JP2014062944A - Information processing devices - Google Patents

Abstract

PROBLEM TO BE SOLVED: To correctly and quickly perform voice recognition of a user's voice command by connecting an information processing device such as a car navigation device and an external device such as a portable phone.SOLUTION: Provided are first and second information processing devices. The first information processing device comprises: an input unit which receives input of a voice command; a transmission unit which transmits the voice command to the second information processing device; a first voice recognition unit which performs voice recognition at a low level at the same time as the transmission of the voice command; an output unit; a determination unit; and a command execution unit. The second information processing device comprises: a second voice recognition unit which performs voice recognition at high level; and a transmission unit which transmits a voice recognition result to the first information processing device. When the determination unit of the first information processing device determines that reliability of voice recognition performed by the first voice recognition unit is high, the first information processing device executes the command recognized by the first voice recognition unit, and when the determination unit determines that the reliability of voice recognition performed by the first voice recognition unit is low, the first information processing device executes the command recognized by the second voice recognition unit.

Description

  The present invention relates to an information processing apparatus, and more particularly to an information processing apparatus having a voice recognition function, such as a car navigation apparatus.

  In an information processing apparatus such as the car navigation apparatus described above, an apparatus capable of recognizing a voice command issued by a user and performing a process corresponding to the command is known. In mobile phones, a process called a concierge service is known in which voice recognition and sentence analysis are processed on the server side using a communication line.

  As a technology related to these, a technology for linking a mobile terminal with an in-vehicle terminal in a vehicle (see Patent Document 1), a technology for enabling a mobile phone application to be used in an in-vehicle device (see Patent Document 2), and a resource for a voice recognition function are limited. A technology related to a speech recognition device (see Patent Document 3) that can be sufficiently recognized even by a known device is known.

JP 2012-27070 A JP 2010-130223 A JP 2005-266192 A

  However, voice recognition devices built into car navigation devices have limited recognition capabilities and have the minimum necessary functions, but they cannot be recognized if the use of the end of a voice command changes or the utterance expression changes. There are many cases. In addition, the concierge service used in a mobile phone uses a communication line and can perform highly accurate speech recognition and sentence analysis, but has a problem that it takes time for speech recognition.

  For this reason, entrusting voice recognition of a car navigation device or the like to a mobile phone concierge service requires a longer recognition time than a voice recognition device built in a car navigation device or the like, and therefore cannot respond quickly. There was a problem.

  Therefore, the present invention has been made in consideration of the above circumstances, and an information processing device such as a car navigation device and an external device such as a mobile phone are connected and used at the same time. An object of the present invention is to provide an information processing apparatus that performs voice recognition on an external device simultaneously with voice recognition and uses the recognition result of the external device when the recognition reliability on the information processing device side is low .

  The present invention comprises a first information processing device having a first level speech recognition function and a second information processing device having a second level speech recognition function higher than the first information processing device, The first information processing device includes an input unit capable of inputting a user's voice command, a transmission unit that transmits the input voice command to the second information processing device, and input simultaneously with transmission of the transmission unit. A first speech recognition unit that performs speech recognition of the received voice command at a first level, and an output unit that outputs a result of speech recognition of the first speech recognition unit. A second voice recognition unit that performs voice recognition of a voice command received from the first information processing apparatus at a second level, and a transmission that transmits a voice recognition result of the second voice recognition unit to the first information processing apparatus A first information processing device further comprising: A receiving unit that receives the voice recognition result of the second voice recognition unit, a determination unit that determines the reliability of the voice recognition of the first voice recognition unit, and the determination unit determines that the reliability is high. A command execution unit that executes a command that has been voice-recognized by one voice recognition unit and that executes a command that has been voice-recognized by the second voice recognition unit when the determination unit determines that the reliability is low. An information processing apparatus characterized by the above is provided.

  According to this, if the first and second information processing apparatuses execute voice command voice recognition processing simultaneously and the reliability of the voice recognition result in the first information processing apparatus is high, the voice recognition result is adopted. If the command is promptly executed and the reliability is low, the voice recognition result in the second information processing apparatus is adopted and an accurate command is executed. Accordingly, it is possible to execute a command execution process quickly and accurately.

  The determination unit of the first information processing apparatus is a determination unit that determines that the voice recognition reliability is low if the first voice recognition unit cannot recognize the voice command of the user. Features. According to this, it is possible to prevent unnecessary command execution processing.

