Patents by Inventor Sibley Verbeck Simon
Sibley Verbeck Simon 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: 11978439Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: GrantFiled: December 20, 2022Date of Patent: May 7, 2024Assignee: TiVo CorporationInventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Publication number: 20230197069Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: ApplicationFiled: December 20, 2022Publication date: June 22, 2023Inventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Patent number: 11562737Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: GrantFiled: December 27, 2019Date of Patent: January 24, 2023Assignee: TIVO CORPORATIONInventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Publication number: 20200312310Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: ApplicationFiled: December 27, 2019Publication date: October 1, 2020Inventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Patent number: 10559301Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: GrantFiled: December 15, 2017Date of Patent: February 11, 2020Assignee: Comcast Interactive Media, LLCInventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Publication number: 20190035388Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: ApplicationFiled: December 15, 2017Publication date: January 31, 2019Applicant: Comcast Interactive Media, LLCInventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Patent number: 9892730Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: GrantFiled: July 1, 2009Date of Patent: February 13, 2018Assignee: Comcast Interactive Media, LLCInventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
-
Patent number: 9542393Abstract: A method and system for indexing, searching, and retrieving information from timed media files based upon relevance intervals. The method and system for indexing, searching, and retrieving this information is based upon relevance intervals so that a portion of a timed media file is returned, which is selected specifically to be relevant to the given information representations, thereby eliminating the need for a manual determination of the relevance and avoiding missing relevant portions. The timed media includes streaming audio, streaming video, timed HTML, animations such as vector-based graphics, slide shows, other timed media, and combinations thereof.Type: GrantFiled: September 2, 2015Date of Patent: January 10, 2017Assignee: Streamsage, Inc.Inventors: Michael Scott Morton, Sibley Verbeck Simon, Noam Carl Unger, Robert Rubinoff, Anthony Ruiz Davis, Kyle Aveni-Deforge
-
Publication number: 20160098396Abstract: A method and system for indexing, searching, and retrieving information from timed media files based upon relevance intervals. The method and system for indexing, searching, and retrieving this information is based upon relevance intervals so that a portion of a timed media file is returned, which is selected specifically to be relevant to the given information representations, thereby eliminating the need for a manual determination of the relevance and avoiding missing relevant portions. The timed media includes streaming audio, streaming video, timed HTML, animations such as vector-based graphics, slide shows, other timed media, and combinations thereof.Type: ApplicationFiled: September 2, 2015Publication date: April 7, 2016Inventors: Michael Scott Morton, Sibley Verbeck Simon, Noam Carl Unger, Robert Rubinoff, Anthony Ruiz Davis, Kyle Aveni-Deforge
-
Patent number: 9244973Abstract: A method and system for indexing, searching, and retrieving information from timed media files based upon relevance intervals. The method and system for indexing, searching, and retrieving this information is based upon relevance intervals so that a portion of a timed media file is returned, which is selected specifically to be relevant to the given information representations, thereby eliminating the need for a manual determination of the relevance and avoiding missing relevant portions. The timed media includes streaming audio, streaming video, timed HTML, animations such as vector-based graphics, slide shows, other timed media, and combinations thereof.Type: GrantFiled: February 10, 2014Date of Patent: January 26, 2016Assignee: Streamsage, Inc.Inventors: Michael Scott Morton, Sibley Verbeck Simon, Noam Carl Unger, Robert Rubinoff, Anthony Ruiz Davis, Kyle Aveni-Deforge
-
Publication number: 20140250131Abstract: A method and system for indexing, searching, and retrieving information from timed media files based upon relevance intervals. The method and system for indexing, searching, and retrieving this information is based upon relevance intervals so that a portion of a timed media file is returned, which is selected specifically to be relevant to the given information representations, thereby eliminating the need for a manual determination of the relevance and avoiding missing relevant portions. The timed media includes streaming audio, streaming video, timed HTML, animations such as vector-based graphics, slide shows, other timed media, and combinations thereof.Type: ApplicationFiled: February 10, 2014Publication date: September 4, 2014Applicant: Streamsage, Inc.Inventors: Michael Scott Morton, Sibley Verbeck Simon, Noam Carl Unger, Robert Rubinoff, Anthony Ruiz Davis, Kyle Aveni-Deforge
-
Patent number: 8706735Abstract: A method and system for indexing, searching, and retrieving information from timed media files based upon relevance intervals. The method and system for indexing, searching, and retrieving this information is based upon relevance intervals so that a portion of a timed media file is returned, which is selected specifically to be relevant to the given information representations, thereby eliminating the need for a manual determination of the relevance and avoiding missing relevant portions. The timed media includes streaming audio, streaming video, timed HTML, animations such as vector-based graphics, slide shows, other timed media, and combinations thereof.Type: GrantFiled: July 31, 2013Date of Patent: April 22, 2014Assignee: Streamsage, Inc.Inventors: Michael Scott Morton, Sibley Verbeck Simon, Noam Carl Unger, Robert Rubinoff, Anthony Ruiz Davis, Kyle Aveni-Deforge
-
Publication number: 20110004462Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.Type: ApplicationFiled: July 1, 2009Publication date: January 6, 2011Applicant: COMCAST INTERACTIVE MEDIA, LLCInventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon