JP2006003450A - Message output control system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To allow a user to feel presence when the voice is outputted from a system. <P>SOLUTION: In a message output control system, a plurality of speakers 50a to 50e are disposed. The speaker which outputs the message is determined from among the plurality of the speakers 50a to 50e. Therefore, the message can be outputted by voice even from the speakers 50b to 50e other than the speaker 50a disposed on a driver's seat side. Consequently, the presence is improved as compared to the case the message is outputted from only the speaker 50a disposed on the driver's seat side. As a result, the user can feel the presence when outputting the message from the system by voice. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a message output control system.

  Conventionally, for example, in a navigation system, when voice guidance is given regarding a route to a destination, a message is output by voice from a speaker provided on the driver's seat side. This makes it easier for the driver to hear the voice guidance message from the navigation system.

  However, if any message is output only from the speaker provided on the driver's seat side, when the message is output by voice, the user will not be realistic.

  The present invention has been made in view of the above points, and an object of the present invention is to provide a message output control system that can evoke a sense of presence when a message from the system is output by voice. To do.

In order to achieve the above object, the message output control system according to claim 1 comprises:
A plurality of speakers provided at a plurality of locations in the passenger compartment;
Message generating means for generating a message output by voice from a speaker;
Speaker determination means for determining a speaker to output a message from among a plurality of speakers based on the message generated by the message generation means;
Output control means for outputting a message by voice from the speaker determined by the speaker determination means.

  As described above, in the message output control system according to the first aspect, a speaker that outputs a message is determined from a plurality of speakers based on the message. For this reason, a message can be output by voice from speakers other than the speaker provided on the driver's seat side. As a result, a sense of reality is improved as compared with a case where a message is output by voice only from a speaker provided on the driver's seat side. Thereby, when outputting a message from the system by voice, it is possible to evoke a sense of reality for the user.

  As described in claim 2, the message generation means responds to the speech content of the user, the voice input means for inputting the voice spoken by the user, the voice recognition means for recognizing the voice input to the voice input means, A message storage means for storing a plurality of messages and an extraction means for extracting a message in response to the message from the message storage means based on the utterance content recognized by the voice recognition means. Thus, for example, when various operations are performed by voice, it is possible to confirm by a message whether or not an operation intended by the user is performed.

  According to a third aspect of the present invention, the speaker determination means includes storage means for storing in advance a correspondence relationship for the speaker to be used for each message, and refers to the correspondence relationship stored in the storage means to Can also be determined. Thereby, when outputting each message by voice, the voice can be surely output from the speaker considered most appropriate.

  According to a fourth aspect of the present invention, there is provided control means for executing predetermined control on a predetermined control target device according to the utterance content recognized by the voice recognition means, and the message generation means is provided on the control target device. It is preferable that a message indicating that predetermined control is executed is generated, and the speaker determination unit determines a speaker provided in a direction where the control target device exists as a speaker to which the message is to be output. For example, when the user inputs “open the sunroof” by voice, the message “open the sunroof” corresponding to the utterance content is output by voice from a speaker provided on the roof in the vehicle interior. Thereby, a user's consciousness can be easily turned to the direction where a control object apparatus exists.

  As described in claim 5, when the message generated by the message generating unit includes information about the direction, the speaker determining unit determines a speaker existing in the direction included in the message as a speaker to which the message is to be output. May be. For example, when the message output control system according to the present invention is applied to a navigation system, a voice guidance message about a route “Please turn left 200m ahead” is output by voice from a speaker provided on the passenger seat side. As a result, the user can be strongly conscious of what to turn left.

  Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. In the present embodiment, an example in which the message output control system is applied to a voice recognition device will be described. FIG. 1 is a block diagram illustrating a schematic configuration of a speech recognition apparatus 100 according to the present embodiment. Hereinafter, the speech recognition apparatus 100 according to the present embodiment will be described in detail.

  As shown in FIG. 1, the speech recognition apparatus 100 includes a speech recognition unit 30 and an output control unit 40. In addition, the voice recognition device 100 is connected to a voice input unit 10 used for voice input, a talk switch 20, speakers 50a to 50e, and a control target device 60.

  The voice input unit 10 and the talk switch 20 are devices used for voice input. When inputting a voice, for example, by pressing a push button of the talk switch 20, an input trigger is transmitted to a voice recognition unit 30 described later. When the voice recognition unit 30 receives the input trigger, the voice input unit 10 is changed to a mode for receiving voice input.

  When the user utters “open the sunroof”, for example, in the mode of accepting the voice input, the voice is converted into a voice signal by the voice input unit 10 and sent to the voice recognition unit 30. The voice recognition unit 30 recognizes this voice, generates a message corresponding to the voice, and gives it to the output control unit 40. For example, when the input voice is recognized as “open the sunroof”, a message “open the sunroof” is generated in response thereto. This message is converted into an audio signal, and is output from one speaker among the speakers 50 a to 50 e by the output control unit 40. This message is composed of a message code to be described later.

The speakers 50a to 50e are provided on the driver's seat side, the passenger seat side, the front side, the rear side, and the roof side in the vehicle interior, and are used for outputting the above-described message by voice. The control target device 60 is a device on which predetermined control is executed according to the utterance content recognized by the voice recognition unit 30. Note that the control target device 60 includes all devices mounted on a vehicle and operable by a user.

  Next, the speech recognition unit 30 of the speech recognition apparatus 100 will be described with reference to FIG. FIG. 2 is a block diagram illustrating a configuration of the voice recognition unit 30. As shown in the figure, the speech recognition unit 30 includes an AD conversion circuit 31, a recognition program processing unit 32, an acoustic model storage unit 33, a recognition dictionary storage unit 34, a message code storage unit 35, and a command code storage unit 36. The

  The AD conversion circuit 31 receives an analog audio signal input via the audio input unit 10 and converts this signal into a digitized signal. The converted digital audio signal is transmitted to the recognition program processing unit 32.

  The recognition program processing unit 32 uses the acoustic model storage unit 33 and the recognition dictionary storage unit 34 to convert a digital voice signal into a recognition word code. First, the recognition program processing unit 32 uses a technique such as a well-known hidden Markov model, which is stored in the acoustic model storage unit 33, for example, and utterance content corresponding to a digital audio signal (hereinafter referred to as recognition word reading). Is analyzed.

  The analyzed recognized word reading is collated with the recognized word reading stored in the recognition dictionary storage unit 34, and the most likely recognized word reading and the recognized word code corresponding to the recognized word reading are extracted. As shown in FIG. 4, the recognition dictionary storage unit 34 is configured to store a recognized word reading and a recognized word code corresponding to the recognized word reading one-on-one.

  The recognition program processing unit 32 refers to the message code storage unit 35 and the command code storage unit 36 and extracts a message code and a command code corresponding to the recognition code. As shown in FIG. 5, the message code storage unit 35 is configured to store a recognized word code and a message code corresponding to the recognized word code on a one-to-one basis. Similarly, as shown in FIG. 6, the command code storage unit 36 is configured to store a recognized word code and a command code corresponding to the recognized word code on a one-to-one basis. The message code is a code that can be identified by the message output unit 43 of the output control unit 40. By giving the message code to the message output control unit 43, a message corresponding to the message code can be output. The command code is a code that can be identified by the control execution unit 44 of the output control unit 40, and outputs a control signal to the control target device 60 so that the control corresponding to the command code is executed.

  Then, the recognition program processing unit 32 outputs the message code and the command code obtained by the above processing to the output control unit 40.

  Next, the output control unit 40 of the speech recognition apparatus 100 will be described with reference to FIG. FIG. 3 is a block diagram illustrating a configuration of the output control unit 40. As shown in the figure, the output control unit 40 includes a message storage unit 41, an output destination speaker code storage unit 42, a message output unit 43, and a control execution unit 44.

  The message output unit 43 refers to the message storage unit 41 and extracts a message corresponding to the message code received from the voice recognition unit 30. As shown in FIG. 7, the message storage unit 41 is configured to store a message code and a message corresponding to the message code on a one-to-one basis. Thus, for example, when various operations are performed by voice, it is possible to confirm by a message whether or not an operation intended by the user is performed.

