Patents by Inventor Daniel Baum

Daniel Baum 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: 11600264
    Abstract: A prosodic speech recognition engine configured to identify prosodic features and patterns in a speech continuum for the extraction of linguistic content including para-syntactic content, discourse function, information structure, meaning, and speaker sentiment.
    Type: Grant
    Filed: November 26, 2018
    Date of Patent: March 7, 2023
    Assignee: YEDA RESEARCH AND DEVELOPMENT CO. LTD.
    Inventors: Elisha Moses, Tirza Biron, Dominik Freche, Daniel Baum, Nadav Matalon, Netanel Ehrmann, Eyal Weinreb
  • Patent number: 11545137
    Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.
    Type: Grant
    Filed: August 3, 2020
    Date of Patent: January 3, 2023
    Assignee: VERINT SYSTEMS INC.
    Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
  • Publication number: 20210224483
    Abstract: A method for expanding an initial ontology via processing of communication data, wherein the initial ontology is a structural representation of language elements comprising a set of entities, a set of terms, a set of term-entity associations, a set of entity-association rules, a set of abstract relations, and a set of relation instances. A method for extracting a set of significant phrases and a set of significant phrase co-occurrences from an input set of documents further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another.
    Type: Application
    Filed: April 8, 2021
    Publication date: July 22, 2021
    Inventors: Daniel Baum, Uri Segal, Ron Wein, Oana Sidi
  • Patent number: 11030406
    Abstract: A method for expanding an initial ontology via processing of communication data, wherein the initial ontology is a structural representation of language elements comprising a set of entities, a set of terms, a set of term-entity associations, a set of entity-association rules, a set of abstract relations, and a set of relation instances. A method for extracting a set of significant phrases and a set of significant phrase co-occurrences from an input set of documents further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another.
    Type: Grant
    Filed: January 27, 2016
    Date of Patent: June 8, 2021
    Assignee: VERINT SYSTEMS LTD.
    Inventors: Daniel Baum, Uri Segal, Ron Wein, Oana Sidi
  • Publication number: 20200388272
    Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.
    Type: Application
    Filed: August 3, 2020
    Publication date: December 10, 2020
    Applicant: Verint Systems Ltd.
    Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
  • Publication number: 20200380960
    Abstract: A prosodic speech recognition engine configured to identify prosodic features and patterns in a speech continuum for the extraction of linguistic content including para-syntactic content, discourse function, information structure, meaning, and speaker sentiment.
    Type: Application
    Filed: November 26, 2018
    Publication date: December 3, 2020
    Applicant: YEDA RESEARCH AND DEVELOPMENT CO. LTD.
    Inventors: Elisha MOSES, Tirza BIRON, Dominik FRECHE, Daniel BAUM, Nadav MATALON, Netanel EHRMANN, Eyal WEINREB
  • Patent number: 10733977
    Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.
    Type: Grant
    Filed: March 29, 2017
    Date of Patent: August 4, 2020
    Assignee: Verint Systems Ltd.
    Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
  • Patent number: 9990920
    Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.
    Type: Grant
    Filed: October 24, 2016
    Date of Patent: June 5, 2018
    Assignee: VERINT SYSTEMS LTD.
    Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
  • Publication number: 20170206893
    Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.
    Type: Application
    Filed: March 29, 2017
    Publication date: July 20, 2017
    Applicant: Verint Systems Ltd.
    Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
  • Patent number: 9633650
    Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.
    Type: Grant
    Filed: May 30, 2014
    Date of Patent: April 25, 2017
    Assignee: Verint Systems Ltd.
    Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
  • Publication number: 20170098445
    Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio tile transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio tile transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.
    Type: Application
    Filed: October 24, 2016
    Publication date: April 6, 2017
    Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
  • Patent number: 9508346
    Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.
    Type: Grant
    Filed: May 30, 2014
    Date of Patent: November 29, 2016
    Assignee: VERINT SYSTEMS LTD.
    Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
  • Publication number: 20160217127
    Abstract: A method for expanding an initial ontology via processing of communication data, wherein the initial ontology is a structural representation of language elements comprising a set of entities, a set of terms, a set of term-entity associations, a set of entity-association rules, a set of abstract relations, and a set of relation instances. A method for extracting a set of significant phrases and a set of significant phrase co-occurrences from an input set of documents further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another.
    Type: Application
    Filed: January 27, 2016
    Publication date: July 28, 2016
    Inventors: Uri Segal, Oana Sidi, Ron Wein, Daniel Baum
  • Publication number: 20160217128
    Abstract: A method for expanding an initial ontology via processing of communication data, wherein the initial ontology is a structural representation of language elements comprising a set of entities, a set of terms, a set of term-entity associations, a set of entity-association rules, a set of abstract relations, and a set of relation instances. A method for extracting a set of significant phrases and a set of significant phrase co-occurrences from an input set of documents further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another.
    Type: Application
    Filed: January 27, 2016
    Publication date: July 28, 2016
    Inventors: Daniel Baum, Uri Segal, Ron Wein, Oana Sidi
  • Patent number: 9174625
    Abstract: To improve the purification action of a catalytic converter that is being heated but has not yet reached a desired operating temperature, the internal combustion engine is driven by an electric machine to convey a flow of heating medium through a catalytic converter for heating purposes before the internal combustion engine is started.
    Type: Grant
    Filed: September 28, 2009
    Date of Patent: November 3, 2015
    Assignee: Dr. Ing. h.c. F. Porsche Aktiengesellschaft
    Inventors: Daniel Baum, Thomas Rauner
  • Publication number: 20150066502
    Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.
    Type: Application
    Filed: May 30, 2014
    Publication date: March 5, 2015
    Applicant: Verint Systems Ltd.
    Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
  • Publication number: 20150066503
    Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.
    Type: Application
    Filed: May 30, 2014
    Publication date: March 5, 2015
    Applicant: VERINT SYSTEMS LTD.
    Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
  • Publication number: 20100146938
    Abstract: To improve the purification action of a catalytic converter that is being heated but has not yet reached a desired operating temperature, the internal combustion engine is driven by an electric machine to convey a flow of heating medium through a catalytic converter for heating purposes before the internal combustion engine is started.
    Type: Application
    Filed: September 28, 2009
    Publication date: June 17, 2010
    Applicant: DR. ING. H.C.F. PORSCHE AKTIENGESELLSCHAFT
    Inventors: Daniel Baum, Thomas Rauner
  • Patent number: 7717340
    Abstract: Methods and apparatus, including computer systems and program products, for enabling the use of machine-readable codes. A computer program receives data generated by reading a machine-readable code and detects the presence of formatting information indicating whether the data's payload is in a first or second format. The program uses a first or second procedure to decode the payload depending on whether the formatting information is detected and what it specifies. In some embodiments, the formatting information can include information about how to decode the payload. The machine-readable code can have been produced according to an encoding instruction associated with an electronic document. The first and second formats can be open and closed formats, respectively. The use of multiple formats can enable multiple, co-existing business models in a document workflow, whereby different parties in the workflow can be charged or required to obtain authorization for the use of machine-readable codes.
    Type: Grant
    Filed: November 3, 2008
    Date of Patent: May 18, 2010
    Assignee: Adobe Systems Incorporated
    Inventors: Kenneth E. Feuerman, Daniel Baum
  • Patent number: 7651151
    Abstract: A convertible vehicle with a movable roof and at least one movable cover part that in its closed position, covers a receiving area for the opened roof situated in the auto body and which can be moved up by at least one drive element is provided. The at least one drive element is arranged on a fastening device that can be mounted on the auto body which is also a support for at least one control unit, a hydraulic pump and connections of control lines leading to the drive units for roof movement. A multifunctional holding or fastening device with several connection flanges to accommodate at least one control unit, a pump, and connections for emerging hydraulic lines is also provided. The multifunctional holding device is designed as a support for at least one drive element for a cover part of a compartment top of a convertible vehicle.
    Type: Grant
    Filed: November 26, 2004
    Date of Patent: January 26, 2010
    Assignee: Wilhelm Karmann GmbH
    Inventors: Marian Daniel Baum, Sven Hollenbeck