JP2012088406A - Electronic apparatus and control method thereof - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an electronic apparatus and a control method thereof, which improve operability by voice recognition in each operation mode when any one of a plurality of operation modes can be set.SOLUTION: A mobile phone 1 comprises: a storage section 70 configured to store normal dictionary data 71 in which a plurality of functions that can be started in normal mode and reading kana for the functions that are referred to in voice recognition, are correlated, and simple dictionary data 72 in which a plurality of functions that can be started in simple mode and reading kana for the functions that are referred to in voice recognition, are correlated; a mode determining section 50 configured to determine whether normal mode or simple mode has been set when voice recognition function is started; and a voice recognition section 60 configured to recognize voice by referring to the normal dictionary data 71 when the determination is made that the normal mode has been set and to recognize voice by referring to the simple dictionary data 72 when the determination is made that the simple mode has been set.

Description

  The present invention relates to an electronic device having a voice recognition function and a control method thereof.

  2. Description of the Related Art Conventionally, electronic devices such as mobile phones and navigation devices have a function for executing predetermined processing by voice recognition. For example, a user of an electronic device can give an instruction such as calling a mail function or selecting from an address book by voice without performing a selection operation.

  Such an electronic device includes a recognition dictionary that is collated with the result of speech recognition. However, there may be situations where the recognition dictionary has to be changed. Patent Document 1 describes a recognition dictionary update process in a distributed processing type voice recognition server used for realizing a voice recognition service for a portable electronic device. In particular, a plurality of voice recognition processes are described. It has been proposed to improve the efficiency of updating the recognition dictionary in the case of holding a part.

  In addition to electronic operation modes, electronic devices may be provided with specific operation modes that simplify operations by limiting executable functions. In the case of this specific operation mode, the convenience can be further improved by the voice recognition function.

JP 2008-15209 A

  By the way, as described in Patent Document 1, a large processing load is required to update the recognition dictionary. On the other hand, the function block itself of the voice recognition process has been made compact and is being mounted on the portable electronic device itself. Of course, since the portable electronic device has a lower processing capability than the server, even if a slight update of the recognition dictionary occurs, the update process takes a long time. As a result, there arises a disadvantage that the response to the user's operation is delayed.

  Therefore, the speech recognition process is made to correspond only to limited functions that can be executed in a specific operation mode, thereby reducing the size of the recognition dictionary and various processing loads related to speech recognition. Then, the convenience of voice recognition cannot be obtained in the normal operation mode. Further, when the recognition dictionary is expanded to correspond to the normal operation mode, the operability by voice recognition is reduced as the number of functions increases and the reading kana (function name) for each mode increases.

  Therefore, an object of the present invention is to provide an electronic device and a control method thereof that improve operability by voice recognition in each operation mode when it can be set to any of a plurality of operation modes.

  The electronic device according to the present invention includes a first operation mode in which a plurality of functions included in the first function group can be activated, and a second operation mode in which a plurality of functions included in the second function group can be activated. A first voice in which a plurality of functions included in the first function group and a reading pseudonym of the function referred to at the time of voice recognition are associated with each other. A storage unit for storing a recognition dictionary, a second speech recognition dictionary in which a plurality of functions included in the second function group and a reading pseudonym of the function referred to during speech recognition are associated with each other; and speech recognition When the function is activated, a determination unit that determines whether the first operation mode or the second operation mode is set, and the determination unit sets the first operation mode. If determined, the first A speech recognition unit that performs speech recognition with reference to the speech recognition dictionary, and performs speech recognition with reference to the second speech recognition dictionary when it is determined that the second operation mode is set. And comprising.

  The electronic device according to the present invention further includes an update unit that updates the reading pseudonym in accordance with the change when any reading pseudonym in the first speech recognition dictionary or the second speech recognition dictionary is changed. The update unit does not update the reading pseudonym according to the change when there is a reading pseudonym identical to the changed reading pseudonym in the same speech recognition dictionary as the speech recognition dictionary in which the reading pseudonym is changed. It is preferable.

  In addition, when the reading kana associated with a predetermined function of one of the first speech recognition dictionaries or the second speech recognition dictionary is changed, the update unit changes the other When there is a reading kana associated with the predetermined function in the voice recognition dictionary, it is preferable to update the reading kana in the other voice recognition dictionary as well as the reading kana in the one voice recognition dictionary.

  The updating unit preferably updates the other speech recognition dictionary when the operation mode is switched from the operation mode referring to the one speech recognition dictionary to the operation mode referring to the other speech recognition dictionary.

  The electronic device according to the present invention further includes a display unit, and the update unit has the same reading kana as the changed reading kana not in the same voice recognition dictionary but in the other voice recognition dictionary. In this case, it is preferable to notify by displaying an operation mode in which the other voice recognition dictionary is referred to and a function associated with the changed reading kana.

  Further, the update unit notifies when the changed reading pseudonym is associated with a function different from that of the one voice recognition dictionary in the other speech recognition dictionary, and the changed reading pseudonym It is preferable not to notify when the function is associated with the same function as the one voice recognition dictionary.

  The control method according to the present invention includes a first operation mode in which a plurality of functions included in the first function group can be activated, and a second operation mode in which a plurality of functions included in the second function group can be activated. A method of controlling an electronic device that can be set to any one of the plurality of functions, wherein the electronic device includes a plurality of functions included in the first function group and a reading pseudonym of the function referred to during speech recognition. A first speech recognition dictionary associated with each other, and a second speech recognition dictionary in which a plurality of functions included in the second function group and a reading pseudonym of the function referred to during speech recognition are associated with each other. A determination step for determining whether the first operation mode or the second operation mode is set when the speech recognition function is stored, and the first operation in the determination step; Set to mode If it is determined that the second operation mode is set, the second voice is recognized by referring to the first voice recognition dictionary. A speech recognition step of performing speech recognition with reference to the recognition dictionary.

  ADVANTAGE OF THE INVENTION According to this invention, when an electronic device can be set to either of several operation modes, the operativity by voice recognition can be improved in each operation mode.

1 is an external perspective view of a mobile phone according to an embodiment of the present invention. It is a block diagram which shows the function of the mobile telephone which concerns on embodiment of this invention. It is a figure which shows the example of an update of the speech recognition dictionary which concerns on embodiment of this invention, and a reading kana. It is a figure which shows the example of data of the some speech recognition dictionary which concerns on embodiment of this invention. It is a figure which shows the example of a display of the warning screen which concerns on embodiment of this invention. It is a flowchart which shows the process at the time of starting of the speech recognition function which concerns on embodiment of this invention. It is a flowchart which shows the edit process of the speech recognition dictionary which concerns on embodiment of this invention.

  Hereinafter, an example of a preferred embodiment of the present invention will be described. In the present embodiment, as an example of an electronic device, a mobile phone that can be set to one of two operation modes of a normal mode (first operation mode) and a simple mode (second operation mode). 1 will be described.

FIG. 1 is an external perspective view of a mobile phone 1 according to the present embodiment.
FIG. 1 shows a so-called foldable mobile phone, but the mobile phone according to the present invention is not limited to this. For example, a sliding type in which one casing is slid in one direction from a state in which both casings are overlapped, or a rotary type in which one casing is rotated around an axis along the overlapping direction ( Turn type), or a type (straight type) in which the operation unit and the display unit are arranged in one housing and does not have a connecting unit.

  The mobile phone 1 includes an operation unit side body 2 and a display unit side body 3. The operation unit side body 2 includes an operation unit 11 on the front surface unit 10 and a microphone 12 to which a voice uttered by a user of the mobile phone 1 during a call or when using a voice recognition application is input. The The operation unit 11 includes a function setting operation button 13 for activating various functions such as various setting functions, a telephone book function, and a mail function, and an input operation button 14 for inputting numbers of telephone numbers, mail characters, and the like. , And a determination operation button 15 for performing determination and scrolling in various operations.

  The display unit side body 3 includes a display unit 21 for displaying various types of information on the surface unit 20 and a receiver 22 for outputting the voice of the other party of the call.

