JP6896335B2 - Speech recognition device and speech recognition method - Google Patents

Description

The present invention relates to a voice recognition device and a voice recognition method, and is particularly suitable for use in a device that performs voice recognition based on the degree of similarity between a voice spoken by a user and a Yomi of a recognition target word registered in a voice recognition dictionary. It is a thing.

Conventionally, in order to avoid one-handed driving when operating a navigation device mounted on a vehicle, a system has been provided in which the navigation device can be operated by voice recognition. For example, when executing a destination address search or facility name search as an application of a navigation device, it is possible to input the place name or facility name specified by voice recognition into the navigation device and perform the search using this as a key. ..

Normally, the voice recognition device performs recognition based on the degree of similarity between the spoken voice input by the user from the microphone and the Yomi of the recognition target word registered in the voice recognition dictionary. Here, in order to enable the navigation device to be operated by the utterance command, the Yomi (voice pattern) of the recognition target word of the place name or facility name registered in the voice recognition dictionary is the place name or facility name registered in the map data. It is usually the same as the reading.

On the other hand, depending on the area, there may be a peculiar reading by the residents of the area regarding the place name and facility name. In this case, even if the user living in the area speaks the place name or facility name in a peculiar reading, it is different from the Yomi of the recognition target word registered in the voice recognition dictionary, so the voice spoken by the user is recognized as the utterance command. Can't.

As a method for solving such a problem, it is conceivable to additionally register Yomi according to the reading method peculiar to the region as a recognition target word in the speech recognition dictionary. However, in this way, if there is a place name or facility name that has the same or similar reading as the additionally registered area-specific Yomi in a place other than that area, that place name or facility name Yomi is also a different recognition target. Since it is registered as a word in the voice recognition dictionary, there is a possibility that erroneous recognition will occur for the input spoken voice.

In addition, the facility names or city / ward / town / village names stored in the original database are leveled in multiple stages according to their name, and in areas far from the vehicle's location, only nationally famous place names and facilities are included in the partial database. On the other hand, in the area around the vehicle position, not only famous place names and facilities but also lesser-known facilities and place names are stored in the partial database, and a navigation device that performs voice recognition for the partial database is known. (See, for example, Patent Document 1).

Further, there is also known a technique for efficiently accumulating related vocabularies so that a desired search can be performed without knowing the name recorded in the speech recognition dictionary (see, for example, Patent Document 2). In the system described in Patent Document 2, related keywords having a semantic relevance to the initial keywords stored in advance in the recognition dictionary database are collected from the WEB information, and the collected related keywords are added to the recognition dictionary database. The voice search unit executes a search with the initial keyword and the related keyword as recognition targets.

Japanese Unexamined Patent Publication No. 2000-74685 JP-A-2009-169470

The present invention has been made to solve the above-mentioned problems, and even when a user who knows a region-specific reading speaks in that reading, a user who does not know the region-specific reading speaks. Even if this is the case, the purpose is to be able to appropriately recognize each uttered voice.

In order to solve the above-mentioned problems, the speech recognition device of the present invention has a basic dictionary storage unit that stores a basic speech recognition dictionary in which basic readings are registered for the recognition target word, and a region for the recognition target word. It is equipped with a regional dictionary storage unit that stores regional voice recognition dictionaries in which unique Yomi is registered. Then, among the voice recognition dictionaries by region, the voice recognition dictionary of the region to which the position information acquired from the navigation device corresponds is enabled, and the voice recognition dictionary of the activated region and the basic voice recognition dictionary are used for voice recognition. I try to recognize it. At that time, the word to be recognized is a place name, and the process of activating the local voice recognition dictionary is performed only when the navigation device is instructed to execute the address search. Alternatively, the recognition target word is the facility name, and the process of activating the local voice recognition dictionary is performed only when the navigation device is instructed to execute the facility name search. Alternatively, the recognition target words are a place name and a facility name, and the process of activating the local voice recognition dictionary is performed only when the navigation device is instructed to execute the address search or the facility name search.

According to the present invention configured as described above, when a user who knows a region-specific reading of a recognition target word performs voice recognition, the voice of the corresponding region is based on the position information acquired from the navigation device. Speech recognition can be performed by enabling the recognition dictionary. As a result, even when a user who knows the reading method peculiar to the area utters the recognition target word in the reading method peculiar to the area, the spoken voice can be appropriately recognized. On the other hand, when a user who does not know how to read the recognition target word peculiar to the region performs voice recognition, the voice recognition can be performed using only the basic voice recognition dictionary without activating the voice recognition dictionary of the region. As a result, it is possible to prevent the uttered voice by a user who does not know the reading method peculiar to the region from being misrecognized as corresponding to the Yomi peculiar to the region. Based on the above, according to the present invention, whether a user who knows a region-specific reading method speaks in that reading method or a user who does not know the region-specific reading method speaks, each spoken voice is appropriately spoken. Can be recognized.

It is a block diagram which shows the functional structure example of the voice recognition apparatus by this Embodiment. It is a flowchart which shows the operation example of the voice recognition apparatus by this Embodiment.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a functional configuration example of the voice recognition device 100 according to the present embodiment. The voice recognition device 100 of the present embodiment performs voice recognition based on the similarity between the utterance voice by the user input from the microphone 200 and the Yomi of the recognition target word registered in the voice recognition dictionary, and performs voice recognition, and recognizes the recognition target word. The utterance voice corresponding to is recognized as an utterance command, and the utterance command is executed for the navigation device 300.

As shown in FIG. 1, the voice recognition device 100 according to the present embodiment includes a basic dictionary storage unit 101, a regional dictionary storage unit 102, a recognition processing unit 11, and a dictionary activation processing unit 12. The recognition processing unit 11 and the dictionary activation processing unit 12 can be configured by any of hardware, DSP (Digital Signal Processor), and software. For example, when configured by software, the recognition processing unit 11 and the dictionary activation processing unit 12 are actually configured to include a computer CPU, RAM, ROM, etc., and may be used as a recording medium such as RAM, ROM, hard disk, or semiconductor memory. It is realized by operating the stored program.

The basic dictionary storage unit 101 stores the basic speech recognition dictionary 101A in which the basic Yomi is registered with respect to the recognition target word. The basic voice recognition dictionary 101A is dictionary data in which a recognition target word consisting of a place name or facility name registered in the map data of the navigation device 300 and a normal Yomi (voice pattern) for the place name or facility name are associated with each other. Is.

_{The regional dictionary storage unit 102 stores regional voice recognition dictionaries 102A 1 to 102A n in} which region-specific Yomi is registered with respect to the recognition target word. By region of the speech recognition dictionary 102A ₁ ~102A _n is, and the same recognition target word as part of the recognition target word that is registered to the base of the speech recognition dictionary 101A, region-specific with respect to place name or facility name relating to the recognition target word It is dictionary data associated with the Yomi (voice pattern) of.

Here, the first speech recognition dictionary 102A ₁ is dictionary data in which region-specific Yomi in the first region is registered. Further, the second voice recognition dictionary 102A ₂ is dictionary data in which the region-specific Yomi in the second region is registered. Similarly, the nth speech recognition dictionary 102A _n is dictionary data in which region-specific Yomi in the nth region is registered.

Regional delimiting Thus a plurality of speech recognition dictionaries 102A ₁ ~102A _n may, for example, be made in units of administrative areas such as prefectures or municipalities. In this case, regional speech recognition dictionary 102A ₁ ~102A _n is stored in the regional dictionary storage unit 102 along with information indicating what corresponds to which administrative district.

Regional separating the plurality of speech recognition dictionaries 102A ₁ ~102A _n can also be assumed that the unit of square mesh of a predetermined size. In this case, a mesh ID is assigned to each mesh and position information on the map is associated with the mesh. For example, the latitude / longitude information of each vertex of the rectangle is associated with each mesh. The regional speech recognition dictionary 102A ₁ ~102A _n is stored along with the corresponding mesh ID to regional dictionary storage unit 102. Here, it is possible to associate one or more mesh IDs with one voice recognition dictionary.

The recognition processing unit 11 calculates an index indicating the degree of similarity between the Yomi (voice pattern) of the recognition target word registered in the voice recognition dictionary and the utterance voice input from the microphone 200, and the calculated index is the threshold value. When a predetermined condition is satisfied, the spoken voice is recognized as a recognition target word satisfying the predetermined condition.

In the present embodiment, as an example of the index, a distance value indicating the degree of closeness (similarity) between the voice pattern of the recognition target word and the spoken voice input from the microphone 200 is used. The smaller the distance value, the higher the similarity. In this case, when the distance value calculated for the spoken voice is smaller than the threshold value, the recognition processing unit 11 recognizes that the spoken voice is a recognition target word below the threshold value.

When an index whose value increases as the degree of similarity increases is used, the recognition processing unit 11 recognizes that when the index calculated for the spoken voice is larger than the threshold value, the spoken voice exceeds the threshold value. Recognize as a word.

Dictionary validation processing unit 12, among the regional speech recognition dictionary 102A ₁ ~102A _n stored in the regional dictionary storage unit 102, areas of speech recognition dictionary location information obtained from the navigation device 300 corresponds To enable. That is, the dictionary activation processing unit 12 determines whether or not there is a voice recognition dictionary in the area to which the position information corresponds in _{the voice recognition dictionaries 102A 1 to 102A n} for each area stored in the area-specific dictionary storage unit 102. If it is determined that there is, the voice recognition dictionary of the corresponding area is activated.

The position information acquired from the navigation device 300 is, for example, home position information registered in the navigation device 300. The navigation device 300 may be an in-vehicle device mounted on a vehicle, or may be a mobile terminal such as a smartphone in which an application having a navigation function is installed.

As described above, when storing the regional speech recognition dictionary 102A ₁ ~102A _n with administrative areas information by location dictionary storing unit 102, location information of the home to be acquired from the navigation device 300, for example, corresponds to the home position It is preferable to use the address information to be used. Dictionary validation processing unit 12 identifies the administrative district that corresponds to the acquired address information from the navigation device 300, among the regional speech recognition dictionary 102A ₁ ~102A _n, is stored together with the information of the specified administrative district Enable your voice recognition dictionary.

On the other hand, when storing a regional voice recognition dictionary 102A ₁ ~102A _n By Location dictionary storage unit 102 together with the mesh ID, the position information of the home to be acquired from the navigation device 300, for example, latitude and longitude information corresponding to the home position Is preferable. The dictionary activation processing unit 12 identifies a mesh in which the latitude / longitude is included in the rectangle based on the latitude / longitude information acquired from the navigation device 300, and among _{the speech recognition dictionaries 102A 1 to 102A n for each region, the above} Enable the speech recognition dictionary stored with the mesh ID of the specified mesh.

Recognition processing unit 11 described above, the voice recognition dictionary 101A of the base stored in the basic dictionary storage unit 101, among the regional speech recognition dictionary 102A ₁ ~102A _n stored in the regional dictionary storage unit 102 , The above-mentioned voice recognition is performed using the local voice recognition dictionary activated by the dictionary activation processing unit 12.

Here, when there is a local voice recognition dictionary activated by the dictionary activation processing unit 12, the recognition processing unit 11 gives priority to the activated local voice recognition dictionary over the basic voice recognition dictionary 101A. It is preferable to use it for voice recognition. The preferential use of the local voice recognition dictionary is enabled by the dictionary activation processing unit 12 and the similarity between the voice pattern of the recognition target word registered in the basic voice recognition dictionary 101A and the spoken voice. If the voice pattern of the recognition target word registered in the local voice recognition dictionary has the same degree of similarity to the spoken voice, the recognition target word registered in the local voice recognition dictionary is preferentially recognized. It means to do.

For example, when the user's home position belongs to the first area, the dictionary activation processing unit 12 uses the voice recognition dictionary 102A ₁ in the first area based on the position information of the home position acquired from the navigation device 300. Activate. It is assumed that a Yomi (speech pattern) called "Sylvin", which is a reading peculiar to the first area, is registered in the voice recognition dictionary 102A _{1 of the first area for a certain place name.} On the other hand, it is assumed that the basic speech recognition dictionary 101A also has a Yomi called "Sylvin" registered as a basic reading for a place name in another area. In this case, when the user speaks "Sylvin", the similarity between the Yomi of "Sylvin" registered in _{the voice recognition dictionary 102A 1 of the first region and the spoken voice is registered in the basic voice recognition dictionary 101A.} The degree of similarity between the Yomi of "Sylvin" and the spoken voice is the same. In this case, the recognition processing unit 11 recognizes that the Yomi peculiar to the first area has been uttered.

If the user's home location is not in the first area, the voice recognition dictionary 102A ₁ in the first area is not activated. If there is no other activated regional speech recognition dictionary, the recognition processing unit 11 performs speech recognition using only the basic speech recognition dictionary 101A stored in the basic dictionary storage section 101. In this case, when the user utters "Sylvin", the recognition processing unit 11 utters the Yomi of "Sylvin" registered in the basic speech recognition dictionary 101A, that is, an area different from the first area. Recognize that Yomi's place name "Sylvin" was spoken.

Also, if the user's home location is not in the first area, the user does not know that the place name in the first area has a unique reading of "Sylvin", so if he / she wants to speak the place name. Will speak in the basic reading. For example, if the basic reading of a place name is "Sylvian", a user who does not know the region-specific reading of "Sylvin" speaks "Sylvian", which is the normal reading. In this case, the recognition processing unit 11 can recognize the place name of "Sylvian" from the similarity between the Yomi of "Sylvian" registered in the basic speech recognition dictionary 101A and the spoken voice.

Here, recognition in favor of the latter when the degree of similarity calculated based on the basic voice recognition dictionary 101A, and the degree of similarity is calculated based on the regional speech recognition dictionary 102A ₁ ~102A _n was the same However, the present invention is not limited to this. For example, than the degree of similarity calculated based on the basic voice recognition dictionary 101A, even when towards the similarity calculated based on regional speech recognition dictionary 102A ₁ ~102A _n is small, the difference is given when it is below that may perform speech recognition using the regional speech recognition dictionary 102A ₁ ~102A _n preferentially.

FIG. 2 is a flowchart showing an operation example of the voice recognition device 100 according to the present embodiment configured as described above. The flowchart shown in FIG. 2 starts when, for example, a user operation for turning on the voice recognition function is performed in the navigation device 300.

First, the dictionary activation processing unit 12 acquires the position information of the home position from the navigation device 300 (step S1). Next, the dictionary activation processing unit 12 performs voice recognition of the area to which the position information acquired in step S1 corresponds in the area- _{specific voice recognition dictionaries 102A 1 to 102A n stored in the area-specific dictionary storage unit 102.} It is determined whether or not there is a dictionary (step S2). Then, when it is determined that there is a voice recognition dictionary in the corresponding area, the dictionary activation processing unit 12 activates the voice recognition dictionary in the corresponding area (step S3).

On the other hand, if it is determined that there is no voice recognition dictionary in the corresponding area, the process of step S3 is not executed, and the process transitions to step S4. The recognition processing unit 11 inputs the uttered voice from the microphone 200 (step S4), and stores the basic voice recognition dictionary 101A stored in the basic dictionary storage unit 101 and the regional dictionary storage unit 102 for each region. of speech recognition dictionaries 102A ₁ ~102A _n, by using the validated local speech recognition dictionary by dictionary validation processing unit 12, performs the speech recognition for speech (step S5). Then, the recognition result is output to the navigation device 300 (step S6), and a series of processes is completed.

As described in detail above, the voice recognition device 100 of the present embodiment has the recognition target word in addition to the basic dictionary storage unit 101 that stores the basic voice recognition dictionary 100A in which the basic readings are registered for the recognition target word. comprising a regional dictionary storage unit 102 which stores a regional voice recognition dictionary 102A ₁ ~102A _n the region-specific readings, which are registered for. Of the regional speech recognition dictionary 102A ₁ ~102A _n, position information obtained from the navigation device 300 will activate the voice recognition dictionary of the corresponding region, the activated voice speech recognition dictionary and basic regions Speech recognition is performed using the recognition dictionary 101A.

According to the present embodiment configured in this way, when a user who knows a region-specific reading of the recognition target word performs voice recognition, the region corresponds to the region based on the position information acquired from the navigation device 300. Speech recognition can be performed by enabling the speech recognition dictionary. As a result, even when a user who knows the reading method peculiar to the area utters the recognition target word in the reading method peculiar to the area, the spoken voice can be appropriately recognized.

On the other hand, when the user does not know the region-specific reading with respect to the recognition objective word is speech recognition does not enable the regional speech recognition dictionary 102A ₁ ~102A _n, using only basic voice recognition dictionary 101A speech Can recognize. As a result, it is possible to prevent the uttered voice by a user who does not know the reading method peculiar to the region from being mistakenly recognized as corresponding to the Yomi peculiar to the region.

Based on the above, according to the present embodiment, each spoken voice is appropriate regardless of whether a user who knows the region-specific reading method speaks in that reading method or a user who does not know the region-specific reading method speaks. Can be recognized.

In the above embodiment, an example in which the home position information registered in the navigation device 300 is used as the position information acquired from the navigation device 300 has been described, but the present invention is not limited to this. For example, the position information acquired from the navigation device 300 may be the current position information detected by the navigation device 300.

In the above embodiment, the recognition target words as a place name, Dictionary validation processing unit 12 in the navigation device 300 only when the execution of the address search is instructed, the regional speech recognition dictionary 102A ₁ ~102A _n The process of activating may be performed. Alternatively, the recognition target words as a facility name dictionary validation processing unit 12, only when the execution of the facility name retrieval in the navigation apparatus 300 is instructed, to enable the regional voice recognition dictionary 102A ₁ ~102A _n The process may be performed. Alternatively, the recognition target word is a place name and a facility name, and the dictionary activation processing unit 12 sets the region-specific voice recognition dictionary 102A _{1 to 102A only when the navigation device 300 is instructed to execute the address search or the facility name search.} A process for activating _{n may be performed.}

Thus, it can be made to enable the regional speech recognition dictionary 102A ₁ ~102A _n only when necessary depending on the application of the navigation device 300. Thereby, it is enabled the regional speech recognition dictionary 102A ₁ ~102A _n when unnecessary, the speech should originally be recognized based on the basic voice recognition dictionary 101A, voice recognition Enabled areas It is possible to reduce the possibility of erroneous recognition such as recognition based on a dictionary.

In addition, the above embodiments are merely examples of embodiment of the present invention, and the technical scope of the present invention should not be construed in a limited manner. That is, the present invention can be implemented in various forms without departing from its gist or its main features.

11 recognition processing section 12 Dictionary validation processing unit 100 the speech recognition apparatus 101 basic dictionary storage unit 101A basic speech recognition dictionary 102 Region dictionary storage unit 102A ₁ ~102A _n regional speech recognition dictionary 300 navigation device

Claims (9)

