KR20040075615A - Subsidiary apparatus of voice recognition system for automobile - Google Patents

Abstract

PURPOSE: A complementary device of a speech recognition system for an automobile is provided to prevent mixing of noise into a speech order by controlling an audio receiver set and/or windows, and to prevent a mistaken recognition of a driver's response speech by outputting a response of a confirmation request speech from the speech recognition system into a hardware-oriented switch signal. CONSTITUTION: A complementary device of the speech recognition system for the automobile includes a speech recognition operating switch(12) for minimizing existence of noise when a driver sends a speech order to the speech recognition system(70). A controlling means(10) stops operation of an audio receiver set of the automobile and intercepts all noise sources when an operation signal of the speech recognition operating switch is inputted. A "yes" switch(14) and a "no" switch(16) respond to a confirmation request message output from the speech recognition system as a hardware-oriented signal in response to the speech order. The operation signals of the "yes" switch and the "no" switch are inputted into the controlling means, and the controlling means operates the speech recognition system according to the operation signals of the "yes" switch and the "no" switch.

Description

Subsidiary apparatus of voice recognition system for automobile}

The present invention relates to a speech recognition system applied to an automobile, and in particular, to control the audio and / or window during the speech command transmission using the speech recognition system installed in the vehicle so that the noise is not mixed in the speech command, the speech recognition system The voice recognition system malfunctions in a driving environment with a lot of noise and ambient noise by preventing false recognition of the driver's response voice by using a hardware switch signal for the audible and negative response of the confirmation request sound. The present invention relates to a voice recognition system complementary device for a vehicle, which can be safely and reliably used, thereby helping the voice recognition system to be actively applied to a vehicle.

In general, the speech recognition system includes a feature extractor (a) and a speech recognizer (b) for recognizing speech according to the extracted speech feature, as schematically illustrated in FIG. 1. That is, the input voice signal undergoes a step of extracting a feature suitable for recognition, and then recognizes the input voice using the result. Here, 'MFC' (Mel-Frequency Cepstrum Coefficient) or 'PLPCC' (Perceptual Linear Prediction Cepstrum Coefficient) is mainly used among various methods of extracting the feature of speech by the feature extractor (a). Voice recognition unit (b) is a method such as 'HMM' (Hidden Markov Model), 'DTW' (Dynamic Time Warping) or a neural network.

However, the speech recognition performance deteriorates in the actual use environment, because some noise is mixed when the voice is input in the real environment. Therefore, for the practical use of speech recognition technology, efforts have been made to develop a speech recognition technology that is robust against noise, but have no practical effect.

As described above, in the feature extraction or recognition process for speech recognition, the performance is severely degraded when the noise intensity is increased, and thus there is a problem that it is more inappropriate to use when the noise is severe, such as a vehicle driving environment.

On the other hand, in recent years, the introduction of telematics (telematics) is a compound word of "telecommunication" and "informatics" in automobiles, and various services using an auto PC have been provided to the driver. Telematics is also called "automatic telematics" in that it uses an auto PC. A driver using a telematics can remotely diagnose a vehicle through a wireless network, and use the auto PC equipped with a wireless modem to provide various information such as traffic information, living information, and emergency rescue. You can use it to send and receive phone messages or voice emails. Although Telematics' Auto PC improves the convenience of use, including the voice recognition system, the voice recognition system is not used effectively for the reasons mentioned above because the driving environment of the vehicle is a lot of noise and noise as described above. Not only that, but it is also reported to affect the driving safety of the car.

In addition to the voice recognition system of the Telematics Auto PC described above, a vehicle includes a large number of devices and systems that need to recognize a driver's command through voice and inform the result of the voice. Therefore, although the voice recognition system has been actively sought to be installed in the automobile, the current speech recognition technology does not satisfactorily solve the problem of low recognition rate in the presence of many voice commands with similar pronunciation or noise. The practical application of the voice recognition system has been difficult.

Therefore, the technical problem to be achieved by the present invention is to solve the above problems of the prior art, by controlling the audio and / or window when transmitting a voice command using a voice recognition system installed in a car noise in the voice command Cars with a lot of noise and ambient noise can be prevented from being mixed, and by preventing the false recognition of the driver's response voice by using a temporary (yes or no) response to the confirmation request voice output from the voice recognition system as a hardware switch signal. The purpose of the present invention is to provide a voice recognition system complementary device for a vehicle, which enables the voice recognition system to be used safely and stably without a malfunction in the driving environment, thereby helping the voice recognition system to be actively applied to a vehicle.

On the other hand, another technical problem to be achieved by the present invention, home or office by installing a voice recognition complementary switch in the position, for example, steering wheel (steering wheel) that the driver can easily operate without special movement while driving It is an object of the present invention to provide a voice recognition system complementary device that can be used more effectively in an automobile environment than in an environment where a user's movement is required.

1 is a schematic configuration diagram of a general speech recognition system.