  Further, the message output unit 43 refers to the output destination speaker code storage unit 42 and extracts an output destination speaker code corresponding to the message code received from the voice recognition unit 30. As shown in FIG. 8, the output destination code storage unit 35 is configured to store a message code and an output destination speaker code corresponding to the message code. Thus, the output destination speaker corresponding to each message is determined in advance.

  The message output unit 43 outputs the extracted message via a speaker corresponding to the extracted output destination speaker code. As shown in FIG. 9, the output destination speaker code is uniquely associated with each of the plurality of speakers 50a to 50e, and the speakers 50a to 50e to be used can be specified by the speaker code.

  The control execution unit 44 executes control corresponding to the command code received from the voice recognition unit 30 for the control target device 60. The control target device 60 is, for example, a sunroof, a trunk, a wiper, or the like. As an example, the control performed on the sunroof is opening and closing the sunroof.

  With the above-described configuration, the speech recognition apparatus according to the present embodiment determines a speaker that outputs a message from a plurality of speakers based on the message. For this reason, a message can be output by voice from speakers other than the speaker provided on the driver's seat side. As a result, a sense of reality is improved as compared with a case where a message is output by voice only from a speaker provided on the driver's seat side. Thereby, when outputting a message from the system by voice, it is possible to evoke a sense of reality for the user.

  Next, the process of the speech recognition apparatus of the present embodiment described above will be described using the flowcharts of FIGS. FIG. 10 is a flowchart showing a main routine of the speech recognition apparatus, and FIG. 11 is a flowchart showing a routine of speech recognition processing. FIG. 12 is a flowchart showing the message output control process. As a specific example, the description will be made assuming that a voice “open the trunk” is input.

  First, in step S10 of FIG. 10, it is determined whether or not the talk switch 20 has been operated. If it is determined that no operation has been performed, the apparatus is in a standby state. On the other hand, when it determines with having operated, it progresses to step S20. In step S20, the voice recognition unit 30 switches to the input mode, and enters a state of accepting voice input. Here, for example, when a voice saying “Open the trunk” is input, the process proceeds to step S30.

  In step S30, voice recognition processing is executed. This voice recognition process will be described with reference to the flowchart of FIG.

  In the flowchart of FIG. 11, first, in step S110, the recognition word reading is analyzed from the input voice. Then, the recognition word code corresponding to the recognition word reading is extracted from the recognition dictionary storage unit 34. Here, the speech “open the trunk” is analyzed to determine the recognition word reading “open the trunk”, and the recognition word code R0002 corresponding to this recognition word reading is extracted. (See FIG. 4).

  In step S120, the message code corresponding to the recognized word code extracted in step S110 is extracted from the message code storage unit 35. Here, the message code M0002 corresponding to the recognition word code R0002 is extracted (see FIG. 5).

  In step S130, a command code corresponding to the recognized word code extracted in step S110 is extracted from the command code storage unit 36. Here, the command code C0002 corresponding to the recognized word code R0002 is extracted (see FIG. 6). In step S140, the extracted message code and command code are transmitted to the output control unit 40.

  Returning to the flowchart of FIG. 10, in step S40, a message output control process is executed. This message output control process will be described with reference to the flowchart of FIG.

  In the flowchart of FIG. 12, first, in step S210, the message output unit 43 extracts a message corresponding to the message code from the message storage unit 41. Here, since the message code is M0002, the message “open trunk” is extracted (see FIG. 7).

  In step S <b> 220, the message output unit 43 extracts an output destination speaker code corresponding to the message code from the output destination speaker code storage unit 42. Here, the output destination speaker code S0004 corresponding to the message code M0002 is extracted (see FIG. 8).

  In step S230, the message output unit 43 outputs the extracted message by voice through a speaker corresponding to the extracted output destination speaker code. Here, since the output destination speaker code corresponds to the speaker (rear) 50d (see FIG. 9), the voice “open the trunk” is output via the speaker (rear) 50d. Thereby, when outputting each message by voice, the voice can be surely output from the speaker considered most appropriate. In addition, the user's consciousness can be easily directed in the backward direction where the trunk exists.

  In step S240, the control execution unit 44 executes control corresponding to the command code. Here, the trunk is opened based on the command code C0002.

  It should be noted that the present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present invention.

