JP2004347943A - Data processor, musical piece reproducing apparatus, control program for data processor, and control program for musical piece reproducing apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a data processor of better operability, a musical piece reproducing apparatus, a control program for the data processor, and a control program for the musical piece reproducing apparatus. <P>SOLUTION: The on-vehicle musical piece reproducing apparatus 100 which selects and reproduces a musical piece based on the speech input from a user is equipped with a memory section 130 which divides the questions for obtaining the speech input from the user as a response to a plurality of layers 300 to 304 in order to specify the musical piece to be selected and stores the same. The apparatus reproduces a question belonging to the certain layer by the speech and urges the user to make answer and thereafter if the apparatus fails to obtain the answer for the question from the user upon lapse of the specified time or if the apparatus could obtain just the prescribed ambiguous expression as the speech input, the apparatus reproduces the question belonging to the layer or the other layer by the speech and urges the user to make answer. The operability is therefore improved. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a data processing device that executes data processing based on a user's voice input, a music reproduction device, and a control program for these devices.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, there has been known a data processing apparatus which enables an operation by voice input instead of a manual operation of a user in order to make the operation of the apparatus simpler. Further, as this type of device, there has been proposed a device in which data processing to be executed is narrowed down based on a plurality of dialogs with a user (for example, see Patent Document 1).
[0003]
In such an apparatus, when the user cannot obtain a response from the user due to, for example, silence during the dialog, the user generally waits without proceeding with the dialog.
[0004]
[Patent Document 1]
JP 2003-108175 A
[0005]
[Problems to be solved by the invention]
However, as described above, when the progress of the dialogue stops, there is a problem that operability deteriorates. Specifically, if the apparatus keeps the dialogue stopped, when the user wants to resume the operation, it is necessary to remember how far the dialogue has progressed or to confirm each time.
[0006]
The present invention has been made in view of the circumstances described above, and has as its object to provide a data processing device, a music reproduction device, a control program for a data processing device, and a control program for a music reproduction device, which have better operability. .
[0007]
[Means for Solving the Problems]
In order to solve the above-mentioned problem, an invention according to claim 1 is a data processing apparatus that executes any one of a plurality of data processes based on a voice input from a user. Storage means for storing voice data for prompting the user, and reproducing one of the voice data to prompt the user to input a voice. If no voice input is obtained from the user, or if only a predetermined ambiguous word is obtained as the voice input, another voice data in the voice data is reproduced, and the user is prompted for voice input. And
[0008]
According to a second aspect of the present invention, in the data processing apparatus according to the first aspect, voice data different from the previously reproduced voice data is reproduced until the user inputs a voice, and the user is prompted to input a voice. It is characterized by.
[0009]
According to a third aspect of the present invention, in the data processing device which executes any one of a plurality of data processes based on a voice input from a user, a question for obtaining a voice input from the user as a response is provided in a plurality of layers. A storage means is provided for separately storing, and after reproducing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time has elapsed, the user did not receive a response to this question. In this case, or when only a predetermined ambiguous word is obtained as a voice input, a question belonging to the hierarchy or another hierarchy is reproduced by voice to prompt the user to respond.
[0010]
According to a fourth aspect of the present invention, in the data processing device which executes any one of a plurality of data processes based on a voice input from a user, a question for obtaining a voice input from the user as a response is stored in a plurality of layers. A storage means is provided for separately storing, and after reproducing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time has elapsed, the user did not receive a response to this question. In this case, or when only a predetermined ambiguous word is obtained, data processing that can be specified from the hierarchy or a question belonging to the hierarchy below is sequentially executed.
[0011]
According to a fifth aspect of the present invention, in a music reproducing apparatus for selecting and reproducing music based on a voice input from a user, a voice for urging the user to input a voice to instruct the reproduction of the music for each music. A storage means for storing data is provided, and one of these voice data is reproduced, and after prompting the user for voice input, even if a predetermined time has elapsed, the user receives voice input in response to the prompt. If not obtained, or if only a predetermined ambiguous word is obtained as a voice input, another voice data in the voice data is reproduced to prompt the user to input a voice.
[0012]
According to a sixth aspect of the present invention, in the music reproducing apparatus according to the fifth aspect, audio data different from the previously reproduced audio data is reproduced until there is a voice input from the user.
