Patents by Inventor Stefan Deichmann

Stefan Deichmann 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: 12026196
    Abstract: An audio file associated with a user voice query may be received at a user device. The audio file may be compared to a plurality of references, such as cache entries, corresponding to a plurality of other voice queries. Based on a determination that the voice query corresponds to one of the references, an operation associated with the voice query may be executed. An indication may be received that the operation was not an intended operation associated with the voice query. Based on receiving this indication, the incorrectly identified operation, associated reference, e.g., voice query, may be disabled for the user or the device. However, the cache entry may remain enabled for one or more of a plurality of other devices.
    Type: Grant
    Filed: April 3, 2020
    Date of Patent: July 2, 2024
    Assignee: COMCAST CABLE COMMUNICATIONS, LLC
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang
  • Patent number: 12002219
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Grant
    Filed: August 26, 2022
    Date of Patent: June 4, 2024
    Assignee: Comcast Cable Communications, LLC
    Inventors: Erik Schwartz, Jan Neumann, Hans Sayyadi, Stefan Deichmann
  • Publication number: 20240096327
    Abstract: Methods, systems, and apparatuses for improved speech recognition and transcription of user utterances are described herein. A user utterance may be processed by a speech recognition computing device. One or more acoustic features associated with the user utterance may be used to determine whether one or more actions are to be performed based on a transcription of the user utterance.
    Type: Application
    Filed: November 28, 2023
    Publication date: March 21, 2024
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang, Geifei Yang
  • Patent number: 11869507
    Abstract: Methods, systems, and apparatuses for improved speech recognition and transcription of user utterances are described herein. A user utterance may be processed by a speech recognition computing device. One or more acoustic features associated with the user utterance may be used to determine whether one or more actions are to be performed based on a transcription of the user utterance.
    Type: Grant
    Filed: December 20, 2022
    Date of Patent: January 9, 2024
    Assignee: COMCAST CABLE COMMUNICATIONS, LLC
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang, Geifei Yang
  • Publication number: 20230122559
    Abstract: Methods, systems, and apparatuses for improved speech recognition and transcription of user utterances are described herein. User utterances may be processed by a speech recognition computing device as well as an acoustic model. The acoustic model may be trained using historical user utterance data and machine learning techniques. The acoustic model may be used to determine whether a transcription determined by the speech recognition computing device should be overridden with an updated transcription.
    Type: Application
    Filed: December 20, 2022
    Publication date: April 20, 2023
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang, Geifei Yang
  • Publication number: 20230040708
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Application
    Filed: August 26, 2022
    Publication date: February 9, 2023
    Inventors: Erik Schwartz, Jan Neumann, Hans Sayyadi, Stefan Deichmann
  • Patent number: 11551694
    Abstract: Methods, systems, and apparatuses for improved speech recognition and transcription of user utterances are described herein. User utterances may be processed by a speech recognition computing device as well as an acoustic model. The acoustic model may be trained using historical user utterance data and machine learning techniques. The acoustic model may be used to determine whether a transcription determined by the speech recognition computing device should be overridden with an updated transcription.
    Type: Grant
    Filed: January 5, 2021
    Date of Patent: January 10, 2023
    Assignee: COMCAST CABLE COMMUNICATIONS, LLC
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang, Geifei Yang
  • Publication number: 20220337913
    Abstract: Various implementations described herein are directed to determining variations or changes to a predetermined programming schedule. In accordance with one method, a predicted end time of video content may be determined to be later than a scheduled end time of the video content. Also, it may be determined that video content scheduled to be displayed on a first stream or channel has been moved to a second stream or channel. A scheduled recording or transmission time of video content may be altered based on detected changes to the predetermined programming schedule. A program listing such as an electronic program guide may be revised based on detected changes to the predetermined programming schedule.
    Type: Application
    Filed: November 24, 2021
    Publication date: October 20, 2022
    Inventors: Brian Curtis, Erik Schwartz, Stefan Deichmann, Jan Neumann
  • Patent number: 11461904
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Grant
    Filed: April 10, 2020
    Date of Patent: October 4, 2022
    Assignee: Comcast Cable Communications, LLC
    Inventors: Erik Schwartz, Jan Neumann, Hans Sayyadi, Stefan Deichmann
  • Publication number: 20220293128
    Abstract: Provided herein are systems and methods for improved speech and command detection. For example, a user utterance may be received by a voice-enabled device. The voice-enabled device and associated system may determine that a first portion of the utterance comprises a complete command, and begin processing the command for execution. Thereafter, the device may receive an additional utterance and determine the additional utterance to be a second portion, related to the first portion, and together with the first portion comprise a different command. The device and associated system can then adjust and process the intended command.