  For example, in the above-described embodiment, an example has been described in which voice is output from an output destination speaker corresponding to a message from the system corresponding to the voice input by the user. However, the present invention may be applied when outputting a message from the system (for example, voice recognition guidance) even if the user does not input voice. For example, the message “Please press the talk switch 20 on the left side of the steering wheel to speak” is output from the system by voice through the speaker (passenger seat) 50b. Thereby, the user's consciousness can be easily directed to the left direction where the talk switch 20 exists.

  In the embodiment described above, the speech recognition device 100 may be used as an input device of a known navigation system. For example, when the user inputs a voice “What is a convenience store?”, A convenience store around the current position of the vehicle is searched through the navigation system, and the search result is output. As an example, a search result message “There is a convenience store on the right side, 5 km away” is output by voice through a speaker (driver's seat) 50a. Thereby, it is possible to make the user strongly aware that there is a convenience store on the right side.

  Furthermore, in the above-described embodiment, the voice recognition device 100 may be used as a voice output device of a known navigation system. For example, a voice guidance message “Please turn right 100m ahead” regarding the route from the navigation system is output by voice from the speaker 50a provided on the driver's seat side. As a result, it is possible to make the user strongly aware that the user should turn right.

In the embodiment described above, the message may be output with a different voice quality for each speaker. For example, messages are output with different voice qualities from speakers on the driver's seat side and the passenger seat side. As a result, the user feels as if two people are speaking. Thereby, compared with the case where a message is output with one voice quality with one fixed speaker, the user can evoke a sense of reality more.

It is a block diagram which shows schematic structure of the speech recognition apparatus 100 in this embodiment. It is a block diagram which shows the structure of the speech recognition part 30 in this embodiment. It is a block diagram which shows the structure of the output control part 40 in this embodiment. It is a table | surface which shows the correspondence of recognition word reading and recognition word code in this embodiment. It is a table | surface which shows the correspondence of a recognition word code and a message code in this embodiment. It is a table | surface which shows the correspondence of a recognition word code and command code in this embodiment. It is a table | surface which shows the correspondence of a message code and a message in this embodiment. It is a table | surface which shows the correspondence of a message code and an output destination speaker code in this embodiment. It is a table | surface which shows the correspondence of an output destination speaker code | cord | chord and an output destination speaker in this embodiment. It is a flowchart which shows the main routine of the speech recognition apparatus in this embodiment. In this embodiment, it is a flowchart which shows the routine of a speech recognition process. In this embodiment, it is a flowchart which shows the routine of a message output control process.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Voice input part 20 ... Talk switch 30 ... Voice recognition part 40 ... Message output control part 50a ... Speaker (driver's seat)
50b ... Speaker (passenger seat)
50c ... Speaker (front)
50d ... Speaker (rear)
50e ... Speaker (roof)

Claims (5)

A plurality of speakers provided at a plurality of locations in the passenger compartment;
Message generating means for generating a message output by voice from the speaker;
Speaker determination means for determining, from the plurality of speakers, a speaker to output the message based on the message generated by the message generation means;
A message output control system comprising: output control means for outputting the message by voice from the speaker determined by the speaker determination means. The message generation means includes:
Voice input means for inputting voice spoken by the user;
Voice recognition means for recognizing voice input to the voice input means;
Message storage means for storing a plurality of messages in response to the user's utterance content;
The message output control system according to claim 1, further comprising: an extraction unit that extracts a message that responds to the content of the utterance recognized by the voice recognition unit from the message storage unit. The speaker determination means
For each message, it is provided with storage means for storing in advance the correspondence relationship for the speaker to be used,
3. The message output control system according to claim 1, wherein a speaker to which the message is to be output is determined with reference to a correspondence relationship stored in the storage unit. In accordance with the utterance content recognized by the voice recognition means, a control means for executing a predetermined control on a predetermined control target device,
The message generation unit generates a message indicating that predetermined control is performed on the control target device, and the speaker determination unit includes a speaker provided in a direction in which the control target device exists. 4. The message output control system according to claim 2, wherein the message is determined as a speaker to be output.   When the message generated by the message generation unit includes information about a direction, the speaker determination unit determines a speaker existing in the direction included in the message as a speaker to which the message is to be output. The message output control system according to any one of claims 1 to 3.

Images