[0013]
According to a seventh aspect of the present invention, in a music reproducing apparatus for selecting and reproducing music based on a voice input from a user, a question for obtaining a voice input from the user as a response to specify a music to be selected is specified. A storage unit is provided for storing the information in a plurality of layers, and after reproducing a question belonging to a certain layer by voice and prompting the user to respond, even if a predetermined time has elapsed, the user receives a response to the question even if a predetermined time has elapsed. If not obtained, or if only a predetermined ambiguous word is obtained as a voice input, a question belonging to the hierarchy or another hierarchy is reproduced by voice to prompt the user to respond.
[0014]
In a music reproducing apparatus for selecting and reproducing music based on a voice input from a user, the invention according to claim 8 may include a question for obtaining a voice input from the user as a response in order to specify a music to be selected. A storage unit is provided for storing the information in a plurality of layers, and after reproducing a question belonging to a certain layer by voice and prompting the user to respond, even if a predetermined time has elapsed, the user receives a response to the question even if a predetermined time has elapsed. If not obtained, or if only a predetermined ambiguous word is obtained as a voice input, songs that can be specified from the hierarchy or questions belonging to the hierarchy below are sequentially selected and reproduced.
[0015]
According to a ninth aspect of the present invention, a data processing device that executes one of a plurality of data processes based on a voice input from a user stores voice data for prompting the user to perform a voice input for each data process. Means for reproducing, and prompting the user to input a voice by reproducing one of the voice data, and if no voice input is obtained from the user in response to the prompt even after a predetermined time has elapsed, Alternatively, when only a predetermined ambiguous word is obtained as a voice input, the other voice data in the voice data is reproduced, and the data processing device is made to function as means for prompting the user to input a voice. Provide a control program.
[0016]
According to a tenth aspect of the present invention, in the data processing device which executes any one of a plurality of data processes based on a voice input from a user, a question for obtaining a voice input from the user as a response is stored in a plurality of layers. Means for separately storing, and when a question belonging to a certain hierarchy is reproduced by voice, and after prompting the user for a response, even if a predetermined time has elapsed, the user does not receive a response to this question Alternatively, when only a predetermined ambiguous word is obtained as a voice input, a question belonging to the hierarchy or another hierarchy is reproduced by voice to function as a means for prompting a user to respond. Provide a control program.
[0017]
The invention according to claim 11 provides a data processing device that executes any one of a plurality of data processes based on a voice input from a user, in which a question for obtaining a voice input from the user as a response is provided in a plurality of hierarchies. Means for separately storing, and when a question belonging to a certain hierarchy is reproduced by voice, and after prompting the user for a response, even if a predetermined time has elapsed, the user does not receive a response to this question Or a control program for a data processing apparatus, which, when only a predetermined ambiguous word is obtained, functions as a means for sequentially executing data processing that can be specified from the hierarchy or a question below the hierarchy. I will provide a.
[0018]
According to a twelfth aspect of the present invention, there is provided a music reproducing apparatus for selecting and reproducing a music piece based on a voice input from a user, and a voice for urging the user to input a voice to instruct the reproduction of the music piece for each music piece. Means for storing data, and reproducing one of these voice data to prompt the user for voice input, and after a predetermined time elapses, the user receives a voice input in response to the prompt. If not, or if only a predetermined ambiguous word is obtained as a voice input, the other voice data in the voice data is reproduced to function as a means for prompting the user to voice input. The present invention provides a control program for a music playback device that performs
[0019]
According to a thirteenth aspect of the present invention, there is provided a music reproducing apparatus for selecting and reproducing music based on a voice input from a user, in order to specify a music to be selected, a question for obtaining a voice input from the user as a response. Means for storing the information in a plurality of layers, and reproducing a question belonging to a certain layer by voice and prompting the user for a response. If not, or if only a predetermined ambiguous word is obtained as a voice input, a question belonging to the hierarchy or another hierarchy is reproduced by voice to function as a means for prompting the user to respond. The present invention provides a control program for a music playback device that performs
[0020]
According to a fourteenth aspect of the present invention, there is provided a music reproducing apparatus for selecting and reproducing music based on a voice input from a user, in order to specify a music to be selected, a question for obtaining a voice input from the user as a response. Means for storing the information in a plurality of layers, and reproducing a question belonging to a certain layer by voice and prompting the user for a response. If not, or if only a predetermined ambiguous word is obtained as a voice input, it is made to function as a means for sequentially selecting and reproducing music that can be specified from the hierarchy or a question below the hierarchy. And a control program for the music reproducing apparatus.
[0021]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, an in-vehicle music reproducing device mounted on a vehicle such as an automobile will be exemplified as the music reproducing device.
[0022]
<First embodiment>
FIG. 1 is a diagram showing a functional configuration of an in-vehicle music reproducing apparatus 100 according to the present embodiment, together with a distribution system 1 for distributing multimedia data such as music data to the in-vehicle music reproducing apparatus 100. As shown in FIG. 1, the distribution system 1 includes a distribution server 10 and an in-vehicle music reproducing apparatus 100, which are connected to each other via a network 4 including the Internet 2 and a wireless communication network 3 so as to be able to perform data communication. ing. Although FIG. 1 illustrates the distribution server 10 and the in-vehicle music reproducing device 100 one by one, the number is arbitrary.
[0023]
The distribution server 10 is composed of a general computer system, and distributes multimedia data such as music data, video data, and text data to the in-vehicle music reproduction device 100 via the network 4. It has a database 11 in which data is stored.
[0024]
The in-vehicle music reproducing apparatus 100 is mounted on a vehicle such as an automobile, and reproduces multimedia data distributed from the distribution server 10. As illustrated, the in-vehicle music reproducing apparatus 100 includes a control unit 110 and a storage unit 130. The control unit 110 includes a CPU, a ROM, a RAM, and the like, and controls each unit of the in-vehicle music reproducing device 100.
[0025]
The communication device 120 performs data communication with various terminal devices connected to the network 4 under the control of the control unit 110. More specifically, the communication device 120 corresponds to a mobile communication device such as a mobile phone or a wireless LAN communication device (Local Area Network), and is connected to the wireless communication network 3 or the Internet 2 via the wireless communication network 3. Data communication with the various terminals. In the present embodiment, the communication device 120 receives multimedia data such as music data and video data from the distribution server 10 by performing data communication particularly with the distribution server 10.
[0026]
The storage unit 130 includes a main storage device such as an HDD (Hard Disk Drive), and various control programs executed by the control unit 110, multimedia data (such as music data and video data) received from the distribution server 10, and synthesis. It stores various data such as text data output by voice. Further, the storage unit 130 stores table data for managing data stored in the storage unit 130 for each type of multimedia (music, text, video, and the like).
[0027]
FIG. 2 is a diagram schematically showing a configuration of a music table 200 for managing music data, which is one of multimedia data. As shown in this figure, one record of the music table 200 includes a music ID, genre information, artist information, music name information, and a new music flag.
[0028]
The song ID is an identifier of the song data, and the genre information indicates the genre to which the song belongs. Examples of the genre include JPOP (Japanese popular music), enka, rock, and classical music. The artist information indicates information of a singer if the song is a song, and information of a conductor or a performance orchestra if the song is a performance-only song such as a classic. For example, when the song is a song, the artist information includes information indicating whether the song is a group or solo, information indicating whether the vocal is male or female, and an artist name (or group name). The song name information shown in the figure indicates the title of the song, and the new song flag is information indicating whether or not the song is treated as a new song. "NO" is indicated.
[0029]
The music table 200 is updated by generating and adding a record corresponding to the music data each time the in-vehicle music reproducing apparatus 100 receives the music data from the distribution server 10 and stores the music data in the storage unit 130. You. Table data for managing multimedia data (for example, video data, etc.) other than music data is also updated every time data is received from the distribution server 10 in the same manner as the music table 200. Will be omitted.
[0030]
In addition, in addition to the above-mentioned information, the song table 200 may include, for example, a songwriter or a composer name as artist information, or a record such as viewing popularity ranking information or sales performance ranking information. It may be configured to include information. Alternatively, the distribution server 10 may generate table data for managing multimedia data such as the music table 200, and the in-vehicle music playback device 100 may receive the data via the network 4.
[0031]
Now, returning to FIG. 1 again, under the control of the control unit 110, the music reproduction unit 140 generates an analog signal based on the music data, which is one of the multimedia data, and outputs the analog signal to the amplifier 142 via the mixer 141. Is what you do. Amplifier 142 amplifies the analog signal from mixer 141 and outputs the amplified signal to speaker 143. The speaker 143 emits sound according to the analog signal input from the amplifier 142. Under this configuration, the control unit 110 outputs the music data stored in the storage unit 130 to the music reproduction unit 140, so that the music sound is output from the speaker 143.
[0032]
The microphone 150 is a sound collection device. In the present embodiment, the microphone 150 collects a sound emitted by the user and outputs an analog signal to the amplifier 151. The amplifier 151 amplifies the input analog signal and outputs it to the A / D converter 152. The A / D converter 152 quantizes the input analog signal into predetermined bits, converts the input signal into a digital signal, and outputs the digital signal to the VR 153 as an audio input signal.
[0033]
The VR (Voice Recognition: voice recognition unit) 153 executes voice recognition processing based on a voice input signal, and outputs a recognition result to the control unit 110. A circuit for voice recognition processing (for example, a DSP (Digital) Signal processor), and the processing can be performed at a higher speed than when the control unit 110 executes the voice recognition processing.
[0034]
A TTS (Text To Speech: voice conversion unit) 160 generates synthetic voice data, which is a digital signal, based on the text data input from the control unit 110 in order to generate a synthesized voice in accordance with the text content. / A converter 161. The D / A converter 161 converts the synthesized voice data into an analog signal and outputs the analog signal to the amplifier 142 via the mixer 141. As a result, a synthesized voice is output from the speaker 143. As described above, an analog signal based on music data and an analog signal based on synthesized voice data are input to the mixer 141, and when both are input simultaneously, the music and the synthesized voice are Is adjusted and output from the speaker 143.
[0035]
The operation unit 154 is used for turning on / off the power, has a plurality of operators such as push-down buttons, detects an operation of the operator by a user, and outputs the operation to the controller 110. In addition, the in-vehicle music reproducing apparatus 100 further includes a display unit (for example, a liquid crystal display) on which various information is displayed, and displays information, video, and the like regarding the music being reproduced. Also, while the user is operating the in-vehicle music reproducing apparatus 100 by voice, the display unit can display a CG composite image or a live-action image so as to give the user the impression of interacting with a natural person. Is displayed.
[0036]
As described above, the in-vehicle music reproducing apparatus 100 has a configuration for recognizing a user's voice, and enables various operations of the apparatus by voice instructions. The operation performed by voice includes, for example, an initial setting (time setting, etc.) of the in-vehicle music reproducing apparatus 100 and a music selecting operation. In the following, in order to avoid complicating the description, an operation when the user selects a music by inputting a voice will be described in detail.
[0037]
In the in-vehicle music reproducing apparatus 100, the music selection by voice input is performed by the user sequentially inputting a plurality of question voices output from the in-vehicle music reproducing apparatus 100 by voice. It has become. The question output from the in-vehicle music reproducing apparatus 100 is a question for specifying a music desired by the user, and is divided into layers (hierarchies) in order from large items to small items in order to narrow down the music. .
[0038]
FIG. 3 is a diagram illustrating an example of a question layer structure used in a music selection operation. As shown in this figure, the question is divided into first to third layers 300 to 304 according to the content. Specifically, the first layer 300 includes questions for specifying the genre of the music to be reproduced, and the genre of the desired music is narrowed down by the user responding to these questions. The second layer 301 and the third layer 302 include a question for narrowing down artists. For example, the second layer 301 includes a question for specifying whether the artist desired by the user is a solo or a group, and the third layer 302 includes a question for specifying the gender of the vocal. On the fourth layer 303, artist candidates identified from responses to the questions included in the first to third layers 300 to 302 are sequentially presented to the user, and the user is allowed to select a desired artist from these candidates. Questions are included. Further, the fifth layer 304 sequentially presents the songs belonging to the artist selected by the user in the question of the fourth layer 303 to the user, and asks the user to select a desired song from these candidates. include.
[0039]
The questions belonging to each of the layers 300 to 304 are registered in advance in a music selection question table (hereinafter simply referred to as “question table”) 400. Specifically, the question table 400 is stored in the storage unit 130 in advance, and, as shown in FIG. 4, records text data indicating a question sentence for each layer to which the question belongs. For example, as shown in an example in this figure, the first layer 300 to which the question for specifying the genre of the music desired by the user belongs is included in the first layer 300 as a question sentence "Do you introduce a new song?" Text data such as "Do you listen?" And "Do you listen to enka?" Are registered.
[0040]
In addition, a phrase that the user will use for answering the question is registered as an answer table 500. This response table 500 is stored in the storage unit 130 in advance, and as shown in FIG. 5, a response phrase is registered for each meaning. In the present embodiment, positive expressions, negative expressions, and ambiguous expressions (ambiguous words) are set in advance as possible meanings of the phrase. The affirmative expression is a phrase meaning the user's consent to the question output by the in-vehicle music reproducing device 100, and includes, for example, “Yes”, “Yeah”, “So”. Negative expressions are phrases that mean rejection of the user, contrary to positive expressions, and include, for example, “No”, “No”, and “No”. Further, the ambiguous expression indicates a response that is not always negative but is not affirmative to the question, and includes, for example, "um", "um", and "that".
