KR20140047985A - Voice recognition apparatus of vehicle with improved voice recognition rate - Google Patents

Voice recognition apparatus of vehicle with improved voice recognition rate Download PDF

Info

Publication number
KR20140047985A
KR20140047985A KR1020120114427A KR20120114427A KR20140047985A KR 20140047985 A KR20140047985 A KR 20140047985A KR 1020120114427 A KR1020120114427 A KR 1020120114427A KR 20120114427 A KR20120114427 A KR 20120114427A KR 20140047985 A KR20140047985 A KR 20140047985A
Authority
KR
South Korea
Prior art keywords
microphone
noise
sound
vehicle
voice recognition
Prior art date
Application number
KR1020120114427A
Other languages
Korean (ko)
Inventor
김용환
Original Assignee
현대모비스 주식회사
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 현대모비스 주식회사 filed Critical 현대모비스 주식회사
Priority to KR1020120114427A priority Critical patent/KR20140047985A/en
Publication of KR20140047985A publication Critical patent/KR20140047985A/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
    • B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
    • B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
    • B60R16/0373—Voice control
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition

Abstract

The present invention relates to a voice recognition device for a vehicle with improved voice recognition rates. The voice recognition device includes a first microphone which receives sound generated from a vehicle, a second microphone, and a head unit which detects noise by comparing sound recognized by the second microphone with stored noise patterns and separates noise from sound recognized by the first microphone when noise is detected. According to the present invention, the voice recognition device can increase voice recognition rates by recognizing voice by separating noise from sound when sound including noise with constant patterns generated from a vehicle is input through the microphones. [Reference numerals] (10) First microphone; (20) Second microphone; (32) First ADC; (34) Second ADC; (36) Signal processing unit; (38) Memory unit; (39) Control unit; (40) PTT button

Description

VOICE RECOGNITION APPARATUS OF VEHICLE WITH IMPROVED VOICE RECOGNITION RATE}

The present invention relates to a voice recognition device of a vehicle having an improved voice recognition rate. More particularly, when the electronic device of the vehicle is controlled by voice through a microphone, the voice recognition rate is lowered due to the noise generated in the vehicle, thereby causing the voice control to malfunction. The present invention relates to a voice recognition device of a vehicle having an improved voice recognition rate, which prevents the user from operating the electronic device of the vehicle while driving, due to the reduced voice recognition rate.

In general, many devices are installed in a vehicle, and recently, devices for the convenience of drivers or passengers have been steadily developed and installed. Representative examples include audio devices and air-conditioning devices, and more and more vehicles are provided with navigations that detect a car's location through satellites and guide a route to a destination.

However, while these convenience devices provide various conveniences to the driver and passengers, there is a problem that the driver's concentration of driving is reduced and distractions are increased and the risk of accidents increases as the driver manipulates the comfort devices while driving. .

In order to solve this problem, in recent years, a vehicle voice recognition device has been developed that recognizes a driver's voice and controls various convenience devices according to the driver's voice command when the driver commands the voice without directly operating the convenience devices.

However, the conventional vehicle voice recognition device has only a microphone for recognizing the driver's voice, there is a problem that the noise generated from the inside or outside of the vehicle is input to the microphone along with the voice and the voice control is not properly performed.

Prior art related to the present invention is Republic of Korea Patent Publication No. 10-2006-0126435 (2008.06.17. Publication, the name of the invention: automatic volume control device and method of the vehicle navigation system).

The present invention has been made to improve the above-mentioned problems, when controlling the electronic device of the vehicle by voice through the microphone, by adding a separate microphone for detecting the noise of a certain pattern of noise, such as engine sound or thunder sound The object of the present invention is to provide a speech recognition apparatus of a vehicle in which the speech recognition rate is improved to extract the speech by separating the noise from the sound recognized through the microphone when it is detected.

According to an aspect of the present invention, a voice recognition apparatus for a vehicle having an improved voice recognition rate may include a first microphone and a second microphone configured to receive sound generated from a vehicle; And a head unit for detecting noise by comparing the sound recognized through the second microphone with a stored noise pattern, and separating the noise from the sound recognized through the first microphone when the noise is detected.

In the present invention, the head unit includes a first ADC (Analog to Digital Converter) and a second ADC for converting the sound recognized by the first microphone and the second microphone into a digital signal, respectively; A memory unit for storing a noise pattern; A signal processor for detecting noise by comparing the sound converted into a digital signal through the second ADC with the noise pattern stored in the memory unit; And a controller for separating the noise from the sound converted into a digital signal through the first ADC when the noise is detected.

In the present invention, when the PTT button is input, the head unit receives the sound recognized through the first microphone as the first ADC, and always receives the sound recognized through the second microphone as the second ADC. Characterized in that the input.

In the present invention, the head unit stores a sound having a fixed pattern as a noise pattern among the sounds recognized through the second microphone when the sound recognized through the first microphone is not input to the first ADC. Characterized in that.

In the present invention, the first microphone and the second microphone is characterized in that located within a predetermined reference distance.

According to the present invention, when a predetermined pattern of noise generated in a vehicle is stored in advance and a sound including the noise is input through a microphone, the voice recognition rate can be increased by separating the noise from the corresponding sound and recognizing the voice.

In addition, the present invention prevents the voice recognition rate of the voice recognition device from lowering due to the noise generated in the vehicle, thereby helping the driver to drive safely since the driver does not need to directly operate the electronic device while driving.

1 is a functional block diagram of a voice recognition device of a vehicle having improved voice recognition rate according to an embodiment of the present invention.

Hereinafter, a voice recognition apparatus of a vehicle having an improved voice recognition rate according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In this process, the thicknesses of the lines and the sizes of the components shown in the drawings may be exaggerated for clarity and convenience of explanation. In addition, the terms described below are defined in consideration of the functions of the present invention, which may vary depending on the intention or custom of the user, the operator. Therefore, definitions of these terms should be made based on the contents throughout this specification.

1 is a functional block diagram of a voice recognition device of a vehicle having improved voice recognition rate according to an embodiment of the present invention.

Referring to FIG. 1, a voice recognition apparatus of a vehicle having an improved voice recognition rate includes a first microphone 10, a second microphone 20, and a head unit 30.

The first microphone 10 and the second microphone 20 are devices that receive sound generated from a vehicle, and in particular, a band pass through which only sound in a frequency band corresponding to a human voice is passed in order to recognize a driver's voice. It includes a filter (not shown), and generates an electric signal according to the vibration to recognize the driver's voice.

At this time, the frequency band passing through the band pass filter of the first microphone 10 and the band pass filter of the second microphone 20 is set to be the same, and noise included in the sound recognized by the first microphone 10 is set. In order to extract and remove from the sound recognized by the second microphone 20, the frequency band passing through the band pass filter of the second microphone 20 and the frequency band passing through the band pass filter of the first microphone 10 and Match.

In particular, since the noise included in the sound input to the first microphone 10 must be separated through the sound recognized through the second microphone 20, in the present embodiment, the first microphone 10 and the second microphone 20 are separated. Install so that it is located within the preset reference distance. In this case, the reference distance means a distance enough to be recognized that the same sound is input to the first microphone 10 and the second microphone 20.

The head unit 30 is a device for detecting noise by comparing the sound recognized through the second microphone 20 with the stored noise pattern, and separating the noise from the sound recognized through the first microphone 10. The first ADC 32, the second ADC 34, the signal processor 36, the memory 38, and the controller 39 are included.

The first ADC 32 converts the sound recognized through the first microphone 10 into a digital signal, and the second ADC 34 converts the sound recognized through the second microphone 20 into a digital signal.

The signal processor 36 detects the noise by comparing the sound converted into the digital signal through the second ADC 34 with the noise pattern stored in the memory unit 38 to be described later, and the memory unit 38 stores the noise pattern. have. A detailed process of storing the noise pattern in the memory unit 38 will be described later.

The controller 39 extracts a voice by separating the noise detected by the signal processor 36 from the sound converted into a digital signal through the first ADC 32 so that each electronic device performs control according to the corresponding voice. .

