JP2008094228A - Call warning device for vehicle - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a call warning device for vehicle capable of avoiding any danger while traveling by preventing any call on a cellular phone during driving of a vehicle by a simple method. <P>SOLUTION: The sound received by a microphone 11 in a cabin is converted into a sound conversion unit 22, and a sound signal separation unit 23 removes the sound signal output by an audio/visual device 3 from the sound signal. The sound signal by the vocalization by each speaker is separated thereby. When a speaker number determination unit 24 determines that the sound signal is given only by one speaker based on the separated sound signal, a voice print data collation unit 25 detects the voice print data from the sound signal, the voice print data is collated with the voice print data of a driver which is registered in advance in a voice print registration unit 17. When it is determined that the voice print data by one speaker in vocalization is matched with the voice print data of the driver, a warning is given from a speaker 6 to the driver to stop the use of a cellular phone. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a call alert device for a vehicle that warns a driver of a vehicle with respect to a phone call.

  Conventionally, the danger to the use of a mobile phone while driving a vehicle has been pointed out. Recently, laws and regulations on the use of mobile phones while driving have been performed, and when a mobile phone is used while driving, a predetermined penalty is to be applied. However, the use of mobile phones by vehicle drivers has not completely disappeared, and countermeasures against this have been urgent from the viewpoint of vehicle technology.

On the other hand, there is a conventional technology related to a call control system that is connected to a mobile phone and determines whether to hold or record a call based on the driver's margin calculated from the behavior of the vehicle and the road on which the vehicle is traveling. (For example, refer to Patent Document 1). According to this, when it is determined that the driver has no room, the call is held and recorded by the mobile phone, so that it is possible to prevent the distraction of concentration due to the call and the traffic accident caused thereby.
JP 2003-125454 A (pages 9-10 and 5-7)

However, according to the above-described conventional technology, every time a user gets in the vehicle, it is time-consuming because his / her mobile phone must be connected to the call control system, which is quite effective for a driver who has forgotten to connect. There wasn't. In addition, the danger of using a mobile phone while driving is that it cannot cope with sudden situations such as pedestrians jumping out on the road, and can be predicted from the behavior of the vehicle and information on the road on which it is running In addition, it has been difficult to sufficiently avoid the danger during actual traveling by the above-described conventional technology.
The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a call alert device for a vehicle that can prevent a call by a mobile phone while driving and avoid a danger during travel. There is.

  In order to solve the problems of the present invention, according to the invention of claim 1, only one speaker speaks within a predetermined duration based on the voice in the passenger compartment, and If the voice quality of the speaker matches the registered driver's voice quality, there is a high possibility that the driver is using a mobile phone. Attention can be given to calls made by the mobile phone, and it is possible to reliably eliminate the danger of traveling due to mobile phone calls. In addition, it is not necessary for the driver to connect a mobile phone every time he gets on, and it is possible to prevent a mobile phone call while driving by an easy method.

According to the invention of claim 2, when it is determined that the voiceprint data of one speaker matches the voiceprint data of the driver, only the driver speaks by issuing a warning to the driver. Can be detected accurately and a warning can be issued.
According to the third aspect of the present invention, the voice signal produced by the speaker can be accurately separated by removing the voice signal output from the audio device of the vehicle from the voice signal obtained by converting the voice in the passenger compartment.

According to the fourth aspect of the present invention, it is possible to sufficiently alert the driver who is driving by emitting a warning sound using the speaker provided in the vehicle interior.
According to the invention of claim 5, by displaying a warning on the display device provided in the passenger compartment, the driver can be strongly cautioned visually.

  A vehicle call warning device 1 according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2. As shown in FIG. 1, the vehicle call warning device 1 according to the present embodiment is formed using a part of a normal vehicle navigation device, although not limited to this. The vehicle call warning device 1 is a position detection device 2 that is a positioning means for detecting the current position of the own vehicle (a vehicle in which the vehicle call warning device 1 is mounted and will be referred to as the own vehicle hereinafter), and the audio of the present invention. An audio / visual device 3 corresponding to the device, an external memory 8, an operation switch group 9, a vehicle speed sensor 10, a microphone 11 provided in a vehicle compartment, and a voice recognition device 12 are provided.

  Among these, the position detection device 2 is a GPS receiver for GPS (Global Positioning System) that detects (positions) the position of the own vehicle based on a radio wave transmitted from an artificial satellite for GPS, and the rotational angular velocity of the own vehicle. It has a gyroscope to detect, a distance sensor to detect the travel distance of the host vehicle, and a geomagnetic sensor (none of which is shown) for detecting the traveling direction of the host vehicle. Since these sensors have errors of different properties, they are configured to be used while complementing each other using a plurality of sensors.

  The audio / visual device 3 includes a controller 4 and a CD / DVD player 5 whose operation is controlled by the controller 4, a speaker 6 provided in the passenger compartment, a display device 7 formed by a CRT, a liquid crystal display, or the like. Yes. The CD / DVD player 5 is for reading data recorded on a CD-ROM or DVD-ROM as a recording medium, and reads audio data from an audio CD-ROM as an audio recording medium, and map data. It also serves to read map data from a map CD-ROM or map DVD-ROM as a recording medium. The display device 7 displays the road map and the position of the traveling vehicle based on the map data recorded on the map CD-ROM or the map DVD-ROM.

  The external memory 8 is composed of a flash memory card or the like, and is provided, for example, for storing program software for supporting information recording media of other standards, or for saving or reading specific data. It has been. The operation switch group 9 includes various mechanical switches and displays for inputting various commands such as designation of a destination and selection of a road map displayed on the display device 7 in order for a driver or the like to operate a navigation function. The touch panel is provided on the screen of the device 7.

  The vehicle speed sensor 10 is not limited to this, but is a pulse sensor attached to the transmission of the vehicle, and the detected value is used for vehicle speed display by a speedometer. The microphone 11 is attached to the interior of the vehicle and receives sound from the vehicle and converts it into an electrical signal (audio signal). The voice recognition device 12 is connected to the microphone 11 and recognizes words from the voice input to the microphone 11 by pattern recognition.

  The position detection device 2, the audio / visual device 3, the external memory 8, the operation switch group 9, the vehicle speed sensor 10, and the voice recognition device 12 described above are connected to the control device 13 (corresponding to the control means according to the present invention). Yes. The control device 13 is mainly configured by a microcomputer including a CPU 14, a ROM 15, a RAM 16, and the like. The ROM 15 stores application software including navigation software and audio software. Further, the control device 13 determines whether the data read from the CD / DVD-ROM set in the CD / DVD player 5 is audio data or map data. Since the navigation function of the vehicle call warning device 1 according to the present embodiment is the same as that of a normal navigation device, description thereof is omitted.

  A voice print registration device 17 and a voice analysis device 21 are connected to the control device 13. Although the voiceprint registration device 17 and the voice analysis device 21 are not limited to this, both are formed by a one-chip microprocessor. The voiceprint registration device 17 (corresponding to the voice registration means according to the present invention) is formed by the voice storage unit 18, the voiceprint data detection unit 19 and the voiceprint data registration unit 20, and registers the voiceprint of the driver of the vehicle. belongs to.

  The voice storage unit 18 is connected to the microphone 11 described above, and converts the voice from the driver received by the microphone 11 into an electrical signal (voice signal) and stores it. The voiceprint data detection unit 19 is connected to the voice storage unit 18 and detects voiceprint data for specifying the driver's voiceprint from the voice signal obtained by converting the voice of the driver. The voiceprint can represent the voice quality of the speaker, and by comparing the voiceprints of a plurality of speakers, it is possible to determine the identity of the utterance by a plurality of people. The voiceprint data registration unit 20 is connected to the voiceprint data detection unit 19 and registers the driver's voiceprint data detected by the voiceprint data detection unit 19. Since voiceprint data is stored in a non-volatile memory, once the driver's voiceprint data is registered, it is registered again unless the driver changes even if the vehicle call warning device 1 is disconnected from the vehicle battery. There is no need.

