KR20200001018A - Voice recognition system - Google Patents

Abstract

The present invention relates to a vehicle voice recognizing system, which comprises: a microphone installed in a vehicle to receive voice of a passenger in the vehicle; a connection unit connected to a control module of the vehicle to input a control signal to the control module of the vehicle for controlling an electronic device installed in the vehicle; an input switch provided in the vehicle to enable the passenger to select a voice recognition mode; a voice control unit for recognizing the voice received through the microphone, generating the control signal corresponding to the recognized voice, and transmitting the generated control signal to the control module of the vehicle through the connection unit when the passenger selects the voice recognition mode by operating the input switch; a directional sound output unit installed in the vehicle to output sound, and outputting a directional sound toward the passenger to prevent the output sound from being input to the microphone; and a switching unit for providing an audio signal inputted from the electronic device for an internal speaker installed in the vehicle or the directional sound output unit, providing the audio signal for the internal speaker when the voice recognition mode is not selected, and providing the audio signal for the directional sound output unit when the voice recognition mode is selected.

Description

Vehicle speech recognition system

The present invention relates to a vehicle speech recognition system, and more particularly, to a vehicle speech recognition system provided with a directional speaker to prevent the sound output into the vehicle from being input into the microphone.

Speech recognition technology is a technology that automatically determines the linguistic meaning of speech by changing the characteristics of the vibration of the voice, such as sound intensity and high and low, into a digital signal and analyzing it and comparing it with the speech data stored in the database. With the development of the Telematics System (Telematics System) is applied to the vehicle is gradually being used in various fields.

In general, a voice recognition device used in a car means a convenient operation of various peripheral devices that provide safety and convenience in driving such as a power window, a wiper, an emergency lamp, an air conditioner, and an audio provided in a car through a driver's voice. do.

Such a voice recognition device is a voice signal commanded by the driver through a microphone is converted into an analog electrical signal, and then a predetermined preprocessing process required for voice recognition is executed, and by separating and analyzing the preprocessed voice signal into a silent section and a voice section. Is done.

However, in the conventional voice recognition device, the sound output from the built-in speaker inside the vehicle is input to the microphone, so that voice recognition is not made accurately and thus, there is a disadvantage in that the accuracy of operation is reduced.

Patent Registration No. 10-1086602: Voice recognition system for a vehicle

The present invention has been made to solve the above problems, and an object of the present invention is to provide a vehicle speech recognition system provided with a directional speaker to prevent the sound output into the vehicle from being input to the microphone.

The vehicle voice recognition system according to the present invention for achieving the above object is controlled by a microphone installed in the vehicle and a control module of the vehicle for controlling the electric equipment installed in the vehicle to receive the voice of the occupant in the vehicle A connection part connected to a control module of the vehicle for inputting a signal, an input switch provided in the vehicle to allow the passenger to select a voice recognition mode, and the passenger to select the voice recognition mode by operating the input switch. The voice control unit recognizes the voice received through the microphone, generates a control signal corresponding to the recognized voice, and transmits the generated control signal to the control module of the vehicle through the connection unit. Installed and outputting sound, to prevent the output sound is input to the microphone In order to provide a directional sound output unit for outputting a directional sound toward the occupant, and to provide an audio signal input from the electrical equipment to the built-in speaker or the directional sound output unit installed in the vehicle, the voice recognition mode is not selected And a switching unit for providing the audio signal to the built-in speaker and providing the audio signal to the directional sound output unit when the voice recognition mode is selected.

The directional sound output unit may include a modulation module configured to generate a directional sound signal using the audio signal provided from the switching unit, and a directional sound signal installed in the vehicle to face the occupant in the vehicle and provided from the modulation module. It is provided with a directional speaker for outputting.

The directional speaker is installed in an interior of the vehicle facing the seat provided in the vehicle so that a rider can ride, so that an output portion for outputting the directional sound is directed toward the seat.

The microphone is preferably installed inside the vehicle except for the output range of the directional speaker from which the directional sound is output.

The modulation module may include an ultrasonic wave generator for generating reference ultrasonic waves, a modulator for modulating an audio signal provided from the switching unit using the reference ultrasonic waves as a carrier wave, an audio signal modulated by the modulator, and the reference ultrasonic waves. And an amplifying unit for amplifying and providing the directional speaker.

The vehicle voice recognition system according to the present invention can prevent the sound output into the vehicle by the directional sound output unit from being input to the microphone, thereby improving the accuracy of the voice recognition.

1 is a perspective view of a vehicle speech recognition system according to the present invention;
FIG. 2 is a block diagram of the vehicle speech recognition system of FIG. 1;
3 is a block diagram of a directional sound output unit of the vehicle speech recognition system of FIG. 1.

Hereinafter, a vehicle voice recognition system according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. As the inventive concept allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to the specific form disclosed, it should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the drawings, similar reference numerals are used for similar elements. In the accompanying drawings, the dimensions of the structures are shown in an enlarged scale than actual for clarity of the invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "comprise" or "have" are intended to indicate that there is a feature, number, step, action, component, part, or combination thereof described on the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in the commonly used dictionaries should be construed as having meanings consistent with the meanings in the context of the related art and shall not be construed in ideal or excessively formal meanings unless expressly defined in this application. Do not.

1 to 3 illustrate a vehicle speech recognition system 100 according to the present invention.

Referring to the drawings, the vehicle voice recognition system 100 includes a microphone 110 installed in the vehicle 10 so as to receive a voice of an occupant in the vehicle 10 and an electric field installed in the vehicle 10. The connection unit 120 connected to the control module 11 of the vehicle 10 to input a control signal to the control module 11 of the vehicle 10 controlling the device, and the passenger to select the voice recognition mode When the input switch 130 provided in the vehicle 10 and the passenger selects the voice recognition mode by operating the input switch 130, and recognizes the voice input through the microphone 110 The voice control unit 140 generates a control signal corresponding to the recognized voice and transmits the generated control signal to the control module 11 of the vehicle 10 through the connection unit 120 and the vehicle ( 10) is installed in the output sound, In order to prevent sound from being input to the microphone 110, a directional sound output unit 150 outputting a directional sound toward the occupant, and a built-in speaker provided with the audio signal input from the electric equipment. 12 or provided to the directional sound output unit 150, when the voice recognition mode is not selected, provides the audio signal to the built-in speaker 12, and when the voice recognition mode is selected, And a switching unit 160 for providing an audio signal to the directional sound output unit 150.

The microphone 110 is installed at the front ceiling of the vehicle 10 so that the passenger's voice of the vehicle 10 can be input more easily. The microphone 110 is applied to a microphone 110 so as to collect a passenger's voice, and when a uttered voice of the passenger is input, the microphone 110 converts it into an electrical voice signal and controls the voice controller 140. ) On the other hand, although the microphone 110 is not shown in the figure, it may be installed on the dashboard or steering wheel of the vehicle 10.

The connection unit 120 may be directly connected to the control module 11 by wire through an external connection port (not shown) connected to the control module 11 of the vehicle 10, or may be a Bluetooth or Zigbee method. The short range wireless communication method may be connected to the control module 11, and may be connected to an external network according to a wireless communication protocol such as Wi-Fi or IEEE to communicate with the control module 11.

Here, the control module 11 of the vehicle 10 is an electronic control unit (ECU) of an electric equipment such as an air conditioner installed in the vehicle 10, a lamp device including a head lamp, a wiper operating device, and a window opening and closing device for opening and closing a window. The body control module 11 (BCM: Body Control Module) for integrating and controlling each component or device of the vehicle 10 by integrating an electronic control unit (SCM) is preferably applied.

The input switch 130 is installed on the steering wheel of the vehicle 10 so that the passenger can easily operate while driving. When the occupant presses the input switch 130 once, the voice recognition mode is selected, and when the occupant presses the input switch 130 again while the voice recognition mode is selected, the voice recognition mode is released.

The voice controller 140 generates a voice recognition unit for recognizing a voice received through the microphone 110, a control signal corresponding to the voice recognized through the voice recognition unit, and generates the control signal through the connection unit. It is provided with an operating unit for transmitting to the control module 11 of the vehicle 10 through 120.

The voice recognition unit may recognize a user's voice by applying a speech recognition algorithm or a speech recognition engine to the voice signal input from the microphone 110.

At this time, the speech signal may be converted into a more useful form for speech recognition. The speech recognizer converts the input speech signal from an analog signal to a digital signal, and detects the start and end points of the speech and includes the same in the speech signal. Detected real voice interval. This is called end point detection (EPD).

In the detected section, features such as Cepstrum, Linear Predictive Coefficient (LPC), Mel Frequency Cepstral Coefficient (MFCC), or Filter Bank Energy A vector extraction technique may be applied to extract a feature vector of voice data VD.

The recognition result can be obtained by comparing the extracted feature vector with the trained reference pattern. To this end, an acoustic model for modeling and comparing signal characteristics of speech and a language model for modeling linguistic order relations such as words or syllables corresponding to a recognized vocabulary may be used.

The acoustic model may be divided into a direct comparison method of setting a recognition object as a feature vector model and comparing it with a feature vector of a speech signal and a statistical method of statistically processing the feature vector of the recognition object.

The direct comparison method is a method of setting a unit of a word, a phoneme, or the like to be recognized as a feature vector model and comparing how similar the input speech is. As a representative example, a vector quantization method is used. According to the vector quantization method, a feature vector of an input speech signal is mapped with a codebook, which is a reference model, and encoded as a representative value, thereby comparing the code values.

The statistical model method is a method of constructing a unit for a recognition object into a state sequence and using a relationship between state columns. The status column may consist of a plurality of nodes. There are two ways to use the relationship between state columns: Dynamic Time Warping (DTW), Hidden Markov Model (HMM), and neural networks.

Dynamic time warping is a method of compensating for differences in the time axis when considering the dynamic characteristics of speech whose length varies over time even if the same person pronounces the same. Assuming a Markov process with probability and observed probability of nodes (output symbols) in each state, we estimate state transition probability and observed probability of the nodes from the training data, and calculate the probability that the voice input from the estimated model will occur. Is a recognition technology.

On the other hand, a language model that models linguistic order relations such as words or syllables may apply acoustic relations between units constituting language to units obtained in speech recognition, thereby reducing acoustic ambiguity and reducing recognition errors. The language model has a model based on a statistical language model and a finite state automata (FSA). The statistical language model uses a chain probability of words such as Unigram, Bigram, and Trigram.

Meanwhile, the speech recognition unit is not limited thereto and may be any recognition means for recognizing the speech signal provided through the microphone 110.

The operation unit generates a control signal corresponding to the voice recognized by the voice recognition unit when the passenger operates the input switch 130 to select the voice recognition mode, and the generated control signal through the connection unit 120 (10) to the control module (11).

Here, the operation unit that may include a command for controlling the electric equipment of the vehicle 10 in the uttered voice of the occupant, an instruction indicating the type of the electric equipment of the vehicle 10, and the type of the electric equipment of each vehicle 10; There is provided a database (not shown) that stores a plurality of instructions relating to the operation according to the present invention, and control signals of the electric devices corresponding to the directives and the instructions.

The operation unit detects a command stored in the database among the voices recognized by the voice recognition unit, and transmits a control signal corresponding to the detected command to the control module 11 of the vehicle 10 through the connection unit 120. For example, when the occupant says 'turn on the air conditioner' inside the vehicle 10, the voice of the occupant input through the microphone 110 is recognized by the voice recognition unit and transmitted to the operating unit. Detects the 'air conditioner' and 'turn on' command, and the control signal for operating the air conditioner corresponding to the command and command among the control signals stored in the database to the control module 11 of the vehicle 10 send.

On the other hand, the operation unit when the passenger operates the input switch 130, if the voice recognition mode is not selected, the control signal so that the passenger can manually input the control signal for the electric equipment of the vehicle 10 to the control module 11 Not transmitted to the control module 11.

The directional sound output unit 150 includes a modulation module 151 for generating a directional sound signal using the audio signal provided from the switching unit 160 and the vehicle so as to face a passenger in the vehicle 10. (10) is provided inside the directional speaker 152 to output a directional sound signal provided from the modulation module 151.

The modulation module 151 includes an ultrasonic generator 153 for generating reference ultrasonic waves, a modulation unit 154 for modulating an audio signal provided from the switching unit 160 using the reference ultrasonic waves as a carrier wave, and the modulation. An audio signal modulated by the unit 154 and an amplifying unit 155 for amplifying the reference ultrasonic waves and providing the amplified speakers to the directional speaker 152 are provided.

The ultrasonic generator 153 is a carrier wave carrying an audio signal provided from the switching unit 160. The ultrasonic wave generator 153 generates reference ultrasonic waves and outputs them to the modulator 154 and the amplifier 155. At this time, the reference ultrasound is preferably 25kHz.

The modulator 154 modulates the audio signal using the reference ultrasound received from the ultrasonic generator 153 as a carrier wave. The amplifier 155 receives the modulated signal and the ultrasonic signal of the ultrasonic generator 153 and amplifies the modulated signal to a predetermined level. Here, the amplified two signals are output to the directional speaker 152. That is, the modulation module 151 generates the directional sound based on the heterodyne principle.

The directional speaker 152 includes a transducer that converts an electrical signal into an audible air pressure wave through a diaphragm. The directional speaker 152 receives the amplified two signals and generates an audible air pressure wave accordingly. The air pressure waves of the two signals generated by the directional speakers 152 penetrate the air and generate a combination tone by nonlinearity of the air, and the occupant hears the directional sound waves corresponding to the frequency difference between these two signals. do.

In this case, the directional speaker 152 is such that the output portion of the directional sound output to the seat in the interior of the vehicle 10 facing the seat provided in the vehicle 10 so that the passenger vehicle can ride Is installed. Here, the microphone 110 may be installed inside the vehicle 10 except for the output range of the directional speaker 152 through which the directional sound is output.

The switching unit 160 is connected to each electronic device so that the audio signal can be provided from the electronic device in the vehicle 10. In addition, the switching unit 160 is connected to the internal speaker 12 of the vehicle 10 and the modulation module 151 of the directional sound output unit 150 via a wire. Here, the electric equipment is applied to a device for outputting an audio signal, such as the vehicle 10 audio and navigation.

When the occupant selects the voice recognition mode through the input switch 130, the switching unit 160 modulates the audio signal input from the electric equipment so that the directional sound is provided to the occupant through the directional sound output unit 150. Output to (151). The modulation module 151 generates the directional sound using the input audio signal and outputs the directional sound to the occupant through the directional speaker 152. On the other hand, if the occupant does not select the voice recognition mode, the switching unit 160 outputs the audio signal input from the electric equipment to the built-in speaker 12.

The vehicle voice recognition system 100 according to the present invention configured as described above may prevent the sound output into the vehicle by the directional sound output unit 150 from being input to the microphone 110, thereby improving accuracy of voice recognition. There is an advantage that can be improved.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the invention. Thus, the present invention should not be limited to the embodiments set forth herein but should be construed in the broadest scope consistent with the principles and novel features set forth herein.

100: vehicle speech recognition system
110: microphone
120: connection
130: input switch
140: voice control unit
150: sound output unit
151: modulation module
152: directional speakers
153: ultrasonic generator
154: modulator
155: amplification unit
160: switching unit

Claims (5)

A microphone installed in the vehicle to receive a voice of a passenger in the vehicle;
A connection part connected to a control module of the vehicle for inputting a control signal to a control module of the vehicle controlling an electric equipment installed in the vehicle;
An input switch provided inside the vehicle to allow the occupant to select a voice recognition mode;
When the occupant selects the voice recognition mode by operating the input switch, the passenger recognizes the voice received through the microphone, generates a control signal corresponding to the recognized voice, and generates the generated control signal through the connection unit. Voice control unit for transmitting to the control module of the vehicle;
A directional sound output unit installed in the vehicle and outputting sound, the directional sound output unit outputting a directional sound toward the occupant to prevent the output sound from being input into the microphone; And
Providing an audio signal input from the electronic device to the built-in speaker installed in the vehicle or the directional sound output unit. When the voice recognition mode is not selected, the audio signal is provided to the built-in speaker. And a switching unit for providing the audio signal to the directional sound output unit when is selected.
Vehicle speech recognition system.
The method of claim 1,
The directional sound output unit
A modulation module for generating a directional sound signal using the audio signal provided from the switching unit; And
And a directional speaker installed inside the vehicle so as to face a passenger in the vehicle and outputting a directional sound signal provided from the modulation module.
Vehicle speech recognition system.
The method of claim 2,
The directional speaker is installed in the interior of the vehicle facing the seat provided in the vehicle so that the passenger vehicle can ride, the output portion for outputting the directional sound toward the seat,
Vehicle speech recognition system.
The method of claim 3,
The microphone is installed inside the vehicle except for the output range of the directional speaker to which the directional sound is output,
Vehicle speech recognition system.
The method of claim 2,
The modulation module
An ultrasonic generator for generating reference ultrasonic waves;
A modulator for modulating the audio signal provided from the switching unit using the reference ultrasound as a carrier; And
And an amplifier for amplifying the audio signal modulated by the modulator and the reference ultrasonic wave and providing the amplified speaker to the directional speaker.
Vehicle speech recognition system.

Images