In the present embodiment, when the PTT button 40 is input, the head unit 30 receives a sound recognized through the first microphone 10 to the first ADC 32, and the second microphone 20. The sound recognized through) is always input to the second ADC 34.

The head unit 30 is a sound recognized through the second microphone 20 when the PTT button 12 is not input so that the sound recognized through the first microphone 10 is not input to the first ADC 32. The sound having a fixed pattern is stored in the memory unit 38 as a noise pattern.

Specifically, since the noise tends to form a certain pattern, the signal processor 36 detects whether the sound recognized by the second microphone 20 and converted into a digital signal has a fixed pattern, and if the fixed pattern indicates the sound, The noise is recognized and stored in the memory unit 38.

At this time, a method of detecting whether a fixed pattern has a method is to temporarily store the digital signal converted by the second ADC 34 in the memory unit 38 and check whether the stored digital signal has a repetitive pattern. Any method of detecting whether the signal has a fixed pattern may be included.

In this case, the sound detected by the signal processor 36 as noise includes noise inside the vehicle and noise outside the vehicle, and noise outside the vehicle may be caused by a weather phenomenon such as rain or thunder, or driving of the vehicle engine. By sound.

That is, in the present embodiment, the head unit 30 always receives a sound recognized through the second microphone 20, and if the received sound indicates a fixed pattern, the head unit 30 recognizes the corresponding sound as noise and recognizes the pattern as a memory 38. Store in

In addition, when the sound recognized through the first microphone 10 is input to the first ADC 32, when the sound is detected by comparing the sound recognized through the second microphone 20 with the noise pattern stored in the memory unit 38, The voice recognition rate of the voice recognition device of the vehicle is improved by extracting a voice by separating noise from the sound recognized through the first microphone 10.

At this time, the noise separation method for removing a specific noise pattern from the acoustic signal converted into a digital signal can be applied by selecting from a known or unknown signal processing method.

Referring to the operation of the speech recognition device of the vehicle with improved speech recognition rate according to an embodiment of the present invention having the above structure as follows.

In the present embodiment, the second microphone 20 located within the reference distance from the first microphone 10 is added to receive the sound input from the vehicle, and if the sound recognized through the second microphone 20 indicates the fixed pattern, Since the sound is recognized as noise and the pattern is stored in the memory unit 38, when the driver executes voice control through the first microphone 10, the noise included in the sound recognized through the first microphone 10 may be separated. Can be.

To this end, when a sound recognized through the first microphone 10 is not input to the first ADC 32, a sound having a fixed pattern among the sounds recognized through the second microphone 20 is a noise pattern as a noise pattern. 38).

When the sound recognized through the first microphone 10 is input to the first ADC 32, the sound is detected by comparing the sound recognized through the second microphone 20 with a noise pattern stored in the memory unit 38. In addition, noise is separated from the sound recognized by the first microphone 10 to extract a voice so that each electronic device performs control according to the corresponding voice.

According to the present exemplary embodiment, when a certain pattern of noise generated in a vehicle is stored in advance, and a sound including the noise is input through a microphone, the voice recognition rate may be increased by separating the noise from the corresponding sound and recognizing the voice.

In addition, the present embodiment may help the driver's safe driving since the driver may directly remove the operation by preventing the voice recognition rate of the voice recognition device from being lowered due to the noise generated in the vehicle.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be taken by way of limitation, I will understand. Accordingly, the true scope of the present invention should be determined by the following claims.

