JP2007263651A - On-vehicle navigation device and vehicle signal detection method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an on-vehicle navigation device and a vehicle signal detection method for detecting a vehicle signal, such as a back signal, even without performing wire connection of its signal line and contributing to the improvement in accuracy of autonomous navigation. <P>SOLUTION: In this on-vehicle navigation device, equipped with the function of executing processes related to navigation by utilizing vehicle signals, the data on the sound of the vehicle signals are previously registered in a storage means, with the sound generated accompanying the outputting of the vehicle signal in a vehicle compartment. While detecting the sounds generated in the vehicle compartment by a microphone (S2), the signal of the sounds inputted through the microphone is compared/collated with the data on the sound registered in the storage means by a sound recognition means (S6), in order to determine whether the waveform of the inputted sound matches the waveform of the vehicle signal (S7). When matching is determined, a signal instructing to that effect is outputted (S8) with this signal and detection of the vehicle signal is conducted. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an on-vehicle navigation device and a vehicle signal detection method, and more particularly to an on-vehicle navigation device and a vehicle signal detection method adapted to detect a vehicle signal using a voice recognition function.

  In a typical in-vehicle navigation device, a control device such as a CPU for controlling all processing related to navigation, a storage device such as a CD-ROM or DVD-ROM storing map data, a display device such as an LCD monitor, A GPS receiver for detecting the current position of the vehicle, a self-contained navigation sensor such as a gyro for detecting the direction and traveling speed of the host vehicle, a vehicle speed sensor, and the like are provided. Then, the control device reads out map data including the current position of the own vehicle from the storage device, draws a map image around the own vehicle position on the screen of the display device based on the map data, and presents the current position of the own vehicle. The vehicle position mark is displayed superimposed on the screen, the map image is scrolled according to the movement of the vehicle, the map image is fixed on the screen and the vehicle position mark is moved , So you can see at a glance where your car is currently driving.

  The in-vehicle navigation device is equipped with a function (route guidance function) for guiding the user so that the user can easily travel on the road without making a mistake. According to this route guidance function, the optimal route connecting from the departure place (typically the vehicle position) to the set destination using the map data is determined by the control device, such as a horizontal search method or Dijkstra method. A simulation calculation is performed to search, and the searched route is stored as a guidance route, so that the guidance route can be distinguished from other roads on the map image while traveling (for example, by changing the color or line width). When the specified distance is reached to the approaching intersection on the guidance route, an enlarged view of the intersection (an arrow indicating the direction of travel at the intersection) Display the distance to the destination, the name of the intersection, etc.), so that the user can grasp the optimum route to the destination.

  In such a navigation device, vehicle signals acquired from various sensors or the like are used for various processes related to navigation. Vehicle signals include GPS signals output from GPS receivers, signals output from autonomous navigation sensors such as gyros, vehicle speed pulses (signals) output from vehicle speed sensors, back signals output from shift position sensors, turn signals There are blinker signals that are output when the (direction indicator) is activated. In particular, the vehicle speed pulse is an indispensable signal for autonomous navigation, and plays an important role in detecting the vehicle position by autonomous navigation using a gyro even when GPS signals are not received or cannot be received. Fulfill. However, the vehicle speed pulse is a signal for instructing the traveling speed of the vehicle to the last, and the traveling direction of the vehicle (whether the vehicle is moving forward or backward) cannot be determined by this signal alone. In order to determine the traveling direction, it is necessary to acquire a back signal, and navigation devices using such a back signal are currently on the market.

  Moreover, some recent navigation devices have a voice recognition function. In such a navigation device, for example, when searching for a facility, it is possible to easily search for a facility by simply inputting the name of the facility via a microphone without performing a manual operation such as a remote control operation.

As a technique related to the above-described conventional technique, for example, as described in Patent Document 1, in a vehicle identification device that determines a type of a vehicle traveling on a road using a sound collecting microphone, for a certain period of time, The vehicle type is discriminated by taking into account the ratio of the level of the frequency band specific to the discrimination target vehicle type to the noise level of the entire band and the similarity between both level waveforms within a certain time.
JP-A-5-325090

  As described above, in the conventional vehicle-mounted navigation device, a vehicle signal such as a vehicle speed pulse or a back signal is acquired and used for processing such as self-contained navigation. Of these vehicle signals, as for the vehicle speed pulse (signal), the method of connecting the signal line to the navigation device body is relatively distributed in the market. Even if additional equipment is installed later, it is possible to increase the accuracy of the self-contained navigation by connecting the signal line of the vehicle speed pulse.

  However, for the back signal, there is not much information on how to connect the signal line, and navigation devices that use the back signal are often limited to genuine products. There was a problem that it could not be used easily. In other words, the back signal can be used to correct the position when the vehicle moves backward (back), but currently, the back signal is used when a navigation unit of another manufacturer's product that is not a genuine product is added later. The signal line of the signal cannot be easily connected to the navigation device body.

  As for the winker signal, for example, there is known a method for determining a small angle branch using the winker signal when changing the course from a main line to a road that is branched at a small angle, but navigation using such a method is known. In many cases, the equipment is limited to genuine products. Further, as with the back signal, there is a problem that the signal for connecting the signal line of the winker signal is not so much available, so that the winker signal cannot be easily used.

  As a method for determining a small angle branch, in addition to the above-described method using the winker signal, a method in which a signal detected by a gyro is appropriately processed is generally used. However, since the signal (level) detected by the gyro is very small, the accuracy of the determination is not so high and the reliability is relatively low.

  The present invention was created in view of the problems in the prior art, and can detect a vehicle signal such as a back signal without connecting the signal lines, thereby contributing to an improvement in accuracy of self-contained navigation. An object is to provide an in-vehicle navigation device and a vehicle signal detection method.

  In order to solve the above-described problems of the prior art, according to one aspect of the present invention, a microphone installed at a predetermined location in a vehicle interior and the vehicle signal generated in advance in association with the output of the vehicle signal in the vehicle interior Storage means for registering the sound data, and voice recognition means for comparing and collating the sound signal input via the microphone with the sound data registered in the storage means. Determines whether the waveform of the input sound matches the waveform of the vehicle signal based on the comparison and collation, and outputs a signal indicating that when it determines that the waveform matches. A navigation device is provided.

  According to the vehicle-mounted navigation device of the present invention, the sound (voice) generated in the passenger compartment is detected by the microphone, and the detected sound signal and the sound data registered in the storage means are detected by the voice recognition means. Are compared with each other to determine whether or not the detected waveform of the sound matches the waveform of the vehicle signal, and when it is determined to match, a signal indicating that is output. Therefore, by detecting this output signal, it can be determined that the signal input at that time is a vehicle signal. That is, even if the signal line of the vehicle signal is not connected (wiring to the navigation device), the navigation device can detect the vehicle signal by voice recognition.

  Information (vehicle signal) recognized in this way can be used for map matching. For example, in the case of a back signal, an AT vehicle can recognize that the vehicle is in a “back” state by detecting (voice recognition) a sound, and can use the recognition result for processing of independent navigation. . As a result, it is possible to improve the accuracy of the self-contained navigation (vehicle position / vehicle direction detection accuracy).

  According to another aspect of the present invention, in an in-vehicle navigation device having a function of executing a process related to navigation using a vehicle signal, the signal generated in advance in the passenger compartment accompanying the output of the vehicle signal. The sound data of the vehicle signal is registered in the storage means, and the sound signal input through the microphone and the sound data registered in the storage means are sounded while detecting the sound generated in the passenger compartment with the microphone. A comparison means is used for recognition, and it is determined whether or not the waveform of the input sound matches the waveform of the vehicle signal based on the comparison check, and when it is determined to match, a signal indicating that is output. A vehicle signal detection method is provided, wherein the vehicle signal is detected by the signal.

  Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

  FIG. 1 is a block diagram showing the configuration of an in-vehicle navigation device according to an embodiment of the present invention.

  In the in-vehicle navigation device 30 according to the present embodiment, reference numeral 1 denotes a hard disk drive (HDD) as a recording medium, and a disk (not shown) driven by the HDD 1 has each scale level (1/12500, 1 / 25000, 1 / 50,000, etc.) are stored in the allocated storage area, which is divided into longitude and latitude widths of appropriate sizes. This map data includes road unit data necessary for various processes such as route search and map matching, and intersection unit data representing details of the intersection, as well as various facilities (convenience store, gas station, super discount shop, department store, Data (position, address, telephone number, various information such as genre, etc.) related to the station. The road unit includes nodes corresponding to points where a plurality of roads intersect such as intersections and branches (points expressed by longitude and latitude) and links corresponding to roads, lanes, and the like connecting the nodes. Further, the HDD 1 stores a search data list used when searching for facilities manually and data (speech recognition dictionary) used when searching by voice recognition in respective allocated storage areas. In the present embodiment, the HDD 1 is used, but other recording media such as a DVD drive (DVD-ROM) and a CD drive (CD-ROM) may be used instead.