[0041]
Under such a configuration, the in-vehicle music reproducing apparatus 100 outputs a question to the user as a synthesized voice, and then picks up the user's response (voice) from the microphone 150 and responds to the voice input signal. Speech recognition is performed to determine whether the user's response is an affirmative expression, a negative expression, or an ambiguous expression.
[0042]
Next, a description will be given of an operation when a music piece is selected by a dialogue including a question from the in-vehicle music reproduction apparatus 100 and a response of the user to the question.
[0043]
FIG. 6 is a flowchart showing a processing procedure of music selection / playback processing executed by the control unit 110 of the vehicle-mounted music playback apparatus 100 for music selection / playback. As shown in the figure, the control unit 110 first initializes a layer variable N to “1” (step Sa1). The layer variable N is for identifying which layer (see FIG. 3) the current question belongs to. Next, the control unit 110 sequentially outputs each of the questions belonging to the Nth layer indicated by the layer variable N to the user as a synthesized voice, and executes a question process for identifying the user's response to these questions (step). Sa2). The specific processing content of this question processing will be described later in detail.
[0044]
Next, in Step Sa2, the control unit 110 determines whether or not a response of an affirmative expression has been received as a response from the user (Step Sa3). If the determination result is NO, the question belonging to the same layer is again asked to the user. In order to give, the processing procedure returns to step Sa2.
[0045]
On the other hand, if the decision result in the step Sa3 is YES, the control unit 110 increments the layer variable N by “1” (step Sa4) and sets the layer variable N to the total number of layers (“4” in the present embodiment). ) Is determined (step Sa5). If the determination result is NO, the control unit 110 returns the processing procedure to step Sa2 in order to give the user a question belonging to the Nth layer specified by the layer variable N. If the determination result is YES, a positive expression response has been obtained for each layer, and the music data desired by the user is specified. Reproduction is performed (step Sa6).
[0046]
Next, the question processing in step Sa2 will be described in more detail with reference to the flowchart shown in FIG.
[0047]
As shown in this figure, in the question processing, the questions belonging to the N-th layer are sequentially output to the user as synthesized speech. Specifically, the control unit 110 first initializes the question variable Q to “1” (Step Sb1). The question variable Q indicates which question among the questions belonging to the layer has been output. Next, the control unit 110 outputs synthesized speech so as to give the user the question specified by the question variable Q (step Sb2). Then, the control unit 110 determines whether or not there is a response from the user (whether or not there is a voice input) within a certain period of time after outputting the synthesized voice of the question (step Sb3).
[0048]
Specifically, in step Sb3, after executing step Sb2, control unit 110 starts counting the timer and continues to accept a voice input. If the control unit 110 obtains a voice input from the user before the timer count times out after a certain period of time has elapsed, the determination result in step Sb3 becomes YES, and the time-out occurs without obtaining the voice input. In this case, the determination result of step Sb3 is NO. More specifically, even if there is a voice input before the timer count times out, the control unit 110 performs voice recognition processing on the voice input, and as a result, the voice is stored in the response table 500 (FIG. If none of the phrases registered in (5) are registered, it is determined that there is no voice input. That is, in step Sb3, the determination result is YES only when there is a voice input (phrase registered in the response table 500) that can be taken as a response to the question.
[0049]
When the determined result in the step Sb3 is YES, the control unit 110 determines whether or not the response obtained as the voice input includes the positive expression phrase (step Sb4). Since there is no need to give the user another question belonging to the current layer, the question processing is terminated, and the procedure proceeds to step Sa3. If the response obtained as the voice input is a negative expression or an ambiguous expression (step Sb4: NO), control unit 110 performs the following processing to give the user the next question belonging to the current layer. Execute. That is, after incrementing the question variable Q by “1” to specify the next question (step Sb5), the control unit 110 determines whether the question variable Q is larger than the total number of questions (step Sb6). If the result is NO, the process returns to step Sb2 and the next question is given to the user. If the result of the determination in step Sb6 is YES, that is, if all the questions belonging to the current layer have been given to the user, the question processing ends, and the procedure proceeds to step Sa3. Then, since a positive expression response has not been obtained in the current layer, the determination result in step Sa3 is NO, and the processing procedure returns to step Sa2 in order to give the user a question belonging to the current layer from the beginning.
[0050]
If the result of the determination in step Sb3 is NO, that is, even if a certain period of time has elapsed after the question was given to the user, a voice input belonging to any of the affirmative expression, the negative expression, and the ambiguous expression is received from the user. If a response has not been obtained, the control unit 110 advances the processing procedure to step Sb5, gives another question belonging to the current layer to the user, and prompts a response.
[0051]
That is, the control unit 110 determines that no response has been obtained after a certain period of time has passed since the question was given to the user (step Sb3: NO), and that an ambiguous expression was obtained as a response (step Sb4). : NO), other questions belonging to the current layer are sequentially given to the user.
[0052]
Accordingly, when the user does not respond positively to the question, the in-vehicle music reproducing apparatus 100 does not stop the progress of the dialog but responds to the question to clarify items (for example, desired By giving the user another question about the genre of the music to be played, the artist, etc.), a natural conversation as if interacting with a natural person is realized.
[0053]
Also, in general, when a user ponders in answering a question, that is, silently responds to the response or gives only an ambiguous response, the user often does not agree with the question. is there. Therefore, as described above, by adopting a configuration in which other questions are sequentially given, the user only has to respond to a desired question, and operability can be improved.
[0054]
Furthermore, when the user is the driver of the vehicle, the interactive operation of the in-vehicle music reproducing device 100 may be performed during driving. Therefore, depending on the driving situation, the driver often concentrates on driving during the interactive operation, and may not respond to the question for a certain period of time. In such a case, if the progress of the dialogue is stopped, the driver needs to remember how far the dialogue has progressed when restarting the dialogue again, and if the driver forgets this, After all, you have to start over from the beginning. On the other hand, according to the present embodiment, the in-vehicle music reproducing apparatus 100 sequentially outputs questions when a response from the user is not obtained for a certain period of time after outputting the question. When the user wants to restart the operation, he or she need only respond when a desired question is output without having to remember the progress of the dialogue, and the operation becomes easy.
[0055]
<Second embodiment>
In the above-described embodiment, the in-vehicle music reproducing device 100 outputs a question, outputs a question, and after a certain period of time, if no response is obtained from the user, or if only an ambiguous expression is obtained, The configuration for outputting another question belonging to the same layer has been described.
[0056]
However, when the user responds to the question, the in-vehicle music reproducing device 100 does not perform processing belonging to the current layer, but performs processing belonging to another layer. May be used. As a specific example of this case, the user selects “Enka” as a desired music genre by responding to a question belonging to the first layer 300 shown in FIG. 3, and then selects the second layer 301 and the third layer 302. There is a case where the user wishes to change the music genre to “JPOP” in the third layer 302 after the dialogue with the user.
[0057]
Therefore, in the present embodiment, as shown in FIG. 8, in the question processing described in the first embodiment, the control unit 110 of the in-vehicle music reproducing device 100 makes a response within a certain time after the question is output. If not (step Sb3: NO), it is determined whether or not the layer variable N is greater than “1” so that the next question to be output is a question belonging to a higher layer (that is, a question regarding a matter determined in the previous dialogue). After the determination (step Sc1), if this determination result is YES, the layer variable N is decremented by "1" (step Sc2), and the processing procedure proceeds to step Sa3. Thereby, the next question when there is no response from the user for a certain period of time becomes a question belonging to a higher layer.
[0058]
If the determination result in step Sc1 is NO, it indicates that there is no higher layer, and the process proceeds to step Sa3 to repeat the question belonging to the current layer from the beginning.
[0059]
Further, even if there is a response within a certain period of time from the question, the control unit 110 determines whether the response is an ambiguous expression (step Sb4). As in the case where there is no time response, the process proceeds to step Sc1 in order to output the question belonging to the higher layer next.
[0060]
As described above, according to the present embodiment, when the user silences a question or uses an ambiguous expression in order to desire a process belonging to another layer, the next question is automatically transmitted to the upper layer. Therefore, the user can cause the apparatus to execute a desired operation by responding when a question of a desired layer is output, without performing an operation such as starting the dialog again from the beginning. .
[0061]
In the present embodiment, the configuration in which the question belongs to the upper layer has been described as an example, but the question may belong to the lower layer. Whether to shift to the upper layer or the lower layer can be appropriately selected according to the layer structure of the question.
[0062]
<Third embodiment>
In the above-described first or second embodiment, when the in-vehicle music reproducing apparatus 100 does not receive a response to the question even after a certain time has elapsed since the question was output, Alternatively, a configuration has been described in which another question is output when only a predetermined ambiguous word is obtained as a voice input.
[0063]
However, in the case where the dialogue for specifying the music has progressed to some extent, such as a music selection / playback operation, a music candidate desired by the user is roughly specified.
[0064]
Therefore, in the present embodiment, as shown in FIG. 9, the control unit 110 of the in-vehicle music reproducing apparatus 100 outputs the question to the user from the user even if a certain period of time has passed since the question was output. If no response is obtained (step Sb3: NO), or if only ambiguous words are obtained as a response by voice input (step Sc3: YES), all songs that can be specified from the current layer are sequentially read. Playback is performed (step Sd2).
[0065]
As described above, in the present embodiment, the in-vehicle music reproducing apparatus 100 proceeds with the progress of the dialog when a response to the question is not obtained from the user or when only a predetermined ambiguous word is obtained as a voice input. Instead of stopping, the processes in the items determined in the dialogue up to the present (ie, the reproduction of the music that can be specified) are sequentially executed, so that at least various processes including the processes desired by the user are executed. It will be.
[0066]
Thereby, for example, when the user specifies the genre of the music but wants to play the others at random, the operation mode such as not responding to the question for a certain period of time or giving an ambiguous expression is also available. It becomes possible and operability is improved.
[0067]
<Modification>
Each of the above-described embodiments is merely an embodiment of the present invention, and can be arbitrarily modified within the scope of the present invention.
[0068]
For example, in each of the above-described embodiments, the case where the present invention is applied to an in-vehicle music reproducing device is illustrated. However, the present invention is not limited to the in-vehicle use and may be a home-use or portable one. May be. Furthermore, the present invention can be applied to any device as long as it performs any one of a plurality of data processes based on a voice input from a user.
[0069]
Further, for example, in each of the above-described embodiments, when an ambiguous expression is obtained as a response from the user to the question, a configuration may be employed in which the user actually learns what kind of processing the user desires.
[0070]
Specifically, as described in the first and second embodiments, when the user's response to the question is an ambiguous expression, the in-vehicle music reproducing device 100 has not been able to obtain a response for a certain period of time. As in the case, other questions are sequentially output. Therefore, when the in-vehicle music reproducing apparatus 100 obtains an ambiguous expression as a response to a certain question, it learns (associates) which question the user affirmed in the sequentially output questions. Alternatively, when an ambiguous expression is used again for the same question, the learned question may be output next. As a result, it is possible to output a question that matches the taste of each user.
[0071]
【The invention's effect】
As described above, according to the present invention, a data processing device, a music reproduction device, a control program for a data processing device, and a control program for a music reproduction device having better operability are provided.
[Brief description of the drawings]
FIG. 1 is a diagram showing a functional configuration of an in-vehicle music reproducing apparatus according to a first embodiment of the present invention, together with a distribution system for distributing multimedia data such as music data to the in-vehicle music reproducing apparatus. .
FIG. 2 is a diagram schematically showing a configuration of a music table.
FIG. 3 is a diagram showing an example of a question layer structure used in a music selection operation.
FIG. 4 is a diagram schematically showing a configuration of a question table.
FIG. 5 is a diagram schematically illustrating a configuration of a response table.
FIG. 6 is a flowchart illustrating a processing procedure of music selection / playback processing according to the first embodiment.
FIG. 7 is a flowchart illustrating a procedure of a question process according to the first embodiment;
FIG. 8 is a flowchart illustrating a procedure of a question process according to the second embodiment of the present invention.
FIG. 9 is a flowchart illustrating a processing procedure of a question process according to the third embodiment of the present invention.
[Explanation of symbols]
100 In-vehicle music playback device
110 control unit
130 storage unit
140 Music playback unit
143 Speaker
150 microphone
200 music table
300-304 layers
400 question table
500 response table

Claims (14)

In a data processing device that executes any one of a plurality of data processes based on a voice input from a user,
Storage means for storing voice data for prompting the user to input voice for each data processing,
After reproducing one of these voice data and prompting the user to input a voice, if a voice input is not obtained from the user in response to the prompt even after a predetermined time has elapsed, or as a voice input. A data processing apparatus characterized in that when only a predetermined ambiguous word is obtained, another voice data in the voice data is reproduced to prompt the user to input a voice. 2. The data processing apparatus according to claim 1, wherein until data is input from the user, audio data different from the previously reproduced audio data is reproduced to prompt the user to input a voice. In a data processing device that executes any one of a plurality of data processes based on a voice input from a user,
Storage means for storing a question for obtaining a voice input from the user as a response in a plurality of layers,
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time elapses, if the user does not receive a response to this question, A data processing apparatus characterized in that when only ambiguous words are obtained, a question belonging to the hierarchy or another hierarchy is reproduced by voice to prompt a user to respond. In a data processing device that executes any one of a plurality of data processes based on a voice input from a user,
Storage means for storing a question for obtaining a voice input from the user as a response in a plurality of layers,
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time has elapsed, if the user has not received a response to this question, or only a predetermined vague word A data processing device which, when not obtained, sequentially executes data processing that can be specified from the hierarchy or a question belonging to the hierarchy below. In a music playback device that selects and plays music based on a voice input from a user,
Storage means for storing voice data for prompting a user to input a voice to instruct reproduction of the music for each music,
After reproducing one of these voice data and prompting the user for voice input, if no voice input is obtained from the user even after a predetermined time has passed, or A music reproducing apparatus characterized in that, when only a predetermined ambiguous word is obtained as input, the other audio data in the audio data is reproduced to prompt the user to input a voice. 6. The music reproducing apparatus according to claim 5, wherein audio data different from the previously reproduced audio data is reproduced until a user inputs a voice. In a music playback device that selects and plays music based on a voice input from a user,
In order to specify a song to be selected, a storage unit is provided for storing a question for obtaining a voice input from a user as a response in a plurality of layers,
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time elapses, if the user does not receive a response to this question, A music reproducing apparatus characterized in that, when only ambiguous words are obtained, a question belonging to the hierarchy or another hierarchy is reproduced by voice to prompt a user to respond. In a music playback device that selects and plays music based on a voice input from a user,
In order to specify a song to be selected, a storage unit is provided for storing a question for obtaining a voice input from a user as a response in a plurality of layers,
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time elapses, if the user does not receive a response to this question, A music reproducing apparatus characterized in that, when only ambiguous words are obtained, music that can be specified from the hierarchy or a question below the hierarchy is sequentially selected and reproduced. A data processing device that executes any one of a plurality of data processes based on a voice input from a user,
Means for storing voice data for prompting the user to input voice for each data processing; and
After reproducing one of these voice data and prompting the user to input a voice, if a voice input is not obtained from the user in response to the prompt even after a predetermined time has elapsed, or as a voice input. A control program for a data processing device, wherein, when only a predetermined ambiguous word is obtained, another voice data in the voice data is reproduced, and the function is made to function as means for prompting a user to input a voice. In a data processing device that executes any one of a plurality of data processes based on a voice input from a user,
Means for storing a question for obtaining a voice input from the user as a response in a plurality of layers, and
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time elapses, if the user does not receive a response to this question, A control program for a data processing device, characterized in that, when only ambiguous words are obtained, a question belonging to the hierarchy or another hierarchy is reproduced by voice and functions as means for prompting a user to respond. A data processing device that executes any one of a plurality of data processes based on a voice input from a user,
Means for storing a question for obtaining a voice input from the user as a response in a plurality of layers, and
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time has elapsed, if the user has not received a response to this question, or only a predetermined vague word A control program for a data processing device, which, when not obtained, functions as means for sequentially executing data processing that can be specified from the hierarchy or a question below the hierarchy. A music playback device that selects and plays music based on voice input from a user,
Means for storing voice data for prompting the user to input a voice to instruct reproduction of the music for each music, and
After reproducing one of these voice data and prompting the user for voice input, if no voice input is obtained from the user even after a predetermined time has passed, or When only a predetermined ambiguous word is obtained as an input, a control program for a music reproducing apparatus, which reproduces another audio data in the audio data and functions as a means for prompting a user to input a voice. A music playback device that selects and plays music based on voice input from a user,
Means for storing a question for obtaining a voice input from a user as a response in a plurality of layers in order to specify a music to be selected, and
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time elapses, if the user does not receive a response to this question, A control program for a music reproducing apparatus, characterized in that when only ambiguous words are obtained, a question belonging to the hierarchy or another hierarchy is reproduced by voice to function as means for prompting a user to respond. A music playback device that selects and plays music based on voice input from a user,
Means for storing a question for obtaining a voice input from a user as a response in a plurality of layers in order to specify a music to be selected, and
After playing a question belonging to a certain hierarchy by voice and prompting the user to respond, even if a predetermined time elapses, if the user does not receive a response to this question, When only ambiguous words are obtained, a control program for a music reproducing apparatus, which functions as a means for sequentially selecting and reproducing music that can be identified from the hierarchy or a question below the hierarchy, and playing the selected music.

Images