Presentation supporting device, presentation supporting method, and computer-readable recording medium

1. A presentation supporting device comprising:

a processor that executes a process comprising;

extracting a first word from a character string included in each region divided from a page of a document file including the page displayed in a unit of a screen during a display;

executing sound recognition;

first calculating a score, with respect to each region in a page currently-displayed on a predetermined display device, based on the first word extracted from the region and a second word acquired as a result of the sound recognition;

second calculating, when the highest score of the scores respectively-calculated for the regions is equal to or higher than a first threshold, a distance between a first region in which a highlight display is currently executed and a second region in which the highest score is equal to or higher than the first threshold;

first determining to execute a highlight display in the second region when a first frequency is equal to or higher than a second threshold, wherein

the first frequency is one of frequencies included in frequency data, and corresponds to the distance between the first region and the second region, wherein

the frequency data is data to which the distance between the first region and the second region and a frequency of occurrence of transition of a highlight display are associated; and

second determining to hold transition of a highlight display in the first region, when the first frequency is lower than the second threshold, until a second frequency of the highest score becoming equal to or higher than the first threshold becomes equal to or higher than a third threshold wherein

the first calculating includes calculating the scores by using at least one of an appearance frequency, the number of morae, and certainty of a result of the sound recognition which are related to the second word, and

the certainty is a value that indicates how similar a recognition result is to a spectrum of each phoneme included in a standard model of a word.

2. The presentation supporting device according to claim 1 , wherein the second calculating includes executing a calculation of the distance when the highest score of the scores respectively-calculated for the regions is higher than the score of the other region for predetermined times.

3. The presentation supporting device according to claim 1 , wherein when the highest score is equal to or higher than a fourth threshold which is higher than the first threshold, the first determining includes determining to execute a highlight display in the second region even when the first frequency is lower than the second threshold.

4. The presentation supporting device according to claim 1 , the process further comprising third calculating a change, which is in an angle of a line of sight before and after transition of the highlight display from the first region to the second region is performed, by using a size of a screen of the display device and a distance between the screen and a position of a predetermined point of view, wherein

when the angle is equal to or greater than a fifth threshold, the second determining includes determining to execute the highlight display in the first region until the second frequency becomes equal to or higher than the third threshold.

5. A presentation supporting method comprising:

extracting, by a processor, a first word from a character string included in each region divided from a page of a document file including the page displayed in a unit of a screen during a display,

executing, by the processor, sound recognition,

first calculating a score, with respect to each region in a page currently-displayed on a predetermined display device, based on the first word extracted from the region and a second word acquired as a result of the sound recognition,

second calculating, when the highest score of the scores respectively-calculated for the regions is equal to or higher than a first threshold, a distance between a first region in which the highlight display is currently executed and a second region in which the highest score is equal to or higher than the first threshold, by the processor,

first determining to execute a highlight display in the second region when a first frequency is equal to or higher than a second threshold, by the processor, wherein

the first frequency is one of frequencies included in frequency data, and corresponds to the distance between the first region and the second region, wherein

the frequency data is data to which the distance between the first region and the second region and a frequency of occurrence of transition of a highlight display are associated, and

second determining to hold transition of a highlight display in the first region, when the first frequency is lower than the second threshold, until a second frequency of the highest score being calculated to be equal to or higher than the first threshold becomes equal to or higher than a third threshold, by the processor wherein

the first calculating includes calculating the scores by using at least one of an appearance frequency, the number of morae, and certainty of a result of the sound recognition which are related to the second word, and

the certainty is a value that indicates how similar a recognition result is to a spectrum of each phoneme included in a standard model of a word.

6. A non-transitory computer-readable recording medium having stored therein a presentation supporting program that causes a computer to execute a process comprising:

extracting a first word from a character string included in each region divided from a page of a document file including the page displayed in a unit of a screen during a display;

executing sound recognition;

first calculating a score, with respect to each region in a page currently-displayed on a predetermined display device, based on the first word extracted from the region and a second word acquired as a result of the sound recognition;

second calculating, when the highest score of the scores respectively-calculated for the regions is equal to or higher than a first threshold, a distance between a first region in which the highlight display is currently executed and a second region in which the highest score is equal to or higher than the first threshold;

first determining to execute a highlight display in the second region when a first frequency is equal to or higher than a second threshold, wherein

the first frequency is one of frequencies included in frequency data, and corresponds to the distance between the first region and the second region, wherein

the frequency data is data to which the distance between the first region and the second region and a frequency of occurrence of transition of a highlight display are associated; and

second determining to hold transition of a highlight display in the first region, when the first frequency is lower than the second threshold, until a second frequency of the highest score being calculated to be equal to or higher than the first threshold becomes equal to or higher than a third threshold wherein

the first calculating includes calculating the scores by using at least one of an appearance frequency, the number of morae, and certainty of a result of the sound recognition which are related to the second word, and

the certainty is a value that indicates how similar a recognition result is to a spectrum of each phoneme included in a standard model of a word.