  Further, the upper end portion of the operation unit side body 2 and the lower end portion of the display unit side body 3 are connected via a hinge mechanism 4. In addition, the mobile phone 1 relatively rotates the operation unit side body 2 and the display unit side body 3 which are connected via the hinge mechanism 4, so that the operation unit side body 2 and the display unit side body 3 are rotated. The body 3 can be in an open state (open state), or the operation unit side body 2 and the display unit side body 3 can be folded (closed state).

FIG. 2 is a block diagram showing functions of the mobile phone 1 according to the present embodiment.
The mobile phone 1 includes an operation unit 11, a display unit 21, a control unit 30, a communication unit 40, a mode determination unit 50, a voice recognition unit 60, a storage unit 70, and a dictionary update unit 80.

  The control unit 30 controls the entire mobile phone 1, and performs predetermined control on each unit such as the display unit 21 and the communication unit 40, for example. In addition, the control unit 30 receives input from the operation unit 11, the communication unit 40, and the like, and executes various processes. And the control part 30 controls the memory | storage part 70 in the case of a process execution, reads various programs and data, and writes data.

  The communication unit 40 communicates with an external device (base station) in a predetermined use frequency band (for example, 2 GHz band, 800 MHz band, etc.). The communication unit 40 demodulates the signal received from the antenna 41 and supplies the processed signal to the control unit 30. Also, the signal supplied from the control unit 30 is modulated and transmitted to an external device via the antenna 41.

  When the voice recognition function is activated, the mode determination unit 50 determines whether the mobile phone 1 is set to the normal mode or the simple mode and is operating.

  The voice recognition unit 60 executes a voice recognition process on the signal input from the microphone 12 based on a command from the control unit 30, and provides a processing result (text information obtained by converting voice into text) to the control unit 30. At this time, when the mode determination unit 50 determines that the normal mode is set, the voice recognition unit 60 refers to the normal dictionary data 71 (first voice recognition dictionary) in the storage unit 70. On the other hand, when it is determined that the simple mode is set, the speech recognition unit 60 refers to the simple dictionary data 72 (second speech recognition dictionary) in the storage unit 70.

  The storage unit 70 stores various programs according to the present embodiment, and is used for arithmetic processing by the control unit 30. Furthermore, the storage unit 70 stores normal dictionary data in which a plurality of functions included in a function group (first function group) that can be activated in the normal mode are associated with a reading pseudonym of this function that is referred to during speech recognition. 71 and simple dictionary data 72 in which a plurality of functions included in the function group (second function group) that can be activated in the simple mode and the reading pseudonym of the function referred to during speech recognition are associated with each other. is doing.

  The speech recognition dictionary is data including choices of reading kana to be collated with text information obtained as a result of speech recognition. Each of these readings is associated with a function that can be activated in each operation mode. If the reading has the same reading as the result of speech recognition, the associated function is controlled by the control unit. 30.

  The dictionary update unit 80 receives an edit input in which either the reading dictionary in the normal dictionary data 71 or the simple dictionary data 72 is changed from the operation unit 11 or the like, and updates the reading table according to this change.

FIG. 3 is a diagram showing an example of updating the speech recognition dictionary and the reading kana according to the present embodiment.
As shown in FIG. 3A, in the speech recognition dictionary (normal dictionary data 71 or simple dictionary data 72), identification data (function ID) of a function that can be activated in each operation mode is associated with a reading pseudonym. Yes. For example, in the first line (No = 0), “function ID = 0” indicating the “use camera” function is associated with the reading “camera”.

  The reading kana in the speech recognition dictionary can be changed to another text by the user. For example, as illustrated in FIG. 3B, when the dictionary update unit 80 receives an edit input for changing “camera” to “chassin”, the dictionary update unit 80 sets the reading kana associated with “function ID = 0” to “ Update to Shashin.

  However, the dictionary update unit 80 notifies the warning and updates the reading pseudonym according to the change when the same reading pseudonym as the thus changed reading pseudonym exists in the same speech recognition dictionary. Absent. Specifically, the dictionary updating unit 80 displays the type of dictionary data and the target function on the display unit 21 to notify the user that updating is not possible.