  Reference numeral 2 denotes a microphone that detects sound (including sound) generated in the passenger compartment and converts it into an analog waveform signal corresponding to the sound level. For example, in the vicinity of the sun visor or the rear mirror in front of the driver's seat, the center of the steering wheel And on the center console (dashboard). The microphone 2 is basically used for inputting an instruction (sound) related to facility search or the like issued by a user (for example, a driver). It is used to detect accompanying sounds (in this embodiment, “peep-peep” sound corresponding to the back signal and “tick” sound corresponding to the blinker signal).

  Reference numeral 3 denotes an operation unit for operating a navigation apparatus body 10 to be described later, and has, for example, a form of a remote controller (remote controller). Although not particularly illustrated, this remote controller displays various menus on the screen of the display device 7 to be described later, selects various menus and various items on the display screen, and executes the selected menus and the like. Various operation keys, buttons, joysticks, and the like are provided. 4 is a communication device such as a mobile phone or an in-vehicle phone for communication with an external information center (in the case of a mobile phone, a dedicated modem is attached), 5 is a GPS signal sent from a GPS satellite A GPS receiver that detects the longitude and latitude of the current position of the vehicle, 6 is a self-contained navigation sensor that includes an angle sensor such as a gyro that detects the direction of the vehicle, a distance sensor that generates a pulse at every fixed distance, etc. Indicates.

  Reference numeral 7 denotes a display device composed of an LCD monitor or the like, which is installed at a substantially middle position of the center console so that the display screen can be seen at least from the driver's seat. On the screen of the display device 7, based on control from the navigation device body 10 described later, guidance information related to navigation (a map around the current position of the vehicle, the vehicle position mark, from the vehicle position to the destination) And various guidance information such as facility search based on voice recognition). Reference numeral 8 denotes a speaker. Similarly, based on the control from the navigation apparatus body 10, the guidance information related to the navigation is output as a voice.

  In the navigation device body 10, 11 is a buffer memory for temporarily storing map data read from the HDD 1 (disk), and 12 is a control unit constituted by a microcomputer or the like. Although not specifically illustrated, the control unit 12 incorporates a memory such as a ROM storing various programs such as a guidance route search program. The control unit 12 basically detects the current position of the host vehicle based on signals output from the GPS receiver 5 according to various programs stored in the memory, and signals output from the autonomous navigation sensor 6. The vehicle's heading and travel speed are calculated based on the map, the map data to be displayed is read from the HDD 1 to the buffer memory 11, and the departure point (own vehicle) is set according to the search conditions set using the read map data. Various processings related to navigation, such as searching for a guidance route from the current location of the vehicle to the destination. Further, as a process related to the present invention, the control unit 12 has a function of controlling a process related to vehicle signal detection based on voice recognition in cooperation with a digital signal processor (DSP) 14 described later. Further, a window opening / closing signal is input to the control unit 12, and control is performed depending on whether any window of the vehicle is in an “open” state or a “closed” state, as will be described later. The unit 12 outputs a control signal for controlling whether or not to lower the threshold level serving as a criterion for detecting the vehicle signal.

  An audio input unit 13 amplifies an analog waveform signal of a sound (voice) detected by the microphone 2 as appropriate, digitizes it, and outputs it. The digitized waveform signal is input to the control unit 12 and to the DSP 14. The DSP 14 has a built-in voice recognition function, and the waveform of a sound (voice) signal detected by the microphone 2 and input via the voice input unit 13 based on control from the control unit 12 as described later is stored in a memory described later. The vehicle signal (back signal / blinker signal) registered in advance is compared and collated (pattern matching processing), and when a coincidence (matching) of both waveforms is detected, a signal indicating that fact is output to the control unit 12. When receiving this signal, the control unit 12 can determine that the sound input at that time is a “vehicle signal sound” (detection of a vehicle signal). The internal configuration of the DSP 14 will be described later.

  Reference numeral 15 denotes a vehicle signal sound registration unit which is a feature of the present invention, and includes, for example, a nonvolatile semiconductor memory such as a flash memory. In the vehicle signal sound registration unit 15, waveform data of a sample sound of a vehicle signal to be detected (in this embodiment, a “peep-peep” sound for a back signal and a “tick” sound for a winker signal) is registered. . As a mode of registration, a back signal and a blinker signal are individually output in advance in the vehicle interior (with the window closed), and a “peep-peep” sound and a “tick” generated in association with each output. The sound is individually detected by the microphone 2, and the detected analog waveform signal is amplified and digitized through the voice input unit 13, and then converted into digital waveform data in WAV (or WAVE) format by the control unit 12, and the vehicle signal sound The data is stored in the registration unit 15 as “WAV waveform”.