It is a voice recognition device that performs voice recognition based on the degree of similarity between the voice spoken by the user and the Yomi of the recognition target word registered in the voice recognition dictionary.
A basic dictionary storage unit that stores a basic speech recognition dictionary in which basic Yomi is registered for the above recognition target word,
A regional dictionary storage unit that stores regional voice recognition dictionaries in which region-specific Yomi is registered for the above recognition target words,
Among the above-mentioned area-specific voice recognition dictionaries stored in the above-mentioned area-specific dictionary storage unit, a dictionary activation processing unit that activates the area-specific voice recognition dictionary whose location information acquired from the navigation device corresponds
It is provided with a recognition processing unit that performs voice recognition using the basic voice recognition dictionary stored in the basic dictionary storage unit and the voice recognition dictionary in the area activated by the dictionary activation processing unit.
The above recognition target word is a place name,
The dictionary activation processing unit is a voice recognition device characterized in that it performs processing for activating a voice recognition dictionary in the area only when the navigation device is instructed to execute an address search. It is a voice recognition device that performs voice recognition based on the degree of similarity between the voice spoken by the user and the Yomi of the recognition target word registered in the voice recognition dictionary.
A basic dictionary storage unit that stores a basic speech recognition dictionary in which basic Yomi is registered for the above recognition target word,
A regional dictionary storage unit that stores regional voice recognition dictionaries in which region-specific Yomi is registered for the above recognition target words,
Among the above-mentioned area-specific voice recognition dictionaries stored in the above-mentioned area-specific dictionary storage unit, a dictionary activation processing unit that activates the area-specific voice recognition dictionary whose location information acquired from the navigation device corresponds
It is provided with a recognition processing unit that performs voice recognition using the basic voice recognition dictionary stored in the basic dictionary storage unit and the voice recognition dictionary in the area activated by the dictionary activation processing unit.
The above recognition target word is the facility name,
The dictionary activation processing unit is a voice recognition device characterized in that it performs processing for activating a voice recognition dictionary in the area only when the navigation device is instructed to execute a facility name search. It is a voice recognition device that performs voice recognition based on the degree of similarity between the voice spoken by the user and the Yomi of the recognition target word registered in the voice recognition dictionary.
A basic dictionary storage unit that stores a basic speech recognition dictionary in which basic Yomi is registered for the above recognition target word,
A regional dictionary storage unit that stores regional voice recognition dictionaries in which region-specific Yomi is registered for the above recognition target words,
Among the above-mentioned area-specific voice recognition dictionaries stored in the above-mentioned area-specific dictionary storage unit, a dictionary activation processing unit that activates the area-specific voice recognition dictionary whose location information acquired from the navigation device corresponds
It is provided with a recognition processing unit that performs voice recognition using the basic voice recognition dictionary stored in the basic dictionary storage unit and the voice recognition dictionary in the area activated by the dictionary activation processing unit.
The above recognition target words are place names and facility names.
The dictionary activation processing unit is a voice recognition device characterized in that it performs a process of activating a voice recognition dictionary in the area only when the navigation device is instructed to execute an address search or a facility name search. The dictionary activation processing unit determines whether or not there is a voice recognition dictionary for the area to which the location information corresponds in the voice recognition dictionary for each area stored in the dictionary storage unit for each area. When it is determined that there is, the voice recognition dictionary of the above applicable area is enabled.
When the recognition processing unit has a local voice recognition dictionary activated by the dictionary activation processing unit, the recognition processing unit preferentially uses the activated local voice recognition dictionary over the basic voice recognition dictionary. The voice recognition device according to any one of claims 1 to 3, wherein the voice recognition is performed. The voice recognition device according to any one of claims 1 to 4, wherein the position information acquired from the navigation device is home position information registered in the navigation device. The voice recognition device according to any one of claims 1 to 4, wherein the position information acquired from the navigation device is the current position information detected by the navigation device. Speaking by the user in a voice recognition device having a basic voice recognition dictionary in which basic yomi is registered for the recognition target word and a region-specific voice recognition dictionary in which region-specific yomi is registered for the recognition target word. It is a voice recognition method that performs voice recognition based on the degree of similarity between voice and Yomi of the recognition target word registered in the voice recognition dictionary.
The first step in which the dictionary activation processing unit of the voice recognition device activates the voice recognition dictionary of the area to which the position information acquired from the navigation device is applicable among the voice recognition dictionaries for each area.
The recognition processing unit of the voice recognition device has a second step of performing the voice recognition using the basic voice recognition dictionary and the voice recognition dictionary of the area activated by the dictionary activation processing unit. And
The above recognition target word is a place name,
In the first step, the dictionary activation processing unit performs a process of activating the voice recognition dictionary in the area only when the navigation device is instructed to execute the address search. Recognition method. Speaking by the user in a voice recognition device having a basic voice recognition dictionary in which basic yomi is registered for the recognition target word and a region-specific voice recognition dictionary in which region-specific yomi is registered for the recognition target word. It is a voice recognition method that performs voice recognition based on the degree of similarity between voice and Yomi of the recognition target word registered in the voice recognition dictionary.
The first step in which the dictionary activation processing unit of the voice recognition device activates the voice recognition dictionary of the area to which the position information acquired from the navigation device is applicable among the voice recognition dictionaries for each area.
The recognition processing unit of the voice recognition device has a second step of performing the voice recognition using the basic voice recognition dictionary and the voice recognition dictionary of the area activated by the dictionary activation processing unit. And
The above recognition target word is the facility name,
In the first step, the dictionary activation processing unit performs a process of activating the voice recognition dictionary in the area only when the navigation device is instructed to execute the facility name search. Voice recognition method. Speaking by the user in a voice recognition device having a basic voice recognition dictionary in which basic yomi is registered for the recognition target word and a region-specific voice recognition dictionary in which region-specific yomi is registered for the recognition target word. It is a voice recognition method that performs voice recognition based on the degree of similarity between voice and Yomi of the recognition target word registered in the voice recognition dictionary.
The first step in which the dictionary activation processing unit of the voice recognition device activates the voice recognition dictionary of the area to which the position information acquired from the navigation device is applicable among the voice recognition dictionaries for each area.
The recognition processing unit of the voice recognition device has a second step of performing the voice recognition using the basic voice recognition dictionary and the voice recognition dictionary of the area activated by the dictionary activation processing unit. And
The above recognition target words are place names and facility names.
In the first step, the dictionary activation processing unit performs a process of activating the voice recognition dictionary in the area only when the navigation device is instructed to execute the address search or the facility name search. Characteristic voice recognition method.

Images