JP2017167600A - Terminal device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To facilitate a process of selecting functions associated with voice recognition processing.SOLUTION: A terminal device 10 includes: a detection unit 15 configured to detect an object approaching the terminal device and measure a period of time the object stays in the proximity (proximity time); an input unit 16 for inputting voice; an execution unit 17 configured to execute functions associated with voice recognition processing on the voice input by the input unit 16; and a determination unit 18 configured to determine a function associated with the voice recognition processing to be executed by the execution means based on the proximity time measured by the detection unit 15.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a terminal device.

  Patent Document 1 discloses an electronic device including a proximity sensor and voice recognition means. In this apparatus, when the proximity sensor detects that an object is close to the apparatus, the apparatus can be operated by voice recognition processing.

Special table 2003-501959 gazette

  In a terminal device typified by a smart phone or the like, various functions such as music playback and user interaction can be used by a user operation using the result of speech recognition processing. The result of the speech recognition process can also be obtained using specific recognition among various recognition methods. Therefore, it is necessary to select a function that acquires the result of speech recognition processing by a specific recognition method or a function that uses the result of speech recognition processing (hereinafter, also referred to as “function related to speech recognition processing”).

  For example, referring to the technique of Patent Document 1, it is considered that the user selects a function related to the voice recognition process by starting the voice recognition process of the terminal using the proximity sensor and then operating the terminal using the voice recognition process. It is done. However, if it is necessary to perform a terminal operation using a voice recognition process for each selection, the user may feel annoying.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide a terminal device that can easily select a function related to speech recognition processing.

  A terminal device according to an aspect of the present invention detects a proximity of an object to the terminal device and detects a proximity time of the detected object, an input unit that inputs sound, and an input unit An execution unit that executes a function related to a voice recognition process for speech; and a determination unit that determines a function related to the voice recognition process executed by the execution unit based on the proximity time measured by the detection unit. .

  According to said terminal device, the function which concerns on the audio | voice recognition process for the input audio | voice is performed. Here, the function to be executed is determined based on the proximity time of the object. Therefore, the user can easily select a function related to speech recognition only by performing an operation of bringing an object close to the terminal device for a predetermined time, for example, holding a hand (close the hand) to the terminal device.

  The determining means may determine a function for acquiring a result of the speech recognition process by a recognition method according to the proximity time as a function related to the speech recognition process. Thereby, it is possible to easily select the recognition method by which the result of the speech recognition process is acquired.

  The determining unit may determine a function using a result of the voice recognition process as a function related to the voice recognition process. Thereby, the function using the result of the voice recognition process can be easily selected.

  According to the present invention, when selecting a function related to speech recognition processing, the selection can be easily performed.

It is a figure which shows schematic structure of a terminal device. It is a figure which shows the hardware constitutions of a terminal device. It is a flowchart which shows an example of the process performed in a terminal device.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant descriptions are omitted.

  FIG. 1 is a diagram illustrating a schematic configuration of a terminal device according to the embodiment. The terminal device 10 is configured to be able to execute various functions available to the user. The terminal device 10 can also be referred to as a voice operation device. This is because at least a part of the functions that can be executed by the terminal device 10 involves an operation using voice recognition processing. When the user of the terminal device 10 uses such a function, the terminal device 10 uses a function related to speech recognition processing (specific speech recognition determined according to the proximity time described later) according to the principle described below using a proximity sensor. A function for obtaining the result of the speech recognition processing by the technique and a function using the result of the speech recognition processing) are selected.

  First, as a function related to the voice recognition process, a function (application) using the result of the voice recognition process will be described. Such an application can be used by a user operation using voice recognition processing. The user can use the application without using an operation (operation of a touch panel, a button, or the like) performed by physically contacting the terminal device 10. The type of application is not particularly limited. In the present embodiment, an application that interacts with the user (interactive application) and an application that reproduces various contents and provides the user (content providing application) will be described as examples. Content providing applications include music playback applications (music apps), video playback applications (video apps), applications that can present and interpret traffic information (travel apps), products There are applications (shopping application) that can provide information and purchase procedures and are useful for shopping, and applications (weather application) that present weather information.

  Next, a function (acquisition function) for acquiring a result of speech recognition processing by a specific recognition method (recognition model) will be described as a function related to the speech recognition processing. This function can also be said to be a function that uses different recognition models for voice recognition processing depending on the application used (the above-mentioned music application, travel application, shopping application, etc.). The recognition model is a method that determines what language model (a model indicating ease of connection between morphemes before and after), an interaction model, and the like are used for speech recognition processing. When a music application is used, it is preferable to use a recognition model (music recognition model) using a language model or the like designed to accurately recognize voices related to the name of a song or the name of a singer. When a travel application is used, it is preferable to use a recognition model (travel recognition model) using a language model or the like designed to accurately recognize voices related to accommodation facilities, tourist facilities, transportation means, and the like. When a shopping application is used, it is preferable to use a recognition model (a recognition model for shopping) using a language model or the like designed to accurately recognize voices related to products, stores, and the like. When a dialogue application is used, a recognition model (a recognition model for dialogue) using a dialogue model according to the user attributes (nationality, age, sex, etc.) may be used. The conversation model is constructed by combining a language model and an acoustic model (a model that shows the correspondence between phonetic features (mel frequency cepstrum coefficients, etc.) and phonemes (individual vowels / consonants)) according to the user's attributes. Also good.

  An example of the usage scene of the function related to the voice recognition processing as described above will be described. In this example, the above-described music application is used by using the result of the speech recognition processing by the recognition model (music recognition model) suitable for the music application. As a premise, as shown in FIG. 1, it is assumed that the terminal device 10 can communicate with a voice recognition server 20 and a content server 30 provided outside the terminal device 10.

  First, the user of the terminal device 10 activates in advance an application (proximity app) for determining a function related to voice recognition processing using the proximity sensor 11 described later in the terminal device 10. For example, the proximity app is activated in response to an instruction to activate the proximity app by a user operation using a touch panel or a button of the terminal device 10. Note that the proximity app may be constantly activated while the terminal device 10 is operating, regardless of whether or not such a user operation is performed. By using this proximity app, the user can select and use a function related to the voice recognition process, as will be described below.

  The user of the terminal device 10 brings his hand close to the terminal device 10 for a predetermined time (for example, holding his hand). As an example, the predetermined time is 0.5 seconds, and in response, the terminal device 10 starts executing the speech recognition process using the music recognition model (wakes up the speech recognition function). Further, the terminal device 10 starts execution of the music application (activates the music application). And a user uses a music application by voice operation. For example, the user utters a sound for designating the type of music desired to be played. The sound for designating the music may be a sound indicating the name of the music or the name of the singer.

  The terminal device 10 inputs (receives) the voice uttered by the user. The terminal device 10 transmits the input voice to the voice recognition server 20. At that time, the terminal device 10 requests the voice recognition server 20 to set the recognition model of the voice recognition processing to be a music recognition model. The voice recognition server 20 executes voice recognition processing based on the music recognition model on the received voice, and obtains the result of the voice recognition processing (such as the name of a song). The voice recognition server 20 transmits the result of voice recognition to the terminal device 10.

  The terminal device 10 executes the music application using the received (acquired) result of the speech recognition process. The terminal device 10 requests the content server 30 to distribute various contents. In this example, the terminal device 10 requests the content server 30 for information (music data) necessary for reproducing the music specified by the result of the voice recognition process. In response to a request from the terminal device 10, the content server 30 transmits (distributes) music data to the terminal device 10.

  The terminal device 10 reproduces the music using the received music data. Thereafter, when the user utters a sound for instructing to stop the reproduction of the music, the voice recognition process is performed again on the sound. In response to the result of the voice recognition process, that is, the instruction to stop the reproduction of the music, the terminal device 10 stops the reproduction of the music.

  As described above, the user selects the function for acquiring the result of the speech recognition process using the speech recognition model as the function (acquisition function) for acquiring the result of the speech recognition process using the specific recognition method (recognition model). The music application can be selected and used as a function (application) using the voice recognition process.

  Hereinafter, the terminal device 10 will be described in detail. As shown in FIG. 1, the terminal device 10 includes a proximity sensor 11, a microphone 12, a speaker 13, and a display 14. The terminal device 10 includes a detection unit 15, an input unit 16, an execution unit 17, and a determination unit 18 as functional blocks.

  The proximity sensor 11 is used to detect the proximity of an object to the terminal device 10 (that is, the proximity of the object to the terminal device). The type of the object is not particularly limited, but is assumed to be a part of the user's body such as the user's hand or finger. Therefore, as the proximity sensor 11, various known proximity sensors that can detect the proximity of a human hand or a finger may be used. The position where the proximity sensor 11 is provided is not particularly limited as long as it can detect whether an object is close to the terminal device 10. For example, when the distance between the object and the terminal device 10 is shorter than several mm to several cm, the proximity sensor 11 detects the proximity of the object to the terminal device 10.

  The detection result of the proximity sensor 11 is sent to the detection unit 15 described later. The detection result of the proximity sensor 11 may be information indicating whether or not an object close to the terminal device 10 exists. The detection result of the proximity sensor 11 is sent to the detection unit 15 in real time or at a predetermined cycle while the proximity sensor 11 is operating, for example.

  The proximity sensor 11 does not operate when the proximity app described above is not activated (OFF), and starts to operate (becomes ON) when the proximity app is activated. The proximity app is executed by the execution unit 17 described later.

  The microphone 12, the speaker 13, and the display 14 are used for exchanging information between the terminal device 10 and the user.

  The microphone 12 detects sounds and sounds generated around the terminal device 10. For example, the voice uttered by the user is detected by the microphone 12 and sent to the input unit 16 described later.

  The speaker 13 is used for outputting sound and sound. When the music application is used, the music is output by the speaker 13. When using the dialog application, the speaker 13 outputs sound for performing a dialog with the user.

  The display 14 is used to output an image (including a moving image). When the moving image application is used, the moving image is output (displayed) on the display 14.

  The types of the microphone 12, the speaker 13, and the display 14 are not particularly limited, and various known ones can be used. A touch panel may be used for the display 14.

  The detection unit 15 is a part (detection unit) that detects the proximity of the object to the terminal device 10 and measures the proximity time of the detected object. The detection unit 15 detects the proximity of the object to the terminal device 10 by receiving the detection result of the proximity sensor 11 described above. If the detection result received from the proximity sensor 11 is a state (detection state) indicating that a proximity object exists, the detection unit 15 detects the proximity of the object to the terminal device 10. If the detection result is a state (non-detection state) indicating that no proximity object exists, the detection unit 15 does not detect the proximity of the object to the terminal device 10.

  The measurement of the proximity time of the object by the detection unit 15 is performed as follows, for example. In other words, the detection unit 15 determines the time from when the object is in proximity to the terminal device 10 to when the object is no longer in proximity to the terminal device 10 (proximity is released). Measure as time. As described above, when the detection result of the proximity sensor 11 is sent in real time or at a predetermined cycle, the detection unit 15 detects when the detection result of the proximity sensor 11 switches from the non-detection state to the detection state. The time difference from when the detection state is switched to the detection state can be measured as the proximity time. For example, if the detection unit 15 has a timer function, the proximity time may be measured using the timer function. The measurement of the proximity time will be described later with reference to FIG.

  The input unit 16 is a part (input means) for inputting the sound detected by the microphone 12. The input unit 16 performs voice recognition processing in response to the proximity of the object detected by the detection unit 15 (in response to the detection result of the proximity sensor 11) or in response to the above-described proximity time being measured. Start inputting voice as the target of. For example, an input unit includes a filtering process for removing noise from an input voice in order to improve accuracy of the voice recognition process, a storage process for temporarily storing voice information input for use in the voice recognition process, and the like. 16 may be executed. The voice input to the input unit 16 is sent to the execution unit 17 described below, and is subjected to voice recognition processing.

