JP5791124B2 - Abstract writing support system, abstract writing support device, abstract writing support method, and program - Google Patents

Description

  The present invention relates to a summary writing support system, a summary writing support device, a summary writing support method, and a program for realizing these, in order to support a writer when a plurality of writers perform summary writing alternately.

  Persons with hearing impairments whose hearing ability in both ears is minus 100 decibels or more (hereinafter simply referred to as “persons with hearing impairments”) can hardly receive language information in speech even if a hearing aid is attached. For this reason, there have been cases where hearing-impaired persons listened to lectures and classes at school, added a sign language interpreter, and added a summary writing interpreter.

  Of these, in the case of attaching a summary writing interpreter, usually two or more summary writing interpreters are assigned to one person with hearing impairment, for example, in a class at school. These summary writers transcribe the teacher's spoken text, etc. with a PC (Personal Computer) or a paper notebook, and present it to the hearing impaired person. The reason why two or more summary writing interpreters are required is that the summary writing work is heavy and the accuracy of summarization tends to be reduced by one person.

  By the way, there are about 20,000 hearing-impaired students under 18 years old nationwide according to a survey conducted by the Ministry of Health, Labor and Welfare in 2008, whereas there are about 10,000 officially registered abstract writing interpreters nationwide. . On the other hand, if there are two or more summary writing interpreters for one hearing impaired student, the number of hearing impaired students who can receive support is simply 1/4. Furthermore, the number of summary writers and the number of hearing impaired students vary by region. For these reasons, a smaller number of hearing-impaired students can only receive support at school.

  In order to increase the number of summary writer interpreters, training is conducted in each group, and new summary writer interpreters are trained as one-year lectures and training, etc. be registered. However, the number of abstract writers is only a slight increase, and there is a problem that many students still cannot receive support.

  Here, it is examined whether the above problem can be solved by the existing technology. For example, Patent Literature 1 discloses a system that supports a writer when writing up a caption of a caption program. The system disclosed in Patent Document 1 detects pauses from audio data of program audio, divides audio data using the detected pauses, and lowers the playback speed or repeats playback as necessary. For example, the divided audio data is processed. For this reason, it becomes easy for the writer to hear the program sound and to easily transcribe subtitles. Therefore, if such a system is used, it is thought that it can contribute to the solution of the said problem that the number of summary writing interpreters is insufficient.

  Patent Document 2 discloses a system that corrects a recognition result in real time while recognizing a voice during a presentation, and displays the obtained recognition result as subtitles. If the system disclosed in Patent Document 2 is introduced, it can be surely contributed by solving the above-mentioned problem that the number of abstract writing interpreters is insufficient.

JP 2004-212799 A JP 2007-256714 A

  By the way, while listening to the speaker's talk during a lecture or lecture, a summary writing interpreter (hereinafter also simply referred to as “writer”) performs a summary writing. From the beginning to the end, the summary is not written by one person alone. This is because the accuracy of the summary writing decreases due to fatigue if performed alone.

  Therefore, there is a case where a method called collaborative input is used, in which writers change their input every certain amount of time or input while complementing each other. Is required for all scribes. For this reason, summary writing is performed while changing the writer at every allocated time so that even an inexperienced writer can participate.

  However, if the writer changes alternately, at the time before and after the change, both the writer and the newly assigned writer will miss or input the contents before and after the change. Problems such as forgetting may occur. Therefore, there is a need for a system that can solve such problems.

  Further, none of the systems disclosed in Patent Document 1 and Patent Document 2 described above is a system corresponding to a case where a plurality of writers perform summary writing alternately. Therefore, even if these systems are used, it is impossible to solve the above-described problem when a plurality of writers perform summary writing in turn.

  Furthermore, since the system disclosed in Patent Document 1 employs a processing method that relies on a special signal for broadcasting, it is not suitable for voice conversion in real time. Therefore, after all, with the system disclosed in Patent Document 1, it is difficult to solve the above shortage of abstract writing interpreters.

  In addition, since the system disclosed in Patent Document 2 depends on speech recognition, if the writer cannot check the recognition error, it can be presented to the user in an expression that the speaker does not intend. There is sex. For this reason, even with the system disclosed in Patent Document 2, it is difficult to solve the above shortage of summary writing interpreters.

[Object of invention]
SUMMARY OF THE INVENTION An object of the present invention is to provide a summary writing support system and a summary writing support device capable of solving the above-mentioned problem and suppressing the occurrence of mistakes by assisting a writer in the case of performing summary writing while a plurality of writers are changing. It is to provide a summary writing support method and program.

To achieve the above object, a summary writing support system according to one aspect of the present invention is a system for supporting a summary writing of a speaker's utterance,
A summary writing support device, a writer terminal used by a writer who performs the summary writing, and a user terminal that uses the summary writing,
The summary writing support device includes:
A voice analysis unit for identifying a silent section from the voice of the utterance;
For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range based on the end point of the allocated time, and the silent section exists within the range Then, when determining, an allocation control unit that changes the end point of the allocation time based on the silent section;
For each assigned time, a voice that transmits time information for specifying a start point and an end point of the assigned time and voice data of the utterance to the writer terminal of the writer to which the assigned time is assigned A distribution unit,
The writer terminal is
A text transmission unit that transmits the text data of the summary writing at the allocated time assigned to the writer to the summary writing support device;
It is characterized by that.

To achieve the above object, a summary writing support apparatus according to one aspect of the present invention is an apparatus for supporting summary writing of a speaker's utterance,
A voice analysis unit for identifying a silent section from the voice of the utterance;
For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range based on the end point of the allocated time, and the silent section exists within the range Then, when determining, an allocation control unit that changes the end point of the allocation time based on the silent section;
A voice that transmits, for each allocated time, time information that identifies a start point and an end point of the allocated time and voice data of the utterance to a terminal device used by a writer who is allocated the allocated time. A distribution department;
It is characterized by having.

In order to achieve the above object, a summary writing support method in one aspect of the present invention is a method for supporting summary writing of a speaker's utterance,
(A) identifying a silent section from the voice of the utterance;
(B) For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range with reference to the end point of the allocated time, and the silent section is the range. Changing the end point of the allotted time based on the silent section when it is determined that it exists within the step, and
(C) For each assigned time, a writer terminal used by a writer who is assigned the assigned time is provided with time information for specifying a start point and an end point of the assigned time, and voice data of the utterance. Send, step, and
It is characterized by having.

Furthermore, in order to achieve the above object, a program according to one aspect of the present invention is a program for supporting summary writing of a speaker's utterance by a computer,
In the computer,
(A) identifying a silent section from the voice of the utterance;
(B) For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range with reference to the end point of the allocated time, and the silent section is the range. Changing the end point of the allotted time based on the silent section when it is determined that it exists within the step, and
(C) For each assigned time, a writer terminal used by a writer who is assigned the assigned time is provided with time information for specifying a start point and an end point of the assigned time, and voice data of the utterance. Send, step, and
Is executed.

  As described above, according to the present invention, when a plurality of writers perform summary writing while changing, it is possible to support the writers and suppress the occurrence of mistakes.

FIG. 1 is a diagram schematically showing an overall configuration of a summary writing support system according to an embodiment of the present invention. FIG. 2 is a block diagram specifically showing the configuration of the abstract writing support system in the embodiment of the present invention. FIG. 3 is a diagram schematically illustrating processing in the voice analysis unit, the allocation control unit 12, and the voice distribution unit illustrated in FIG. FIG. 4 is a diagram illustrating an example of a text list stored in the text list storage unit illustrated in FIG. FIG. 5 is a flowchart showing the operation of the summary writing support apparatus in the embodiment of the present invention. FIG. 6 is a flowchart showing the operation of the writer terminal in the embodiment of the present invention. FIG. 7 is a flowchart showing the operation of the user terminal in the embodiment of the present invention. FIG. 8 is a block diagram illustrating an example of a computer that implements the abstract writing support apparatus, the writer terminal, and the user terminal according to the embodiment of the present invention. FIG. 9 is a diagram showing a specific example of the duplicate character string deletion process shown in FIG.

(Embodiment)
Hereinafter, a summary writing support system, a summary writing support device, a summary writing support method, and a program according to an embodiment of the present invention will be described with reference to FIGS.

[System configuration]
Initially, the whole structure of the summary writing assistance system in this Embodiment is demonstrated using FIG. FIG. 1 is a diagram schematically showing an overall configuration of a summary writing support system according to an embodiment of the present invention. In FIG. 2, the same or equivalent parts are denoted by the same reference numerals.

  A summary writing support system 100 shown in FIG. 1 is a system for supporting summary writing of a speaker's utterance. As shown in FIG. 1, the summary writing support system 100 includes a summary writing support device 10, a terminal device (hereinafter referred to as “writer terminal”) 30 used by a writer who performs summary writing, and a summary writing. A terminal device (hereinafter referred to as “user terminal”) 40 to be used.

  As illustrated in FIG. 1, the summary writing support apparatus 10 includes a voice analysis unit 11, an assignment control unit 12, and a voice distribution unit 13. The voice analysis unit 11 specifies a silent section from the speech voice.

  The allocation control unit 12 determines, for each allocation time allocated to the writer, whether or not a silent section exists within a range with reference to the end point of each allocation time. The end point of is changed based on the silent section.

  For each assigned time, the voice delivery unit 13 sends, to the writer terminal 30 of the writer to which each assigned time is assigned, time information for specifying the start point and the end point of the assigned time, and speech voice data. Send.

  Furthermore, as shown in FIG. 1, the writer terminal 30 includes a text transmission unit 32. When the writer performs summary writing on the assigned time of speech and inputs text data, the text transmission unit 32 transmits the summary writing text data to the summary writing support device 10.

  As described above, in the present embodiment, the silent period near the end is specified for each allocated time assigned to each writer, and when the silent period is specified, the allocated time is divided by the silent period. In addition, the allocation time is adjusted. In other words, in the present embodiment, when the summary writing is performed while a plurality of writers change, the allocation time is adjusted so that the change can be easily performed. For this reason, the occurrence of mistakes such as missing the contents before and after the change and forgetting to input is suppressed.

  Next, the configuration of the abstract writing support system in the present embodiment will be described more specifically with reference to FIG. FIG. 2 is a block diagram specifically showing the configuration of the abstract writing support system in the embodiment of the present invention. In FIG. 2, the same or equivalent parts are denoted by the same reference numerals. In FIG. 2, the same reference numerals as those shown in FIG. 1 denote the same parts as those shown in FIG.

[System configuration: Summary writing support device]
As shown in FIG. 2, in the present embodiment, the summary writing support apparatus 10 includes a receiving unit 21, an input control unit 22, in addition to the voice analysis unit 11, the allocation control unit 12, and the voice distribution unit 13. A duplicate deletion unit 23, a text list storage unit 24, and a transmission unit 25 are provided.

  Among these, the voice analysis unit 11, the allocation control unit 12, and the voice distribution unit 13 described above provide the voice distribution function 1 in the summary writing support apparatus 10. In addition, the receiving unit 21, the input control unit 22, the duplicate deletion unit 23, the text list storage unit 24, and the transmission unit 25 provide the duplicate deletion function 2 in the summary writing support apparatus 10 as described later.

  In the present embodiment, summary writing support apparatus 10 is constructed by introducing a program into a computer. At this time, the computer for constructing the abstract writing support apparatus 10 may be one or two or more. For example, the above-described audio distribution function 1 may be constructed with one computer, and the above-described duplicate deletion function 2 may be constructed with another computer.

  In the present embodiment, the speech of a speaker such as a lecturer or a lecturer in a lecture is first collected by a microphone or the like, converted into speech data there, and then input to the summary writing support apparatus 10. The voice analysis unit 11 specifies a silent section from the input voice data using a voice recognition engine, and outputs the start point and end point of the specified silent section to the allocation control unit 12.

  Further, in the present embodiment, the voice analysis unit 11 further specifies a silent section whose length is equal to or less than a threshold among the specified silent sections, and only the silent section whose length is equal to or smaller than the threshold is a start point and an end point. Can also be output to the allocation control unit 12. This is because, for example, a silent section of 1 second or less often corresponds to a section where a speaker is breathing, and is likely to be a break in the talk. Further, in this case, the allocation control unit 12 performs allocation control using a silent section whose length is equal to or less than a threshold value.

  In addition, in the present embodiment, in addition to the above-described processing, the allocation control unit 12 sets the start time of the next allocation time allocated to another writer following the current allocation time as the current allocation time and the next allocation time. Can be set so as to overlap the set time. In this case, the replacement of the summary writer becomes even easier, and the occurrence of mistakes can be further suppressed.

  Moreover, in this Embodiment, the audio | voice delivery part 13 complete | finishes the present allocation time after transmission of the time information and audio | voice data mentioned above to the writer terminal 30 of the writer who is currently allocated allocation time. Can also be notified. Furthermore, the voice delivery unit 13 can also notify the writer terminal 30 of another writer who is assigned the next assigned time of the current assigned time, the start of the next assigned time.

  The duplication deletion unit 23 deletes duplicate character strings when text data of summary writing at the allocated time allocated to the writer is transmitted from the writer terminal 30. First, the duplicate deletion unit 21 obtains a character string at the beginning of the transmitted text data and a character string at the end of the text data of the summary writing at the previous allocation time assigned to another writer. Compare. Then, the duplicate deletion unit 23 deletes the matching leading character string from the transmitted text data when the two match.

  Specifically, in the present embodiment, when text data of summary writing at the allocated time allocated to the writer is transmitted from the writer terminal 30, the receiving unit 21 receives this and receives the received text. Data is input to the input control unit 22. And the input control part 22 accumulate | stores the text data transmitted from the writer's terminal of a writer for every allocation time, and couple | bonds it in the order transmitted. Further, the input control unit 22 inputs the integrated text data to the duplication deletion unit 23.

  In this case, the duplication deletion unit 23 compares the character string on the head side of the text data integrated at the latest allocation time with the character string on the tail side of the text date integrated at the previous allocation time. If the two match, the duplicate deletion unit 23 deletes the matching first character string from the text data integrated at the latest allocation time. Note that the text integrated at the previous allocation time is deleted. The data is stored in the sentence list storage unit 24 as a sentence list (see FIG. 4 described later).

  When the deletion is performed by the duplication deletion unit 23, the transmission unit 25 transmits the text data from which the leading character string has been deleted to the user terminal 40. On the other hand, if the deletion is not performed by the duplicate deletion unit 23, the transmission unit 25 transmits the transmitted text data (integrated text data) to the user terminal 40 as it is.

  Moreover, in this Embodiment, the allocation control part 12 can assign | assign a number to each allocation time in order, In this case, the audio | voice delivery part 13 adds this time information in addition to time information and audio | voice data. A number (hereinafter referred to as “allocation number”) assigned to the specified allocation time can also be transmitted to the writer terminal 30. When the assignment number is transmitted to the writer terminal 30, in the writer terminal 30, the text transmission unit 32 assigns the corresponding assignment number to the text data, and the text data to which the corresponding assignment number is assigned. Will be sent.

  In addition, when an allocation number indicating an allocation time is assigned to the text data transmitted from the writer terminal 30, the input control unit 22 can manage the allocation time of the text data by the allocation number. That is, the input control unit 22 integrates text data assigned with the same assignment number into one.

  Also, in this case, the duplication control unit compares the text data of the current allocation number with the text data of the previous allocation number, and deletes the duplicated portion. In addition, the sentence list storage unit 24 also registers this assigned number in the sentence list. In addition to the text data, the transmission unit 25 also transmits an allocation number assigned to the text data to the user terminal 40.

  Here, the function of the abstract writing support apparatus 10 will be described more specifically with reference to FIGS. 3 and 4. First, the voice delivery function 1 will be described with reference to FIG. FIG. 3 is a diagram schematically illustrating processing in the voice analysis unit, the allocation control unit 12, and the voice distribution unit illustrated in FIG.

  As shown in FIG. 3, when the voice data of the uttered voice 51 is input, the voice analysis unit 11 uses a voice recognition engine to convert the voice data into voice sections 52-1 to 52-3 and a silent section 53-. Decomposes into 1-53-4. Then, the voice analysis unit 11 outputs information specifying the silent sections 53-1 to 53-4 to the allocation control unit 12.

  The allocation control unit 12 specifies the silent sections 53-1 to 53-4 based on the information from the voice analysis unit 11. Then, the allocation control unit 12 compares the allocation time 61 allocated to the writer A with the silent sections 53-1 to 54-1. Then, the allocation control unit 12 determines whether each silent section exists within a range with the end point 61b of the allocation time 61 as a reference. Specifically, the allocation control unit 12 determines whether each silent section exists in a section that is a combination of the pre-designated section 71 set before the end point 61b and the post-designated section 72 set after the end point 61b. judge.

  In the example of FIG. 3, since the silent section 53-2 exists within the section that includes the previous designated section 71 and the subsequent designated section 72, the assignment control unit 12 assigns the assigned time 61 to the silent section 53-2. It is divided by (end point) and is assigned time 62.

  At the same time, the allocation control unit 12 sets the start point 63a of the allocation time 63 so that the allocation time 63 allocated to the writer B and the allocation time 62 allocated to the writer A overlap. Specifically, the allocation control unit 12 sets the start point 63a of the allocation time 63 so as to be earlier by the overlap section 81 before the end point 62b of the allocation time 62.

  Thereafter, the voice distribution unit 13 transmits time information for specifying the start point 62a and the end point 62b of the new allocation time 62 and the voice data 91 of the utterance. In addition, the voice delivery unit 13 notifies the writer terminal 30 of the writer B of the newly set starting point 63 a of the allocated time 63.

  Next, the duplicate deletion function 2 will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of a text list stored in the text list storage unit illustrated in FIG.

  In the present embodiment, the receiving unit 21 receives text data to which an allocation number indicating an allocation time is given from the writer terminal 30, and passes the received text data and the allocation number to the input control unit 22.

  The input control unit 22 accumulates text data to which the same assignment number is assigned until a notification of input completion is received from the writer terminal 30. When the input completion notification is transmitted from the writer terminal 30, the input control unit 22 combines the text data to which the same assignment number is assigned, and duplicates the text data combined with the assignment number 23. To pass.

  When receiving the assigned number and the text data, the duplicate deletion unit 23 searches the text list stored in the text list storage unit 24. As shown in FIG. 4, the text list registers the combined text data and the assigned number assigned to it.

  Then, as a result of the search, the duplicate deletion unit 23 extracts the specified text data when the text data with the one lower assigned number can be specified from the sentence list. Then, the duplication deletion unit 23 compares the character string on the tail side of the text data extracted from the sentence list with the character string on the head side of the integrated text data passed from the input control unit 22, and both are duplicated. If this is the case, delete the character string at the beginning of the latter.

  Thereafter, the duplication deletion unit 23 passes the text data from which the character string has been deleted to the transmission unit 25. Further, the duplication deletion unit 23 registers the text data from which the character string has been deleted and the assigned number thereof in a sentence list.

  On the other hand, as a result of the search, if the duplicate deletion unit 23 cannot identify text data having a younger assigned number from the sentence list, the duplicate deletion unit 23 transmits the integrated text data passed from the input control unit 22 to the transmission unit 25. To pass. Further, the duplication deletion unit 23 registers the text data and the assigned number in a sentence list.

[System configuration: scribe terminal]
As shown in FIG. 2, the writer terminal 30 is connected to an audio playback device 6 and an input device 7. The audio reproduction device 6 is, for example, a speaker provided in the writer terminal 30. The input device 7 is an input device such as a mouse, a keyboard, or a touch panel.

  As shown in FIG. 2, the writer terminal 30 includes a voice receiving unit 31 and a text input unit 32 that receives text data input from the input device 7 in addition to the text transmission unit 32 described above. Yes.

  The voice receiving unit 31 receives voice data from the abstract writing support apparatus 10 and outputs it to the voice reproduction apparatus 6. Thereby, the audio reproduction device 6 reproduces the voice of the speaker. Then, the writer performs summary writing while listening to the voice, and inputs the text data via the input device 7. When the text input unit 32 receives the input text data, it passes it to the text transmission unit 32.

  The text transmission unit 32 assigns the allocation number transmitted from the voice distribution unit 13 to the text data received from the text input unit 32, and transmits the text data with the allocation number to the summary writing support apparatus 10. .

[System configuration: User terminal]
As shown in FIG. 2, the display device 8 is connected to the user terminal 40. The display device 8 is a liquid crystal display device or the like connected to or built in the user terminal 40. As shown in FIG. 2, the user terminal 40 includes a text receiving unit 41 and a display unit 42.

  The text receiving unit 41 receives the text data transmitted from the transmitting unit 25 of the summary writing support apparatus 10 and the assigned number assigned thereto, and passes them to the display unit 42. The display unit 42 displays the transmitted text data on the screen of the display device 8 in the order of the assignment numbers together with the assignment numbers. As a result, the hearing impaired person who is the user can confirm the summary writing of the speaker's voice.

  Moreover, the writer terminal 30 and the user terminal 40 mentioned above can be constructed by causing a computer to execute a program. In this case, examples of the computer include a personal computer, a smartphone, and a tablet terminal.

[System operation]
Next, the operation of the abstract writing support system 100 according to the embodiment of the present invention will be described with reference to FIGS. In the following description, FIGS. In the following example, it is assumed that the summary writing support system 100 is used for lectures at schools, lectures, and the like.

  In the present embodiment, the summary writing support method is implemented by operating the summary writing support system 100. Therefore, the description of the summary writing support method in the present embodiment is replaced with the following description of the operation of the summary writing support system 100.

[System Operation: Summary Writing Support Device]
First, the operation in the abstract writing support apparatus 10 will be described with reference to FIG. FIG. 5 is a flowchart showing the operation of the summary writing support apparatus in the embodiment of the present invention.

  First, a class is started and a speaker including a lecturer utters a voice. As a result, the utterance of the speaker is collected by a microphone or the like, converted there to voice data, and then output to the summary writing support apparatus 10. Then, as shown in FIG. 5, the voice analysis unit 11 receives the voice data (step A1), uses the voice recognition engine to identify the silence period from the voice data, and the start point of the identified silence period and The end point is output to the allocation control unit 12 (step A2).

  Next, the allocation control unit 12 determines whether or not the silent section exists within a range based on the end point of the current allocated time. If it is determined that the silent section exists, the end point of the current allocated time is determined as the silent section. (Step A3). In addition, the allocation control unit 12 sets the start time of the next allocation time allocated to another writer following the current allocation time so that the current allocation time and the next allocation time overlap with the set time. Set.

  The voice distribution unit 13 sends to the writer terminal 30 of the writer to whom the current allocation time is allocated time information specifying the start point and end point of the current allocation time, voice data of the utterance, and the current allocation The allocation number corresponding to the time is transmitted (step A4).

  When there is a change in step A3, the voice distribution unit 13 transmits time information for specifying the start point and end point of the changed allocation time. Furthermore, the voice delivery unit 13 notifies the writer terminal 30 of another writer who is assigned the next assigned time of the current assigned time, the start of the next assigned time.

  Next, when the text data of the summary writing at the allotted time assigned to the writer is transmitted from the writer terminal 30, the receiving unit 21 receives this, and receives the received text data and the attached text data. Is assigned to the input control unit 22 (step A5).

  The input control unit 22 accumulates the text data with the same assigned number in the order in which it is transmitted, and determines whether or not an input completion notification from the writer terminal 30 is received in the receiving unit 21. (Step A6).

  As a result of the determination in step A6, if not received, step A5 is executed again. On the other hand, if it is received as a result of the determination in step A6, the input control unit 22 combines the text data to which the same allocation number is assigned, and passes the text data combined with the allocation number to the duplicate deletion unit 23. .

  When the duplication deletion unit 23 receives the allocation number and the text data, the duplication deletion unit 23 searches the text list stored in the text list storage unit 24 and extracts text data with one lower allocation number. Then, the duplication deletion unit 23 compares the character string on the tail side of the text data extracted from the sentence list with the character string on the head side of the integrated text data passed from the input control unit 22, and both are duplicated. If so, the latter character string at the head is deleted (step A7).

  Next, the duplication deletion unit 23 passes the text data from which the character string has been deleted to the transmission unit 25. In addition, the duplication deletion unit 23 registers the text data from which the character string has been deleted and its assigned number in the sentence list (step A8).

  Note that the duplicate deletion unit 23 passes the integrated text data passed from the input control unit 22 to the transmission unit 25 when the text data having the younger assigned number cannot be identified by the search. Further, the duplication deletion unit 23 registers the text data and the assigned number in a sentence list.

  Thereafter, the transmission unit 25 transmits the text data received from the duplication deletion unit 23 and the assignment number assigned thereto to the user terminal 40 (step A9). Steps A1 to A9 are repeatedly executed. Further, in the present embodiment, steps A1 to A4 and steps A5 to A9 may be executed independently and in parallel.

[System operation: scribe terminal]
Next, the operation in the writer terminal 30 will be described with reference to FIG. FIG. 6 is a flowchart showing the operation of the writer terminal in the embodiment of the present invention.

  As shown in FIG. 6, first, the voice receiving unit 31 receives voice data and an assigned number from the abstract writing support apparatus 10 (step B1). Then, when the voice receiving unit 31 outputs the received voice data to the voice playback device 6, the voice playback device 6 plays back the voice of the speaker (step B2).

  Subsequently, the writer performs summary writing while listening to the voice, and inputs the text data via the input device 7. Thereby, the text input part 32 receives the input of text data (step B3). Then, the text input unit 32 passes the text data to the text transmission unit 32.

  The text transmission unit 32 assigns the allocation number transmitted from the voice distribution unit 13 to the text data received from the text input unit 32, and transmits the text data with the allocation number to the summary writing support apparatus 10. (Step B4).

  After execution of step B4, the above-described step A5 is executed in the summary writing support apparatus 10. Steps B <b> 1 to B <b> 4 are executed every time voice data and an assigned number are transmitted from the summary writing support apparatus 10.

[System operation: User terminal]
Subsequently, an operation in the user terminal 40 will be described with reference to FIG. FIG. 7 is a flowchart showing the operation of the user terminal in the embodiment of the present invention.

  As shown in FIG. 7, first, the text receiving unit 41 receives the text data transmitted from the transmitting unit 25 of the summary writing support apparatus 10 and the assigned number assigned thereto (step C1). Then, the transmission unit 25 passes the received text data and assignment number to the display unit 42.

  Next, the display unit 42 causes the transmitted text data to be displayed on the screen of the display device 8 in the order of the assignment number together with the assignment number (step C2). As a result, the hearing impaired person who is the user can confirm the summary writing of the speaker's voice.

[Effects of the embodiment]
As described above, according to the embodiment of the present invention, the allocation time is adjusted so that the allocation time is divided by the silent period, and the allocation time is set so that the continuous allocation time partially overlaps. To be done. For this reason, in the case where a plurality of writers perform summary writing while changing, it is easy to change, and thus the occurrence of mistakes such as missing the contents before and after the change and forgetting to input is suppressed. In addition, since the character strings that are repeatedly input by a plurality of writers are deleted and presented to the user at the portion where the allocation time overlaps, the summary writing becomes easy for the user to understand.

  As a result, according to the present embodiment, even if an inexperienced writer makes a summary writing, it is possible to provide a high-precision summary writing. It is done. Furthermore, since pseudo input can be realized, the immediacy of information can be improved.

[Modification]
The present embodiment is not limited to the above example. For example, in the present embodiment, it is possible to notify the writer terminal 30 of the overlapping portion of the allocated time, and instruct the writer to refrain from input at the overlapping portion. In this case, the process in the duplication deletion part 23 can be omitted.

[program]
The program in the present embodiment may be a program that causes a computer to execute steps A1 to A9 shown in FIG. By installing and executing this program on a computer, the abstract writing support apparatus 10 according to the present embodiment can be realized. In this case, the CPU (Central Processing Unit) of the computer functions as the voice analysis unit 11, the allocation control unit 12, the voice distribution unit 13, the reception unit 21, the input control unit 22, the duplication deletion unit 23, and the transmission unit 25. To do.

  When the abstract writing support apparatus 10 is realized by, for example, two computers, a program for executing steps A1 to A4 shown in FIG. 5 may be installed and executed on one computer. And what is necessary is just to install and run the program which performs step A5-A9 shown in FIG. 5 in another computer.

  Here, the computer which implement | achieves the abstract writing assistance apparatus 10, the writer terminal 30, and the user terminal 40 by executing the program in this Embodiment is demonstrated using FIG. FIG. 8 is a block diagram illustrating an example of a computer that implements the abstract writing support apparatus, the writer terminal, and the user terminal according to the embodiment of the present invention.

  As shown in FIG. 8, the computer 110 includes a CPU 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These units are connected to each other via a bus 121 so that data communication is possible.

  The CPU 111 performs various calculations by developing the program (code) in the present embodiment stored in the storage device 113 in the main memory 112 and executing them in a predetermined order. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory). Further, the program in the present embodiment is provided in a state of being stored in a computer-readable recording medium 120. Note that the program in the present embodiment may be distributed on the Internet connected via the communication interface 117.

  Specific examples of the storage device 113 include a hard disk and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and an input device 118 such as a keyboard and a mouse. The display controller 115 is connected to the display device 119 and controls display on the display device 119.

  The data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, and reads a program from the recording medium 120 and writes a processing result in the computer 110 to the recording medium 120. The communication interface 117 mediates data transmission between the CPU 111 and another computer.

  Specific examples of the recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic storage media such as a flexible disk, or CD- An optical storage medium such as ROM (Compact Disk Read Only Memory) can be used.

  Subsequently, an embodiment of the present invention will be described with reference to FIG. FIG. 9 is a diagram showing a specific example of the duplicate character string deletion process shown in FIG. In the following, description will be given focusing on the specific example of steps A5 to A9 shown in FIG.

  First, it is assumed that the receiving unit 21 receives text data with an allocation number of 4 "Progressed. Today we will proceed from the 12th line, XXXX renewal." (Step A5). The receiving unit 21 passes this allocation number and text data to the input control unit 22.

  Next, assuming that the completion of input is notified from the writer terminal 30 (step A6), the input control unit 22 proceeds with this text data “Today. It is passed to the input control unit 22.

  Next, the duplicate deletion unit 23 receives the allocation number and the text data, calculates “3” as the previous allocation number, and searches the text list stored in the text list storage unit 24. As shown in FIG. 4, since the text data with the allocation number 3 is registered, the duplicate removal unit 23 performs the text data with the allocation number 3 “Yes, yesterday has advanced to the XXX disturbance that occurred in the year XXX.” To get.

  Then, the duplication deletion unit 23 compares the character string on the end side of the text data with the allocation number 3 extracted from the sentence list with the character string on the top side of the text data with the allocation number 4 and duplicates them. The character string “Proceeded” is identified. Thereafter, the duplicate deletion unit 23 deletes the duplicated character string “advanced” (step A7).

  Next, the duplication deletion unit 23 passes to the transmission unit 25 the text data of the allocation number 4 from which the character string has been deleted, “Today, the 12th line, we will proceed from the renewal of XXX.” Further, the duplicate deletion unit 23 registers the text data of the allocation number 4 from which the character string has been deleted and the allocation number “4” in the sentence list (step A8). Thereafter, the transmission unit 25 transmits the text data of the allocation number 4 from which the character string has been deleted and the allocation number “4” to the user terminal 40 (step A9).

  Thereafter, in the user terminal 40, the text receiving unit 41 receives the allocation number “4” and the text data “Today, the 12th line, we will proceed from the renewal of XXX” (step C1). Then, the text data of the allocation numbers 1 to 4 are displayed on the display screen of the user terminal 40 in the order of the allocation numbers (step C2).

  Part or all of the above-described embodiment can be expressed by (Appendix 1) to (Appendix 26) described below, but is not limited to the following description.

(Appendix 1)
A system for supporting summary writing of speaker's utterances,
A summary writing support device, a writer terminal used by a writer who performs the summary writing, and a user terminal that uses the summary writing,
The summary writing support device includes:
A voice analysis unit for identifying a silent section from the voice of the utterance;
For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range based on the end point of the allocated time, and the silent section exists within the range Then, when determining, an allocation control unit that changes the end point of the allocation time based on the silent section;
For each assigned time, a voice that transmits time information for specifying a start point and an end point of the assigned time and voice data of the utterance to the writer terminal of the writer to which the assigned time is assigned A distribution unit,
The writer terminal is
A text transmission unit that transmits the text data of the summary writing at the allocated time assigned to the writer to the summary writing support device;
This is a summary writing support system.

(Appendix 2)
The summary brush Ki支 assistance device,
When the text data of the summary writing at the allotted time assigned to the writer is transmitted from the writer terminal, the character string at the head of the transmitted text data and another writer Compares the character string at the end of the text data of the summary writing at the previous allocated time, and if both match, from the sent text data, Delete the character string, duplicate deletion part,
When the deletion is performed, the text data from which the character string on the top side is deleted is transmitted to the user terminal. When the deletion is not performed, the transmitted text data is used as the usage data. A transmitting unit for transmitting to the user terminal;
The summary writing support system according to Appendix 1, further comprising:

(Appendix 3)
In the captioning Ki支 assistance device, the allocation control unit is further the start time of another scribe the next allocated time allocated subsequent to the allocated time, and the corresponding allocated time and the next allocated time Set to overlap for the set time,
The abstract writing support system according to appendix 1 or 2.

(Appendix 4)
In the summary brush Ki支 assistance device, the audio delivering unit,
After the transmission of the time information and the voice data to the writer terminal of the writer who is assigned the assigned time, the end of the assigned time is notified,
Notifying the writer terminal of another writer who is assigned the next assigned time of the assigned time, the start of the next assigned time,
The abstract writing support system according to any one of appendices 1 to 3.

(Appendix 5)
The summary brush Ki支 assistance device, for each of the allocated time, accumulates text data transmitted from the scribes terminal of the scribe, bind in the order sent, further comprising an input control unit,
Characters in the summary brush Ki支 assistance device, the duplicate removal section, at the end side of the character string at the beginning side of the text data that is integrated in the latest allocation time, text date integrated in the previous allotted time Compare the columns, and if they match, delete the matching first string from the text data integrated at the latest allocation time,
The abstract writing support system according to Appendix 2.

(Appendix 6)
In the summary brush Ki支 assistance device,
The allocation control unit sequentially assigns a number to each of the allocation times,
In addition to the time information and the voice data, the voice distribution unit transmits a number assigned to the allocated time specified by the time information,
In the writer terminal,
The text transmission unit gives a number corresponding to the text data, transmits the text data to which the corresponding number is assigned,
In the summary brush Ki支 assistance device,
The abstract writing support system according to appendix 5, wherein the input control unit integrates text data assigned with the same number into one.

(Appendix 7)
In the summary brush Ki支 assistance device, the transmission unit, in addition to the text data, send a number assigned to the text data to the user terminal,
The user terminal displays the transmitted text data on the screen in the order of the numbers assigned thereto.
The abstract writing support system according to appendix 6.

(Appendix 8)
In the summary brush Ki支 assistance device,
The voice analysis unit further specifies a silent section whose length is equal to or less than a threshold among the silent sections specified from the speech voice,
The summary writing support system according to any one of appendices 1 to 7, wherein the allocation control unit performs a determination using a silent section whose specified length is equal to or less than a threshold value.

(Appendix 9)
A device for supporting the summary writing of a speaker's utterance,
A voice analysis unit for identifying a silent section from the voice of the utterance;
For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range based on the end point of the allocated time, and the silent section exists within the range Then, when determining, an allocation control unit that changes the end point of the allocation time based on the silent section;
A voice that transmits, for each allocated time, time information that identifies a start point and an end point of the allocated time and voice data of the utterance to a terminal device used by a writer who is allocated the allocated time. A distribution department;
An abstract writing support apparatus characterized by comprising:

(Appendix 10)
When the text data of the summary writing at the allotted time allocated to the writer is transmitted from the terminal device used by the writer, the character string at the head of the transmitted text data is different from Compare the character string at the end of the text data of the summary writing at the previous allocation time assigned to the writer of the previous, and if both match, from the text data sent, match Delete the first character string that is
When the deletion is performed, the text data from which the character string on the top side is deleted is transmitted to the terminal device of the user who uses the summary writing. When the deletion is not performed, the transmitted text data is transmitted. A transmission unit for transmitting text data to a terminal device of a user who uses summary writing;
The summary writing support apparatus according to appendix 9, further comprising:

(Appendix 11)
The allocation control unit further sets the start time of the next allocation time allocated to another writer following the allocation time so that the allocation time and the next allocation time overlap. To
The abstract writing support apparatus according to appendix 9 or 10.

(Appendix 12)
The voice delivery unit
After the transmission of the time information and the voice data to the terminal device used by the writer who is assigned the assigned time, the end of the assigned time is notified,
Notifying the terminal device used by another writer who is assigned the next assigned time of the assigned time, the start of the next assigned time,
The abstract writing support apparatus according to appendices 9 to 11.

(Appendix 13)
Further comprising an input control unit that accumulates text data transmitted from the terminal device used by the writer for each allocated time, and combines them in the order of transmission;
The duplicate deletion unit compares the character string on the head side of the text data integrated at the latest allocation time with the character string on the tail side of the text date integrated at the previous allocation time, and both If they match, delete the matching first character string from the text data integrated in the latest allocation time,
The abstract writing support apparatus according to attachment 11.

(Appendix 14)
The voice analysis unit further specifies a silent section whose length is equal to or less than a threshold among the silent sections specified from the speech voice,
The summary writing support apparatus according to any one of appendices 9 to 13, wherein the allocation control unit performs a determination using a silent section whose specified length is equal to or less than a threshold value.

(Appendix 15)
A method for supporting summary writing of a speaker's utterance,
(A) identifying a silent section from the voice of the utterance;
(B) For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range with reference to the end point of the allocated time, and the silent section is the range. Changing the end point of the allotted time based on the silent section when it is determined that it exists within the step, and
(C) For each assigned time, a writer terminal used by a writer who is assigned the assigned time is provided with time information for specifying a start point and an end point of the assigned time, and voice data of the utterance. Send, step, and
An abstract writing support method characterized by comprising:

(Appendix 16)
(D) When the text data of the summary writing at the allotted time allocated to the writer is transmitted from the writer terminal, a character string at the head of the transmitted text data, Compared to the character string at the end of the text data of the summary writing at the previous allocation time assigned to the writer, and if both match, it matches from the sent text data Delete the string on the first side, and
(E) when the deletion is performed in the step (d), the text data from which the leading character string is deleted is transmitted to the user terminal; and
(F) If the deletion is not performed in the step (d), the transmitted text data is transmitted to the user terminal; and
The summary writing support method according to supplementary note 15, further comprising:

(Appendix 17)
(G) After execution of the step (b), the start time of the next allocation time allocated to another writer following the allocation time is the time when the allocation time and the next allocation time are set. Set the steps so that they overlap.
The abstract writing support method according to Supplementary Note 15 or 16, further comprising:

(Appendix 18)
(H) Notifying the end of the allocated time after transmitting the time information and the voice data in the step (c) to the writer terminal of the writer who is allocated the allocated time, Notifying the writer's terminal of another writer who is assigned the next quota time of the start of the next quota time,
The abstract writing support method according to any one of appendices 15 to 17, further comprising:

(Appendix 19)
(I) storing the text data transmitted from the writer's terminal of the writer for each allocated time, and further combining them in the order of transmission;
In the step (d), a character string at the beginning of the text data integrated at the latest allocation time is compared with a character string at the end of the text date integrated at the previous allocation time; and , If the two match, delete the matching leading character string from the text data integrated at the latest allocation time,
The abstract writing support method according to appendix 16.

(Appendix 20)
In the step (a), among the silence sections identified from the speech voice, a silence section having a length equal to or less than a threshold value is further specified.
The abstract writing support method according to any one of supplementary notes 15 to 19, wherein in the step (b), the determination is performed using a silent section whose specified length is equal to or less than a threshold value.

(Appendix 21)
A program for supporting the summary writing of a speaker's utterance by a computer,
In the computer,
(A) identifying a silent section from the voice of the utterance;
(B) For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range with reference to the end point of the allocated time, and the silent section is the range. Changing the end point of the allotted time based on the silent section when it is determined that it exists within the step, and
(C) For each assigned time, a writer terminal used by a writer who is assigned the assigned time is provided with time information for specifying a start point and an end point of the assigned time, and voice data of the utterance. Send, step, and
A program that executes

(Appendix 22)
(D) When the text data of the summary writing at the allotted time allocated to the writer is transmitted from the writer terminal, a character string at the head of the transmitted text data, Compared to the character string at the end of the text data of the summary writing at the previous allocation time assigned to the writer, and if both match, it matches from the sent text data Delete the string on the first side, and
(E) when the deletion is performed in the step (d), the text data from which the leading character string is deleted is transmitted to the user terminal; and
(F) If the deletion is not performed in the step (d), the transmitted text data is transmitted to the user terminal; and
The program according to appendix 21, wherein the program is further executed by the computer.

(Appendix 23)
(G) After execution of the step (b), the start time of the next allocation time allocated to another writer following the allocation time is the time when the allocation time and the next allocation time are set. Set the steps so that they overlap.
The program according to appendix 21 or 22, which is further executed by the computer.

(Appendix 24)
(H) Notifying the end of the allocated time after transmitting the time information and the voice data in the step (c) to the writer terminal of the writer who is allocated the allocated time, Notifying the writer's terminal of another writer who is assigned the next quota time of the start of the next quota time,
The program according to any one of appendices 21 to 23, further executed by the computer.

(Appendix 25)
(I) Accumulating text data transmitted from the writer's terminal of the writer for each allocated time, and combining them in the order of transmission, further causing the computer to execute a step;
In the step (d), a character string at the beginning of the text data integrated at the latest allocation time is compared with a character string at the end of the text date integrated at the previous allocation time; and , If the two match, delete the matching leading character string from the text data integrated at the latest allocation time,
The program according to attachment 22.

(Appendix 26)
In the step (a), among the silence sections identified from the speech voice, a silence section having a length equal to or less than a threshold value is further specified.
The program according to any one of appendices 21 to 25, wherein in the step (b), the determination is performed using a silent section whose specified length is equal to or less than a threshold value.

  As described above, according to the present invention, when a plurality of writers perform summary writing while changing, it is possible to support the writers and suppress the occurrence of mistakes. The present invention is useful not only for classes in schools and the like but also for various lectures as long as it is a field that requires abstract writing.

DESCRIPTION OF SYMBOLS 1 Voice delivery function 2 Duplicate deletion function 6 Voice playback device 7 Input device 8 Display device 10 Summary writing support device 11 Voice analysis part 12 Assignment control part 13 Voice delivery part 21 Reception part 22 Input control part 23 Duplicate deletion part 24 Text list storage Unit 25 transmitting unit 30 writer terminal 31 voice receiving unit 32 text transmitting unit 33 text input unit 40 user terminal 41 text receiving unit 42 display unit 51 voice data of speech voice 52-1 to 52-3 voice section 53-1 53-4 Silent section 61 Allocation time 61a Start point 61b End point 62 Allocation time (after change)
62a Start point 62b End point 63 Allocated time (next)
63a Start point 71 Previous designated section 72 Later designated section 81 Overlapping section 91 Speech data of speech voice 100 Summary writing support system 110 Computer 111 CPU
112 Main Memory 113 Storage Device 114 Input Interface 115 Display Controller 116 Data Reader / Writer 117 Communication Interface 118 Input Device 119 Display Device 120 Recording Medium 121 Bus

Claims (10)

A system for supporting summary writing of speaker's utterances,
A summary writing support device, a writer terminal used by a writer who performs the summary writing, and a user terminal that uses the summary writing,
The summary writing support device includes:
A voice analysis unit for identifying a silent section from the voice of the utterance;
For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range based on the end point of the allocated time, and the silent section exists within the range Then, when determining, an allocation control unit that changes the end point of the allocation time based on the silent section;
For each assigned time, a voice that transmits time information for specifying a start point and an end point of the assigned time and voice data of the utterance to the writer terminal of the writer to which the assigned time is assigned A distribution unit,
The writer terminal is
A text transmission unit that transmits the text data of the summary writing at the allocated time assigned to the writer to the summary writing support device;
This is a summary writing support system. The summary brush Ki支 assistance device,
When the text data of the summary writing at the allotted time assigned to the writer is transmitted from the writer terminal, the character string at the head of the transmitted text data and another writer Compares the character string at the end of the text data of the summary writing at the previous allocated time, and if both match, from the sent text data, Delete the character string, duplicate deletion part,
When the deletion is performed, the text data from which the character string on the top side is deleted is transmitted to the user terminal. When the deletion is not performed, the transmitted text data is used as the usage data. A transmitting unit for transmitting to the user terminal;
The summary writing support system according to claim 1, further comprising: In the summary brush Ki支 assistance device, the allocation control unit is further the start time of another scribe the next allocated time allocated subsequent to the allocated time, and the corresponding allocated time and the next allocated time Set to overlap for the set time,
The abstract writing support system according to claim 1 or 2. In the summary brush Ki支 assistance device, the audio delivering unit,
After the transmission of the time information and the voice data to the writer terminal of the writer who is assigned the assigned time, the end of the assigned time is notified,
Notifying the writer terminal of another writer who is assigned the next assigned time of the assigned time, the start of the next assigned time,
The abstract writing support system according to claim 1. The summary brush Ki支 assistance device, for each of the allocated time, accumulates text data transmitted from the scribes terminal of the scribe, bind in the order sent, further comprising an input control unit,
Characters in the summary brush Ki支 assistance device, the duplicate removal section, at the end side of the character string at the beginning side of the text data that is integrated in the latest allocation time, text date integrated in the previous allotted time Compare the columns, and if they match, delete the matching first string from the text data integrated at the latest allocation time,
The abstract writing support system according to claim 2. In the summary brush Ki支 assistance device,
The allocation control unit sequentially assigns a number to each of the allocation times,
In addition to the time information and the voice data, the voice distribution unit transmits a number assigned to the allocated time specified by the time information,
In the writer terminal,
The text transmission unit gives a number corresponding to the text data, transmits the text data to which the corresponding number is assigned,
In the summary brush Ki支 assistance device,
6. The abstract writing support system according to claim 5, wherein the input control unit integrates text data assigned with the same number into one. In the summary brush Ki支 assistance device, the transmission unit, in addition to the text data, send a number assigned to the text data to the user terminal,
The user terminal displays the transmitted text data on the screen in the order of the numbers assigned thereto.
The abstract writing support system according to claim 6. A device for supporting the summary writing of a speaker's utterance,
A voice analysis unit for identifying a silent section from the voice of the utterance;
For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range based on the end point of the allocated time, and the silent section exists within the range Then, when determining, an allocation control unit that changes the end point of the allocation time based on the silent section;
A voice that transmits, for each allocated time, time information that identifies a start point and an end point of the allocated time and voice data of the utterance to a terminal device used by a writer who is allocated the allocated time. A distribution department;
An abstract writing support apparatus characterized by comprising: A method for supporting summary writing of a speaker's utterance,
(A) identifying a silent section from the voice of the utterance by a computer ;
(B) For each allocation time allocated to the writer who performs the summary writing by the computer, it is determined whether the silent section exists within a range with reference to the end point of the allocation time, and the silence Changing the end point of the allocated time based on the silent section when determining that the section exists within the range; and
(C) Time information for specifying a start point and an end point of the allocated time on a writer terminal used by a writer who is allocated the allocated time for each allocated time by the computer; Sending audio data, step,
An abstract writing support method characterized by comprising: A program for supporting the summary writing of a speaker's utterance by a computer,
In the computer,
(A) identifying a silent section from the voice of the utterance;
(B) For each allocation time allocated to the writer who performs the summary writing, it is determined whether the silent section exists within a range with reference to the end point of the allocated time, and the silent section is the range. Changing the end point of the allotted time based on the silent section when it is determined that it exists within the step, and
(C) For each assigned time, a writer terminal used by a writer who is assigned the assigned time is provided with time information for specifying a start point and an end point of the assigned time, and voice data of the utterance. Send, step, and
A program that executes

Images