  On the other hand, the voice analysis device 21 includes a voice conversion unit 22 (corresponding to a voice conversion unit according to the present invention), a voice signal separation unit 23 (corresponding to a voice signal separation unit according to the present invention), a speaker number determination unit 24 (present book). (Corresponding to the number-of-speakers judging means according to the invention) and a voiceprint data collating unit 25 (corresponding to the speech collating means according to the present invention). The voice conversion unit 22 is connected to the microphone 11, and converts the voice in the passenger compartment received by the microphone 11 into an electrical signal (voice signal) and stores it. The audio signal separation unit 23 is connected to the audio conversion unit 22, and the audio signal formed by the audio conversion unit 22 is included when the audio generated from the audio / visual device 3 is included in the audio in the vehicle interior. The audio signal output from the audio / visual device 3 is removed from the audio signal. Thereafter, the remaining audio signals are separated into audio signals by utterances (conversations) for each speaker in the vehicle interior. As a method for separating an audio signal, for example, a method described in Japanese Patent Laid-Open No. 2001-306600, which is a patent publication, can be used.

  The number-of-speakers determination unit 24 is connected to the audio signal separation unit 23, and determines how many speakers are speaking in the vehicle interior from the audio signals separated by the audio signal separation unit 23. The voiceprint data matching unit 25 is connected to the voice signal separation unit 23, the speaker number determination unit 24, and the voiceprint data registration unit 20 of the voiceprint registration device 17, and one person speaks in the passenger compartment by the speaker number determination unit 24. If it is determined that the voice print data is detected, the voice print data is detected from the voice signal of the voice of one person, and is compared with the driver's voice print data registered in the voice print data registration unit 20 to determine the identity of both voice print data. To do. The method for determining the identity of a plurality of utterances by collating voiceprint data is described in the aforementioned Japanese Patent Application Laid-Open No. 2001-306600 or “Introduction to Electronic and Information Engineering Series 2 Acoustic and Speech Engineering” ( The method based on speaker recognition described in Sadahiro Furui (published by Modern Science Co., Ltd.) can be used.

  Next, based on FIG. 2, a method of calling warning by the control device 13 and the voice analysis device 21 will be described. When it is first determined that the vehicle is running based on the detection value of the vehicle speed sensor 10 (step S201), it is next determined whether or not there is an audio input to the microphone 11 (step S202). When there is a voice input to the microphone 11, the voice conversion unit 22 of the voice analysis device 21 converts the vehicle interior voice input to the microphone 11 into an electrical signal (voice signal) for a predetermined duration. And stored (step S203). Here, it is preferable that the predetermined continuous time is set longer than the time required for a plurality of people to communicate in a normal conversation. The converted audio signal is separated in the audio signal separation unit 23 after the audio signal output by the audio / visual device 3 is removed, and then into an audio signal produced by each speaker (step S204).

  Next, based on the separated audio signal, the speaker number determination unit 24 determines whether or not the audio signal is an audio signal of only one speaker (step S205). If it is determined that the separated audio signal is an audio signal for only one speaker and that only one speaker is speaking for a predetermined duration in the passenger compartment, the voiceprint data matching unit 25 After the voiceprint data is detected from the voice signal of the one speaker who is speaking (step S206), the voiceprint data is collated with the driver's voiceprint data registered in advance in the voiceprint registration device 17 before driving. (Step S207).

  As a result, when it is determined that the voiceprint data of one speaker who is speaking matches the driver's voiceprint data (step S208), the driver is likely to be using the mobile phone. 13 is stored in advance in the controller 4 of the audio-visual device 3 “Are you using a mobile phone? If you are using it, stop using it immediately. ] Is issued from the speaker 6 provided in the passenger compartment to warn the driver (step S209). If it is determined in step S201 described above that the vehicle is not traveling, or if it is determined in step S202 that there is no voice input to the microphone 11, the voice signal separated in step S205 is only one speaker. If it is determined that the voice signal is not the voice signal of the driver, and if it is determined in step S208 that the voiceprint data of one speaker does not match the voiceprint data of the driver, the program by the control device 13 is temporarily terminated. .