  The execution unit 17 is a part (execution unit) that executes a function related to the voice recognition process for the voice input to the input unit 16. Here, the function related to the speech recognition processing executed by the execution unit 17 is determined by the determination unit 18.

  The determining unit 18 is a part (determining unit) that determines a function related to the voice recognition process executed by the executing unit 17 based on the proximity time measured by the detecting unit 15. Specifically, the determination unit 18 obtains a result of the speech recognition processing by a specific recognition model such as a music recognition model, a travel recognition model, or a shopping recognition model based on the proximity time (acquisition function). And a function (application) using a result of the voice recognition processing such as a music application, a travel application, and a shopping application is determined. The determination result of the determination unit 18 is sent to the execution unit 17.

  The function is determined based on the proximity time, for example, as follows. That is, information (table) in which a plurality of different proximity times and functions are described in association with each other is created in advance and stored in a storage unit (not shown) in the terminal device 10. Specifically, in this table, a plurality of different proximity times, recognition models, and applications are described in association with each other. By referring to such a table, the determination unit 18 can determine a function (acquisition function and application) related to the voice recognition processing based on the proximity time (corresponding to the proximity time).

  As an example, when the proximity time is 0.5 seconds, the determination unit 18 determines the acquisition function as a function for acquiring the result of the speech recognition process using the music recognition model or the shopping recognition model as described above. May be. At the same time, the determination unit 18 may determine a function (application) related to the voice recognition processing as a music application, a shopping application, or the like. When the proximity time is 1 second, the determination unit 18 may determine the recognition model as the recognition model for interaction as described above. At the same time, the determination unit 18 may determine the application as a dialogue application.

  The combination of the proximity time and the function (acquisition function or application) related to the determined voice recognition process is not limited to the above example. In the example described later with reference to the flowchart of FIG. 3, when the proximity time is less than 0.5 seconds, the acquisition function is determined as the function for acquiring the result of the speech recognition processing by the travel recognition model, and otherwise The function for acquiring the result of the speech recognition processing by the shopping recognition model is determined.

  Returning to the description of the execution unit 17 again, the execution unit 17 executes the function related to the speech recognition processing determined by the determination unit 18 according to the determination result sent from the determination unit 18. As a specific example, a case where a music application is used will be described below.

  In order to use the music application by a user operation, the execution unit 17 causes the input unit 16 to start inputting voice from the microphone 12 as a target of voice recognition processing. When the voice input by the input unit 16 is sent to the execution unit 17, the execution unit 17 transmits this voice to the voice recognition server 20. Further, the execution unit 17 transmits information (recognition model designation information) for designating a specific recognition model (recognition model for music in this example) in the acquisition function determined by the determination unit 18 to the speech recognition server 20. To do.

  The voice recognition server 20 performs voice recognition processing on the voice received from the execution unit 17 based on the recognition model (in this example, a music recognition model) of the voice recognition process specified by the recognition model designation information received from the execution unit 17. Execute. For example, the speech recognition server 20 includes a plurality of speech recognition engines respectively corresponding to various recognition models that may be specified by the recognition model specifying information. The voice recognition server 20 can execute a voice recognition process using a designated voice recognition process recognition model (a music recognition model in this example) by using different voice recognition engines according to the recognition model designation information. The result of the speech recognition process is the same as that obtained by a known speech recognition process. For example, character string data (text data) corresponding to the voice received from the execution unit 17 and information indicating the meaning of the character string (such as part of speech of each word included in the character string) are obtained as a result of the voice recognition process. It is done. The voice recognition server 20 transmits the result of the voice recognition process to the execution unit 17.

  The execution unit 17 performs an operation on the music application using the result of the speech recognition process using a specific recognition model (in this example, a music recognition model) received (acquired) from the speech recognition server 20. The result of the voice recognition processing here is various commands for designating a specific music piece, instructing the reproduction of the music piece, or instructing the stop of the reproduction of the music piece in the music application. When the result of the voice recognition process is a specific music designation and reproduction instruction, the execution unit 17 transmits a request for distribution of the music data to the content server 30.