  Reference numeral 16 denotes a map drawing unit that performs map image drawing processing using map data read to the buffer memory 11 based on control from the control unit 12, and reference numeral 17 denotes various menu screens (operation screens) depending on the operation status. An operation screen / mark generator 18 for generating various marks such as a vehicle position mark and a cursor, and 18 are all nodes from the starting point to the destination of the guidance route searched by the controller 12 (points expressed in longitude and latitude) The guide route storage unit 19 stores data relating to the coordinates of the navigation route, 19 reads out the data of the guide route from the guide route storage unit 18 based on the control from the control unit 12, and the guide route is referred to as another road. The guidance route drawing part which draws with a different display mode (for example, changing a color, making line width thick, etc.) is shown.

  Reference numeral 20 denotes an image composition unit. Based on the control from the control unit 12, the map image drawn by the map drawing unit 16 is added to the guide route drawn by the guide route drawing unit 19, the operation screen / mark generation unit 17. The generated operation screen and various marks such as the vehicle position mark are overlaid and displayed on the screen of the display device 7. Reference numeral 21 denotes an audio output unit which converts the guidance information (digital information) related to the navigation into an analog audio signal based on the control from the control unit 12 and outputs it to the speaker 8.

  Next, the internal configuration of the DSP (digital signal processor) 14 will be described with reference to FIG.

  The DSP 14 is for detecting a vehicle signal by pattern matching based on voice recognition as described above, and as a functional block related to the present invention, as shown in the figure, a CPU 41, a memory (RAM) 42, A buffer memory 43, a voice recognition processing unit 44, and a threshold setting unit 45 are provided. Based on the control from the control unit 12, the CPU 41 cooperates with the voice recognition processing unit 44 to execute processing related to vehicle signal detection based on voice recognition. The RAM 42 is used as a temporary memory for taking in the waveform data of the sample sound of the vehicle signal registered in the vehicle signal sound registration unit 15 when executing processing related to vehicle signal detection based on the voice recognition. The buffer memory 43 sequentially receives sound (voice) signals detected by the microphone 2 and amplified and digitized through the voice input unit 13 and sends them to the voice recognition processing unit 44. Further, the threshold value setting unit 45 is set with a threshold value serving as a determination criterion for detecting a vehicle signal (back signal / blinker signal) via the CPU 41 based on the control from the control unit 12. . This threshold value is set to the lowest level of the sample sound of the vehicle signal registered in advance in the vehicle signal sound registration unit 15 (the sound acquired when the window is fully closed).

  The voice recognition processing unit 44 basically performs a pattern matching process between the sound (voice) signal input via the buffer memory 43 and the waveform data of the vehicle signal (sample sound) captured in the RAM 42. As a processing method, for example, based on the control from the CPU 41, a sound (voice) signal is sequentially sampled and input via the buffer memory 43, and the input sound (voice) signal is subjected to Fourier transform, and at that time The sound level for each frequency band is calculated, and the calculated signal level for each frequency band is compared with the threshold value set by the threshold setting unit 45 (minimum level of the sample sound of the vehicle signal). When the input sound (voice) signal is equal to or higher than the set threshold value in the entire frequency band, the input sound (voice) signal is compared with the waveform of the sample sound of the vehicle signal (pattern matching process). Then, when the coincidence (matching) between the two is detected, a signal to that effect is output to the control unit 12 via the CPU 41.

  In the in-vehicle navigation device 30 of the present embodiment configured as described above, the control unit 12 is a “control unit”, the DSP 14 is a “voice recognition unit”, and the vehicle signal sound registration unit 15 is a “storage unit”. Each corresponds.

  Hereinafter, processing related to vehicle signal detection based on voice recognition performed by the DSP 14 in cooperation with the control unit 12 in the in-vehicle navigation device 30 of the present embodiment will be described with reference to FIG. 3 showing an example thereof. As an initial state of the device 30, the vehicle signal sound registering unit 15 is registered with waveform data of each sample sound ("Peepy" sound and "Tick" sound) of the back signal and the blinker signal, All (windows) are in the “closed” state.

  In this state, in the first step S1, the DSP 14 stores the waveform data of the sample sound of the vehicle signal registered in the vehicle signal sound registration unit 15 in the RAM 42 via the CPU 41 based on the control from the control unit 12. take in.

  In the next step S 2, the DSP 14 sequentially inputs the sound (voice) signal detected by the microphone 2 to the voice recognition processing unit 44 through the voice input unit 13 and the buffer memory 43 based on the control from the CPU 41. As described above, the speech recognition processing unit 44 performs a Fourier transform on the input sound (voice) signal as an example of the processing, and calculates a sound level for each frequency band.

  In the next step S3, the level of the input sound (voice) signal is set to the threshold value set by the threshold value setting unit 45 (minimum level of the sample sound of the vehicle signal) by the voice recognition processing unit 44 in the DSP 14. ) It is determined whether it is above (YES) or not (NO). In other words, in the above processing example, each sound level calculated for each frequency band is compared with the set threshold value, and it is determined whether or not the set threshold value is exceeded in all frequency bands. If the determination result is YES, the process proceeds to step S4. If the determination result is NO, the process returns to step S2 to repeat the above process.

  In step S4, in response to the window opening / closing signal, the control unit 12 determines whether any window of the vehicle is open (YES) or not (NO). If the determination result is YES, the process proceeds to step S5, and if the determination result is NO, the process proceeds to step S6. At this time, the control unit 12 supplies the DSP 14 with a control signal for controlling whether or not to lower the set threshold level depending on whether any window of the vehicle is open.

  In step S5 (when the window is open), in the DSP 14, the threshold value is set to a predetermined level by the threshold value setting unit 45 based on the control from the CPU 41 by the control signal supplied from the control unit 12. Lower. That is, when the window is opened, sound from outside the vehicle (including back sound output from other vehicles in some cases) is also input to the microphone 2, and the input level of the vehicle signal in the vehicle interior that should be detected originally is This is because the setting threshold value needs to be lowered in accordance with the amount of reduction because it relatively decreases.

  In the next step S6, the DSP 14 uses the voice recognition processing unit 44 based on the control from the CPU 41 to input the input sound (voice) signal and the registered sound data (the waveform of the vehicle signal (sample sound) captured in the RAM 42). Compare and match (pattern matching process).

  In the next step S7, the speech recognition processing unit 44 in the DSP 14 determines whether or not both waveforms are “matched” (YES) or not (NO) based on the comparison and collation. If the determination result is YES, the process proceeds to step S8, and if the determination result is NO, the process returns to step S2 and the above process is repeated.

  In the next step S8, the voice recognition processing unit 44 notifies the control unit 12 via the CPU 41 of the fact. That is, a signal instructing that the input sound signal matches the registered sound data is output to the control unit 12. Thereby, in the control part 12, the sound currently inputted can be judged as "vehicle signal sound" (detection of a vehicle signal). Then, this processing flow is “end”.

  As described above, according to the vehicle-mounted navigation device 30 (FIG. 1) according to the present embodiment, the DSP 14 (voice recognition processing unit 44) detects sound (voice) generated in the passenger compartment with the microphone 2. Then, the sound signal input from the microphone 2 via the audio input unit 13 and the waveform data of the vehicle signal (sample sound) captured in the RAM 42 are compared and collated (pattern matching processing), and the two waveforms match (matching). ) Is output to the control unit 12 when it is detected. Therefore, by detecting this signal, the control unit 12 can determine that the signal input at that time is a vehicle signal (a back signal or a blinker signal). In other words, the navigation device 30 can detect the vehicle signal by voice recognition without connecting the signal lines of the vehicle signal (wiring to the navigation device 30).

  The vehicle signal thus recognized by voice can be used for map matching. For example, in the case of a back signal, by detecting “voice recognition” sound (voice recognition), the navigation device 30 recognizes that the vehicle is in the “back” state, and uses the back signal for the processing of the independent navigation. Can do. As a result, it is possible to improve the accuracy of the self-contained navigation (vehicle position / vehicle direction detection accuracy).

  Further, in the case of a blinker signal, the navigation device 30 automatically detects a “tick” sound (voice recognition) at an intersection or a branch point (for example, a place where a course is changed from a main line to a road that branches at a small angle). It can be recognized that the car is about to change course (for example, it can be recognized that the car has got off the main line). And the accuracy of self-contained navigation can be improved by utilizing this recognized information for map matching. In the conventional technology, the small angle branch is determined based on the detection of a small signal of the gyro, and its reliability is relatively low. In this embodiment, however, the “click” sound of the blinker is sounded. Since detection is performed based on recognition, more accurate recognition is possible.

