminal 100. The identification module may include a user identification module (UIM), a subscriber identify module (SIM), and a universal user authentication module ( Universal Subscriber Identity Module (USIM), and the like. Devices with identification modules (hereinafter referred to as "identification devices") can be manufactured in a smart card format. Therefore, the identification device may be connected to the terminal 100 through a port. Alternatively, the identification device may be manufactured in the form of a vehicle key.

The controller 190 typically controls the overall operation of the telematics terminal. For example, it performs related control and processing for data communication, video call, route search, vehicle control and the like. The controller 190 includes a multimedia module 191 for playing multimedia, an airbag controller 192 for controlling an airbag mounted in a vehicle, and an emergency battery controller 193 for controlling an emergency battery mounted in a vehicle. Or the like. The multimedia module 191, the airbag controller 192, and the emergency battery controller 193 may be implemented in the controller 180 or may be implemented separately from the controller 190. The controller 190 may perform a speech recognition function of recognizing a user's voice received through the microphone 132, converting the user's voice into a text, or recognizing a predetermined command.

The controller 190 may perform a pattern recognition process for recognizing a writing input or a drawing input performed on the touch screen as text and an image, respectively.

An example in which the controller 190 performs a voice recognition function is as follows.

In general, two processes are required for speech recognition. The first step is to extract words from the user's voice using an acoustic model. The acoustic model extracts words having a high probability of matching statistically from the user's voice received using the microphone 132 and converts the voice into text.

The second process is to determine the meaning of text using a language model or a grammar file. The language model is a file including probability information related to word order, and a grammar file is a file of a small size including a set of preset word combinations.

When a word is extracted using the voice, noise removal and noise compensation are performed from the voice. When the speech recognition is performed in a noise environment that is different from the noise characteristic assumed by the acoustic model, it is difficult to extract the correct speech feature in the process of noise removal and noise compensation.

The power supply unit 200 receives an external power source and an internal power source under the control of the controller 190 to supply power for operation of each component.

The power supply unit 200 may be a battery mounted in a vehicle or a battery mounted independently for the telematics terminal 100.

Various embodiments described herein may be implemented in a recording medium readable by a computer or similar device using, for example, software, hardware or a combination thereof.

According to a hardware implementation, the embodiments described herein include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), and the like. It may be implemented using at least one of processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions. The described embodiments may be implemented by the controller 190 itself.

According to the software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein. Software code may be implemented in software applications written in a suitable programming language. The software code may be stored in the memory 170 and executed by the controller 190.

As shown in FIG. 1, the microphone 132 may receive a voice of a vehicle occupant.

The wireless communication unit 110 may transmit information related to the noise environment of the vehicle to the server. The information related to the noise environment of the vehicle may include at least one of a driving speed of the vehicle, whether the air conditioner module is operated and the strength of the operation, whether the window is opened or closed, and the position information of the vehicle.

Information related to the noise environment of the vehicle may be transmitted to a server and used by the server to select an acoustic model suitable for the noise environment of the vehicle. In selecting the acoustic model, the server may use information collected by the server in addition to the information related to the driving environment received from the vehicle.

The information collected by the server may include at least one of a road state of a road on which the vehicle is running, a noise state around the vehicle, and weather around the vehicle.

For example, the server may receive location information of the vehicle from the vehicle and collect information such as road conditions, temperatures, and weather at a location where the vehicle is located. The server may select a suitable acoustic model using information related to the temperature, the weather of the location of the vehicle and the noise environment of the vehicle received from the vehicle.

The server may include information related to the plurality of acoustic models. The information related to the plurality of acoustic models refers to information related to a noise environment of a vehicle corresponding to the acoustic model. The server selects an acoustic model capable of showing the highest voice recognition rate under the noise environment, using the information collected by the server and the noise environment of the vehicle received from the vehicle.

The wireless communication unit 110 may receive information related to the acoustic model selected by the server. The plurality of acoustic models may be stored in whole or in part in the memory 170. Alternatively, the plurality of acoustic models may be stored in whole or in part in the server.

The server may update a plurality of previously stored acoustic models and other new acoustic models. The telematics terminal 100 may download the updated acoustic model through the wireless communication unit 110.

The wireless communication unit 110 may periodically transmit information related to the noise environment of the vehicle in transmitting information related to the noise environment of the vehicle to a server. The wireless communication unit 110 periodically receives information related to the noise environment of the vehicle to the server, and based on this, receives the information related to the acoustic model selected by the server. The controller 190 may periodically update the acoustic model for speech recognition of the telematics terminal 100 with the acoustic model selected by the server.

When the occupant of the vehicle receives an input for activating a voice recognition function, the wireless communication unit 110 may transmit information related to the noise environment of the vehicle to a server. When the voice recognition is not normally performed, information related to the noise environment of the vehicle is not transmitted to the server, and information related to the noise environment of the vehicle may be transmitted to the server only when the acoustic model is required for the voice recognition.