  The content server 30 acquires music data in response to the request received from the execution unit 17. For example, the content server 30 includes a storage unit (not shown) that stores various content information that may be requested from the execution unit 17. In that case, the content server 30 acquires content information corresponding to the request from the storage unit. In this example, the content server 30 acquires the music data from various music data stored in the storage unit. The content server 30 transmits the acquired music data to the execution unit 17.

  The execution unit 17 uses the music data received from the content server 30 to reproduce the music. Specifically, the execution unit 17 causes the speaker 13 to output the music.

  The above is an example of processing executed when a music application is used. Similarly, when a travel application, a shopping application, a dialogue application, or the like is used, the execution unit 17 includes an input unit 16, a voice recognition server, and the like. These apps can be executed by cooperating with 20 and the speaker 13. By cooperating with the display 14, the execution unit 17 can provide an image to the user.

  FIG. 2 shows a hardware configuration of the terminal device 10. As shown in FIG. 2, the terminal device 10 includes one or more CPUs (Central Processing Units) 101, a RAM (Random Access Memory) 102 and a ROM (Read Only Memory) 103, which are main storage devices, and an operation module (operations). Part) 104, a communication module (communication part) 105, the proximity sensor 11, the microphone 12, the speaker 13, and the display 14 described above. When the communication module 105 performs wireless communication, an antenna 107 is further added. By operating these components by a program or the like, each function of the terminal device 10 described above with reference to FIG. 1 is exhibited.

  FIG. 3 is a flowchart illustrating an example of processing executed in the terminal device 10. In this example, it is assumed that there is no object close to the terminal device 10 at the start of processing.

  In step S1, in the terminal device 10, the proximity sensor is turned on. This process is executed by the execution unit 17 in response to an instruction to start a proximity app by a user operation such as a touch panel or a button. When the proximity sensor 11 is turned on, the detection result of the proximity sensor 11 is sent to the detection unit 15. As described above, since there is no object that is close to the terminal device 10 at the start of the processing of this flowchart, the detection result of the proximity sensor 11 sent to the detection unit 15 is in a non-proximity state here.

  In step S2, it is determined whether or not there is a close object. This determination is performed by the detection unit 15 determining whether or not a proximity object exists based on the detection result of the proximity sensor 11. Specifically, when the detection result of the proximity sensor 11 switches from the non-proximity state to the proximity state, the detection unit 15 determines that there is a proximity object (detection of proximity of the object has started). If there is a close object (step S2: YES), the process proceeds to step S3. When that is not right (step S2: NO), the process of step S2 is performed again. At that time, the process of step S2 may be executed again after waiting for a predetermined waiting time process.

  In step S3, the measurement of the proximity time is started. Specifically, the detection unit 15 starts measuring the proximity time with the timing at which the proximity detection is started in the previous step S2 as a start time.

  In step S4, it is determined whether or not there is a close object. This determination is performed by the detection unit 15 determining whether or not a proximity object exists based on the detection result of the proximity sensor 11. If the detection result is still in the proximity state, the detection unit 15 determines that there is a proximity object. When the detection result is in a non-proximity state, the detection unit 15 determines that there is no proximity object. If there is no adjacent object (detection is no longer continued) (step S4: YES), the process proceeds to step S6. Otherwise (step S4: NO), the process proceeds to step S5.

  In step S5, the measurement of the proximity time is continued for a predetermined period. During this time, the detection unit 15 continues the above-described measurement. The length of the predetermined period may be set as a minimum unit (resolution) of the proximity time to be measured, for example. After the process of step S5 is completed, the process is returned to step S4.

  In step S6, the measurement of the proximity time is terminated. Specifically, the detection unit 15 ends the measurement of the proximity time with the timing when the proximity object disappears in the previous step S4 (the detection of the proximity is not continued) as the end point. The time from the time when the proximity time measurement is started in step S3 to the time when the proximity time measurement is completed in step S6 is measured as the proximity time.

  In step S7, it is determined whether or not the proximity time is less than a predetermined threshold value. In this example, the threshold is 0.5 seconds. Specifically, the determination unit 18 determines whether or not the measured proximity time is less than a threshold value. If the proximity time is less than the threshold (step S7: YES), the process proceeds to step S8. If not (step S7: NO), the process proceeds to step S9.

  In step S8, the recognition method (recognition model) of the speech recognition process is determined for travel (that is, travel recognition model). Specifically, the determination unit 18 determines the function (acquisition function) for acquiring the result of the speech recognition process by the specific recognition method (recognition model) as the function for acquiring the result of the speech recognition process by the travel recognition model. . In addition, the determination unit 18 determines a function (application) using the result of the voice recognition process as a travel application. After step S8 is completed, the process proceeds to step S10.

  In step S9, the recognition method (recognition model) of the speech recognition process is determined for shopping (that is, the shopping recognition model). Specifically, the determination unit 18 determines the acquisition function as a function for acquiring the result of the speech recognition process using the shopping recognition model. Moreover, the determination part 18 determines an application as a shopping application. After the process of step S9 is completed, the process proceeds to step S10.

  In step S10, voice recognition is started. Specifically, the execution unit 17 causes the input unit 16 to start inputting voice from the microphone 12 as a target of voice recognition processing. And the execution part 17 starts execution of the function which concerns on the speech recognition process determined by the determination part 18 by previous step S8 or S9. As described above, the execution unit 17 cooperates with the voice recognition server 20, the content server 30, the microphone 12, the speaker 13, the display 14, and the like to determine the recognition model (in this example, the travel recognition model or A speech recognition process using a shopping recognition model) is executed, and a result of the speech recognition process is acquired. Further, the determined application (in this example, a travel application or a shopping application) is executed using the result of the voice recognition processing.

  According to the terminal device 10 described above, the function related to the speech recognition process to be executed based on the proximity time of the object is determined (steps S7 to S9), and the determined speech recognition process for the input speech. The function concerning is executed (step S10). Therefore, the user of the terminal device 10 can easily select a function related to speech recognition only by performing an operation of bringing an object close to the terminal device 10 for a predetermined time, for example, holding the hand over the terminal device 10. it can.

  As a function related to the speech recognition process, a function (acquisition function) for acquiring the result of the speech recognition process by the recognition method according to the proximity time (a specific recognition model determined according to the proximity time) is determined (Step S8, S9). Specifically, the acquisition function is determined to be a function for acquiring the result of the speech recognition processing by the travel recognition model (step S8), or determined to be a function for acquiring the result of the speech recognition processing by the shopping recognition model. (Step S9). Thereby, the user of the terminal device 10 can easily select what recognition model is used to obtain the result of the speech recognition process.

  In addition, as a function related to the voice recognition process, a function (application) using a result of the voice recognition process such as a travel application or a shopping application is determined (steps S8 and S10). Thereby, the user of the terminal device 10 can easily select whether to use the application.

  As mentioned above, although one Embodiment of this invention was described, this invention is not limited to the said embodiment.

  In the above-described embodiment, the determination unit 18 performs both of the function (acquisition function) for acquiring the result of the speech recognition process using the specific recognition technique (recognition model) and the function (application) using the result of the speech recognition process. An example of determining based on the above has been described. However, only one of the acquisition function and the application may be determined based on the proximity time, and the other may be a predetermined recognition model or application.

  In the above-described embodiment, there are two types of functions related to the speech recognition process determined based on the proximity time. However, three or more types of functions may be determined based on the proximity time. As an example, when the proximity time is less than the first threshold, the function (acquisition function) for acquiring the result of the speech recognition process by the specific recognition model is changed to the first acquisition function (for example, the speech recognition process by the travel recognition model). If the proximity time is greater than or equal to the first threshold and less than the second threshold, the second acquisition function (for example, the result of the speech recognition process using the shopping recognition model) If the proximity time is other than that (second threshold or more), the result of the speech recognition processing by the third acquisition function (for example, the music recognition model or the conversation recognition model) is determined. The function to obtain may be determined. The same can be applied to the determination of functions (travel application, shopping application, dialogue application, music application, etc.) using the result of the voice recognition processing.

  Moreover, in the said embodiment, although the function which concerns on a speech recognition process was determined using the threshold value judgment whether proximity | contact time is less than a threshold value, other criteria may be used. As an example, a function related to speech recognition processing may be determined based on whether or not the proximity time is within a set range.

  Moreover, in the said embodiment, the terminal device 10 uses the one speech recognition server 20 provided with the several speech recognition engine, and the recognition method (recognition model) of a speech recognition process is changed by changing a speech recognition engine according to proximity time. However, the recognition model may be switched by the terminal device 10 selecting and using a plurality of speech recognition servers having different speech recognition engines according to the proximity time. Similarly, a plurality of content servers storing different types of content information in the storage unit may be selectively used according to the proximity time.

  Moreover, in the said embodiment, when the function which concerns on a speech recognition process is utilized, the process for acquiring a speech recognition process and a content was provided outside the terminal devices 10, such as the speech recognition server 20 and the content server 30. Although executed by the server, at least a part of the processing executed by the voice recognition server 20 and the content server 30 may be executed in the terminal device 10. In that case, the execution unit 17 of the terminal device 10 may be configured to be able to execute at least some of the functions of the voice recognition server 20 and the content server 30.

  Further, in the terminal device 10, as described above with reference to FIG. 3, the input until the function related to the speech recognition process is determined according to the proximity time (before step S <b> 10 in FIG. 3). The voice input by the unit 16 is not started. In the meantime, the filtering process for removing noise from the input voice for the voice recognition process by the input unit 16 and the storage process for temporarily storing the input voice information are not executed. (Because the operation of the input unit 16 is turned off), the power consumption can be reduced accordingly.

  Some apps (such as a music app and a dialogue app) may not require image output by the display 14. While such an application is being used, control may be performed so that the display 14 of the terminal device 10 is not displayed (turned off). This control may be performed by the execution unit 17. If the application is used when the display 14 is turned off (turned off) in this way, the terminal device 10 has a power consumption equivalent to that of the display 14 than when the application is used when the display 14 is turned on (lit). Power consumption can be reduced.

  In addition, when content such as music or video is already being played on the terminal device 10, when the proximity of the object is detected by the detection unit 15 and the proximity time is detected, the playback of the content is interrupted. Also good. Specifically, while the content is being played back, a proximity object is detected in step S2 shown in FIG. 3 (step S2: YES), and then the process in each step proceeds, and the process in step S8 or step S9 When the process is completed, the process of step S10 may be executed after the reproduction of the content is interrupted at that time. As a result, the user can newly select and use the function related to the voice recognition process in preference to the function already executed (reproduction of content in this example).

  Since the user's hand is wet, the terminal device described above can be used in a scene where the user cannot touch the terminal device to operate the terminal device. More preferably, the terminal device 10 selects and executes a function related to voice processing even when the screen is locked on the display 14 (a state where data input or screen output is restricted). It is good to keep. Thus, the user can select and use the function related to the voice recognition process without performing an operation for releasing the screen lock (an operation for touching the terminal device and inputting the unlock code). It becomes like this.

  DESCRIPTION OF SYMBOLS 10 ... Terminal device, 11 ... Proximity sensor, 12 ... Microphone, 13 ... Speaker, 14 ... Display, 15 ... Detection part, 16 ... Input part, 17 ... Execution part, 18 ... Determination part, 20 ... Voice recognition server, 30 ... Content server.

Claims (3)

Detecting means for detecting the proximity of the object to the terminal device and measuring the proximity time of the detected object;
An input means for inputting voice;
Execution means for executing a function related to voice recognition processing for voice input by the input means;
A determination unit that determines a function related to a voice recognition process executed by the execution unit based on a proximity time measured by the detection unit;
Comprising
Terminal device.   The terminal device according to claim 1, wherein the determination unit determines a function for acquiring a result of the voice recognition process by a recognition method according to the proximity time as a function related to the voice recognition process.   The terminal device according to claim 1, wherein the determination unit determines a function using a result of the voice recognition process as a function related to the voice recognition process.

Images