Patents by Inventor Kazuo Sumita
Kazuo Sumita has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8055495Abstract: An associated-information storage unit stores a name of associated information and a display position in association with each other. An example storage unit stores a semantic class, an example in a source language, and an example in a target language in association with each other. A dictionary storage unit stores the name of associated information and the semantic class in association with each other. An acquiring unit acquires the name of the associated information corresponding to the display position of the selected associated information from the associated-information storage unit, and acquires a semantic class corresponding to the acquired name of the associated information from the dictionary storage unit. A translation unit acquires an example in the target language corresponding to the acquired semantic class and a speech recognition result from the example storage unit, thereby translating the recognition result.Type: GrantFiled: September 6, 2007Date of Patent: November 8, 2011Assignee: Kabushiki Kaisha ToshibaInventor: Kazuo Sumita
-
Patent number: 7974844Abstract: A speech recognition apparatus includes a first-candidate selecting unit that selects a recognition result of a first speech from first recognition candidates based on likelihood of the first recognition candidates; a second-candidate selecting unit that extracts recognition candidates of a object word contained in the first speech and recognition candidates of a clue word from second recognition candidates, acquires the relevance ratio associated with the semantic relation between the extracted recognition candidates of the object word and the extracted recognition candidates of the clue word, and selects a recognition result of the second speech based on the acquired relevance ratio; a correction-portion identifying unit that identifies a portion corresponding to the object word in the first speech; and a correcting unit that corrects the word on identified portion.Type: GrantFiled: March 1, 2007Date of Patent: July 5, 2011Assignee: Kabushiki Kaisha ToshibaInventor: Kazuo Sumita
-
Patent number: 7747871Abstract: An information recording apparatus comprises an encryption section encrypting contents information and also a license condition referred to to limit use of the contents information and a decoding key for decoding the encrypted contents information to generate license information, and a recording section recording the encrypted contents information and the generated license information on a recording medium. An information reproducing apparatus comprises a decoder unit decoding the license information recorded on the recording medium using a second decoding key for decoding the license information and deciding on the basis of the license condition contained in the decoded license information whether the contents information can be used. If it is decided that the contents information can be used, the encrypted contents information recorded on the recording medium is decoded using the first decoding key contained in the decoded license information.Type: GrantFiled: August 27, 2002Date of Patent: June 29, 2010Assignee: Kabushiki Kaisha ToshibaInventors: Toru Kambayashi, Koichiro Akiyama, Shuichi Tsujimoto, Kazuo Sumita, Hideki Hirakawa, Toshihiro Sugaya
-
Publication number: 20090228263Abstract: A machine translating apparatus includes an input unit that inputs a source language sentence, a syntax analyzing unit that performs a syntactic analysis on the source language sentence and generates syntax information, an extracting unit that extracts from the syntax information the first partial information that includes the first partial structure including all the nodes under the most significant nodes that are the nodes of the syntax information and the corresponding morphemes, and also extracts the second partial information including the second subtree representing a difference between two items of the first partial information and the corresponding morphemes, a translating unit that translates the morphemes of all the items of the partial information with multiple translation systems, and a most-plausible structure selecting unit that selects a combination for which the average of the translation scores takes the maximum value.Type: ApplicationFiled: January 27, 2009Publication date: September 10, 2009Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Satoshi Kamatani, Tetsuro Chino, Kazuo Sumita
-
Publication number: 20090222257Abstract: A translation direction specifying unit specifies a first language and a second language. A speech recognizing unit recognizes a speech signal of the first language and outputs a first language character string. A first translating unit translates the first language character string into a second language character string that will be displayed on a display device. A keyword extracting unit extracts a keyword for a document retrieval from the first language character string or the second language character string, with which a document retrieving unit performs a document retrieval. A second translating unit translates a retrieved document into its opponent language, which will be displayed on the display device.Type: ApplicationFiled: February 18, 2009Publication date: September 3, 2009Inventors: Kazuo SUMITA, Tetsuro CHINO, Satoshi KAMATANI, Kouji UENO
-
Publication number: 20080221877Abstract: A response storage unit stores a response, a watching degree relative to a display unit, and an output form of the response to a speaker and the display unit. An extracting unit extracts a request from a speech recognition result. A response determining unit determines a response based on the extracted request. A direction detector detects a viewing direction of a user. A watching-degree determining unit determines a watching degree based on the viewing direction. An output controller obtains an output form corresponding to the response and the determined watching degree from the response storage unit, and output the response to the speaker and the display unit according to the obtained output form.Type: ApplicationFiled: September 13, 2007Publication date: September 11, 2008Inventor: Kazuo Sumita
-
Publication number: 20080208563Abstract: An associated-information storage unit stores a name of associated information and a display position in association with each other. An example storage unit stores a semantic class, an example in a source language, and an example in a target language in association with each other. A dictionary storage unit stores the name of associated information and the semantic class in association with each other. An acquiring unit acquires the name of the associated information corresponding to the display position of the selected associated information from the associated-information storage unit, and acquires a semantic class corresponding to the acquired name of the associated information from the dictionary storage unit. A translation unit acquires an example in the target language corresponding to the acquired semantic class and a speech recognition result from the example storage unit, thereby translating the recognition result.Type: ApplicationFiled: September 6, 2007Publication date: August 28, 2008Inventor: Kazuo Sumita
-
Patent number: 7343495Abstract: An information recording apparatus comprises an encryption section encrypting contents information and also a license condition referred to to limit use of the contents information and a decoding key for decoding the encrypted contents information to generate license information, and a recording section recording the encrypted contents information and the generated license information on a recording medium. An information reproducing apparatus comprises a decoder unit decoding the license information recorded on the recording medium using a second decoding key for decoding the license information and deciding on the basis of the license condition contained in the decoded license information whether the contents information can be used. If it is decided that the contents information can be used, the encrypted contents information recorded on the recording medium is decoded using the first decoding key contained in the decoded license information.Type: GrantFiled: August 27, 2002Date of Patent: March 11, 2008Assignee: Kabushiki Kaisha ToshibaInventors: Toru Kambayashi, Koichiro Akiyama, Shuichi Tsujimoto, Kazuo Sumita, Hideki Hirakawa, Toshihiro Sugaya
-
Publication number: 20070225980Abstract: A speech recognition apparatus includes a first-candidate selecting unit that selects a recognition result of a first speech from first recognition candidates based on likelihood of the first recognition candidates; a second-candidate selecting unit that extracts recognition candidates of a object word contained in the first speech and recognition candidates of a clue word from second recognition candidates, acquires the relevance ratio associated with the semantic relation between the extracted recognition candidates of the object word and the extracted recognition candidates of the clue word, and selects a recognition result of the second speech based on the acquired relevance ratio; a correction-portion identifying unit that identifies a portion corresponding to the object word in the first speech; and a correcting unit that corrects the word on identified portion.Type: ApplicationFiled: March 1, 2007Publication date: September 27, 2007Inventor: Kazuo Sumita
-
Publication number: 20070124131Abstract: An input apparatus which presents examples suitable to users, including an example storage module to store a plurality of example expressions; an edit storage module to store edits when a user edits the plurality of example expressions; a presentation example determining module to determine one or more presentation examples to be presented to the user from the plurality of example expressions stored in the example storage module; an edit adapting module to edit the presentation examples determined by the presentation example determining module based on the edits stored in the edit storage module; a display control module to present the presentation examples determined by the presentation example determining module to the user; and an entry accepting module to accept one of the presentation examples as a selected example when one of the presentation examples is selected by the user, or to receive edits from the user to one of the presentation examples and accept the edited presentation example as the selectedType: ApplicationFiled: September 28, 2006Publication date: May 31, 2007Inventors: Tetsuro Chino, Satoshi Kamatani, Kazuo Sumita
-
Publication number: 20070118351Abstract: An apparatus includes a first search unit that searches a storage unit for a first example of a first language based on a sentence in the first language; a second search unit that searches for a second example of a second language corresponding to the first example, the second language containing the same meaning as the first example; a determining unit that determines whether a plurality of the second examples exist; a first acquisition unit that acquires the first example corresponding to each of the second example from the storage unit; a second acquisition unit that acquires the second example corresponding to the first example acquired from the storage unit; and a choice generating unit that generates the first example acquired associated with the least number of the second examples acquired as a choice of the first example to be output.Type: ApplicationFiled: September 13, 2006Publication date: May 24, 2007Inventor: Kazuo Sumita
-
Patent number: 7209942Abstract: By moving image analysis, acoustic/speech analysis, or text analysis for multimedia information in a database, feature data representing the type of information is acquired, and the feature data is stored into the database added to the multimedia information. A search engine extracts partial images of user's interest from the multimedia information on the basis of the feature data and a user profile data. A link section associates the representative images (still images) of the partial images with multimedia images and displays the list of representative images and feature data. Thus, only a portion of the user's concern is extracted from an enormous amount of multimedia information, and individual information is selectively provided in units of users.Type: GrantFiled: December 23, 1999Date of Patent: April 24, 2007Assignee: Kabushiki Kaisha ToshibaInventors: Osamu Hori, Miwako Doi, Kazuo Sumita, Hideki Hirakawa
-
Patent number: 7065708Abstract: A computerized document processing apparatus for creating an abstract includes document storage for storing a computerized document, keyword storage for storing keywords, an abstract creation section for creating an abstract by extracting at least a character string containing a keyword stored in the keyword storage section from the computerized document stored in the document storage section, a document modification section for modifying the computerized document to link the keyword in the computerized document with the same keyword in the abstract, and a display section for displaying the abstract and the modified document that is linked with the abstract. The modified document is displayed when the linked keyword in the abstract is selected.Type: GrantFiled: February 23, 2004Date of Patent: June 20, 2006Assignee: Kabushiki Kaisha ToshibaInventors: Kenji Ono, Hideki Hirakawa, Kazuo Sumita
-