  In addition, since there are overlapping functions in the normal dictionary data 71 and the simple dictionary data 72, different reading pseudonyms may be associated with the same function ID.

FIG. 4 is a diagram illustrating a data example of a plurality of speech recognition dictionaries according to the present embodiment.
In the normal dictionary data 71, reading names are associated with 200 function IDs, respectively. On the other hand, in the simple dictionary data 72, the reading pseudonym is associated with 50 function IDs. In this example, function IDs 0 to 49 are common to both dictionary data, but the reading pseudonyms do not necessarily match. For example, in the normal dictionary data 71, “camera menu” is associated with the function ID = 1, but in the simple dictionary data 72, “camera out” is associated.

  Here, in the simple dictionary data 72, when the reading kana with the function ID = 0 is updated from “camera” to “shashin”, the reading kana is different from the normal dictionary data 71. Since the reading function is the same function, the user can enable the dictionary data automatic updating function when the user wishes to use the same reading pseudonym.

  That is, when the reading kana of one dictionary data in the normal dictionary data 71 or the simple dictionary data 72 is updated, the dictionary updating unit 80 reads the reading kana of the same function in the other dictionary data at a predetermined timing. It is updated in the same way as the reading of one dictionary data.

  Here, the predetermined timing is when the processing load of the mobile phone 1 becomes low, when the operation mode is changed, or when the other dictionary data is referred to, that is, the operation mode is changed. When the voice recognition function is activated.

  When one of the dictionary data (for example, simple dictionary data 72) is updated, the dictionary updating unit 80 stores the updated function and reading kana correspondence data. Then, when the operation mode (for example, the normal mode) that refers to the other dictionary data (for example, the normal dictionary data 71) is activated, the dictionary update unit 80 selects the other based on the stored association data. Dictionary data (for example, normal dictionary data 71) is updated. The association data may be stored as update data separately from the dictionary data, or may be stored by adding an update flag to the target record of any dictionary data.

  When dictionary data is automatically updated in this way, the dictionary update unit 80 needs to control so that the changed reading pseudonym does not overlap in any dictionary data. Therefore, the dictionary update unit 80 does not exist in one dictionary data (for example, simple dictionary data 72) whose edited reading is to be edited, but in the other dictionary data (for example, normal dictionary data 71). If present, an operation mode (for example, a normal mode) referring to the other dictionary data and a function name associated with the changed reading pseudonym are displayed on the display unit 21 to notify a warning.

  However, the dictionary update unit 80 associates the changed reading pseudonym with a different function ID in the other dictionary data (for example, normal dictionary data 71) from that of the other dictionary data (for example, simple dictionary data 72). If it is associated with the same function ID as one of the dictionary data, the warning is not notified.

FIG. 5 is a diagram illustrating a display example of a warning screen according to the present embodiment.
In this example, in the simple mode, an edit input for changing the reading kana “camera” (b) corresponding to the function “use camera” (a) to “shashin” is accepted (c).

  When editing input is completed (OK button is pressed) and update processing is executed on the confirmation screen (d) (registration button is pressed), a warning screen is displayed (e). In this case, the simple dictionary data 72 does not have another function with the reading kana “shashin”, but the normal dictionary data 71 has the function “picture folder” with the reading kana “shashin”. ing. Accordingly, “normal” is displayed as the type of dictionary data, and “picture folder” is displayed as the function name. Thereafter, the dictionary update unit 80 transitions to the confirmation screen (f) in response to receiving a key input from the operation unit 11 or time-out, and prompts re-editing of the reading kana.

FIG. 6 is a flowchart showing processing upon activation of the voice recognition function according to the present embodiment.
In step S1, the mode determination unit 50 determines whether or not the operation mode of the mobile phone 1 is the simple mode (normal mode). If this determination is YES, control unit 30 moves the process to step S3, and if the determination is NO, the control unit 30 moves the process to step S2.

  In step S <b> 2, the voice recognition unit 60 reads from the storage unit 70 normal dictionary data 71 corresponding to a function group that can be activated in the normal mode.

  In step S <b> 3, the voice recognition unit 60 reads the simple dictionary data 72 corresponding to the function group that can be activated in the simple mode from the storage unit 70.

  In step S4, in order to synchronize the read dictionary data with the other dictionary data, the dictionary update unit 80 updates the read kana that has been updated with the other dictionary data but not updated with the read dictionary data.

FIG. 7 is a flowchart showing the speech recognition dictionary editing process according to the present embodiment.
In step S11, the dictionary update unit 80 accepts an edit input for changing the reading pseudonym of the dictionary data in the current operation mode.

  In step S <b> 12, the dictionary update unit 80 determines whether the editing content has been confirmed. The dictionary update unit 80 moves the process to step S13 if the determination is YES, and moves the process to step S19 if the determination is NO.

  In step S13, the dictionary updating unit 80 first determines whether or not different functions and reading kana are duplicated in the dictionary data whose edit contents are to be edited (for example, simple dictionary data 72). The dictionary update unit 80 moves the process to step S14 when this determination is YES, and moves the process to step S15 when the determination is NO.

  In step S <b> 14, the dictionary update unit 80 displays an operation mode for referring to dictionary data with duplicated readings and a duplicated function on the display unit 21 and issues a warning. And a process returns to step S11 and edit input is continued.

  In step S15, the dictionary update unit 80 does not have duplicate readings in the same dictionary data. Next, in the dictionary data (for example, normal dictionary data 71) in which the determined editing content is different from the editing target, It is determined whether or not different functions and readings are duplicated. If this determination is YES, the dictionary updating unit 80 moves the process to step S16, and if the determination is NO, the dictionary updating unit 80 moves the process to step S17.

  In step S <b> 16, the dictionary update unit 80 determines whether or not the functions having duplicate readings are the same. The dictionary update unit 80 moves the process to step S17 when this determination is YES, and moves the process to step S14 when the determination is NO.

  In step S <b> 17, the dictionary update unit 80 updates both dictionary data with the confirmed editing contents because there is no duplication of reading kana in any dictionary data. Or, in another case, since the reading kana matches with the same function in different dictionaries, in that case, the dictionary update unit 80 updates the dictionary data on the edited dictionary side.

  In step S18, the dictionary update unit 80 displays the update result of step S17 on the display unit 21 to notify the user.

  In step S19, the dictionary update unit 80 determines whether or not to end the process. Specifically, the dictionary update unit 80 determines to end this process in response to an end instruction from the user or the occurrence of an interrupt process. If the determination is YES, the dictionary updating unit 80 ends the process. If the determination is NO, the dictionary updating unit 80 moves the process to step S11 and continues the edit input.

  As described above, according to the present embodiment, the mobile phone 1 associates the function group that can be activated in each operation mode and the reading pseudonym for each of the normal mode and the simple mode during voice recognition. Refer to separate dictionary data. Therefore, the dictionary data can be minimized in each operation mode, so that the mobile phone 1 improves operability by voice recognition in each operation mode when it can be set to any of a plurality of operation modes.

  Further, since the mobile phone 1 can accept an edit input for changing the reading kana and update the dictionary data, the convenience of the user can be improved. Further, at this time, the mobile phone 1 is not updated when the same reading kana as the changed reading kana exists, so that the reading kana can be controlled not to overlap in the same dictionary data.

  Further, when the reading kana of one dictionary data is updated, the cellular phone 1 updates the reading kana of the other dictionary data in the same manner as the one dictionary data at a predetermined timing. Accordingly, since the mobile phone 1 can automatically synchronize a plurality of voice recognition dictionaries, the user can perform the same function by the same utterance regardless of which operation mode the mobile phone 1 is set to. Can be started.

  Further, the cellular phone 1 performs the dictionary data update process by editing the input timing when the operation mode is changed or when the operation mode is changed and the voice recognition function is activated. Dispersion from time can reduce processing load.

  Further, when the changed reading pseudonym overlaps with the other dictionary data, the mobile phone 1 displays the type of the dictionary data that is duplicated, that is, the operation mode, and the duplicated function. Therefore, the mobile phone 1 can suppress duplication of reading kana even between a plurality of voice recognition dictionaries and can inform the user of the contents of duplication in detail.