The wireless communication unit 110 may transmit information related to the noise environment of the vehicle to a server when any event occurs. The optional event may include at least one of increasing or decreasing the vehicle interior noise, increasing or decreasing the vehicle traveling speed, operating the air conditioner module, changing the operation intensity and terminating the operation, opening or closing the window.

When the telematics terminal 100 detects the arbitrary event using the in-vehicle network, the random event is highly likely to change the noise environment of the vehicle, and thus is optional only when the random event occurs. And transmits information related to the noise environment of the vehicle to the server.

The controller 190 may perform voice recognition using the selected acoustic model. As the noise environment of the vehicle changes, the controller 190 performs voice recognition using an acoustic model selected by the server to have the highest voice recognition rate. As a result, even if the noise environment inside the vehicle changes, a high voice recognition rate can be obtained.

The controller 190 may determine whether information related to the selected acoustic model is stored in the memory 170 from the server. When the selected acoustic model is not stored in the memory 170, the controller 190 may download the selected acoustic model from the server.

2 is a flowchart illustrating a voice recognition method of a telematics terminal related to an embodiment of the present invention.

As shown in FIG. 2, the telematics terminal 100 may transmit information related to a noise environment to a server (S110). The information related to the noise environment of the vehicle may include at least one of a driving speed of the vehicle, whether the air conditioner module is operated and an operating strength, whether the window is opened or closed, and the position information of the vehicle.

The telematics terminal 100 may receive information related to an acoustic model selected by a server using information related to the driving environment among a plurality of acoustic models (S120). The selected acoustic model may be an acoustic model selected from a plurality of acoustic models using information related to a noise environment of the vehicle received from the vehicle or information collected by a server. The information collected by the server may include at least one of a road state of a road on which the vehicle is running, a noise state around the vehicle, and weather around the vehicle.

The telematics terminal 100 may determine whether the selected acoustic model is stored in the memory 170 (S130). For example, a code corresponding to the selected acoustic model may be received from the server. The telematics terminal 100 may compare the codes corresponding to the plurality of acoustic models stored in the memory 170 with the received codes. If there is a code that matches the received code among the plurality of codes, the telematics terminal 100 may determine that the selected acoustic model is stored in the memory 170.

In this case, voice recognition may be performed using the selected acoustic model (S140). If there is no code that matches the received code among the plurality of codes, the telematics terminal 100 may download the selected acoustic model from the server (S150).

3 is a flowchart illustrating a voice recognition method of a telematics terminal according to another embodiment of the present invention.

As shown in FIG. 3, the telematics terminal 100 may periodically transmit information related to the noise environment to a server (S210). The telematics terminal 100 may periodically transmit information related to the noise environment to a server and perform voice recognition using an acoustic model selected by the server. In this case, the selected acoustic model may be periodically changed to match the driving environment of the moving object.

4 is a flowchart illustrating a voice recognition method of a telematics terminal according to another embodiment of the present invention.

As shown in FIG. 4, the telematics terminal 100 may detect occurrence of an arbitrary event (S311). The optional event may include at least one of increasing or decreasing the vehicle interior noise, increasing or decreasing the vehicle traveling speed, operating the air conditioner module, changing the operation intensity and terminating the operation, opening or closing the window. In order to detect the arbitrary event, the telematics terminal 100 may detect the arbitrary event by using a network in the mobile body. For example, when the predetermined event is the opening or closing of the window, the telematics terminal 100 may be connected to a door sensor that detects the opening or closing of the window to detect whether the window is open or closed. . The telematics terminal 100 and the sensors detecting the random event may be connected using a network such as a controller-area network (CAN), a local interconnect network (LIN), a FlexRay, or a media oriented systems transport (MOST). .

Events that significantly change the information related to the noise environment may be set as an arbitrary event, and when the random event occurs, it may be determined that the noise environment is likely to be greatly changed. If the noise environment fluctuates significantly, it is necessary to select an acoustic model different from the acoustic model in use to increase the speech recognition rate. In this case, the telematics terminal 100 may selectively transmit information related to the noise environment only when the random event occurs, and perform voice recognition using the acoustic model selected by the server.

5 is a flowchart illustrating a voice recognition method of a telematics terminal according to another embodiment of the present invention.

As shown in FIG. 5, the telematics terminal 100 may receive an input for activating voice recognition from a user (S411).

When the input for activating the voice recognition is received, the telematics terminal 100 may periodically transmit information related to the noise environment (S412).

When the telematics terminal 100 performs voice recognition, selection of an acoustic model for improving voice recognition rate is required when the user wants to use the voice recognition function.

Therefore, when the telematics terminal 100 requires a separate input from the user to enter the voice recognition mode, the telematics terminal 100 selectively transmits information related to the noise environment to the server when the user wants to use the voice recognition function. In addition, information related to the bonded acoustic model may be received.

In addition, according to an embodiment of the present invention, the above-described method may be implemented as code that can be read by a processor in a medium in which a program is recorded. Examples of processor-readable media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, and may be implemented in the form of a carrier wave (for example, transmission over the Internet). Include.

The telematics terminal having the voice recognition method described above is not limited to the configuration and method of the above-described embodiments, but the embodiments may be modified in whole or in part to enable various modifications. It may alternatively be configured in combination.

1 is a block diagram of a telematics terminal related to an embodiment of the present invention.

2 is a flowchart illustrating a voice recognition method of a telematics terminal related to an embodiment of the present invention.

3 is a flowchart illustrating a voice recognition method of a telematics terminal related to another embodiment of the present invention.

4 is a flowchart illustrating a voice recognition method of a telematics terminal related to another embodiment of the present invention.

5 is a flowchart illustrating a voice recognition method of a telematics terminal related to another embodiment of the present invention.

Claims (21)

Transmitting information related to a noise environment of the vehicle to a server; Receiving information related to an acoustic model selected by a server using information related to the driving environment among a plurality of acoustic models; Speech recognition method of the telematics terminal comprising the step of performing speech recognition using the selected acoustic model. According to claim 1, Information related to the noise environment of the vehicle, A voice recognition method of a telematics terminal including at least one of a driving speed of a vehicle, whether or not an air conditioner module is operated and an operating strength, whether a window is opened or closed, and location information of the vehicle. According to claim 1, The transmitting step, And a step of periodically transmitting information related to the noise environment of the vehicle to a server. According to claim 1, The transmitting step, And transmitting information related to the noise environment of the vehicle to a server when an input for activating the speech recognition function is received from a passenger of the vehicle. According to claim 1, The transmitting step, And transmitting information related to the noise environment of the vehicle to a server when an event occurs. 6. The method of claim 5, The random event is A voice recognition method of a telematics terminal, which includes at least one of an increase or a decrease in vehicle interior noise, an increase or a decrease in a vehicle driving speed, an operation of an air conditioner module, a change and termination of an operation strength, and an opening or closing of a window. According to claim 1, The plurality of acoustic models, All or part of the telematics terminal is stored, or all or part of the voice recognition method of the telematics terminal is stored in the server. According to claim 1, And if the selected acoustic model is not stored in the telematics terminal, downloading the selected acoustic model from the server. According to claim 1, The selected acoustic model, Speech recognition method of a telematics terminal, which is an acoustic model selected from a plurality of acoustic models using information related to a noise environment of a vehicle received from the vehicle or information collected by a server. The method of claim 9, The information collected by the server, A voice recognition method of a telematics terminal including at least one of a road state of a road on which a vehicle is running, a noise state around a vehicle, and weather around the vehicle. The computer-readable recording medium according to any one of claims 1 to 10, wherein a program for performing a voice recognition method of the telematics terminal is recorded. A microphone for receiving a voice of a vehicle occupant; A wireless communication unit transmitting information related to a noise environment of a vehicle to a server and receiving information related to an acoustic model selected by the server using information related to the driving environment among a plurality of acoustic models; and And a controller configured to perform voice recognition using the selected acoustic model. The method of claim 12. Information related to the noise environment of the vehicle, A voice recognition method of a telematics terminal including at least one of a driving speed of a vehicle, whether or not an air conditioner module is operated and an operating strength, whether a window is opened or closed, and location information of the vehicle. The method of claim 12, The wireless communication unit, Telematics terminal for periodically transmitting information related to the noise environment of the vehicle to the server. The method of claim 12, Further comprising a user input unit for receiving an input for activating the voice recognition function from the occupant of the vehicle, The wireless communication unit, And when the input is received, transmitting information related to the noise environment of the vehicle to a server. The method of claim 12, The wireless communication unit, Telematics terminal for transmitting information related to the noise environment of the vehicle to the server when any event occurs. The method of claim 16, The random event is A telematics terminal comprising at least one of an increase or a decrease in vehicle interior noise, an increase or a decrease in the vehicle traveling speed, an operation of an air conditioner module, a change in operation intensity and an end of operation, and an opening or closing of a window. The method of claim 12, A telematics terminal further comprising a memory for storing all or part of the plurality of acoustic models. The method of claim 12, The control unit, It is determined whether the selected acoustic model is stored in the telematics terminal. The wireless communication unit, And when the selected acoustic model is not stored in the telematics terminal, downloading the selected acoustic model from the server. The method of claim 12, The selected acoustic model, And a acoustic model selected from a plurality of acoustic models using information related to a noise environment of the vehicle received from the vehicle or information collected by a server. The method of claim 20, The information collected by the server, A telematics terminal including at least one of a road state of a road on which a vehicle is running, a noise state around a vehicle, and weather around the vehicle.

Images