Publication number: 20040243392Abstract: A communication support apparatus comprises an acquisition unit configured to acquire source-language information represented in a first language, a first determination unit configured to determine a level of importance of the source-language information, a setting unit configured to set, based on the level of importance, an accuracy of translation with which the source-language information is translated into corresponding language information represented in a second language, and a translation unit configured to translate the source-language information into the corresponding language information with the accuracy.Type: ApplicationFiled: January 9, 2004Publication date: December 2, 2004Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Tetsuro Chino, Kazuo Sumita, Tatsuya Izuha, Yuka Morimoto
-
Publication number: 20040162842Abstract: There is provided a computerized document processing system which allows processing in creating an abstract to be distributed and an original document to be readily modified to relate the abstract with the original document. The computerized document processing system comprises a keyword holding section for holding keywords, document storage means for holding a computerized document transferred via a network, abstract creating means for creating an abstract by extracting at least a character string containing a keyword held in the keyword holding section from the computerized document held in the document storage means, document modifying means for modifying the computerized document such that it can be represented while relating with the abstract created by the document modifying means, and modified document storage means for storing the computerized document modified by the document modifying means.Type: ApplicationFiled: February 23, 2004Publication date: August 19, 2004Applicant: Kabushiki Kaisha ToshibaInventors: Kenji Ono, Hideki Hirakawa, Kazuo Sumita
-
Publication number: 20040158853Abstract: An audiovisual apparatus for presenting televisual programs includes a reception section for receiving an EPG (Electronic Program Guide) in which televisual programs to be provided are classified into categories according to tastes of users to allow selection of the televisual program in accordance with the categories together with contents information of a televisual program or independently of the contents information, a generation section for generating a program selection window for selecting a desired program in accordance with the categories on the basis of the EPG received by the reception section, and a selection section for selecting a televisual program to be reproduced or recorded from the program selection window.Type: ApplicationFiled: February 9, 2004Publication date: August 12, 2004Inventors: Miwako Doi, Osamu Hori, Kazuo Sumita, Hideki Hirakawa
-
Patent number: 6742163Abstract: A computerized document processing apparatus for creating an abstract includes document storage for storing a computerized document, keyword storage for storing keywords, an abstract creation section for creating an abstract by extracting at least a character string containing a keyword stored in the keyword storage section from the computerized document stored in the document storage section, a document modification section for modifying the computerized document to link the keyword in the computerized document with the same keyword in the abstract, and a display section for displaying the abstract and the modified document that is linked with the abstract. The modified document is displayed when the linked keyword in the abstract is selected.Type: GrantFiled: January 30, 1998Date of Patent: May 25, 2004Assignee: Kabushiki Kaisha ToshibaInventors: Kenji Ono, Hideki Hirakawa, Kazuo Sumita
-
Patent number: 6581207Abstract: In an information filtering unit connected with user's video equipment by a communications line, a program content analyzing section analyzes the contents of broadcast programs from a broadcasting station in terms of substantial information such as video and sound. A collation evaluation section evaluates the similarity between the analyses and a user's profile stored in a profile storage section. A program selecting selection transmits the result of program selection to the video equipment in the form of time information. The video equipment receives and records a program from the broadcasting station in accordance with the time information sent from the information filtering unit.Type: GrantFiled: June 29, 1999Date of Patent: June 17, 2003Assignee: Kabushiki Kaisha ToshibaInventors: Kazuo Sumita, Miwako Doi, Osamu Hori, Hideki Hirakawa
-
Publication number: 20030101142Abstract: An information recording apparatus comprises an encryption section encrypting contents information and also a license condition referred to to limit use of the contents information and a decoding key for decoding the encrypted contents information to generate license information, and a recording section recording the encrypted contents information and the generated license information on a recording medium. An information reproducing apparatus comprises a decoder unit decoding the license information recorded on the recording medium using a second decoding key for decoding the license information and deciding on the basis of the license condition contained in the decoded license information whether the contents information can be used. If it is decided that the contents information can be used, the encrypted contents information recorded on the recording medium is decoded using the first decoding key contained in the decoded license information.Type: ApplicationFiled: August 27, 2002Publication date: May 29, 2003Inventors: Toru Kambayashi, Koichiro Akiyama, Shuichi Tsujimoto, Kazuo Sumita, Hideki Hirakawa, Toshihiro Sugaya
-
Publication number: 20030004888Abstract: An information recording apparatus comprises an encryption section encrypting contents information and also a license condition referred to to limit use of the contents information and a decoding key for decoding the encrypted contents information to generate license information, and a recording section recording the encrypted contents information and the generated license information on a recording medium. An information reproducing apparatus comprises a decoder unit decoding the license information recorded on the recording medium using a second decoding key for decoding the license information and deciding on the basis of the license condition contained in the decoded license information whether the contents information can be used. If it is decided that the contents information can be used, the encrypted contents information recorded on the recording medium is decoded using the first decoding key contained in the decoded license information.Type: ApplicationFiled: August 27, 2002Publication date: January 2, 2003Inventors: Toru Kambayashi, Koichiro Akiyama, Shuichi Tsujimoto, Kazuo Sumita, Hideki Hirakawa, Toshihiro Sugaya