JP2014086808A - On-vehicle system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an on-vehicle system capable of reliably perform confirmation when the erroneous recognition of voice recognition processing occurs in a portable terminal device connected to an on-vehicle device and also suppressing an operation corresponding to the erroneous recognition.SOLUTION: A hands-free telephone device 50 includes: a telephone directory storage unit 66 for storing telephone directory data including multiple names or nominal designations; a comparison unit 52B for comparing a voice recognition result transmitted from a portable terminal device 10 with each one of the multiple names or nominal designations included in the telephone directory data, and determining the presence/absence of a name or a nominal designation corresponding to the voice recognition result; and an operation confirmation unit 52C for determining correctness in voice recognition processing by the portable terminal device 10 on the basis of the determination result of the comparison unit 52B and performing subsequent operation content confirmation in accordance with the correctness determination result.

Description

  The present invention relates to a vehicle-mounted system that performs voice recognition processing on a voice input to a vehicle-mounted device by a mobile terminal device.

  Conventionally, there has been known a hands-free telephone system in which a mobile phone is connected to an in-vehicle device, and the phone book data of the mobile phone is transferred to the in-vehicle device and the phone book data is held in both the in-vehicle device and the mobile phone. (For example, refer to Patent Documents 1 and 2.) By using these hands-free phone systems, users can operate the in-vehicle device to make a call using a mobile phone, and can talk to the other party using a microphone or speaker provided in the in-vehicle device. It becomes.

JP 2009-267535 A JP 2009-81824 A

  Recently, mobile terminal devices having a telephone function have been widely used. In this portable terminal device, various functions are realized by executing various application software. Among them, a voice is input to a voice input using a built-in microphone or a voice input from the outside. A function for performing recognition processing (voice recognition function) is also included. When trying to use the voice recognition function using such a portable terminal device in the hands-free telephone system disclosed in Patent Documents 1 and 2, the following cases are considered and there is a problem.

  Voice recognition processing is performed by sending the voice of the other party's name / name input by the user using the in-vehicle device to the mobile terminal device, and one name / name is selected from the phone book data provided in the mobile terminal device. The case where it selects is considered. The name / name as the recognition result is output, for example, by voice in the mobile terminal device and displayed on the display unit of the mobile terminal device.

  Assuming that the driver and the passenger get on the vehicle, the names and names included in the phone book data include those that the passenger does not want to be known. For example, this may be the case when a customer is on board at work. In such a case, there is a risk that names and names that are not desired to be known due to misrecognition during the speech recognition process are output or displayed as a recognition result. In particular, when a vehicle travels, there is a high possibility that erroneous recognition will occur due to node noise or the like mixed in the input voice. In addition, if the confirmation is insufficient when a misrecognition occurs, there is a possibility that a call is made to the misrecognized call partner.

  In addition, the inconvenience associated with such misrecognition is considered not only in the hands-free telephone system but also in other in-vehicle systems. For example, there is a case where a mobile terminal device is connected to the navigation system and one of registered points is selected by voice.

  The present invention was created in view of the above points, and its purpose is to reliably perform confirmation when a voice recognition process is erroneously recognized in a mobile terminal device connected to an in-vehicle device. It is possible to provide an in-vehicle system capable of suppressing an operation corresponding to erroneous recognition.

  In order to solve the above-described problems, an in-vehicle system according to the present invention includes an in-vehicle device and a mobile terminal device connected to each other, and voice input using a microphone connected to the in-vehicle device is stored in the mobile terminal device. The voice recognition processing is performed on the input voice by the mobile terminal device, and the recognition result is transmitted to the in-vehicle device. The in-vehicle device compares the first registration information storage means for storing the first registration information including a plurality of selection information, the recognition result sent from the mobile terminal device, and each of the plurality of selection information, Comparison means for determining presence / absence of selection information corresponding to the recognition result, and correct / incorrect determination of voice recognition processing by the mobile terminal device based on the determination result by the comparison means, and subsequent operation contents corresponding to this correct / incorrect determination result Operation confirmation means for performing confirmation.