  As mentioned above, although embodiment of this invention was described, this invention is not restricted to embodiment mentioned above. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.

  In the above-described embodiment, the mobile phone 1 is described as an electronic device. However, the electronic device is not limited to this, and the present invention is not limited to the PHS (registered trademark; Personal Handyphone System) and PDA (Personal Digital Assistant). ), A game machine, a navigation device, a personal computer, and the like.

1 Mobile phone (electronic equipment)
DESCRIPTION OF SYMBOLS 11 Operation part 21 Display part 30 Control part 40 Communication part 41 Antenna 50 Mode determination part (determination part)
60 voice recognition unit 70 storage unit 71 normal dictionary data (first voice recognition dictionary)
72 Easy dictionary data (second speech recognition dictionary)
80 Dictionary Update Department

Claims (7)

Can be set to one of a first operation mode in which a plurality of functions included in the first function group can be activated and a second operation mode in which a plurality of functions included in the second function group can be activated. Electronic equipment,
A first speech recognition dictionary in which a plurality of functions included in the first function group and a reading pseudonym of the function referred to during speech recognition are associated with each other, and a plurality of functions included in the second function group A storage unit for storing a second speech recognition dictionary in which a function and a reading pseudonym of the function referred to during speech recognition are associated with each other;
A determination unit that determines whether the first operation mode or the second operation mode is set when the speech recognition function is activated;
When the determination unit determines that the first operation mode is set, speech recognition is performed with reference to the first voice recognition dictionary, while the second operation mode is set. An electronic device comprising: a voice recognition unit that performs voice recognition with reference to the second voice recognition dictionary when it is determined that the second voice recognition dictionary is present. When any reading kana in the first voice recognition dictionary or the second voice recognition dictionary is changed, an update unit that updates the reading kana according to the change is further provided.
The update unit does not update the reading pseudonym according to the change when there is a reading pseudonym identical to the changed reading pseudonym in the same speech recognition dictionary as the speech recognition dictionary in which the reading pseudonym is changed. Item 2. The electronic device according to Item 1.   The update unit recognizes the other voice when the reading kana associated with a predetermined function of one of the first voice recognition dictionaries or the second voice recognition dictionary is changed. 3. The electronic device according to claim 2, wherein, in the dictionary, when there is a reading kana associated with the predetermined function, the reading kana in the other voice recognition dictionary is updated in the same manner as the reading kana in the one voice recognition dictionary. .   4. The electronic device according to claim 3, wherein the update unit updates the other speech recognition dictionary when the mode is switched from an operation mode that refers to the one speech recognition dictionary to an operation mode that refers to the other speech recognition dictionary. 5. machine. A display unit;
The update unit is configured to refer to the other speech recognition dictionary when the same reading pseudonym as the changed reading pseudonym does not exist in the same speech recognition dictionary but exists in the other speech recognition dictionary; and The electronic device according to claim 2, wherein the electronic device is notified by displaying a function associated with the changed reading pseudonym.   The update unit notifies when the changed reading pseudonym is associated with a function different from that of the one speech recognition dictionary in the other speech recognition dictionary, and the changed reading pseudonym is the one The electronic device according to claim 5, wherein the electronic device is not notified when associated with the same function as the voice recognition dictionary. Can be set to one of a first operation mode in which a plurality of functions included in the first function group can be activated and a second operation mode in which a plurality of functions included in the second function group can be activated. A control method for an electronic device,
The electronic device includes a first speech recognition dictionary in which a plurality of functions included in the first function group and a reading pseudonym of the function referred to during speech recognition are associated with each other, and the second function group A second speech recognition dictionary in which a plurality of functions included in the text and a reading pseudonym of the function referred to during speech recognition are associated with each other,
A determination step of determining whether the first operation mode or the second operation mode is set when the voice recognition function is activated;
If it is determined in the determination step that the first operation mode is set, speech recognition is performed with reference to the first speech recognition dictionary, while the second operation mode is set. A speech recognition step of performing speech recognition with reference to the second speech recognition dictionary when it is determined that the second speech recognition dictionary is present.

Images