The determination unit of the first information processing apparatus performs voice recognition according to a user instruction from the voice recognition result output from the output unit after the voice recognition of the user's voice command is performed by the first voice recognition unit. The determination unit determines that the reliability is low.
According to this, when an erroneous voice recognition is performed, an erroneous command execution process can be prevented by a user instruction.

  According to the present invention, when a voice command is given and voice recognition processing is simultaneously executed by the first and second information processing apparatuses, and the reliability of the voice recognition result in the first information processing apparatus is high, the voice is processed. If the recognition result is adopted, the command is quickly executed, and if the reliability is low, the voice recognition result in the second information processing apparatus is adopted and the accurate command is executed. Accordingly, it is possible to execute a command execution process quickly and accurately.

1 is a configuration block diagram of an embodiment of an information processing apparatus of the present invention. It is explanatory drawing which shows the content of the processing operation of the information processing apparatus of this invention. It is explanatory drawing which shows the detailed processing operation of the information processing apparatus of this invention.

  The best mode for carrying out the present invention will be described below with reference to the drawings. However, this does not limit the present invention.

<Configuration of Information Processing Apparatus of the Invention>
FIG. 1 is a block diagram showing the configuration of an embodiment of an information processing apparatus according to the present invention. In the present embodiment, an example in which the information processing apparatus of the present invention includes a car navigation apparatus 1 and a mobile phone 2 will be described. The car navigation device 1 uses a commercially available device that is mounted in a car and performs route guidance using GPS (Global Positioning System), but this is an example, and an electronic device having a relatively low-dimensional voice recognition function. Any electronic device may be used as long as it is a device. For example, instead of a vehicle-mounted type, it may be a small and light electronic device having a route guidance function that can be carried by an individual, or a household electric product with a built-in voice recognition function that cooperates with a mobile phone.

  In the present example, the mobile phone 2 is a mobile phone that has been used in the past, but may be any terminal device that can use a voice recognition service (so-called concierge service). For example, it may be a small and lightweight terminal device having portability such as a smartphone or a tablet terminal. The mobile phone 2 can be connected to the voice recognition server 3 through a communication line. The voice recognition server 3 has a priority recognition word database.

  The car navigation device 1 mainly includes a navigation control unit 11, a voice input unit 12, a voice data transmission unit 13, a built-in navigation voice recognition unit 14, a recognition reliability determination unit 15, a command execution unit 16, and a portable voice recognition data reception unit 17. And a command execution / answer voice playback unit 18. In addition to these functions, various operation buttons, a data input / output unit in which a touch panel and a display panel are integrated, and various functions for performing a navigation operation are provided.

  The navigation control unit 11 is a part that controls the operation of each functional block of the car navigation device 1, and is mainly configured by a microcomputer including a CPU, a ROM, a RAM, an I / O controller, a timer, and the like. The CPU executes each function of the car navigation apparatus 1 by organically operating various hardware based on a program stored in a ROM or the like.

  The voice input unit 12 is for inputting a user's voice, and converts the input user's voice into voice data. The voice data transmission unit 13 transmits the voice data to the navigation built-in voice recognition unit 14 and simultaneously transmits the voice data to the voice data reception unit 22 of the mobile phone 2. The navigation built-in voice recognition unit 14 performs voice recognition of voice data and converts the voice data into voice recognition data.

  The recognition reliability determination unit 15 determines whether or not the voice recognition data recognized by the navigation built-in voice recognition unit 14 is appropriate. The command execution unit 16 executes a command based on the voice recognition data converted by the navigation built-in voice recognition unit 13. The mobile voice recognition data receiving unit 17 receives the voice recognition data transmitted from the mobile voice recognition data transmitting unit 24 on the mobile phone 2 side. The command execution / answer voice reproduction unit 18 executes a command based on the voice recognition data received by the portable voice recognition data reception unit 17 and reproduces the answer voice obtained as a voice data answer.

  The mobile phone 2 mainly includes a mobile phone control unit 21, a voice data receiving unit 22, a mobile voice recognition unit 23, and a mobile voice recognition data transmission unit 24. In addition to these functions, various operation buttons, a data input / output unit in which a touch panel and a display panel are integrated, and various functions for performing operations as a mobile phone are provided.

  The mobile phone control unit 21 is a part that controls the operation of each functional block of the mobile phone 2 and is mainly composed of a microcomputer including a CPU, a ROM, a RAM, an I / O controller, a timer, and the like. The CPU executes each function of the mobile phone 2 by organically operating various hardware based on a program stored in a ROM or the like.

  The audio data receiving unit 22 receives the audio data transmitted from the audio data transmitting unit 13 of the car navigation device 1. The portable voice recognition unit 23 transmits the data received by the voice data receiving unit 22 to the voice recognition server 3 and receives the voice recognition data from the voice recognition server 3. The portable voice recognition data transmitting unit 24 transmits the voice recognition data received from the voice recognition server 3 to the portable voice recognition data receiving unit 17 of the car navigation device 1.

<Operation of Information Processing Apparatus of the Present Invention>
The contents of the processing operation of the information processing apparatus according to the present invention will be described with reference to FIG. The processing operations are shown for the car navigation device 1, the mobile phone 2, and the voice recognition server 3, respectively. These processes are performed by the navigation control unit 11 for the car navigation device 1 and by the mobile phone control unit 21 for the mobile phone 2. The car navigation device 1 and the mobile phone 2 are connected by Bluetooth (registered trademark) or a wired 4. The mobile phone 2 and the voice recognition server 3 are connected by a communication line 5 such as a mobile phone network or WiMAX / Wi-Fi (registered trademark).

  Processing on the car navigation device 1 side will be described. In step S1, when a user's voice is input as a command to the voice input unit 12 of the car navigation apparatus 1, the voice data is sent to the voice data receiving unit 22 of the mobile phone 2 by the voice data transmitting unit 13 in step S2. At the same time, it is sent to the voice recognition unit 14 with built-in navigation. As a result, the voice recognition process is started simultaneously in the car navigation device 1 and the mobile phone 2.

  In step S3, the voice data is recognized by the navigation built-in voice recognition unit 14, and in step S4, the recognition reliability determination unit 15 determines the recognition reliability. This determination will be described later. When the reliability of voice recognition is high, the command execution unit 16 executes a command for voice recognition with built-in navigation in step S5, and in step S6, voice recognition on the mobile phone 2 side is canceled and the process ends. On the other hand, when the reliability of voice recognition is low, portable voice recognition data is received by the portable voice recognition data receiving unit 17 from the portable voice recognition data transmitting unit 24 of the mobile phone 2 in step S7. The portable voice recognition data includes voice recognition data as a response and a command to the car navigation device. In step S8, the command execution / answer voice reproduction unit 18 reproduces the command execution / answer voice by portable voice recognition.

  The determination of the recognition reliability in the recognition reliability determination unit 15 in step S4 described above is performed as follows. That is, the navigation built-in voice recognition unit 14 determines that the recognition reliability is low when the voice cannot be recognized. Also, if the recognition result is displayed on the display panel, or if the recognition result is played back as a sound, the user determines that the recognition result is inappropriate and cancels the recognition result. It is determined that the degree is low. In other cases, it is determined that the recognition reliability is high.

  Processing on the mobile phone 2 side will be described. When the voice data is received by the voice data receiving unit 22 from the car navigation device 1, the portable voice recognition unit 23 performs portable voice recognition in step S9. This is generally called a concierge service. In this process, the voice data and the model name of the car navigation device are transmitted to the voice recognition server 3 through the communication line 5, and the voice recognition result is received from the voice recognition server 3. Then, the voice recognition data and the command are transmitted to the portable voice recognition data receiving unit 17 of the car navigation device 1.

  The voice recognition server 3 has a priority recognition word database 31. The priority recognition word database 31 is used to obtain a priority recognition word from the model name of the car navigation device, and to create voice recognition data and commands. Use.

  In this way, voice recognition is performed simultaneously with the car navigation device and the mobile phone, and when the reliability of the voice recognition result built into the car navigation device is high, the voice recognition result of the car navigation device is used and built into the car navigation device. If the reliability of the speech recognition result is low or incorrect, the speech recognition result of the mobile phone is used.

  FIG. 3 shows the details of the processing operation of the information processing apparatus of the present invention. In the figure, the entire processing contents of the car navigation apparatus 1, the mobile phone 2, and the voice recognition server 3 are shown in association with each other.

  As an initial setting at the time of connection, the car navigation device 1 performs an initial connection procedure with the mobile phone 2 in step T1, and transmits model information of the car navigation device to the mobile phone 2 in step T2. The cellular phone 2 performs an initial connection procedure with the car navigation device 1 in step T21, and acquires model information of the car navigation device in step T22.