  Furthermore, since the speech recognition function (pattern matching processing function) is built in the DSP 14 provided separately from the microcomputer (control unit) 12, the control unit 12 interrupts the processing that should be originally performed (various processes related to navigation). Thus, the vehicle signal (back signal / blinker signal) can be detected.

  In the above-described embodiment, when pattern matching processing is performed between input sound (voice) signal and registration sound (sample signal of vehicle signal) data (step S6 in FIG. 2), when the vehicle window is open. Decreases the set threshold value to a predetermined level (step S5). At that time, depending on the situation around the vehicle, the adjacent vehicle may output a back sound. In this case, the back sound from the adjacent vehicle is also input to the microphone 2, It seems to be difficult to distinguish it from the output back sound.

  However, even if the adjacent vehicle is the same model as the own vehicle and the detection waveform of the back sound is similar to that of the own vehicle, the back sound that is generated outside the vehicle and the back sound that is generated inside the vehicle interior are generally Since there is a considerable difference in level, it is sufficiently possible to distinguish between the two by comparing this level difference. That is, when the pattern matching process is performed in step S6, the back sound of the own vehicle detected through the microphone 2 and the level of each signal of the back sound of the adjacent vehicle are also compared to sufficiently increase the back sound of the own vehicle. Can be identified.

  In the above-described embodiment, the case where the speech recognition function is built in the DSP 14 provided separately from the control unit 12 that executes various processes related to navigation has been described as an example. As is clear from the above, it is not always necessary to provide the DSP 14, and an equivalent voice recognition function is built in the control unit 12 so that the DSP 14 can be installed. It can be omitted.

It is a block diagram which shows the structure of the vehicle-mounted navigation apparatus which concerns on one Embodiment of this invention. It is a block diagram which shows the internal structure of DSP in the apparatus of FIG. It is a flowchart which shows an example of the process which concerns on the vehicle signal detection based on the voice recognition which DSP performs in cooperation with a control part in the apparatus of FIG.

Explanation of symbols

1 ... HDD,
2 ... Microphone,
3 ... operation part,
5 ... GPS receiver,
6 ... Self-contained navigation sensor,
7 ... display device,
8 ... Speaker,
12 ... Control part (control means),
14 ... DSP (voice recognition means),
15 ... Vehicle signal sound registration unit (storage means),
30 ... In-vehicle navigation device,
42 ... RAM,
44 ... voice recognition processing unit,
45: Threshold setting unit.

Claims (5)

A microphone installed at a predetermined location in the passenger compartment;
Storage means for previously registering the sound data of the vehicle signal generated in association with the output of the vehicle signal in the passenger compartment;
Voice recognition means for comparing and collating the sound signal input through the microphone with the sound data registered in the storage means;
The voice recognition means determines whether or not the waveform of the input sound matches the waveform of the vehicle signal based on the comparison and collation, and outputs a signal indicating that when it determines that they match. A vehicle-mounted navigation device.   Furthermore, it comprises control means for controlling processing related to navigation, and the control means detects the vehicle signal when receiving a signal indicating that from the voice recognition means, and the detected result is self-contained navigation. The in-vehicle navigation device according to claim 1, wherein the in-vehicle navigation device is used for the processing. The voice recognition means has means for variably setting a threshold value as a determination criterion for detecting a vehicle signal corresponding to a sound registered in the storage means,
The control means controls whether or not to lower the threshold setting level for the voice recognition means in response to a window opening / closing signal instructing whether any window of the vehicle is open. The in-vehicle navigation device according to claim 2, wherein a signal is output.   The in-vehicle navigation device according to claim 1, wherein the sound data of the vehicle signal registered in the storage means includes data of a sample sound for the back signal and a sample sound for the winker signal. In a vehicle-mounted navigation device having a function of executing processing related to navigation using a vehicle signal,
Register the sound data of the vehicle signal generated in advance in the passenger compartment accompanying the output of the vehicle signal in the storage means,
While detecting the sound generated in the passenger compartment with a microphone, the sound recognition means compares and compares the sound signal input through the microphone with the sound data registered in the storage means,
Determine whether the waveform of the input sound matches the waveform of the vehicle signal based on the comparison verification,
A vehicle signal detection method comprising: outputting a signal indicating that when it is determined that the two match, and detecting the vehicle signal based on the signal.

Images