Figure 2 is a block diagram of an embodiment of a voice recognition system complementary device for a vehicle according to the present invention.

Figure 3 is a block diagram of another embodiment of a voice recognition system complementary device for a vehicle according to the present invention.

Figure 4 is a flow chart of the operation of the automotive voice recognition system complementary device according to the present invention.

<Description of the symbols for the main parts of the drawings>

10.Voice recognition complementary control device

12 ... Voice recognition switch

14 ... 'switch

16 ... 'Negative' Switch

22.Car Audio

24.Power window (window)

26.Vehicle speed sensor

In order to achieve the above object, an apparatus for supplementing a speech recognition system for a vehicle according to the present invention is a supplementary apparatus that is complementarily employed in a speech recognition system applied to an automobile, wherein a driver intends to transmit a speech command to the speech recognition system. A switch for voice recognition operation which is operated to minimize the presence of noise when the device is operated; Control means for stopping the operation of the car audio when the operation signal of the voice recognition operation switch is input and cutting off a source of sound that may become a noise in the voice command; And 'able' for informing the confirmation request message output from the voice recognition system in response to the voice command to a hardware signal (可; yes, yes, no; no, no). Including a 'switch' and a 'non' switch,

Each operation signal of the 'ga' switch and the 'sub' switch is input to the control means, and the control means is configured to operate the voice recognition system in response to each operation signal of the 'ga' switch and the 'sub' switch. Characterized in that.

In a preferred embodiment of the present invention, when the operation speed of the voice recognition operation switch is input, if the vehicle speed is higher than the set speed and the vehicle window is open, the control unit controls to close the window to reduce the ambient noise. Prevent ingress;

In a preferred embodiment of the invention, each switch is a pushbutton switch that is ON when the user is holding the pushed state, and each switch is attached to a steering wheel and used.

Hereinafter, with reference to the accompanying drawings will be described in detail a preferred embodiment of the voice recognition system complementary device for a vehicle according to the present invention. In the following description of the present invention, when it is determined that detailed descriptions of related well-known technologies or configurations may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described below are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or an operator. Therefore, the definition should be made based on the contents throughout the specification.

2 is a configuration diagram of an embodiment of a voice recognition system complementary device for a vehicle according to the present invention, Figure 3 is a configuration diagram of another embodiment of a voice recognition system complementary device for a vehicle according to the present invention, Figure 4 is The operation of the voice recognition system complementary device according to.

Referring to FIG. 2, an apparatus for supplementing a speech recognition system for a vehicle according to the present invention includes a switch for speech recognition operation operated by a driver to minimize the presence of noise when a driver wants to transmit a speech command to the speech recognition system 70. 12) and a sound that may stop the operation of the car audio 22 when the ON signal of the voice recognition operation switch is being input (when the driver presses the switch) and become noise in the voice command. Complementary control device for blocking the source of the (10), and in response to the confirmation request message output from the speech recognition system 70 in response to the voice command (可; Yes, yes), A 'no' switch 14 and a 'negative' switch 16 for informing a negative confirmation are made. Here, each operation signal of the 'ga' switch 14 and the 'sub' switch 16 is input to the complementary control device 10 as shown, the complementary control device 10 is a 'ga' switch 14 And the voice recognition system 70 in response to each operation signal of the 'sub' switch 16. The voice recognition operation switch 12 and the temporary switch 14 and the sub-switch 16 are preferably pushbutton switches that are ON when the user (driver) is kept in a pressed state, These switches are all attached to the steering wheel for the operator's convenience.

The complementary control device 10 of the present invention controls the power window 24 associated with the vehicle window, and receives a vehicle speed sensor 26 signal and a window opening sensor 28 signal for this purpose.

In the embodiment of Figure 2, the voice recognition system 70, the position search control device 50, the display 52, the microphone 62, the speaker 64, the position search / speech synthesis server 80 is commercialized As the components for the location search (road guidance) service, the voice recognition system 70 is a voice data and to the location search / voice synthesis server 80, the location search (road guidance) data is stored through the antenna (ANT) Send or receive location search request data.

2 is an example of the case where the voice recognition system 70 is mounted in a vehicle, and the embodiment of FIG. 3 is an example of the case where the voice recognition system is not built in the vehicle, and in the case of the embodiment of FIG. Server 90 performs up to voice recognition. That is, in the embodiment of FIG. 3, the location search / voice synthesis / voice recognition integrated server 90 has a location search request, a voice recognition and a voice synthesis function, and has a location search control device 50 mounted on a vehicle. Send and receive voice data, execution data, and the like. In the embodiment of Figs. 2 and 3, they have the same configuration except for the difference between whether the components related to voice recognition are in a vehicle or not.

The operation of the vehicle voice recognition system complementary device according to the present invention configured as described above will be described with reference to FIG.