10: first microphone 20: second microphone
30: head unit 32: first ADC
34: second ADC 36: signal processor
38: memory unit 39: control unit
40: PTT button

Claims (5)

A first microphone and a second microphone to receive sound generated from a vehicle; And
A head unit for detecting a noise by comparing the sound recognized through the second microphone with a stored noise pattern, and separating the noise from the sound recognized through the first microphone when the noise is detected.
Speech recognition device of a vehicle with improved speech recognition rate comprising a.
The method of claim 1,
The head unit includes a first ADC (Analog to Digital Converter) and a second ADC for converting the sound recognized by the first microphone and the second microphone into a digital signal, respectively;
A memory unit for storing a noise pattern;
A signal processor for detecting noise by comparing the sound converted into a digital signal through the second ADC with the noise pattern stored in the memory unit; And
A controller for separating the noise from the sound converted into a digital signal through the first ADC when the noise is detected
Voice recognition device of a vehicle with improved speech recognition rate comprising a.
3. The method of claim 2,
When the PTT button is input, the head unit receives the sound recognized through the first microphone through the first ADC, and receives the sound recognized through the second microphone through the second ADC. Voice recognition device of the vehicle, the speech recognition rate is improved.
The method of claim 3,
The head unit may store a sound having a fixed pattern in the memory unit as a noise pattern among sounds recognized through the second microphone when the sound recognized through the first microphone is not input to the first ADC. The speech recognition device of the vehicle with improved speech recognition rate.
The method of claim 1,
And the first microphone and the second microphone are located within a preset reference distance.
KR1020120114427A 2012-10-15 2012-10-15 Voice recognition apparatus of vehicle with improved voice recognition rate KR20140047985A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020120114427A KR20140047985A (en) 2012-10-15 2012-10-15 Voice recognition apparatus of vehicle with improved voice recognition rate

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020120114427A KR20140047985A (en) 2012-10-15 2012-10-15 Voice recognition apparatus of vehicle with improved voice recognition rate

Publications (1)

Publication Number Publication Date
KR20140047985A true KR20140047985A (en) 2014-04-23

Family

ID=50654305

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020120114427A KR20140047985A (en) 2012-10-15 2012-10-15 Voice recognition apparatus of vehicle with improved voice recognition rate

Country Status (1)

Country Link
KR (1) KR20140047985A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9799334B2 (en) 2014-12-17 2017-10-24 Hyundai Motor Company Speech recognition apparatus, vehicle including the same, and method of controlling the same

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9799334B2 (en) 2014-12-17 2017-10-24 Hyundai Motor Company Speech recognition apparatus, vehicle including the same, and method of controlling the same

Similar Documents

Publication Publication Date Title
US9230538B2 (en) Voice recognition device and navigation device
JP4965036B2 (en) A method for controlling a device via an audio signal, particularly in an automobile
JP3920097B2 (en) Voice recognition device for in-vehicle equipment
JP2009020423A (en) Speech recognition device and speech recognition method
JPWO2017042906A1 (en) In-vehicle voice recognition device and in-vehicle device
EP3654329A1 (en) In-vehicle device and speech recognition method
US9847091B2 (en) Speech processing apparatus, speech processing method, speech processing program, method of attaching speech processing apparatus, ceiling member, and vehicle
EP2977986B1 (en) Audio command adaptive processing system and method
JP6361565B2 (en) In-vehicle device operation control device
KR20160037484A (en) Voice recognition apparatus and method
JP6459330B2 (en) Speech recognition apparatus, speech recognition method, and speech recognition program
US10026414B2 (en) Speech processing system, vehicle, speech processing unit, steering wheel unit, speech processing method, and speech processing program
KR20140047985A (en) Voice recognition apparatus of vehicle with improved voice recognition rate
KR20180005828A (en) Method and vehicle controller for intuitive adjusting sound volume
JP4016529B2 (en) Noise suppression device, voice recognition device, and vehicle navigation device
KR20160050135A (en) Method and apparatus for controlling volume of audio for vehicle
WO2006025106A1 (en) Voice recognition system, voice recognizing method and its program
KR101592761B1 (en) Method for processing voice data in vehicle
KR102406115B1 (en) System and method for automatic control of vehicle audio
JP4429691B2 (en) On-vehicle acoustic device, control method for on-vehicle acoustic device, control program for on-vehicle acoustic device, and recording medium
KR20010106799A (en) Apparatus for recognizing speech in a motor vehicle
JP2001222291A (en) Controller using voice recognition device
JP2008309865A (en) Voice recognition device and voice recognition method
JP2003084795A (en) On-vehicle voice recognition system
JP2003162296A (en) Voice input device

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination