Assisting Apparatus, Assisting Program and Assisting Method

• US 20100214476A1
• Filed: 02/22/2010
• Published: 08/26/2010
• Est. Priority Date: 02/24/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ozeki, Hiroaki, Saitoh, Takashi, Miyamoto, Kohtaroh
• Granted Patent: US 8,401,857 B2
• Time in Patent Office: Days
• US Class Current: 348/468
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 21/440236 by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
• CPC Class Codes: H04N 21/4884 for displaying subtitles

Abstract

Assisting apparatus that assists in a task for generating task-completed data from original data. The assisting apparatus includes: a conversion unit that converts the original data into converted data in order to keep a content of the original data secret from an operator in charge of the task; an interface unit that provides the converted data to the operator, and thereby allows the operator to perform the task by using the converted data and thus to generate a task-completed version of the converted data; and an inverse conversion unit that generates the task-completed data by performing inverse conversion of the task-completed version of the converted data.

Claims

1. An assisting apparatus that assists in a task for generating task-completed data from original data, the assisting apparatus comprising:

a conversion unit that converts the original data into converted data in order to keep a content of the original data secret from an operator in charge of the task;

an interface unit that provides the converted data to the operator, and thereby allows the operator to perform the task by using the converted data and thus to generate a task-completed version of the converted data; and

an inverse conversion unit that generates the task-completed data by performing inverse conversion of the task-completed version of the converted data.

2. The assisting apparatus according to claim 1, wherein

the conversion unit converts the original data with audio or text into the converted data with audio or text, and

the inverse conversion unit generates the task-completed data with audio or text by performing inverse conversion of the task-completed version of the converted data with audio or text.

3. The assisting apparatus according to claim 1, wherein

the conversion unit converts the original data with audio into the converted data with audio,

the interface unit provides the converted data to the operator, and thereby allows the operator to generate the task-completed version of the converted data with text on the basis of the audio of the converted data, and

the inverse conversion unit generates the task-completed data with text by performing inverse conversion of the task-completed version of the converted data.

4. The assisting apparatus according to claim 3, wherein

the conversion unit converts, into the converted data, the original data on a moving image with audio, the original data including an image and audio,

the interface unit provides the converted data to the operator, and thereby allows the operator to generate the task-completed version of the converted data including a transcribed text corresponding to the audio on the basis of the converted data, and

the inverse conversion unit generates the task-completed data including a transcribed text added to the moving image with audio, by performing inverse conversion of the task-completed version of the converted data.

5. The assisting apparatus according to claim 4, further comprising a speech recognition unit that generates a speech recognition text by recognizing audio of the original data, wherein

the conversion unit converts the original data and a speech recognition text of the original data into the converted data and a speech recognition text of the converted data, and

the interface unit provides the converted data and the speech recognition text of the converted data to the operator, and thereby allows the operator to edit the speech recognition text of the converted data and to generate a transcription corresponding to audio of the converted data.

6. The assisting apparatus according to claim 5, wherein

the conversion unit generates the converted data and the speech recognition text of the converted data by inserting different audio and a different text into at least one section of the audio of the original data and at least one section of the speech recognition text of the original data, respectively, and

the inverse conversion unit generates the task-completed data by removing the sections corresponding to the different audio and text from the task-completed version of the converted data.

7. The assisting apparatus according to claim 6, wherein, when judging that a proper noun that should be kept secret from the operator is included in the audio and the speech recognition text of the original data, the conversion unit generates the converted data and the speech recognition text of the converted data by inserting audio of a different proper noun and a text of a different proper noun into at least one section of the audio of the original data and at least one section of the speech recognition text of the original data, respectively.

8. The assisting apparatus according to claim 5, wherein

the conversion unit generates the converted data and the speech recognition text of the converted data by rearranging sections of each of the original data and the speech recognition text of the original data, and

the inverse conversion unit generates the task-completed data by arranging sections of the task-completed version of the converted data back to the original order.

9. The assisting apparatus according to claim 8, further comprising a word/phrase storage unit that stores whether or not each of a plurality of words/phrases should be kept secret from the operator, wherein

the conversion unit rearranges sections of each of the original data and the speech recognition text of the original data, and thereby disperses words/phrases that should be kept secret in the original data and the speech recognition text of the original data.

10. The assisting apparatus according to claim 9, further comprising a word/phrase registration unit that, if a particular word/phrase in the speech recognition text of the converted data is replaced by the operator with a word/phrase that should be kept secret through the interface unit, registers the particular word/phrase in the word/phrase storage unit as the word/phrase that should be kept secret.

11. The assisting apparatus according to claim 10, wherein

the word/phrase storage unit stores, for each of the plurality of words/phrases, presentation timing at which the word/phrase is allowed to be presented to the operator, and

the interface unit presents a section of the converted data and the speech recognition text of the converted data including the word/phrase associated with the presentation timing to the operator at timing satisfying the presentation timing.

12. The assisting apparatus according to claim 11, further comprising an equalization unit that equalizes at least one of pitch, strength and utterance speed of the audio of the converted data generated by the conversion unit.

13. The assisting apparatus according to claim 8, wherein the interface unit distributes a plurality of divided data to a plurality of the operators, the divided data obtained by dividing the converted data, allows each of the plurality of operators to perform the task by using the corresponding divided data, and thereby generates the task-completed version of the converted data by putting together a plurality of task-completed versions of the divided data.

14. The assisting apparatus according to claim 13, further comprising:

a word/phrase storage unit that stores a secret degree of each of a plurality of words/phrases; and

an operator information storage unit that stores, for each of the plurality of operators, a highest secret degree of words/phrases which are allowed to be presented to the operator, wherein,

in accordance with the secret degree of a word/phrase included in each of the divided data, the interface unit selects one of the operators to whom the divided data is to be provided.

15. A storage medium tangibly embodying therein or thereon computer executable instructions which, when executed, will cause a computer to function as an assisting apparatus for assisting in a task for generating task-completed data from original data, as claimed in claim 1.

16. An assisting apparatus that assists in a task for generating task-completed data from original data, the assisting apparatus comprising:

a word/phrase storage unit that stores, in association with each of a plurality of words/phrases, presentation timing at which the word/phrase is allowed to be presented to an operator; and

an interface unit that presents a section of the original data including any of the words/phrases stored in the word/phrase storage unit, to the operator at timing satisfying the presentation timing corresponding to the word/phrase, and thereby allows the operator to perform the task on the section in the original data.

17. A storage medium tangibly embodying therein or thereon computer executable instructions which, when executed, will cause a computer to function as an assisting apparatus for assisting in a task for generating task-completed data from original data, as claimed in claim 16.

18. An assisting apparatus for assisting in a task for generating, from original data of a moving image with audio including an image and audio, task-completed data including a transcribed text added to the moving image with audio, the assisting apparatus comprising:

a speech recognition unit that generates a speech recognition text by recognizing audio of the original data;

a conversion unit that converts the original data and the speech recognition text of the original data into converted data and a speech recognition text of the converted data in order to keep a content of the original data secret from an operator in charge of the task;

an equalization unit that equalizes at least one of pitch, strength and utterance speed of audio of the converted data generated by the conversion unit;

an interface unit that provides the converted data and the speech recognition text of the converted data to the operator, and thereby allows the operator to edit the speech recognition text of the converted data and thus to generate a task-completed version of the converted data including a transcribed text corresponding to the audio; and

an inverse conversion unit that generates the task-completed data by performing inverse conversion of the task-completed version of the converted data, wherein

the conversion unit generates the converted data and the speech recognition text of the converted data by inserting audio of a different proper noun and a text of a different proper noun into at least one section of the audio of the original data and at least one section of the speech recognition text of the original data, respectively, and also by rearranging sections of each of the original data and the speech recognition text of the original data, and

the inverse conversion unit generates the task-completed data by arranging sections of the task-completed version of the converted data back to the original order and also by removing the sections corresponding to the different audio and text from the task-completed version of the converted data.

19. A computer implemented method for assisting in a task for generating task-completed data from original data, the assisting method comprising the steps of:

converting the original data into converted data in order to keep a content of the original data secret from an operator in charge of the task;

providing the converted data to the operator, to allow the operator to perform the task by using the converted data and thus to generate a task-completed version of the converted data; and

generating the task-completed data by performing inverse conversion of the task-completed version of the converted data.