For example, when a driver wants to receive location search (road and traffic guidance) information provided by the server 80 or 90 through a voice command, press the voice recognition operation switch 12 to generate a switch ON signal. Input to the complementary control device 10 (S10). The reason for inputting the switch-on signal to the complementary control device 10 by pressing the voice recognition operation switch 12 is that, when the voice command is made as described above, the audio sound in the vehicle and / or the noise around the vehicle is generated. This is to close the window by stopping the operation of the audio and operating the power window 24 so as not to mix.

When the on signal of the voice recognition operation switch 12 is input to the complementary control device 10, the supplementary control device 10 checks the operation state of the audio 22, and if the audio 22 is operating, the operation is performed. It stops so that an audio sound is not output (S12) (S14).

Then, the complementary control device 10 determines that there is room for ambient noise to flow into the vehicle when the car window is open, and operates the power window 24 to close the window (S16) (S20). At this time, the open state of the automobile window is preferably determined by the window open sensor 28. On the other hand, considering that the ambient noise of the car may be ignored if the car does not drive at a certain speed or more, the window may be operated by operating the power window 24 only when the vehicle speed is higher than a certain speed (for example, 50 km / h). It may be made to close (S18) (S20).

If the sound sources that can be mixed with noise in the voice command as described above are blocked, the driver says the voice command (eg, "Gangbuk-gu Office") (S22). The voice command of the driver, that is, the voice "Gangbuk-gu Office" is recognized by the voice recognition system 70 through the microphone 62. The voice recognition system 70 and the position search control device 50 cooperate with each other in order to confirm whether they have recognized the voice command spoken by the driver as a confirmation request message, for example, "Do you want Gangdong-gu office?" ? "Is asked (S24).

The confirmation request message "Do you want Gangdong-gu Office?" Is that the voice recognition system 70 incorrectly recognized the driver's voice command "Gangbuk-gu Office" and outputs the driver. 'Press the switch 16, the voice recognition system 70 to inform the hardware signal that the voice command was incorrectly recognized, and then input the voice command "Gangbuk-gu Office" again (S26) (S28).

When the voice command "Gangbuk-gu Office" of the driver is input again, the voice command is recognized by the voice recognition system 70 through the microphone 62 as described above, and the voice recognition system 70 and the position search control device 50, together with each other, and outputs a confirmation request message "Would you like Gangbuk-gu Office?" ).

The confirmation request message "Do you want Gangbuk-gu Office?" Is that the voice recognition system 70 correctly recognizes the driver's voice command "Gangbuk-gu Office", so the driver switches the 'ga' switch attached to the steering wheel (handle). Press 14 to notify the hardware signal that the voice recognition system 70 correctly recognized the voice command (S32). When the driver presses the '14' switch 14, the position search control device 50 receives the position search data for the Gangbuk-gu office through communication with the server 80 and performs road guidance (S34).

As a result, the present invention can completely solve the problem of low recognition rate of speech in a noisy automobile environment, thereby enabling the application of the speech recognition system to automobiles.

As described above, the apparatus for supplementing a speech recognition system for a vehicle according to the present invention controls audio and / or a window during speech command transmission using a speech recognition system installed in a vehicle so that noise is not mixed in the speech command. Voice recognition in the driving environment with a lot of noise and ambient noise by preventing the driver's misunderstanding of the driver's response voice by using the switch signal of the positive and negative (yes, no) response of the confirmation request output from the voice recognition system. It offers the advantage that the system can be used safely and reliably, thereby enabling the voice recognition system to be actively applied to the vehicle.

Although a preferred embodiment of the present invention has been described in detail above, those skilled in the art to which the present invention pertains may make various changes without departing from the spirit and scope of the invention as defined in the appended claims. It will be appreciated that modifications or variations may be made. Therefore, changes in the future embodiments of the present invention will not be able to escape the technology of the present invention.

Claims (3)

In the complementary device complementary to the voice recognition system applied to the car, A voice recognition operation switch operated by the driver to minimize the presence of noise when the driver wants to transmit a voice command to the voice recognition system; Control means for stopping the operation of the car audio when the operation signal of the voice recognition operation switch is input and cutting off a source of sound that may become a noise in the voice command; In response to the voice command, a 'switch' and a 'switch' indicating a hardware signal to the confirmation request message output from the voice recognition system (可; yes, yes) and negative (不; no, no) Including a sub-switch, Each operation signal of the 'ga' switch and the 'sub' switch is input to the control means, and the control means is configured to operate the voice recognition system in response to each operation signal of the 'ga' switch and the 'sub' switch. Car speech recognition system complementary device, characterized in that. According to claim 1, If the vehicle speed is higher than the set speed when the operation signal of the voice recognition operation switch is input and the vehicle window (window) is open, the control unit controls to close the window to prevent the inflow of ambient noise Car speech recognition system complementary device, characterized in that. The vehicle according to claim 1, wherein if the vehicle window is open when the operation signal of the voice recognition operation switch is input, the controller controls to close the window to prevent the inflow of ambient noise. Voice recognition system complementary device.