  Since the result of voice recognition processing in the mobile terminal device and each selection information of the first registration information held in the in-vehicle device are compared to make a correct / incorrect determination of the recognition result, confirmation when an erroneous recognition occurs It can be done reliably. Moreover, it becomes easy to suppress the operation | movement at the time of performing misrecognition by confirming the operation | movement content after that according to a correct / incorrect determination result.

  The recognition result sent from the mobile terminal device to the in-vehicle device is text data obtained by the speech recognition processing, and the comparison unit determines whether there is selection information having a character string that matches the text data. It is desirable to do. Thereby, a comparison with a recognition result and each selection information of 1st registration information can be performed easily and reliably.

  In addition, the mobile terminal device described above stores second registration information storage means for storing second registration information including a plurality of selection information in which at least a part of the plurality of selection information included in the first registration information is duplicated. And voice recognition processing means for extracting one of a plurality of selection information corresponding to the second registration information as a recognition result by performing voice recognition processing on the voice sent from the in-vehicle device. It is desirable to provide. Thereby, it is possible to register a part of a plurality of selection information held in the mobile terminal device as the first registration information in the in-vehicle device and select one of them using the voice recognition It becomes. Therefore, even when a large number of selection information is registered in the mobile terminal device, a part of the selection information is registered in the in-vehicle device, and other selection information is known to the passenger other than the user (driver). Can be prevented.

  Further, it is desirable that the operation confirmation unit described above confirms the operation content in a state where the content of the selection information can be grasped when the comparison unit determines that there is selection information corresponding to the recognition result. . In particular, it is desirable that the operation confirmation unit described above confirms the operation content by outputting a sound including the content of the selection information. Alternatively, it is desirable that the operation confirmation unit described above confirms the operation content by performing display including the content of the selection information. As a result, the operation information can be confirmed so that the contents of the selection information registered in the in-vehicle device can be understood, and it can be easily and reliably confirmed that the recognition result is correct.

  Further, it is desirable that the above-described operation confirmation unit confirms the operation content while the content of the selection information is concealed when the comparison unit determines that there is no selection information corresponding to the recognition result. As a result, it is possible to check the operation so that the contents other than the selection information registered in the in-vehicle device are not known, and to prevent the recognition result from being known to passengers other than the user (driver). it can.

  The first registration information and the second registration information described above are phone book data for specifying a call partner with a telephone function provided in the portable terminal device, and the selection information is a name or name indicating the call partner in the phone book data. Information is desirable. As a result, when inputting the other party by voice, it is possible to check the recognition result and the operation content by distinguishing the name etc. registered in the in-vehicle device from the name not registered, etc. It is possible to prevent a call to an unintended call partner due to recognition, and information about an unintended call partner to be known to a passenger other than the user (driver).

1 is a diagram illustrating an overall configuration of a hands-free telephone system according to an embodiment. It is a figure which shows the structure of a portable terminal device. It is a figure which shows the structure of a hands-free telephone apparatus. It is a flowchart which shows the operation | movement procedure of the hands-free telephone apparatus which makes a telephone call by designating the other party by voice input. It is a figure which shows the specific example which performs operation | movement confirmation in the state which can recognize the name or the content of the name. It is a figure which shows the specific example which performs operation | movement confirmation in the state which concealed the name or the content of the name.

  Hereinafter, a hands-free telephone system according to an embodiment to which an in-vehicle system of the present invention is applied will be described with reference to the drawings. FIG. 1 is a diagram illustrating an overall configuration of a hands-free telephone system according to an embodiment. This system is mounted on a vehicle and allows a user to make a call without holding a mobile phone or the like. The mobile terminal device 10 has a mobile phone function, and the mobile terminal device 10. And a hands-free telephone device 50 as an in-vehicle device connected to the mobile phone. For example, in the hands-free phone system according to the present embodiment, the mobile terminal device 10 and the hands-free phone device 50 are connected to each other by Bluetooth (registered trademark).

  FIG. 2 is a diagram illustrating a configuration of the mobile terminal device 10. The mobile terminal device 10 is a mobile terminal generally called a smartphone (registered trademark), for example, and has functions of a mobile phone and a mobile information terminal. The mobile terminal device 10 includes a control unit 12, an operation unit 13A, a touch panel 13B, an input processing unit 14, a display unit 15, a display processing unit 16, a transmitter 18, a receiver 19, a transmission / reception unit 20, a telephone directory storage unit 22, An audio processing unit 24, an amplifier 25, a speaker 26, and an interface unit (IF) 30 are provided.

  The control unit 12 is for controlling the entire mobile terminal device 10, and is realized by a CPU executing a predetermined program stored in a ROM, a RAM, or the like. The operation unit 13A includes various switches. The touch panel 13B detects the indicated position when a part of the screen of the display unit 15 is pointed by the user. The user can perform various operation instructions and various inputs using the touch panel 13B or the operation unit 13A. The input processing unit 14 monitors the operation content of the operation unit 13A and the touch panel 13B, and detects the content input by the user.

  The display unit 15 is composed of an LCD (Liquid Crystal Display) or the like and displays various types of information. The display processing unit 16 displays on the display unit 15 an operation screen including a plurality of operation icons and a screen including various information created by the control unit 12.

  The transmitter 18 inputs the voice of the user (speaker). The receiver 19 outputs the other party's voice. In general, the transmitter 18 is constituted by a microphone, and the receiver 19 is constituted by an earphone or a speaker. The transmission / reception unit 20 operates when a call button (not shown) such as the operation unit 13A is pressed, converts a radio signal received via the antenna 21 into a baseband signal during reception, and is included in the received signal Control data to be input to the control unit 12 and an audio signal to the receiver 19. In addition, at the time of transmission, the transmission / reception unit 20 converts control data input from the control unit 12 and a voice signal input from the transmitter 18 into a radio signal and directs the antenna 21 toward a base station (not shown). Send. In this way, the transmission / reception unit 20 performs call processing and Internet connection processing by performing outgoing / incoming processing with the base station.

  The phone book storage unit 22 stores phone book data including at least “name or name” and “phone number” of a plurality of call partners. The “name or name” includes a character string indicating a reading name in addition to a character string (for example, kanji notation) used for display. For example, up to hundreds of phone book data can be stored, and mail addresses may be included in addition to “name or name” and “phone number”.

  The audio processing unit 24 is for outputting various sounds to the speaker in addition to the case where the mobile terminal device 10 operates as a music player, and performs audio decoding processing for each data format and outputs an audio signal. This audio signal is amplified by the amplifier 25 and output from the speaker 26.

  The interface unit 30 is a communication device (Bluetooth device) that transmits and receives various data to and from the handsfree telephone device 50 via Bluetooth. In the present embodiment, the mobile terminal device 10 and the hands-free telephone device 50 are connected to each other by Bluetooth. However, they are connected via a USB (Universal Serial Bus) interface or a wireless LAN (Local Area). Network) may be used for connection.

  The control unit 12 described above includes a voice recognition processing unit 12A and an HF (hands free) processing unit 12B. The voice recognition processing unit 12A performs voice recognition processing on the voice input from the transmitter 18 and the voice sent from the handsfree telephone device 50. For example, when voice input is performed on the other party, the voice recognition processing unit 12A performs voice recognition processing on the input voice corresponding to the name or name and is included in the phone book data stored in the phone book storage unit 22. Among the “name or name”, the one with the closest reading is extracted and text data indicating the reading is output as a recognition result. The text data as the recognition result is sent to the hands-free telephone device 50 via the interface unit 30. Note that if there is no “name or name” that is close to the reading pseudonym, an error notification is sent to that effect.

  The HF processing unit 12B performs voice input using a microphone (to be described later) provided in the hands-free telephone device 50, and uses the telephone function of the mobile terminal device 10 to make a call with the other party on the mobile terminal device 10 side. Perform a series of hands-free processing.

  FIG. 3 is a diagram showing a configuration of the hands-free telephone device 50. As shown in FIG. The hands-free telephone device 50 includes not only a case dedicated to a hands-free telephone system but also a case where the hands-free telephone device 50 is provided in a part of an audio device, a navigation device, or the like. The hands-free telephone device 50 includes a control unit 52, a reception circuit 54, an amplifier 55, a speaker 56, a transmission circuit 58, a microphone 59, an operation unit 61A, a touch panel 61B, an input processing unit 62, a display unit 63, and a display processing unit 64. A phone book storage unit 66 and an interface unit (IF) 70.

  The control unit 52 controls the entire hands-free telephone device 50, and is realized by executing a predetermined program stored in a ROM, a RAM, or the like by the CPU. The receiving circuit 54 outputs the voice signal of the incoming call partner (in this embodiment, sent from the mobile terminal device 10) from the speaker 56 via the amplifier 55. The transmission circuit 58 performs a process of inputting the user's voice via the microphone 59 when performing a hands-free process to make a call.

  The operation unit 61A includes various keys, switches, operation knobs, and the like provided in the housing of the hands-free telephone device 50. The touch panel 61B detects the indicated position when a part of the screen of the display unit 63 is pointed by the user. The user can perform various operation instructions and various inputs using the touch panel 61B or the operation unit 61A. The input processing unit 62 monitors the operation content of the operation unit 61A and the touch panel 61B, and detects the operation content by the user. The display unit 63 is configured by an LCD or the like, and displays various types of information. The display processing unit 64 displays an operation screen including a plurality of operation icons and a screen including various information created by the control unit 52 on the display unit 63.

  The phone book storage unit 66 stores phone book data including at least “name or name” and “phone number” of a plurality of call partners. The “name or name” includes a character string indicating a reading name in addition to a character string (for example, kanji notation) used for display. By the way, a part of the phone book data stored in the phone book storage unit 22 provided in the mobile terminal device 10 (for example, 10 cases) is transferred and stored in the phone book storage unit 66. The call partner to be transferred to the telephone directory storage unit 66 can be arbitrarily selected by the user. Alternatively, the phone book data stored in the phone book storage unit 66 may be individually input by operating the operation unit 61A and the touch panel 61B separately from the phone book data in the phone book storage unit 22, for example. Good.

  The interface unit 70 is a communication device (Bluetooth device) that transmits and receives various data to and from the mobile terminal device 10 via Bluetooth. When the mobile terminal device 10 and the hands-free telephone device 50 are connected by other than Bluetooth (USB interface, wireless LAN, etc.), an interface unit 70 corresponding to the connection form is used.

  The control unit 52 described above includes an HF (hands free) processing unit 52A, a comparison unit 52B, and an operation confirmation unit 52C. The HF processing unit 52A performs a voice input using the microphone 59 provided in the hands-free telephone device 50, and uses a telephone function of the mobile terminal device 10 to make a series of calls on the hands-free telephone device 50 side that makes a call with the other party. Perform hands-free processing.

  The comparison unit 52B compares the text data sent as the recognition result from the mobile terminal device 10 with the character string of the reading name of “name or name” included in the phone book data stored in the phone book storage unit 66. Then, it is determined whether or not there is a “name or name” whose kana reading matches the text data. The operation confirmation unit 52C performs correct / incorrect determination of the voice recognition process by the mobile terminal device 10 based on the determination result by the comparison unit 52B, and performs subsequent operation content confirmation corresponding to the correct / incorrect determination result. Specifically, the operation confirmation unit 52C, when the comparison unit 52B determines that there is a “name or name” having a reading pseudonym of a character string that matches the text data as the recognition result, Check the operation details in a state where the "name or name" can be grasped. On the other hand, when the comparison unit 52B determines that there is no “name or name” having a reading name of a character string that matches the text data as the recognition result, the operation confirmation unit 52C determines that the “name or name Check the operation details while keeping " A specific example of the operation content confirmation will be described later.

  The phone book storage unit 66 described above is the first registration information storage unit, the phone book storage unit 22 is the second registration information storage unit, and the phone book data stored in the phone book storage unit 66 is the first registration information. In addition, the phone book data stored in the phone book storage unit 22 corresponds to the second registration information, and the “name or name” included in the phone book data stored in the phone book storage units 66 and 22 corresponds to the selection information. To do. The comparison unit 52B corresponds to the comparison unit, the operation confirmation unit 52C corresponds to the operation confirmation unit, and the voice recognition processing unit 12A corresponds to the voice recognition processing unit.

  The hands-free telephone system of this embodiment has such a configuration, and the operation thereof will be described next. FIG. 4 is a flowchart showing an operation procedure of the hands-free telephone device 50 for making a call by designating a call partner by voice input. For example, when the user operates the operation unit 61A or the touch panel 61B to instruct the start of an operation for making a call by designating a call partner by voice input, the operation procedure shown in FIG. 4 is started.

  First, the HF processing unit 52A determines whether or not a voice input for designating a call partner has been made (step 100). If there is no voice input, a negative determination is made and this determination is repeated. Further, when voice input is made using the microphone 59, an affirmative determination is made in the determination of step 100.

  Next, the HF processing unit 52A transmits the voice input using the microphone 59 to the portable terminal device 10 via the interface unit 70, and requests the portable terminal device 10 to perform voice recognition processing on the input voice ( Step 102). In response to this request, the mobile terminal device 10 performs speech recognition processing by the speech recognition processing unit 12A, and text data indicating a reading name of “name or name” as a recognition result corresponding to the input speech is mobile terminal device. 10 is sent back.

  The comparison unit 52B determines whether or not text data as a recognition result has been received from the mobile terminal device 10 (step 104). If not received, a negative determination is made and this determination is repeated. When text data as a recognition result is sent from the mobile terminal device 10, an affirmative determination is made in the determination of step 104. Next, the comparison unit 52B includes a plurality of “names or names” included in the phone book data stored in the phone book storage unit 66 in which the received text data and the character string of the reading kana match. Whether or not (step 106).

  If there is a match, an affirmative determination is made. In this case, the operation confirmation unit 52C performs the operation confirmation in a state where the contents of “name or name” in which the text data as the recognition result and the reading kana match can be grasped (steps 108 and 110). Specifically, the operation confirmation unit 52C outputs an operation content confirmation voice including a reading name “name or name” from the speaker 56 via the reception circuit 54 and the amplifier 55 (step 108), and “name or name”. A screen for confirming the operation content including the display name character string is displayed on the display unit 63 via the display processing unit 64 (step 110).

  FIG. 5 is a diagram illustrating a specific example in which operation confirmation is performed in a state where the name or the contents of the name can be recognized. In the example shown in FIG. 5, a specific example of the operation check when the user instructs the telephone by voice “Call Yamada xxx” is shown. If this “Yamada xxx” is included in the phone book data in the phone book storage unit 66, an affirmative judgment is made in the judgment of step 106. Then, as shown in FIG. 5, an operation confirmation screen including a character string “Do you want to call Yamada xxx?” And selection buttons “Yes” and “Cancel” is displayed.

  Next, the operation confirmation unit 52C determines whether or not an operation instruction has been given by the user (step 112). If neither the selection button “Yes” nor “Cancel” is selected by the user, a negative determination is made, and this determination is repeated. Further, when the user selects one of the selection buttons “Yes” and “Cancel”, an affirmative determination is made in the determination of step 112. This operation instruction is performed when the user instructs the selection of any button by operating the operation unit 61A or the touch panel 61B. Note that a voice that reads “Yes” or “Cancel” is input from the microphone 59, this input voice is sent to the mobile terminal device 10, a voice recognition process is requested, and text data as a result of the recognition is received. It may be determined whether the button is selected.

  Next, the HF processing unit 52A performs an operation in accordance with the selected instruction (“Yes” or “Cancel”) (step 114). Specifically, when “Yes” is selected, the HF processing unit 52A sends an instruction to make a call to the telephone number corresponding to “Yamada xxx” to the mobile terminal device 10. Thereafter, the HF processing unit 12B of the mobile terminal device 10 makes a call to this telephone number, and the user can talk with the other party using the microphone 59 and the speaker 56 of the hands-free telephone device 50. In addition, when “Cancel” is selected, the HF processing unit 52A instructs to stop the operation of making a call to the mobile terminal device 10.

  If the text data received from the mobile terminal device 10 and the “name or name” included in the phone book data stored in the phone book storage unit 66 do not match the character string of the reading kana. A negative determination is made in the determination of step 106. Note that in the case of “no matching character string”, the “name or name” included in the phone book data in the phone book storage unit 22 of the mobile terminal device 10 is specified. "" Is not included in the phone book data in the phone book storage unit 66 of the hands-free phone device 50, the user can add "name or name" included in the phone book data in the phone book storage unit 66 of the hands-free phone device 50. This includes the case where it is determined that “name” or “name” does not exist due to misrecognition at the time of performing voice recognition processing, although it is intended that “name” is input by voice. In such a case, the operation confirmation unit 52C confirms the operation while concealing the content of “name or name” in which the text data as the recognition result and the reading pseudonym coincide with each other (steps 116 and 118). Specifically, the operation confirmation unit 52C outputs an operation content confirmation voice that does not include the reading of “name or name” from the speaker 56 via the reception circuit 54 and the amplifier 55 (step 116) and “name” Or, an operation content confirmation screen that does not include the display character string “name” is displayed on the display unit 63 via the display processing unit 64 (step 118).

  FIG. 6 is a diagram illustrating a specific example in which operation confirmation is performed in a state where the name or the contents of the name are concealed. In the example shown in FIG. 6, the user does not include “Yamada OO” (not included in the phone book data in the phone book storage unit 66 of the mobile terminal device 10). A specific example of the operation confirmation when instructing to make a phone call is shown. If this “Yamada OO” is not included in the telephone directory data in the telephone directory storage unit 66, a negative determination is made in the determination of step 106. Then, as shown in FIG. 6, an operation confirmation screen including a character string “I am trying to make a call to an unregistered contact” and selection buttons “call”, “confirm caller”, and “retry”. Is displayed.

  Next, the operation confirmation unit 52C determines whether or not an operation instruction has been given by the user (step 120). If none of the selection buttons “call”, “confirm caller”, and “retry” is selected by the user, a negative determination is made, and this determination is repeated. If the user selects any of the selection buttons “call”, “confirm caller”, and “retry”, an affirmative determination is made in step 120. This operation instruction is performed when the user instructs the selection of any button by operating the operation unit 61A or the touch panel 61B. Note that a voice that reads out any of “calling”, “confirm caller”, and “retry” is input from the microphone 59, and this input voice is sent to the mobile terminal device 10 to request voice recognition processing, and the recognition result It is also possible to determine which button has been selected by receiving the text data.

  Next, the HF processing unit 52A performs an operation in accordance with the selected instruction (“transmission”, “confirm caller”, “retry”) (step 122). Specifically, when “call” is selected, the HF processing unit 52A sends an instruction to make a call to the telephone number corresponding to “Yamada OO” to the mobile terminal device 10. Thereafter, the HF processing unit 12B of the mobile terminal device 10 makes a call to this telephone number, and the user can talk with the other party using the microphone 59 and the speaker 56 of the hands-free telephone device 50. When “confirm caller” is selected, the HF processing unit 52A displays a confirmation screen including “Yamada OO” as a caller on a part of the character string on the display unit 63. Then, a confirmation operation including outputting a confirmation voice including a reading pseudonym “Yamada OO” from the speaker 56 is performed. If “retry” is selected, the HF processing unit 52A repeats the operations in and after step 100 in order to start again from the voice input.

  Thus, in the hands-free telephone system of the present embodiment, each “name or name” of the result of the voice recognition process in the mobile terminal device 10 and the telephone book data stored in the telephone book storage unit 66 of the hands-free telephone device 50. Since the recognition result is judged as to whether the recognition result is correct or not, the confirmation when the recognition error occurs can be surely performed. Moreover, it becomes easy to suppress the operation | movement at the time of performing misrecognition by confirming the operation | movement content after that according to a correct / incorrect determination result. In particular, the recognition result sent from the mobile terminal device 10 to the hands-free telephone device 50 is text data, and the comparison unit 52B compares the text data with the reading name of “name or name” and corresponds. The presence or absence of “name or name” is determined, and this comparison operation can be easily and reliably performed.

  Further, a part of a plurality of “names or names” included in the phone book data stored in the phone book storage unit 22 of the mobile terminal device 10 is stored in the phone book storage unit 66 of the hands-free phone device 50. It is possible to select one of them by using voice recognition by registering as telephone directory data. Accordingly, even when a large number of “names or names” are registered in the mobile terminal device 10, some of them are registered in the hands-free telephone device 50, and the other “names or names” are registered by the user. It can be made not to be known to passengers other than (driver).

  In addition, the “name or name” registered in the hands-free telephone device 50 can be checked for the operation content so that the content can be understood, and it can be easily and reliably confirmed that the recognition result is correct. On the other hand, operation of the “name or name” that is not registered in the hands-free telephone device 50 can be confirmed so that the contents are not known, and the recognition result is not known to passengers other than the user (driver). Can be.

  In addition, this invention is not limited to the said embodiment, A various deformation | transformation implementation is possible within the range of the summary of this invention. For example, in the above-described embodiment, the present invention is applied to a hands-free telephone system mounted on a vehicle. However, an in-vehicle system in which a portable terminal device having a voice recognition processing function and an in-vehicle device other than the hands-free telephone device are combined. The present invention may be applied to. For example, the present invention can be applied to a case where a mobile terminal device is connected to an in-vehicle navigation device and any of registration points is selected by voice.

  As described above, according to the present invention, the result of speech recognition processing in the mobile terminal device is compared with each selection information of the first registration information held in the in-vehicle device, and the correctness determination of the recognition result is performed. Therefore, it is possible to reliably perform confirmation when erroneous recognition occurs. Moreover, it becomes easy to suppress the operation | movement at the time of performing misrecognition by confirming the operation | movement content after that according to a correct / incorrect determination result.

DESCRIPTION OF SYMBOLS 10 Portable terminal device 12,52 Control part 12A Speech recognition process part 12B, 52A HF (hands free) process part 13A, 61A Operation part 13B, 61B Touch panel 15,63 Display part 22,66 Telephone book memory | storage part 26,56 Speaker 30 70 Interface part (IF)
50 Hands-free telephone device 59 Microphone 52B Comparison unit 52C Operation confirmation unit

Claims (8)

An in-vehicle device and a mobile terminal device connected to each other, and a voice input using a microphone connected to the in-vehicle device is transmitted to the mobile terminal device, and the mobile terminal device In the in-vehicle system that performs voice recognition processing and transmits the recognition result to the in-vehicle device,
The in-vehicle device is
First registration information storage means for storing first registration information including a plurality of selection information;
Comparison means for comparing the recognition result sent from the mobile terminal device and each of the plurality of selection information, and determining the presence or absence of the selection information corresponding to the recognition result;
Based on the determination result by the comparison unit, correct / incorrect determination of voice recognition processing by the mobile terminal device, and in response to the correct / incorrect determination result, operation confirmation unit for confirming subsequent operation contents;
An in-vehicle system comprising: In claim 1,
The recognition result sent from the mobile terminal device to the in-vehicle device is text data obtained by voice recognition processing,
The in-vehicle system characterized in that the comparison means determines the presence or absence of the selection information having a character string that matches the text data. In claim 1 or 2,
The portable terminal device
Second registration information storage means for storing second registration information including a plurality of selection information in which at least a part of the plurality of selection information included in the first registration information is duplicated;
Voice recognition processing means for extracting one of the plurality of selection information corresponding to the second registration information as a recognition result by performing voice recognition processing on the voice sent from the in-vehicle device; ,
An in-vehicle system comprising: In any one of Claims 1-3,
The operation confirmation unit performs operation content confirmation in a state in which the content of the selection information can be grasped when the comparison unit determines that the selection information corresponding to the recognition result is present. In-vehicle system. In claim 4,
The in-vehicle system, wherein the operation confirmation unit confirms the operation content by outputting a sound including the content of the selection information. In claim 4 or 5,
The in-vehicle system, wherein the operation confirmation unit confirms the operation content by performing display including the content of the selection information. In any one of Claims 1-6,
The operation confirmation unit performs operation content confirmation in a state where the content of the selection information is concealed when the comparison unit determines that there is no selection information corresponding to the recognition result. In-vehicle system. In any one of Claims 1-7,
The first and second registration information is phone book data for specifying a call partner with a telephone function provided in the portable terminal device;
The in-vehicle system, wherein the selection information is information of a name or a name indicating a call partner in the phone book data.

Images