    Type: Application
    Filed: March 10, 2021
    Publication date: September 15, 2022
    Inventors: Rui Min, Stefan Deichmann, Mariel Sabraw, Yajie Mao
  • Publication number: 20220215840
    Abstract: Methods, systems, and apparatuses for improved speech recognition and transcription of user utterances are described herein. User utterances may be processed by a speech recognition computing device as well as an acoustic model. The acoustic model may be trained using historical user utterance data and machine learning techniques. The acoustic model may be used to determine whether a transcription determined by the speech recognition computing device should be overridden with an updated transcription.
    Type: Application
    Filed: January 5, 2021
    Publication date: July 7, 2022
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang, Geifei Yang
  • Publication number: 20220215835
    Abstract: Methods and systems are disclosed for determining a probability that a prospective wakeup or activation word is not an actual wakeup or activation word for a user device but instead is a word that has characteristics of, or otherwise sounds similar to, a wakeup or activation word and is received as a result of output of a content asset as opposed to being spoken by a user of the user device. Audio data associated with output of a content asset may be received and evaluated to determine if a prospective wakeup word in the audio data is an actual wakeup word or is, instead, not a wakeup word.
    Type: Application
    Filed: January 6, 2021
    Publication date: July 7, 2022
    Inventors: Rui Min, Mariel Sabraw, Hongcheng Wang, Stefan Deichmann
  • Patent number: 11218775
    Abstract: Various implementations described herein are directed to determining variations or changes to a predetermined programming schedule. In accordance with one method, a predicted end time of video content may be determined to be later than a scheduled end time of the video content. Also, it may be determined that video content scheduled to be displayed on a first stream or channel has been moved to a second stream or channel. A scheduled recording or transmission time of video content may be altered based on detected changes to the predetermined programming schedule. A program listing such as an electronic program guide may be revised based on detected changes to the predetermined programming schedule.
    Type: Grant
    Filed: September 8, 2016
    Date of Patent: January 4, 2022
    Assignee: Comcast Cable Communications, LLC
    Inventors: Brian Curtis, Erik Schwartz, Stefan Deichmann, Jan Neumann
  • Publication number: 20210311989
    Abstract: An audio file associated with a user voice query may be received at a user device. The audio file may be compared to a plurality of references, such as cache entries, corresponding to a plurality of other voice queries. Based on a determination that the voice query corresponds to one of the references, an operation associated with the voice query may be executed. An indication may be received that the operation was not an intended operation associated with the voice query. Based on receiving this indication, the incorrectly identified operation, associated reference, e.g., voice query, may be disabled for the user or the device. However, the cache entry may remain enabled for one or more of a plurality of other devices.
    Type: Application
    Filed: April 3, 2020
    Publication date: October 7, 2021
    Inventors: Rui Min, Stefan Deichmann, Hongcheng Wang
  • Publication number: 20200242781
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Application
    Filed: April 10, 2020
    Publication date: July 30, 2020
    Inventors: Erik Schwartz, Jan Neumann, Hans Sayyadi, Stefan Deichmann
  • Patent number: 10657653
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Grant
    Filed: April 6, 2017
    Date of Patent: May 19, 2020
    Assignee: Comcast Cable Communications, LLC
    Inventors: Erik Schwartz, Jan Neumann, Hans Sayyadi, Stefan Deichmann
  • Publication number: 20180070146
    Abstract: Various implementations described herein are directed to determining variations or changes to a predetermined programming schedule. In accordance with one method, a predicted end time of video content may be determined to be later than a scheduled end time of the video content. Also, it may be determined that video content scheduled to be displayed on a first stream or channel has been moved to a second stream or channel. A scheduled recording or transmission time of video content may be altered based on detected changes to the predetermined programming schedule. A program listing such as an electronic program guide may be revised based on detected changes to the predetermined programming schedule.
    Type: Application
    Filed: September 8, 2016
    Publication date: March 8, 2018
    Inventors: Brian Curtis, Erik Schwartz, Stefan Deichmann, Jan Neumann
  • Publication number: 20180061064
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Application
    Filed: April 6, 2017
    Publication date: March 1, 2018
    Inventors: Erik Schwartz, Jan Neumann, Hassan Sayyadi-Harikandehei, Stefan Deichmann
  • Patent number: 9646387
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Grant
    Filed: October 15, 2014
    Date of Patent: May 9, 2017
    Assignee: Comcast Cable Communications, LLC
    Inventors: Erik Schwartz, Jan Neumann, Hassan Sayyadi-Harikandehei, Stefan Deichmann
  • Publication number: 20160110877
    Abstract: According to some aspects, methods and systems may include receiving, by a computing device, metadata identifying an event occurring in a video program, and determining an expected motion of objects in the identified event. The methods and systems may further include analyzing motion energy in the video program to identify video frames in which the event occurs, and storing information identifying the video frames in which the event occurs.
    Type: Application
    Filed: October 15, 2014
    Publication date: April 21, 2016
    Inventors: Erik Schwartz, Jan Neumann, Hassan Sayyadi-Harikandehei, Stefan Deichmann