  According to the present embodiment, only one speaker speaks within a predetermined duration based on the voice in the passenger compartment, and the voice print data of the one speaker speaking and the registered driver's voiceprint data. If the voiceprint data matches, the driver is likely to be using a mobile phone. Therefore, a warning is issued to the driver by driving the mobile phone while driving. It is possible to reliably eliminate the danger of traveling due to telephone calls. In addition, it is not necessary for the driver to connect a mobile phone every time he gets on, and it is possible to prevent a mobile phone call while driving by an easy method.

In addition, by using voiceprint data to determine whether the voice of one speaker matches the voice of the driver, it is possible to accurately detect that only the driver is speaking and issue a warning. Can be emitted. Further, by removing the audio signal output from the audio / visual device 3 of the vehicle from the audio signal obtained by converting the audio in the vehicle interior, the audio signal generated by the speaker can be accurately separated. Further, by issuing a warning sound using the speaker 6 provided in the passenger compartment, it is possible to sufficiently alert the driver who is driving.
<Other embodiments>
The present invention is not limited to the above-described embodiments, and can be modified or expanded as follows.

When it is determined that the driver is speaking alone, a warning may be displayed on a display device provided in the passenger compartment. By doing so, the driver can be strongly alerted visually.
Furthermore, the driver can be more strongly alerted by flushing the screen of the display device instead of or together with the warning display.
The vehicle call alert device according to the present invention is not necessarily formed using the vehicle navigation device.
Register the voiceprint data of multiple drivers in the voiceprint registration device, and issue a warning when the voiceprint data of one speaker speaking matches the voiceprint data of one of the registered drivers. May be.

1 is an overall configuration diagram of a vehicle call warning device according to an embodiment of the present invention. The flowchart which shows the control method of the call alert apparatus for vehicles shown in FIG.

Explanation of symbols

  In the drawings, 1 is a vehicle call warning device, 3 is an audio / visual device (audio device), 6 is a speaker, 7 is a display device, 13 is a control device (control means), and 17 is a voiceprint registration device (voice registration means). , 22 is a speech conversion unit (speech conversion unit), 23 is a speech signal separation unit (speech signal separation unit), 24 is a speaker number determination unit (speaker number determination unit), and 25 is a voiceprint data verification unit (voice verification unit). ).

Claims (5)

Voice registration means for registering the voice quality of the driver of the vehicle;
Audio conversion means for receiving audio within a predetermined continuous time in the passenger compartment and converting it into audio signals;
A voice signal separating means for separating the voice signal formed by the voice converting means into a voice signal produced by each speaker;
Based on the audio signal separated by the audio signal separation means, a speaker number determination means for determining whether only one speaker is speaking within a predetermined duration time;
When it is determined by the speaker number determination means that only one speaker is speaking within a predetermined duration, the voice quality of the one speaker is checked against the voice quality registered in the voice registration means Voice verification means;
When the voice collating means determines that the voice quality of one speaker matches the voice quality of the driver, the vehicle has a control means for issuing a warning to the driver about a mobile phone call. Call alert device.   The voice registration means registers the driver's voice print data, and the voice verification means determines whether the voice print data of one speaker matches the driver's voice print data registered in the voice registration means. 2. The vehicle according to claim 1, wherein said control means issues a warning for a call by a mobile phone to the driver when it is determined that the voice print data of one speaker matches the voice print data of the driver. Call warning device.   3. The call alert device for a vehicle according to claim 1, wherein the audio signal separating unit removes an audio signal output from an audio device of the vehicle from the audio signal formed by the audio converting unit.   The vehicle call warning device according to any one of claims 1 to 3, wherein the control means emits a warning sound for a call made by a mobile phone to a driver using a speaker provided in a vehicle interior. .   The vehicle call warning device according to any one of claims 1 to 4, wherein the control means displays a warning for a call by a mobile phone to a driver on a display device provided in a vehicle interior.

Images