  The car navigation apparatus 1 starts the voice recognition process of the user input as a command in step T3, acquires voice data in step T4, and transmits the voice data to the mobile phone 2 in step T5. In step T6, voice recognition processing is performed. If the reliability of the voice recognition process is high in step T7, the command is executed by the voice recognition with built-in navigation in step T8, and the voice recognition data of the mobile phone and the command of the navigation device are canceled in step T9. . On the other hand, if the reliability of the voice recognition processing is low, in step T10, the mobile phone 2 is instructed to transmit the recognition result to receive the voice recognition data and the navigation device command, and in step T11, the command is executed by portable voice recognition. / Play the answer voice.

  In step T23, the cellular phone 2 receives the voice data from the car navigation device 1, and transmits the voice data and the model name of the navigation device to the voice recognition server 3 in step T24.

  In step T31, the voice recognition server 3 receives voice data and the model name of the navigation device from the mobile phone 2, and in step T32, the voice recognition engine performs voice recognition processing called a so-called concierge service. In this process, a priority command word database 31 is used to obtain a corresponding command list from the model name of the navigation device. In step T33, the reply voice recognition data and the command of the navigation device are transmitted to the mobile phone 2.

  When the mobile phone 2 receives the answer voice recognition data and the navigation device command from the voice recognition server 3 in step T25, in step T26, whether or not there is an instruction to cancel the voice recognition data of the mobile phone from the car navigation device 1, and Check whether there is an instruction to send voice recognition data. If there is an instruction to cancel the voice recognition data, the voice recognition data of the mobile phone is canceled. If there is an instruction to transmit the voice recognition data of the mobile phone, the answer voice recognition data and the command of the navigation device are set in step T27. Transmit to the navigation device 1.

  As described above, the car navigation device 1 receives the portable voice recognition data and the navigation device command in step T10, and performs command execution / answer voice reproduction by portable voice recognition in step T11.

  As described above, according to the present invention, the user's voice command is simultaneously given to the car navigation device and the mobile phone. If the voice command has simple contents, the voice recognition function built in the car navigation device is used to perform voice recognition processing at high speed. In the case of such complicated contents, it is possible to perform voice recognition and command execution processing quickly and accurately by performing accurate voice recognition processing using the voice recognition result of the mobile phone.

DESCRIPTION OF SYMBOLS 1 Car navigation apparatus 2 Mobile phone 3 Voice recognition server 4 Wired 5 Communication line 11 Navigation control part 12 Voice input part 13 Voice data transmission part 14 Built-in voice recognition part 15 Recognition reliability determination part 16 Command execution part 17 Portable voice recognition data Reception unit 18 Command execution / answer voice reproduction unit 21 Mobile phone control unit 22 Voice data reception unit 23 Mobile voice recognition unit 24 Mobile voice recognition data transmission unit 31 Priority recognition word database

Claims (3)

A first information processing apparatus having a first level voice recognition function and a second information processing apparatus having a second level voice recognition function higher than the first information processing apparatus;
The first information processing device includes an input unit capable of inputting a user's voice command, a transmission unit that transmits the input voice command to the second information processing device, and input simultaneously with transmission of the transmission unit. A first voice recognition unit that performs voice recognition of the voice command at a first level, and an output unit that outputs a result of voice recognition of the first voice recognition unit,
The second information processing apparatus includes a second voice recognition unit that performs voice recognition of the voice command received from the first information processing apparatus at a second level, and a voice recognition result of the second voice recognition unit as the first information. A transmission unit for transmitting to the information processing apparatus,
The first information processing apparatus further includes a receiving unit that receives the voice recognition result of the second voice recognition unit, a determination unit that determines the reliability of voice recognition of the first voice recognition unit, and a When it is determined that the degree is high, the command recognized by the first voice recognition unit is executed, and when the reliability is determined by the determination unit to be low, the second voice recognition unit performs voice recognition. An information processing apparatus comprising a command execution unit for executing a command that has been executed.   The determination unit of the first information processing apparatus is a determination unit that determines that the voice recognition reliability is low if the first voice recognition unit cannot recognize the voice command of the user. The information processing apparatus according to claim 1.   The determination unit of the first information processing apparatus determines the reliability of the voice recognition based on the user's instruction from the voice recognition result output from the output unit after the voice recognition of the user's voice command is performed by the first voice recognition unit. The information processing apparatus according to claim 2, wherein the information processing apparatus is a determination unit that determines that the value is low.

Images