WO2016067348A1 - Presentation support method, presentation support program, and presentation support device - Google Patents

Abstract

A presentation support device (10) extracts a first word from a character string in each of the regions into which a page of a document file is divided, each of the pages of the document file being displayed on a per screen basis during display. The presentation support device (10) carries out speech recognition, and calculates a degree of relevance from the first word extracted from each region in the page being displayed on a display device 5 and a second word acquired as a result of the speech recognition. The presentation support device (10) sets a faster speed for progressing the highlighting of a region the higher the degree of relevance calculated for that region is or sets a slower speed for progressing the highlighting of a region the lower the degree of relevance for that region is. The presentation support device (10) controls the highlight display on a page in accordance with a speed set for each region.

Description

Presentation support method, presentation support program, and presentation support apparatus

The present invention relates to a presentation support method, a presentation support program, and a presentation support apparatus.

As an example of a technology that supports presentation, there is a technique that presents a presenter or a listener with a part that the presenter is explaining. For example, a display device has been proposed that aims to suppress skipping of a document. This display device recognizes a phrase uttered by a speaker, identifies a read-out portion of a document being displayed on a display panel based on the recognized phrase, and displays a display state of the identified portion as a first state. The display state is changed to a second display state different from the first display state, for example, highlight display such as blinking.

JP 2009-271814 A JP 2005-208292 A JP 2002-268667 A Japanese Patent Laid-Open No. 61-036853

However, in the above technique, there are cases where the explanation part of the presenter is not highlighted as described below.

That is, in the above display device, speech recognition is used to obtain a phrase uttered by a speaker. However, when misrecognition occurs in voice recognition, a portion where the speaker is not explaining due to the misrecognition is highlighted, and as a result, the speaker's explanation portion may not be highlighted. In this case, the display device cannot present the explanation part to the speaker or the listener, and may disturb the presentation.

In one aspect, an object of the present invention is to provide a presentation support method, a presentation support program, and a presentation support apparatus that can suppress a situation where an explanation part of a presenter is not highlighted.

According to one aspect of the presentation support method, a computer executes a process of extracting a first word from a character string included in each area of a document file including a page displayed on a screen basis when the page is divided. To do. Further, the computer executes speech recognition, and for each region in the page being displayed on the predetermined display unit, the first word extracted from the region and the second word obtained as a result of the speech recognition The process of calculating the degree of association from the above is executed. Further, the computer sets a higher speed for the highlight display of the region as the region having a higher degree of relevance calculated for each region, or advances the highlight display of the region as the region having a lower relevance level. Execute processing to set the speed lower. Further, the computer executes a process of controlling the highlight display in the page according to the speed set for each area.

∙ The situation where the explanation part of the presenter is not highlighted can be suppressed.

FIG. 1 is a diagram illustrating the configuration of the presentation support system according to the first embodiment. FIG. 2 is a block diagram illustrating a functional configuration of the presentation support apparatus according to the first embodiment. FIG. 3 is a diagram illustrating an example of extracted word data. FIG. 4 is a diagram illustrating an example of a temporal change related to the progress of highlight display. FIG. 5 is a diagram illustrating a transition example of the slide screen. FIG. 6 is a diagram illustrating a transition example of the slide screen. FIG. 7 is a flowchart illustrating the procedure of the weighting process according to the first embodiment. FIG. 8 is a flowchart illustrating the procedure of the speech recognition process according to the first embodiment. FIG. 9 is a flowchart illustrating the procedure of the display control process according to the first embodiment. FIG. 10 is a diagram illustrating a hardware configuration example of a computer that executes the presentation support program according to the first embodiment and the second embodiment.

Hereinafter, the presentation support method, presentation support program, and presentation support apparatus according to the present application will be described with reference to the accompanying drawings. Note that this embodiment does not limit the disclosed technology. Each embodiment can be appropriately combined within a range in which processing contents are not contradictory.

[System configuration]
FIG. 1 is a diagram illustrating the configuration of the presentation support system according to the first embodiment. The presentation support system 1 shown in FIG. 1 highlights an area including a word obtained as a result of recognition of speech input from the microphone 3 in a presentation screen on which a document file is displayed on the display device 5. I will provide a.

As part of this presentation support service, the presentation support system 1 realizes display control that increases the speed of highlighting as the area having a higher degree of relevance to a word and lowers the speed of highlighting as the area having a lower degree of relevance. To do. This suppresses the situation where the presenter's explanation part is not highlighted.

Here, in the following, as an example, it is assumed that the above display control function is added to presentation software, and one or more slides included in a document file created using the presentation software are displayed on the display device 5. Assume that the presentation is progressed by displaying. Such slides can be imported with text and graphics as well as content created by other application programs. For example, you can import documents created with word processing software, tables and graphs created with spreadsheet software, images and movies taken with an imaging device, and images and movies edited with image editing software. And can be imported.

As shown in FIG. 1, the presentation support system 1 accommodates a microphone 3, a display device 5, an input device 7, and a presentation support device 10. The peripheral devices such as the microphone 3, the display device 5 and the input device 7 and the presentation support device 10 are connected by wire or wirelessly.

The microphone 3 is a device that converts sound into an electrical signal, and is sometimes called a microphone. For example, the microphone 3 can be attached to a presenter who performs a presentation. In this case, a headset-type or tie-pin type microphone can be attached to a predetermined position of the presenter's body or clothes, or a hand-type microphone can be carried by the presenter. The microphone 3 can also be installed at a predetermined position in a range where the utterance of the presenter can be collected. In this case, the microphone 3 may be an attachment type or a stationary type microphone. In any of these cases, a microphone having any type of directivity can be adopted as the microphone 3, but sounds other than the presenter's utterance, for example, the utterance of the listener and the noise such as noise are collected. In order to suppress this, the sensitivity of the microphone can be limited to the speaking direction of the presenter. The microphone 3 can employ any conversion method such as a dynamic type, an electret capacitor type, or a capacitor type.

The analog signal obtained by collecting sound in the microphone 3 is converted into a digital signal and then input to the presentation support apparatus 10.

The display device 5 is a device that displays various types of information. For example, the display device 5 may be a liquid crystal display or an organic EL (electroluminescence) display that realizes display by light emission, or a projector that realizes display by projection. Further, the number of installed display devices 5 is not necessarily limited to one, and a plurality of display devices 5 may be provided. For example, a liquid crystal display can be mounted as a display device for a presenter or a person concerned, and a projector and a screen for projecting an image projected by the projector can be mounted as a display device shared by the presenter and the audience. In addition, a dedicated liquid crystal display may be mounted on each listener.

The display device 5 displays a presentation screen according to an instruction from the presentation support device 10 as an example. For example, the display device 5 displays a slide of a document file opened by presentation software that operates on the presentation support device 10. In this case, the display device 5 can display any slide specified by the presenter via the input device 7 among the slides included in the document file, and the slide show function of the presentation software is set to the ON state. In this case, the slides included in the document file can be switched and displayed in the order in which the slides are created.

The input device 7 is a device that receives instruction inputs for various types of information. For example, when the display device 5 is mounted as a liquid crystal display, a mouse or a keyboard or a touch sensor bonded on the liquid crystal display can be adopted as the input device 7. Further, when the display device 5 is mounted as a projector, a laser pointer indicating the position on the screen projected on the screen can be mounted as the input device 7. That is, among laser pointers, there is also a laser pointer with a remote control function provided with an operation unit such as various buttons for advancing and returning a slide page. The operation unit of the laser pointer with a remote control function can be used as the input device 7. Furthermore, an image sensor that senses the position of the light spot pointed by the laser pointer can be mounted as the input device 7.

As an example, the input device 7 accepts a specification of a document file to be executed by the presentation software on the presentation support device 10, an operation of advancing a slide page, an operation of returning a slide page, and the like. The operation accepted through the input device 7 in this way is output to the presentation support device 10.

The presentation support apparatus 10 is a computer on which presentation software is executed.

As an embodiment, the presentation support apparatus 10 may employ an information processing apparatus such as a desktop or notebook personal computer. In addition, the presentation support apparatus 10 can employ not only a stationary terminal such as the personal computer but also various portable terminal apparatuses. For example, as an example of the mobile terminal device, mobile communication terminals such as smartphones, mobile phones and PHS (Personal Handyphone System), and slate terminals such as PDA (Personal Digital Assistants) are included in the category.

In the present embodiment, as an example, it is assumed that the presentation support apparatus 10 provides the above-described presentation support service in a stand-alone manner that independently executes the above-described presentation software without depending on external resources. Although the details will be described later, the presentation support service is not limited to the implementation provided in a stand-alone manner. For example, a client server system can be constructed by providing a server that provides the presentation support service to a client that executes presentation software.

[Configuration of Presentation Support Device 10]
Next, the functional configuration of the presentation support apparatus 10 according to the present embodiment will be described. FIG. 2 is a block diagram illustrating a functional configuration of the presentation support apparatus 10 according to the first embodiment. As shown in FIG. 2, the presentation support apparatus 10 includes an input / output I / F (InterFace) unit 11, a storage unit 13, and a control unit 15.

The input / output I / F unit 11 is an interface for performing input / output with peripheral devices such as the microphone 3, the display device 5, and the input device 7.

As one embodiment, the input / output I / F unit 11 outputs the audio data input from the microphone 3 to the control unit 15. Further, the input / output I / F unit 11 outputs the slide image data output from the control unit 15 to the display device 5, highlights an area included in the slide output from the control unit 15, or cancels the instruction. An instruction is output to the display device 5. The input / output I / F unit 11 outputs various operations input from the input device 7 to the control unit 15.

The storage unit 13 is a device that stores data used for various programs such as an OS (Operating System) and presentation software executed by the control unit 15 and application programs.

As an embodiment, the storage unit 13 is implemented as a main storage device in the presentation support apparatus 10. For example, various semiconductor memory elements such as RAM (Random Access Memory) and flash memory can be employed for the storage unit 13. The storage unit 13 can also be implemented as an auxiliary storage device. In this case, HDD (Hard Disk Drive), optical disk, SSD (Solid State Drive), etc. can be adopted.

The storage unit 13 stores document data 13a, extracted word data 13b, and recognized word data 13c as an example of data used in a program executed by the control unit 15. Note that the extracted word data 13b and the recognized word data 13c other than the document data 13a are intermediate data generated through processing by the control unit 15, and will be described together with the description of the control unit 15. In addition to the above data, the storage unit 13 can also store other electronic data such as a presentation timetable.

Document data 13a is data relating to a document.

As an embodiment, a document file in which one or a plurality of slides are created using presentation software can be adopted as the document data 13a. Such slides can be imported with text and graphics as well as content created by other application programs. For example, you can import documents created with word processing software, tables and graphs created with spreadsheet software, images and movies taken with an imaging device, and images and movies edited with image editing software. And can be imported. In this way, in order to realize a keyword search by voice recognition, meta information including a character string such as an explanatory word or a description of the content is added to the content other than the text before the presentation is started. Can do.

The control unit 15 has an internal memory for storing various programs and control data, and executes various processes using these.

As an embodiment, the control unit 15 is implemented as a central processing unit, a so-called CPU (Central Processing Unit). Note that the control unit 15 does not necessarily have to be implemented as a central processing unit, and may be implemented as an MPU (Micro Processing Unit). Further, the control unit 15 can be realized by hard wired logic such as ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

The control unit 15 virtually implements the following processing unit by executing various programs. For example, as shown in FIG. 2, the control unit 15 includes a dividing unit 15a, an extracting unit 15b, an adding unit 15c, a recognizing unit 15d, a calculating unit 15e, a setting unit 15f, and a display control unit 15g. Have.

The dividing unit 15a is a processing unit that divides a slide into a plurality of regions.

As an embodiment, the dividing unit 15a reads a document file that has received a designation first among document files included in the document data 13a stored in the storage unit 13. Here, as an example, the case where the dividing unit 15a reads the document file from the storage unit 13 is illustrated, but the document file acquisition path is not limited thereto. For example, the dividing unit 15a can also acquire an image from an auxiliary storage device such as a hard disk or an optical disk, or a removable medium such as a memory card or a USB (Universal Serial Bus) memory. The acquisition unit 15a can also acquire an image by receiving it from an external device via a network.

Subsequently, the dividing unit 15a divides the slide included in the previously read document file into a plurality of areas. For example, the dividing unit 15a divides the slide in units of one sentence, line, paragraph, and the like. In this case, the dividing unit 15a scans a character string included in the slide, detects a delimiter character corresponding to a space, a punctuation point, or a line feed, and sets the delimiter character as a boundary of the region. The dividing unit 15a divides a character string included in the slide before and after the boundary. Thus, the slide is divided into a plurality of areas for each delimiter character. In addition, the dividing unit 15a assigns an index for identifying the area to the area obtained by dividing the slide. Here, the case where the slide is automatically divided is illustrated, but the slide may be manually divided by designating the boundary of the area via the input device 7 or the like.

The extraction unit 15b is a processing unit that extracts words from the character string included in the region.

As one embodiment, the extraction unit 15b selects one of a plurality of areas after dividing the slide. Subsequently, the extraction unit 15b extracts a word by executing natural language processing on the character string included in the previously selected region. For example, the extraction unit 15b extracts a word whose part of speech is a noun from morphemes obtained by executing morphological analysis or the like on a character string in the region. And the extraction part 15b provides the index allocated to the area | region where the said word is included to each word extracted previously. Thereafter, the extraction unit 15b repeatedly executes the extraction of the word and the assignment of the index until all the regions included in the slide are selected. In addition, although the case where the area | region which a slide contains was processed one by one was illustrated here, it cannot be overemphasized that each area | region can be processed in parallel.

The assigning unit 15c is a processing unit that assigns a weight to each word.

As an embodiment, the assigning unit 15 c calculates the appearance frequency f _k of the word k for each word included in the slide after the extraction unit 15 b extracts the words from all the regions. As an example of such appearance frequency, the assigning unit 15c calculates the total number of appearances for each word by counting the number of times the word k appears on the same slide. Then, applying section 15c imparts the weights w _k of the word corresponding to the frequency f _k, which is calculated for each word before. In this case, the assigning unit 15 c uses a weight calculation formula in which the weight w _k becomes smaller as the appearance frequency f _k becomes higher. For example, the assigning unit 15 c assigns the weight w _k calculated by substituting the appearance frequency f _k to the weight calculation formula “w _k = 1 / f _k ² ” to the word k. Then, the assigning unit 15 c registers the extracted word data 13 b in which the word k, the index idx, and the weight w _k are associated with the storage unit 13.

FIG. 3 is a diagram illustrating an example of the extracted word data 13b. FIG. 3 shows extracted word data relating to one slide out of a plurality of slides. In the example of the extracted word data 13b shown in FIG. 3, this means that the word “a” appears in two areas, the area “idx1” and the area “idx2”. Further, the word "a", since frequency is "2", 0.25 is assigned as a weight to compute the ^{1/2 2.} Further, it means that the word “b” appears in two areas of the area “idx1” and the area “idx3”. Furthermore, since the appearance frequency of the word “b” is “2”, 0.25 is given as a weight. Further, it means that the word “c” appears in two areas of the area “idx1” and the area “idx2”. Furthermore, since the appearance frequency of the word “c” is “2”, 0.25 is given as a weight. Further, it means that the word “d” appears in two areas of the area “idx2” and the area “idx3”. Furthermore, since the appearance frequency of the word “d” is “2”, 0.25 is given as a weight. Finally, it means that the word “e” appears in one area of the area “idx3”. Then, the word "e", since the frequency of occurrence is "1", 1 is given as a weight to the calculation of the 1/1 ^2. FIG. 3 illustrates the extracted word data related to one slide. However, in the other slides, the value of each item is different, but the computer can identify the word region and weight as in the example of FIG. Extracted word data is stored.

Note that details of an application example regarding the method of calculating the word weight _fk will be described later, but the word weight _fk is not limited to the above example. That is, the assigning unit 15c can calculate the word weight _fk using a factor other than the above total number of appearances, or add another factor to the above total number of appearances and add the word weight fk. _k can be calculated.

The recognition unit 15d is a processing unit that performs voice recognition.

As an embodiment, the recognition unit 15d is activated when the presentation software receives a presentation start instruction with the document file opened, and waits until an audio signal having a predetermined time length is input from the microphone 3. For example, it waits for an audio signal having a time length of at least one frame, for example, 10 msec. The recognizing unit 15d performs voice recognition such as word spotting on the voice signal every time a voice signal having a predetermined time length is input from the microphone 3. At this time, the recognizing unit 15d extracts the extracted word data related to the slide that is included in the document file that is being executed by the presentation software among the extracted word data 13b stored in the storage unit 13 and that is being displayed on the display device 5. Apply to word spotting. Thereby, the recognition unit 15d recognizes whether or not a word extracted from each region included in the slide being displayed exists in the utterance of the presenter. Then, when a word is recognized from the audio signal, the recognition unit 15 d registers the recognition word data 13 c in which the word and the time when the word is recognized are associated with each other in the storage unit 13. When the same word is recognized a plurality of times as time passes, the last, that is, the latest recognized time is registered in the storage unit 13.

Thereafter, the recognizing unit 15d determines whether or not there is a word for which a predetermined period has elapsed since it was registered in the storage unit 13 in the recognized word data 13c stored in the storage unit 13. For example, for each word included in the recognized word data 13c, the recognizing unit 15d has a difference between the time registered in association with the word and the time when the recognizing unit 15d refers to the recognized word data 13c, that is, the current time. It is determined whether or not a predetermined threshold is exceeded. At this time, the recognizing unit 15d can change the threshold value used for the above determination according to the unit in which the slide is divided by the dividing unit 15a, for example, one sentence, line, paragraph, or the like. For example, when the slide is divided in units of lines, it can be assumed that the number of characters read out in one area is approximately 20 to 30 characters. In this case, 5 to 10 seconds can be used as an example of the threshold value. Further, when the slide is divided in units of paragraphs, it can be assumed that a time longer than the line unit is devoted to reading. In this case, 20 to 30 seconds can be used as an example of the above threshold.

Here, when there is a word for which a predetermined period has elapsed since it was registered in the storage unit 13, there is a high possibility that the explanation regarding the slide area including the word has ended. If such a word is left, the possibility that the area where the explanation has ended will be highlighted. Therefore, the recognition unit 15d deletes the record related to the word from the recognized word data 13c stored in the storage unit 13. On the other hand, when there is no word for which a predetermined period has elapsed since registration in the storage unit 13, there is a high possibility that the description regarding the slide area where the word included in the recognized word data 13c appears has not ended. In this case, there is a low possibility that the area for which the explanation has been completed is displayed with highlight. Therefore, the recognition unit 15d leaves the word included in the recognition word data 13c stored in the storage unit 13 without deleting it.

Further, the recognition unit 15d determines whether or not the slide page displayed on the display device 5 has been changed. For example, the recognizing unit 15d determines whether a slide is switched by a slide show or an operation for advancing a slide page or an operation for returning a slide page is received via the input device 7. At this time, when the slide page displayed on the display device 5 is changed, it is highly possible that the description of the presenter is switched from the slide of the page before the change to the slide of the page after the change. In this case, the recognition unit 15d deletes the recognized word data 13c stored in the storage unit 13. On the other hand, when the slide page displayed on the display device 5 is not changed, there is a high possibility that the page explained by the presenter will not change. In this case, the recognition unit 15d leaves the word included in the recognized word data 13c stored in the storage unit 13 without deleting it.

Through these series of operations, the recognizing unit 15d recognizes a word that is highly likely to be explained by the presenter in the displayed slide. In the following, a word included in the extracted word data 13b is described as an “extracted word”, and a word included in the recognized word data 13c is described as a “recognized word” to distinguish the labels from each other. is there.

The calculation unit 15e is a processing unit that calculates the degree of association between the region in the slide being displayed and the word obtained as a speech recognition result.

As one embodiment, the calculation unit 15e selects one index among the indexes of the area included in the slide that is being displayed on the display device 5. Subsequently, the calculation unit 15e calculates the area from the weight assigned to the extracted word that matches the recognized word of the recognized word data 13c among the extracted words of the extracted word data 13b associated with the previously selected index area. The relevance of is calculated. For example, when calculating the degree of association r _x of the region x using the above-described word weight w _k , the calculation unit 15e adds the weights w _k given to the extracted words that match the recognized word, thereby calculating the degree of association. r _x can be calculated. At this time, if there is no word that matches the recognized word among the extracted words associated with the index area, the relevance of the area is calculated as zero. By such calculation logic, the degree of relevance between the description contents of each area in the slide and the utterance contents of the presenter is obtained as the “relevance degree”.

The setting unit 15f is a processing unit that sets the speed at which highlight display of the area in the slide is advanced. Hereinafter, the speed at which highlight display proceeds is sometimes referred to as “highlight speed”.

As an embodiment, the setting unit 15f sets a higher highlight speed for a region with a higher relevance or a lower highlight speed for a region with a lower relevance each time the relevance is calculated by the calculator 15e. To do. For example, to set the highlight velocity v _x of the region x with the degree of association r _x, setting unit 15f, the above related to the calculation formula of the highlight velocity v _x 'v _{x =} V × r _x " It can be calculated by substituting the degree r _x . “V” included in the calculation formula is a predetermined fixed value. That is, by using the calculation formula of the highlights velocity v _x, it is possible to calculate a highlight velocity v _x proportional to the value of relevance r _x.

The display control unit 15g is a processing unit that executes display control for the display device 5.

As one embodiment, when a document file is opened by presentation software, the display control unit 15g causes the display device 5 to display a slide included in the document file. At this time, the display control unit 15g may display the slide of the first page among the slides included in the document file, or may display the slide of the page edited last.

After that, when receiving a presentation start instruction, the display control unit 15g executes the following process every time the setting unit 15f sets the highlight speed of each area. That is, the display control unit 15g advances the highlight display according to the highlight speed set for each area included in the slide being displayed. That is, the display control unit 15g does not always complete the highlight display immediately because a value greater than zero is set as the highlight speed of the region. That is, the display control unit 15g advances the highlight display toward the completion at the highlight speed set by the setting unit 15f. As a result, the highlight display is advanced toward a display form different from the display form set at the time of creating the slide in the region where the highlight speed greater than zero is set. Hereinafter, the degree of progress of highlight display of an area toward completion may be referred to as “progress”.

Here, the display control unit 15g can execute arbitrary highlight display. For example, the display control unit 15g can realize the highlight display by increasing the luminance of the character string included in the region or the background of the character string, rather than the luminance set to the region at the time of creating the slide. Further, the display control unit 15g may change the font of the character string, or change the background display color or fill. In addition, the display control unit 15g can also realize highlighting by highlighting the area.

Further, the display control unit 15g monitors the presence / absence of a region where the progress of highlight display is equal to or greater than a predetermined threshold. When there is an area where the progress of highlight display is equal to or greater than a predetermined threshold, the area is higher than the area where the progress of highlight display is less than the threshold, in other words, the sum of relevance. It can be judged that the average was maintained at a high level. In this case, the display control unit 15g maintains the setting of the highlight speed of the area where the progress of highlight display is equal to or higher than the threshold, and the highlight display of the area where the progress of highlight display is less than the threshold is changed to the original. Returning to the state, the highlight speed of the area where the progress of highlight display is less than the threshold is reset to zero. As a result, highlight display is executed by narrowing down to a region where it can be determined that the presenter is an explanation location based on the passage of time or the accumulation of extracted words that match the recognized word over time.

After that, the display control unit 15g determines whether or not the degree of association calculated by the calculation unit 15e decreases in an area where the progress degree of highlight display is equal to or greater than the threshold value. For example, if the current relevance level calculated this time is lower than the past relevance level calculated last time, the number of extracted words that match the recognized word decreases over time, or only extracted words with low weight are recognized. It can be determined that there is a change in situation such as not matching the word. In this case, the display control unit 15g returns the highlight display of the area where the degree of relevance is reduced to the original state, and resets the highlight speed to zero. In this example, the highlight display is canceled when the current relevance level is lower than the past relevance level. However, the highlight display is performed when the current relevance level is lower than the past relevance level by a certain value. You can also cancel.

Further, when the display control unit 15g receives a page switching instruction via the input device 7, the display control unit 15g changes the slide to be displayed on the display device 5. For example, when an operation for advancing a page is received, the display control unit 15g causes the display device 5 to display a slide on the next page of the slide being displayed. Further, when the operation of returning the page is received, the display control unit 15g causes the display device 5 to display the slide of the previous page of the slide being displayed.

[Concrete example]
Next, a specific example of the presentation support method will be described with reference to FIGS. FIG. 4 is a diagram illustrating an example of a temporal change related to the progress of highlight display. 5 and 6 are diagrams showing an example of transition of the slide screen. In these FIG. 4, the case where the relevance degree of each area | region which the slide currently displayed on the display apparatus 5 includes using the extracted word data 13b shown in FIG. 3 is illustrated. 5 and 6 exemplify a case in which the slide being displayed on the display device 5 includes three areas of the indices idx1 to idx3 according to the example of the extracted word data 13b illustrated in FIG. Here, as an example of the highlight display, a case where reverse display of each area is executed according to the highlight speed set for the area is illustrated.

As shown in FIG. 4, since no word has been recognized until time t1, highlight display has not been executed in any of the areas of the index idx1 to idx3. That is, as shown in the uppermost part of FIG. 5, the areas of the indices idx1 to idx3 are displayed with the display form set when the slide is created.

Here, assuming that the word “a” is recognized at time t1, the relevance of each region is calculated as follows. That is, as shown in FIG. 3, since the extracted word includes the recognized word “a” in which the weight “0.25” is set in the two areas of the index idx1 and the index idx2, the degree of association is “0”. .25 ". On the other hand, since no recognized word is included in the area of index idx3, the degree of association is calculated as “0”. As a result, a highlight speed proportional to the relevance “0.25” is set in the two areas of index idx1 and index idx2, and the highlight speed is set to zero in the area of index idx3. .

At the time t2, the slide screen shown second from the top in FIG. 5 is displayed. That is, in the two areas of the index idx1 and the index idx2, the highlight display progresses to the same extent, while the area of the index idx3 transitions to a state where the highlight display does not progress.

Suppose that the word “b” is recognized at the time t2. In this case, in the area of the index idx1, two recognition words of a recognition word “a” with a weight “0.25” set as an extracted word and a recognition word “b” with a weight “0.25” set Therefore, the relevance is calculated as “0.5”. In addition, since the extracted word includes the recognized word “a” with the weight “0.25” set in the area of the index idx2, the degree of association is calculated as “0.25”. Is done. On the other hand, since the recognized word “b” with the weight “0.25” set in the extracted word is included in the area of the index idx3, the degree of association is calculated as “0.25”. As a result, a highlight speed proportional to the degree of association “0.5” is set in the index idx1, and a highlight speed proportional to the degree of association “0.25” is set in the area of the index idx2. In the area of idx3, a highlight speed proportional to the relevance “0.25” is set. That is, at time t2, the highlight speed of each region is “idx1> idx2 = idx3”.

Then, at time t3, the screen transitions to the third slide screen from the top in FIG. That is, a difference starts in the progress of highlight display between the two areas of index idx1 and index idx2. In other words, the area with the index idx1 is highlighted more greatly than the area with the index idx2. Further, the area of the index idx3 is delayed from the progress of the highlight display of the index idx2 by the amount that the highlight speed is set later than the index idx2.

Suppose that the word “c” is recognized at the time t3. In this case, in the area of the index idx1, the recognized word “a” with the weight “0.25”, the recognized word “b” with the weight “0.25”, and the weight “0.25” are set. The extracted word includes three recognition words “c” for which “is set”. For this reason, the relevance is calculated as “0.75” by the calculation of “0.25 + 0.25 + 0.25”. The area of index idx2 includes a recognized word “a” in which a weight “0.25” is set for the extracted word and a recognized word “c” in which the weight “0.25” is set for the extracted word. Therefore, the relevance is calculated as “0.5”. On the other hand, in the area of index idx3, as in the case of time t2, the extracted word includes the recognized word “b” having the weight “0.25”, so the degree of association is calculated as “0.25”. Is done. As a result, a highlight speed proportional to the relevance degree “0.75” is set in the index idx1, and a highlight speed proportional to the relevance degree “0.5” is set in the area of the index idx2. In the area of idx3, a highlight speed proportional to the relevance “0.25” is set. That is, at time t3, the highlight speed of each region is “idx1> idx2> idx3”.

After that, at time t4, the screen changes to the fourth slide screen from the top in FIG. That is, the process proceeds until the highlight display of the area of index idx1 reaches the threshold value. On the other hand, although the two areas of the index idx2 and the index idx3 have a difference in their progress, the progress does not reach the threshold.

In this way, when the highlight display of the area of the index idx1 proceeds to the threshold value, the screen transitions to the slide screen shown first from the top in FIG. That is, the area of the index idx1 in which the highlight display has progressed to the threshold is maintained as it is, while the area of the index idx2 and the index idx3 in which the highlight display has not progressed to the threshold is highlighted. Canceled.

Thereafter, the transition is made with the first slide screen from the top in FIG. 6 until time t5, and the recognized words “a”, “b”, and “c” are deleted from the recognized word data 13c at time t5. If it does, it will change to the slide screen shown to the 2nd from the top of FIG. That is, since the three regions from index idx1 to index idx3 do not include the recognized word, the relevance is calculated as “0”. As a result, the degree of relevance of the area with the index idx1 in which the highlight display has progressed to the threshold value is reduced, so that the highlight display of the area with the index idx1 is canceled. For this reason, all three areas of the index idx1 to the index idx3 return to the default display form set when the slide is created. The second slide screen from the top in FIG. 6 is maintained until the word “e” is recognized at time t6.

After that, when the word “e” is recognized at time t6, the relevance of each region is calculated as follows. In other words, the index idx3 is the only area in which the recognized word “e” is included in the extracted word among the three areas. For this reason, the weight “1” set for the recognized word “e” is calculated as the degree of association in the area of the index idx3. On the other hand, since the areas of index idx1 and index idx2 do not include any recognized word, the degree of association is calculated as “0”. As a result, the highlight speed is set to zero in the two areas of index idx1 and index idx2, and the highlight speed proportional to the degree of association “1” is set in the area of index idx3.

As a result, at time t7, the highlight display of the area of index idx3 proceeds to the threshold value. In this case, a transition is made to the third slide screen from the top in FIG. In other words, the area of index idx3 where the highlight display has progressed to the threshold is maintained as it is, while the areas of index idx2 and index idx3 both have the default display form set when the slide is created. Maintained.

At this time, the period until the progress of highlight display in the area of index idx3 reaches the threshold is shorter than the period until the progress of highlight display of the area of index idx1 reaches the threshold. This is because, in the area of index idx3, a highlight speed proportional to the relevance degree “1” is set, and therefore, the relevance degree “0.75” is the highest among the time points of time t1, time t2, and time t3. This is because the period until the degree of progress reaches the threshold is shorter than the highlight display in the area of the index idx1 in which the highlight speed proportional to is set.

5 and FIG. 6, when the presenter explains the area of index idx1 from time t1 to time t5, the area including index idx1 can be highlighted. That is, at the stage of time t1 and time t2, just because the recognized word is included in the extracted word in the area of index idx2 or index idx3, only the highlight display of the area of index idx2 or index idx3 does not proceed. The highlight display also proceeds in the area of index idx1. Therefore, it is possible to suppress the situation where the presenter's explanation part is not highlighted.

Furthermore, when the presenter explains the area of index idx3 from time t6, words that are included only in the extracted word of the area of index idx3 are recognized. As described above, when the presenter has a high degree of accuracy in explaining the area with the index idx3, the progress of highlight display in the area with the index idx3 can be increased. Accordingly, it is possible to suppress a situation where attention is focused on a highlight display that may cause an error while suppressing a decrease in response from the utterance of the presenter to the highlight display.

[Process flow]
Next, a processing flow of the presentation support apparatus 10 according to the present embodiment will be described. Here, description will be made in the order of (1) weighting processing, (2) speech recognition processing, and (3) display control processing executed by the presentation support apparatus 10.

(1) Weighting Process FIG. 7 is a flowchart illustrating the procedure of the weighting process according to the first embodiment. This process can be started automatically or manually. For example, when starting automatically, when the presentation software saves the document file in the storage unit 13 and then closes, or when the document file is saved in the storage unit 13 while editing the document file via the presentation, Can be activated. In addition, when starting with manual setting, the processing can be activated when an instruction to execute presentation pre-processing is received via the input device 7. In any case, the processing is started by reading out the document file corresponding to the save or execution instruction from the document files included in the document data 13a stored in the storage unit 13.

As shown in FIG. 7, the dividing unit 15a divides the slide included in the document file into a plurality of areas in units of one sentence, line, paragraph, or the like (step S101). Subsequently, the dividing unit 15a assigns an index for identifying each area to the area obtained in step S101 (step S102).

And the extraction part 15b selects one index among the indexes allocated by step S102 (step S103). Subsequently, the extraction unit 15b extracts a word whose part of speech is a noun from morphemes obtained by executing morphological analysis or the like on the character string in the index area selected in step S103 (step S104). Thereafter, the extraction unit 15b gives each word extracted in step S104 an index assigned to the area including the word (step S105).

Then, the extraction unit 15b repeatedly executes the processes from step S103 to step S105 until all the indexes assigned in step S102 are selected (No in step S106).

After that, when all the indexes assigned in step S101 are selected (step S106 Yes), the assigning unit 15c calculates the appearance frequency f _k of the word k for each word included in the slide (step S107). Then, the assigning unit 15c assigns a word weight w _k corresponding to the appearance frequency f _k calculated for each word in step S107 (step S108). On top of that, imparting unit 15c, the word k, and registers the extracted word data 13b index idx and weights _{w k} is associated to the storage unit 13 (step S109), and ends the process.

(2) Voice Recognition Processing FIG. 8 is a flowchart illustrating the procedure of voice recognition processing according to the first embodiment. This process is started when the presentation software receives a presentation start instruction with the document file opened, and is repeatedly executed until a presentation end instruction is received.

As shown in FIG. 8, the recognition unit 15d waits until an audio signal having a predetermined time length is input from the microphone 3 until an audio signal having a time length of, for example, at least one frame, for example, 10 msec is input (Step S15). S301).

Then, when an audio signal having a predetermined time length is input from the microphone 3 (Yes at Step S301), the recognition unit 15d performs voice recognition such as word spotting on the audio signal (Step S302). When word spotting is executed in step S302, the slide is included in the document file being executed by the presentation software among the extracted word data 13b stored in the storage unit 13 and is being displayed on the display device 5. Extracted word data relating to a certain slide is applied as dictionary data.

At this time, when a word is recognized from the audio signal (Yes in step S303), the recognition unit 15d stores the recognized word data 13c in which the word recognized in step S302 and the time when the word is recognized are associated with each other. (Step S304), and the process proceeds to step S305.

On the other hand, when a voice signal having a predetermined time length is not input from the microphone 3 or when a word is not recognized from the voice signal (No in Step S301 or Step S303), the subsequent processing is skipped and the processing proceeds to Step S305. .

Here, the recognizing unit 15d determines whether or not there is a word for which a predetermined period has elapsed since registration in the storage unit 13 among the recognized word data 13c stored in the storage unit 13 (step S305). If there is a word for which a predetermined period has elapsed since registration in the storage unit 13 (Yes in step S305), the recognition unit 15d deletes the record related to the word from the recognized word data 13c stored in the storage unit 13. (Step S306). If there is no word for which a predetermined period has elapsed since registration in the storage unit 13 (No in step S305), the process of step S306 is skipped and the process proceeds to step S307.

Thereafter, the recognition unit 15d determines whether or not the slide page displayed on the display device 5 has been changed (step S307). At this time, when the slide page displayed on the display device 5 is changed (Yes in step S307), the recognition unit 15d deletes the recognized word data 13c stored in the storage unit 13 (step S308), and in step S301. Return to processing. If the slide page displayed on the display device 5 has not been changed (No at Step S307), the process returns to Step S301 without executing Step S308.

(3) Display Control Process FIG. 9 is a flowchart illustrating the procedure of the display control process according to the first embodiment. This process is executed in parallel with the voice recognition process shown in FIG. 8, and is started when the presentation software receives a presentation start instruction with the document file opened, and gives a presentation end instruction. It is repeatedly executed until it is accepted. The cycle in which the execution of the process is repeated may be the same as or different from the voice recognition process shown in FIG. 8, and is executed in synchronization with the voice recognition process shown in FIG. It can also be executed asynchronously.

As shown in FIG. 9, the calculation unit 15e selects one index from among the indexes of the area included in the slide being displayed on the display device 5 (step S501). Subsequently, the calculation unit 15e calculates the degree of association of the area from the weights assigned to the extracted words that match the recognized word among the extracted words of the extracted word data 13b associated with the index area selected in step S501. Calculate (step S502).

Then, the setting unit 15f sets the highlight speed higher as the relevance calculated in step S502 is higher for the index area selected in step S501, or sets the highlight speed lower as the relevance is lower. (Step S503).

Thereafter, the processes from step S501 to step S503 are repeatedly executed until all indexes are selected (No in step S504). As a result, the processing from step S501 to step S503 is repeatedly executed until the highlight speed is set for all regions.

Thereafter, when all the indexes are selected (step S504 Yes), the presence / absence of an area where the progress of highlight display is equal to or greater than a predetermined threshold is monitored (step S505). At this time, when there is no region where the progress degree of highlight display is equal to or greater than the predetermined threshold (No in step S505), the display control unit 15g executes the following process. That is, the display control unit 15g advances the highlight display of each area according to the highlight speed set for each area in step S503 (step S506), and ends the process.

On the other hand, when there is an area where the progress degree of highlight display is equal to or greater than the predetermined threshold (Yes in step S505), the display control unit 15g executes the following process. That is, the display control unit 15g maintains the setting of the highlight speed in the area where the progress of highlight display is equal to or higher than the threshold, and the highlight display of the area where the progress of highlight display is less than the threshold is in the original state. The highlight display is canceled by returning to (step S507), and the highlight speed of the area where the progress of highlight display is less than the threshold is reset to zero (step S508).

Subsequently, the display control unit 15g determines whether or not the current relevance level is less than the past relevance level in an area where the progress degree of highlight display is equal to or greater than the threshold (step S509). At this time, if the current relevance level is equal to or higher than the past relevance level (No in step S509), the display control unit 15g advances the highlight display of each area according to the highlight speed set in each area in step S508. (Step S506), the process ends.

On the other hand, if the current relevance level is less than the past relevance level (Yes in step S509), the display control unit 15g cancels the highlight display by returning the highlight display of the area with the low relevance level to the original state. (Step S510), the highlight speed is reset to zero (Step S511), and the process ends.

[One aspect of effect]
As described above, when the presentation support apparatus 10 according to the present embodiment highlights an area including a word obtained as a speech recognition result on the presentation screen, the presentation support apparatus 10 The speed of highlighting is increased as the display is made, and the speed of highlighting is lowered as the display is in a region having a lower degree of association.

Thus, in the presentation support apparatus 10 according to the present embodiment, the area where the highlight display is executed is not necessarily limited to the alternative. For this reason, when a word is detected across a plurality of areas by voice recognition, highlight display is executed in each area. Therefore, it is possible to increase the possibility that the presenting part of the presenter is included in the area where the highlight display is executed. Therefore, according to the presentation support apparatus 10 according to the present embodiment, it is possible to suppress the situation where the presenting part of the presenter is not highlighted.

Furthermore, in the presentation support apparatus 10 according to the present embodiment, the speed of highlighting a region varies depending on the degree of association between words and regions obtained as a result of speech recognition. For example, even when a plurality of areas are highlighted, the response of highlight display regarding an area that is highly likely to be an explanation part of the presenter is increased. As a result, it is possible to easily draw attention to a region that is highly likely to be an explanation location of the presenter. At the same time, the response of highlight display relating to the region that is unlikely to be an explanation location of the presenter is lowered. As a result, it is possible to delay the perception of an area where the possibility of not being the presenting part of the presenter is higher than other areas. As described above, it is possible to suppress a situation in which attention is focused on a highlight display that may cause an error while suppressing a decrease in response from the utterance of the presenter to the highlight display.

Now, although the embodiments related to the disclosed device have been described so far, the present invention may be implemented in various different forms other than the above-described embodiments. Therefore, another embodiment included in the present invention will be described below.

[Highlights other than text]
In the first embodiment, the case where the region including the character string in the slide is highlighted is illustrated. However, the slide may include a graph, a table, an image, a movie, or the like in addition to the character string. It doesn't matter. In this case, for example, the presentation support device 10 generates extracted word data in the same manner as in the first embodiment by extracting words from character strings included in meta information set in graphs, tables, images, and moving images. be able to.

[Target of highlight display]
In the first embodiment, the case where highlight display and non-display are switched depending on whether or not the progress of highlight display is equal to or higher than the threshold is illustrated. However, the display and non-display of highlight are switched depending on other factors. You can also. For example, the display control unit 15g can switch between display and non-display of the highlight depending on whether or not the relevance of the region or the highlight speed of the region is equal to or higher than a predetermined threshold. In this case, the display and non-display of the highlight can be controlled before the highlight display progresses with time.

[Application example of appearance frequency]
In the first embodiment, the case where the total number of appearances in which the number of times the word k appears on the same slide is counted is used as the appearance frequency. However, the appearance frequency is not necessarily limited to the total number of appearances. For example, the number of appearances between regions in which the number of times the word k appears between the regions can be counted can be used as the appearance frequency. As an example, when the word k appears in one area among the three areas of the indices idx1 to idx3, the frequency of appearance between the areas is 1/3, so the weight of the word k is 1 / ( 1/3) ² is given. At this time, the number of times that the word k appears in one region is not counted as the total number of times, and the same weight is given even if it appears multiple times.

[Application example 1 of weighting method]
Further, in the first embodiment, the case where the weight is given to the word k according to the appearance frequency of the word k is exemplified, but the weight can be given to the word k by a factor other than the appearance frequency. For example, the assigning unit 15c can assign a weight to the word k according to the number of mora of the word k. Specifically, the assigning unit 15c can assign a greater weight as the number of mora of the word k increases. For example, the following two formulas can be used as an example of a weight calculation formula. That is, when the weight of the mora number m of the word k is w _m and the mora number m is larger than a fixed value M, for example, “6”, “w _m = 1 (m> M)” is used. When the mora number m is a fixed value M or less, “w _m = m / M (m ≦ M)” is used. In addition, although the case where a mora phoneme was used was illustrated here, it cannot be overemphasized that another phoneme can be used.

In general, the accuracy of speech recognition tends to decrease as the number of mora phonemes decreases. Therefore, according to the above weighting method, a larger weight is given when the number of mora phonemes of the word k is larger than when the number of mora phonemes of the word k is small. As a result that can be given, the calculation accuracy of the relevance can be improved. It should be noted that the weighting method described in this section can be implemented by using it alone instead of the weighting method described in the first embodiment, or the weighting method described in the first embodiment. It can also be implemented in combination with other weighting methods described in the second embodiment.

[Application example 2 of weighting method]
In the first embodiment, the case where the extracted word is given a weight before the speech recognition is executed is illustrated, but the weighting method is not limited to this. For example, the presentation support apparatus 10 can give a weight to a recognized word after voice recognition is performed. That is, when speech recognition is performed, the likelihood that the recognized word is a correct answer such as learning data, that is, a so-called score is often calculated together with the recognized word. For this reason, the presentation support apparatus 10 can also give a weight to the recognized word according to the score. It should be noted that the weighting method described in this section can be implemented by using it alone instead of the weighting method described in the first embodiment, or the weighting method described in the first embodiment. It can also be implemented in combination with other weighting methods described in the second embodiment.

[Application Example 1 of Relevance Calculation Method]
In the first embodiment, the case in which the degree of association is calculated for each region based on the number of extracted words that match the recognized word is exemplified, but the method for calculating the degree of association is not limited to this. That is, in the first embodiment, the case where the weights of the extracted words that match the recognized words are added is illustrated. It can also be calculated for each. The reason for using such a relevance calculation method is that the total number of extracted words extracted from each region is not necessarily the same or substantially the same. For this reason, when adding the weights of the extracted words that match the recognized words, the region having a smaller total number of extracted words may be calculated with an unreasonably lower relevance than the region having a large total number of extracted words. For this reason, the above-mentioned ratio is used as it is as the degree of relevance, or the total value obtained by adding the weights of the extracted words that match the recognized word is normalized using the above-mentioned ratio, thereby increasing the calculation accuracy of the degree of relevance. be able to. It should be noted that the weighting method described in this section can be implemented by using it alone instead of the weighting method described in the first embodiment, or the weighting method described in the first embodiment. It can also be implemented in combination with other weighting methods described in the second embodiment.

[Presenter instructions]
For example, the presentation support apparatus 10 can accept an instruction to accelerate or cancel highlight display via the input device 7 or the like. For example, an instruction to accelerate highlight display or an instruction to cancel highlight display is given to a predetermined key included in a keyboard, a predetermined button of a mouse, or a predetermined button of a laser pointer with a remote control function. Assign keys and buttons to accept. When the presentation support apparatus 10 receives an instruction for accelerating highlight display, the presentation support apparatus 10 accelerates the highlight speed in a region where the degree of progress of highlight display is the highest when the instruction is received. At this time, the presentation support apparatus 10 also includes raising the progress of highlight display in a region where the progress of highlight display is the highest to a threshold value at a time. On the other hand, when the presentation support apparatus 10 receives an instruction to cancel highlight display, the presentation support apparatus 10 cancels highlight display of the area where the progress of highlight display is the highest when the instruction is received and highlights the area. You can also reset the speed.

Here, the presenter creates slides that the presenter himself uses for the presentation, and the presenter himself assembles the slide description order and logical configuration as preparations for the presentation. It is likely that you will notice the highlighted area on the slide. This increases the possibility that the listener can accept an instruction to accelerate the highlight display or notice an instruction to cancel the highlight display before noticing the highlight display. Therefore, it is possible to increase the response of highlight display to the listener, or to suppress a situation where the listener notices an erroneous highlight display.

[Relation degree calculation range]
In the above-described first embodiment, the case where the degree of association of each area is calculated by focusing on the area in the slide being displayed is illustrated, but the calculation range of the degree of association is not necessarily limited thereto. For example, an area other than the slide being displayed can also be included in the relevance calculation range. At this time, when the relevance level of the region other than the slide being displayed is higher than the relevance level of the region within the slide being displayed, the presentation support apparatus 10 has the highest relevance level for the slide displayed on the display device 5. After switching to a slide having an area, highlight display regarding the area can be advanced.

[Application examples of document files]
In the first embodiment, the case where the document file created by the presentation software is used has been exemplified. However, the document file created by another application program can be used. That is, if the document file includes a page that is displayed in units of screens at the time of display, the page of the word processing software document file is replaced with a slide, or the sheet of the spreadsheet software document file is replaced with a slide. The processing shown in FIG. 9 can be similarly applied.

[Other implementation examples]
In the first embodiment, the case where the presentation support apparatus 10 provides the presentation support service in a stand-alone manner in which the presentation software 10 is independently executed without depending on an external resource is exemplified. Can also be adopted. For example, a client server system can be constructed by providing a server that provides the presentation support service to a client that executes presentation software. In this case, the server device can be implemented by installing a presentation support program for realizing the above presentation support service as package software or online software. For example, the server device 10 may be implemented as a Web server that provides the presentation support service, or may be implemented as a cloud that provides the presentation support service by outsourcing. In the first embodiment, it is assumed that the presentation support program is added to the presentation software. However, when a request for referring to the presentation support program as a library is received from a client having a license authority, the presentation support program is It can also be plugged in.

[Presentation support program]
The various processes described in the above embodiments can be realized by executing a prepared program on a computer such as a personal computer or a workstation. In the following, an example of a computer that executes a presentation support program having the same function as that of the above embodiment will be described with reference to FIG.

FIG. 10 is a diagram illustrating a hardware configuration example of a computer that executes the presentation support program according to the first and second embodiments. As illustrated in FIG. 10, the computer 100 includes an operation unit 110a, a speaker 110b, a camera 110c, a display 120, and a communication unit 130. Further, the computer 100 includes a CPU 150, a ROM 160, an HDD 170, and a RAM 180. These units 110 to 180 are connected via a bus 140.

As shown in FIG. 10, the HDD 170 is similar to the dividing unit 15a, the extracting unit 15b, the adding unit 15c, the recognizing unit 15d, the calculating unit 15e, the setting unit 15f, and the display control unit 15g described in the first embodiment. A presentation support program 170a that performs the function is stored. This presentation support program 170a is integrated or separated in the same manner as each component of the dividing unit 15a, extracting unit 15b, adding unit 15c, recognizing unit 15d, calculating unit 15e, setting unit 15f and display control unit 15g shown in FIG. It doesn't matter. That is, the HDD 170 does not necessarily have to store all the data shown in the first embodiment, and data used for processing may be stored in the HDD 170.

Under such an environment, the CPU 150 reads the presentation support program 170a from the HDD 170 and develops it on the RAM 180. As a result, the presentation support program 170a functions as a presentation support process 180a as shown in FIG. The presentation support process 180a expands various data read from the HDD 170 in an area allocated to the presentation support process 180a in the storage area of the RAM 180, and executes various processes using the expanded data. For example, examples of processing executed by the presentation support process 180a include the processing shown in FIGS. Note that the CPU 150 does not necessarily operate all the processing units described in the first embodiment, and the processing unit corresponding to the process to be executed may be virtually realized.

Note that the presentation support program 170a may not necessarily be stored in the HDD 170 or the ROM 160 from the beginning. For example, each program is stored in a “portable physical medium” such as a flexible disk inserted into the computer 100, so-called FD, CD-ROM, DVD disk, magneto-optical disk, or IC card. Then, the computer 100 may acquire and execute each program from these portable physical media. In addition, each program is stored in another computer or server device connected to the computer 100 via a public line, the Internet, a LAN, a WAN, etc., and the computer 100 acquires and executes each program from these. It may be.

DESCRIPTION OF SYMBOLS 1 Presentation support system 3 Microphone 5 Display apparatus 7 Input device 10 Presentation support apparatus 11 Input / output I / F part 13 Storage part 15 Control part 15a Division part 15b Extraction part 15c Assignment part 15d Recognition part 15e Calculation part 15f Setting part 15g Display control Part

Claims (13)

1. Computer
   A first word is extracted from a character string included in the area for each area into which a page of a document file including a page displayed in units of screen is divided;
   Perform speech recognition,
   Calculating the degree of association from the first word extracted from the region and the second word obtained as a result of the speech recognition for each region in the page being displayed on the predetermined display unit;
   The higher the degree of relevance calculated for each area, the higher the speed at which highlight display of the area proceeds, or the lower the degree of relevance, the lower the speed at which highlight display of the area proceeds,
   A presentation support method, comprising: executing a process of controlling highlight display in the page according to a speed set for each area.
2. The computer is
   Further executing a process of storing the second word obtained as a result of the speech recognition for a predetermined period after being registered in the storage unit;
   The calculating process calculates the relevance for each region using the second word stored in the storage unit,
   The presentation support method according to claim 1, wherein the setting processing sets a highlight display speed of each area each time the relevance is calculated for each area.
3. 3. The presentation support method according to claim 1, wherein the controlling process executes highlight display regarding an area where the relevance level or the progress level of the highlight display is a predetermined threshold value or more.
4. 4. The presentation support method according to claim 3, wherein the control processing cancels highlight display related to an area where the degree of association or the progress of highlight display is less than a predetermined threshold.
5. The presentation support method according to claim 1, wherein the computer further executes a process of assigning a weight to the first word extracted for each region.
6. The presentation support method according to claim 5, wherein the assigning process assigns a weight to the first word using an appearance frequency of the first word in the page.
7. 6. The presentation support method according to claim 5, wherein the assigning process assigns a weight to the first word using the number of mora of the first word.
8. The presentation support method according to claim 1, wherein the calculating process calculates the relevance for each region based on the number of first words that match the second word.
9. The calculation processing includes calculating the degree of association for each region based on a ratio of the number of first words matching the second word to the number of first words extracted from the region. The presentation support method according to claim 1, wherein:
10. The computer is
    Accepts instructions to accelerate the highlighting;
    2. The presentation support method according to claim 1, wherein when the instruction is received, the controlling process accelerates highlight display in an area where the progress of highlight display is the highest. 3.
11. The computer is
    Accepting an instruction to cancel the highlighting;
    2. The presentation support method according to claim 1, wherein when the instruction is received, the control processing cancels highlight display in an area other than the area where the highlight display progress is highest.
12. On the computer,
    A first word is extracted from a character string included in the area for each area into which a page of a document file including a page displayed in units of screen is divided;
    Perform speech recognition,
    Calculating the degree of association from the first word extracted from the region and the second word obtained as a result of the speech recognition for each region in the page being displayed on the predetermined display unit;
    The higher the degree of relevance calculated for each area, the higher the speed at which highlight display of the area proceeds, or the lower the degree of relevance, the lower the speed at which highlight display of the area proceeds,
    A presentation support program for executing a process of controlling highlight display in the page according to a speed set for each area.
13. An extraction unit that extracts a first word from a character string included in each area of the divided page of a document file including a page displayed in screen units when displayed;
    A recognition unit that performs speech recognition;
    A calculation unit that calculates the degree of association from the first word extracted from the region and the second word obtained as a result of the speech recognition for each region in the page being displayed on the predetermined display unit;
    A setting for setting a higher speed for the highlight display of the area to be set higher for an area having a higher relevance calculated for each area, or a setting for setting a lower speed for the highlight display of the area for a lower relevance level. And
    A display control unit that controls highlight display in the page according to a speed set for each region.

Images