Patents by Inventor Ido Shapira
Ido Shapira 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: 11933985Abstract: A method for producing light-guide optical elements (LOEs) (16, 18, 56, 58) each having a set of mutually-parallel partially-reflecting surfaces (17) located between, and oriented non-parallel to, a pair of major external surfaces, and at least one region (30a, 30b, 30c) without partially-reflecting surfaces. The method includes bonding together parallel-faced plates (4) at interfaces to form a stack (42) of plates with partially-reflecting coatings between them. The stack is cut and polished to form a boundary plane (48, 48a, 48b) intersecting the interfaces, and a block (50, 50a, 50b) of transparent material is bonded to the stack. The resulting precursor structure (52, 52?) is sliced along parallel planes to form slices, each containing a part of the stack for the active region of the LOE and a part of the block.Type: GrantFiled: February 2, 2021Date of Patent: March 19, 2024Assignee: LUMUS LTD.Inventors: Ido Fuchs, Edgar Friedmann, Elad Sharlin, Kobi Greenstein, Lilach Zuaretz, Tsion Eisenffeld, Shimon Grabarnik, Amir Shapira, Dror Hermoni
-
Publication number: 20240021206Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: ApplicationFiled: September 27, 2023Publication date: January 18, 2024Applicant: VERINT SYSTEMS INC.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 11776547Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: GrantFiled: January 17, 2022Date of Patent: October 3, 2023Assignee: Verint Systems Inc.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 11636860Abstract: Disclosed herein are methods of diarizing audio data using first-pass blind diarization and second-pass blind diarization that generate speaker statistical models, wherein the first pass-blind diarization is on a per-frame basis and the second pass-blind diarization is on a per-word basis, and methods of creating acoustic signatures for a common speaker based only on the statistical models of the speakers in each audio session.Type: GrantFiled: July 21, 2020Date of Patent: April 25, 2023Assignee: Verint Systems Ltd.Inventors: Alex Gorodetski, Oana Sidi, Ron Wein, Ido Shapira
-
Patent number: 11545137Abstract: 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: GrantFiled: August 3, 2020Date of Patent: January 3, 2023Assignee: VERINT SYSTEMS INC.Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
-
Patent number: 11380333Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: July 5, 2022Assignee: Verint Systems Inc.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 11367450Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: June 21, 2022Assignee: Verint Systems Inc.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Publication number: 20220139399Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: ApplicationFiled: January 17, 2022Publication date: May 5, 2022Applicant: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 11322154Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. At least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcribed customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: May 3, 2022Assignee: Verint Systems Inc.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 11227603Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: GrantFiled: April 14, 2020Date of Patent: January 18, 2022Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 10950242Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: March 16, 2021Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 10950241Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: March 16, 2021Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 10902856Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: January 26, 2021Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Publication number: 20200388272Abstract: 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: ApplicationFiled: August 3, 2020Publication date: December 10, 2020Applicant: Verint Systems Ltd.Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
-
Publication number: 20200349956Abstract: Disclosed herein are methods of diarizing audio data using first-pass blind diarization and second-pass blind diarization that generate speaker statistical models, wherein the first pass-blind diarization is on a per-frame basis and the second pass-blind diarization is on a per-word basis, and methods of creating acoustic signatures for a common speaker based only on the statistical models of the speakers in each audio session.Type: ApplicationFiled: July 21, 2020Publication date: November 5, 2020Inventors: Alex Gorodetski, Oana Sidi, Ron Wein, Ido Shapira
-
Publication number: 20200312334Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: ApplicationFiled: April 14, 2020Publication date: October 1, 2020Applicant: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 10733977Abstract: 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: GrantFiled: March 29, 2017Date of Patent: August 4, 2020Assignee: Verint Systems Ltd.Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
-
Patent number: 10726848Abstract: Disclosed herein are methods of diarizing audio data using first-pass blind diarization and second-pass blind diarization that generate speaker statistical models, wherein the first pass-blind diarization is on a per-frame basis and the second pass-blind diarization is on a per-word basis, and methods of creating acoustic signatures for a common speaker based only on the statistical models of the speakers in each audio session.Type: GrantFiled: January 22, 2018Date of Patent: July 28, 2020Assignee: VERINT SYSTEMS LTD.Inventors: Alex Gorodetski, Oana Sidi, Ron Wein, Ido Shapira
-
Patent number: 10720164Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: December 4, 2019Date of Patent: July 21, 2020Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 10692500Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: September 30, 2019Date of Patent: June 23, 2020Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss